From cce93208f383969d718c92c526c5e834cd3a2733 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 18 Oct 2019 22:43:09 +0200 Subject: commit first draft of barycenter.py --- src/python/gudhi/barycenter.py | 187 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 187 insertions(+) create mode 100644 src/python/gudhi/barycenter.py (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py new file mode 100644 index 00000000..c46f6926 --- /dev/null +++ b/src/python/gudhi/barycenter.py @@ -0,0 +1,187 @@ +import ot +import numpy as np +import matplotlib.pyplot as plt +from matplotlib.patches import Polygon + +def _proj_on_diag(x): + return np.array([(x[0] + x[1]) / 2, (x[0] + x[1]) / 2]) + + +def _norm2(x, y): + return (y[0] - x[0])**2 + (y[1] - x[1])**2 + + +def _norm_inf(x, y): + return np.max(np.abs(y[0] - x[0]), np.abs(y[1] - x[1])) + + +def _cost_matrix(X, Y): + """ + :param X: (n x 2) numpy.array encoding the first diagram + :param Y: (m x 2) numpy.array encoding the second diagram + :return: The cost matrix with size (k x k) where k = |d_1| + |d_2| in order to encode matching to diagonal + """ + n, m = len(X), len(Y) + k = n + m + M = np.zeros((k, k)) + for i in range(n): # go throught X points + x_i = X[i] + p_x_i = _proj_on_diag(x_i) # proj of x_i on the diagonal + dist_x_delta = _norm2(x_i, p_x_i) # distance to the diagonal regarding the ground norm + for j in range(m): # go throught d_2 points + y_j = Y[j] + p_y_j = _proj_on_diag(y_j) + M[i, j] = _norm2(x_i, y_j) + dist_y_delta = _norm2(y_j, p_y_j) + for it in range(m): + M[n + it, j] = dist_y_delta + for it in range(n): + M[i, m + it] = dist_x_delta + + return M + + +def _optimal_matching(M): + n = len(M) + # if input weights are empty lists, pot treat the uniform assignement problem and returns a bistochastic matrix (up to *n). + P = ot.emd(a=[], b=[], M=M) * n + # return the list of indices j such that L[i] = j iff P[i,j] = 1 + return np.nonzero(P)[1] + + +def _mean(x, m): + """ + :param x: a list of 2D-points, of diagonal, x_0... x_{k-1} + :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal + :returns: the weighted mean of x with (m-k) copies of Delta taken into account (defined by mukherjee etc.) + """ + k = len(x) + if k > 0: + w = np.mean(x, axis=0) + w_delta = _proj_on_diag(w) + return (k * w + (m-k) * w_delta) / m + else: + return np.array([0, 0]) + + +def lagrangian_barycenter(pdiagset, init=None, verbose=False): + """ + Compute the estimated barycenter computed with the Hungarian algorithm provided by Mukherjee et al + It is a local minima of the corresponding Frechet function. + It exactly belongs to the persistence diagram space (because all computations are made on it). + :param pdiagset: a list of size N containing numpy.array of shape (n x + 2) (n can variate), encoding a set of persistence diagrams with only finite + coordinates. + :param init: The initial value for barycenter estimate. If None, init is made on a random diagram from the dataset. Otherwise, it must be a (n x 2) numpy.array enconding a persistence diagram with n points. + :returns: If not verbose (default), the barycenter estimate (local minima of the energy function). If verbose, returns a triplet (Y, a, e) where Y is the barycenter estimate, a is the assignments between the points of Y and thoses of the diagrams, and e is the energy value reached by the estimate. + """ + m = len(pdiagset) # number of diagrams we are averaging + X = pdiagset # to shorten notations + nb_off_diag = np.array([len(X_i) for X_i in X]) # store the number of off-diagonal point for each of the X_i + + # Initialisation of barycenter + if init is None: + i0 = np.random.randint(m) # Index of first state for the barycenter + Y = X[i0].copy() + else: + Y = init.copy() + + not_converged = True # stoping criterion + while not_converged: + K = len(Y) # current nb of points in Y (some might be on diagonal) + G = np.zeros((K, m)) # will store for each j, the (index) point matched in each other diagram (might be the diagonal). + updated_points = np.zeros((K, 2)) # will store the new positions of the points of Y + new_created_points = [] # will store eventual new points. + + # Step 1 : compute optimal matching (Y, X_i) for each X_i + for i in range(m): + M = _cost_matrix(Y, X[i]) + indices = _optimal_matching(M) + for y_j, x_i_j in enumerate(indices): + if y_j < K: # we matched an off diagonal point to x_i_j... + if x_i_j < nb_off_diag[i]: # ...which is also an off-diagonal point + G[y_j, i] = x_i_j + else: # ...which is a diagonal point + G[y_j, i] = -1 # -1 stands for the diagonal (mask) + else: # We matched a diagonal point to x_i_j... + if x_i_j < nb_off_diag[i]: # which is a off-diag point ! so we need to create a new point in Y + new_y = _mean(np.array([X[i][x_i_j]]), m) # Average this point with (m-1) copies of Delta + new_created_points.append(new_y) + + # Step 2 : Compute new points (mean) + for j in range(K): + matched_points = [X[i][int(G[j, i])] for i in range(m) if G[j, i] > -1] + updated_points[j] = _mean(matched_points, m) + + if new_created_points: + Y = np.concatenate((updated_points, new_created_points)) + else: + Y = updated_points + + # Step 3 : we update our estimation of the barycenter + if len(new_created_points) == 0 and np.array_equal(updated_points, Y): + not_converged = False + + if verbose: + matchings = [] + energy = 0 + n_y = len(Y) + for i in range(m): + M = _cost_matrix(Y, X[i]) + edges = _optimal_matching(M) + matchings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) + #energy += total_cost + + #energy /= m + _plot_barycenter(X, Y, matchings) + plt.show() + return Y, matchings, energy + else: + return Y + +def _plot_barycenter(X, Y, matchings): + fig = plt.figure() + ax = fig.add_subplot(111) + + # n_y = len(Y.points) + for i in range(len(X)): + indices = matchings[i] + n_i = len(X[i]) + + for (y_j, x_i_j) in enumerate(indices): + y = Y[y_j] + if y[0] != y[1]: + if x_i_j < n_i: # not mapped with the diag + x = X[i][x_i_j] + else: # y_j is matched to the diagonal + x = _proj_on_diag(y) + ax.plot([y[0], x[0]], [y[1], x[1]], c='black', + linestyle="dashed") + + ax.scatter(Y[:,0], Y[:,1], color='purple', marker='d') + + for dgm in X: + ax.scatter(dgm[:,0], dgm[:,1], marker ='o') + + shift = 0.1 # for improved rendering + xmin = min([np.min(x[:,0]) for x in X]) - shift + xmax = max([np.max(x[:,0]) for x in X]) + shift + ymin = min([np.max(x[:,1]) for x in X]) - shift + ymax = max([np.max(x[:,1]) for x in X]) + shift + themin = min(xmin, ymin) + themax = max(xmax, ymax) + ax.set_xlim(themin, themax) + ax.set_ylim(themin, themax) + ax.add_patch(Polygon([[themin,themin], [themax,themin], [themax,themax]], fill=True, color='lightgrey')) + ax.set_xticks([]) + ax.set_yticks([]) + ax.set_aspect('equal', adjustable='box') + ax.set_title("example of (estimated) barycenter") + + +if __name__=="__main__": + dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) + dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) + dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) + X = [dg1, dg2, dg3] + Y, a, e = lagrangian_barycenter(X, verbose=True) -- cgit v1.2.3 From 48f7e17c5e9d4f6936bfdf6384015fe833e30c74 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 18 Oct 2019 23:18:53 +0200 Subject: updated documentation in barycenter.py --- src/python/gudhi/barycenter.py | 78 ++++++++++++++++++++++++++++++------------ 1 file changed, 57 insertions(+), 21 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index c46f6926..85666631 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -4,22 +4,30 @@ import matplotlib.pyplot as plt from matplotlib.patches import Polygon def _proj_on_diag(x): + """ + :param x: numpy.array of length 2, encoding a point on the upper half plane. + :returns: numpy.array of length 2, orthogonal projection of the point onto + the diagonal. + """ return np.array([(x[0] + x[1]) / 2, (x[0] + x[1]) / 2]) def _norm2(x, y): + """ + :param x: numpy.array of length 2, encoding a point on the upper half plane. + :param y: numpy.array of length 2, encoding a point on the upper half plane. + :returns: distance between the two points for the euclidean norm. + """ return (y[0] - x[0])**2 + (y[1] - x[1])**2 -def _norm_inf(x, y): - return np.max(np.abs(y[0] - x[0]), np.abs(y[1] - x[1])) - - def _cost_matrix(X, Y): """ :param X: (n x 2) numpy.array encoding the first diagram :param Y: (m x 2) numpy.array encoding the second diagram - :return: The cost matrix with size (k x k) where k = |d_1| + |d_2| in order to encode matching to diagonal + :return: numpy.array with size (k x k) where k = |X| + |Y|, encoding the + cost matrix between points (including the diagonal, with repetition to + ensure one-to-one matchings. """ n, m = len(X), len(Y) k = n + m @@ -42,8 +50,15 @@ def _cost_matrix(X, Y): def _optimal_matching(M): + """ + :param M: numpy.array of size (k x k), encoding the cost matrix between the + points of two diagrams. + :returns: list of length (k) such that L[i] = j if and only if P[i,j]=1 + where P is a bi-stochastic matrix that minimize . + """ n = len(M) - # if input weights are empty lists, pot treat the uniform assignement problem and returns a bistochastic matrix (up to *n). + # if input weights are empty lists, pot treats the uniform assignement + # problem and returns a bistochastic matrix (up to *n). P = ot.emd(a=[], b=[], M=M) * n # return the list of indices j such that L[i] = j iff P[i,j] = 1 return np.nonzero(P)[1] @@ -53,7 +68,8 @@ def _mean(x, m): """ :param x: a list of 2D-points, of diagonal, x_0... x_{k-1} :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal - :returns: the weighted mean of x with (m-k) copies of Delta taken into account (defined by mukherjee etc.) + :returns: the weighted mean of x with (m-k) copies of Delta taken into + account. """ k = len(x) if k > 0: @@ -66,14 +82,23 @@ def _mean(x, m): def lagrangian_barycenter(pdiagset, init=None, verbose=False): """ - Compute the estimated barycenter computed with the Hungarian algorithm provided by Mukherjee et al - It is a local minima of the corresponding Frechet function. - It exactly belongs to the persistence diagram space (because all computations are made on it). - :param pdiagset: a list of size N containing numpy.array of shape (n x - 2) (n can variate), encoding a set of persistence diagrams with only finite - coordinates. - :param init: The initial value for barycenter estimate. If None, init is made on a random diagram from the dataset. Otherwise, it must be a (n x 2) numpy.array enconding a persistence diagram with n points. - :returns: If not verbose (default), the barycenter estimate (local minima of the energy function). If verbose, returns a triplet (Y, a, e) where Y is the barycenter estimate, a is the assignments between the points of Y and thoses of the diagrams, and e is the energy value reached by the estimate. + Compute the estimated barycenter computed with the algorithm provided + by Turner et al (2014). + It is a local minima of the corresponding Frechet function. + :param pdiagset: a list of size N containing numpy.array of shape (n x 2) + (n can variate), encoding a set of + persistence diagrams with only finite coordinates. + :param init: The initial value for barycenter estimate. + If None, init is made on a random diagram from the dataset. + Otherwise, it must be a (n x 2) numpy.array enconding a persistence diagram with n points. + :param verbose: if True, returns additional information about the + barycenters (assignment and energy). + :returns: If not verbose (default), a numpy.array encoding + the barycenter estimate (local minima of the energy function). + If verbose, returns a triplet (Y, a, e) + where Y is the barycenter estimate, a is the assignments between the + points of Y and thoses of the diagrams, + and e is the energy value reached by the estimate. """ m = len(pdiagset) # number of diagrams we are averaging X = pdiagset # to shorten notations @@ -90,7 +115,10 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): while not_converged: K = len(Y) # current nb of points in Y (some might be on diagonal) G = np.zeros((K, m)) # will store for each j, the (index) point matched in each other diagram (might be the diagonal). - updated_points = np.zeros((K, 2)) # will store the new positions of the points of Y + updated_points = np.zeros((K, 2)) # will store the new positions of + # the points of Y. + # If points disappear, there thrown + # on [0,0] by default. new_created_points = [] # will store eventual new points. # Step 1 : compute optimal matching (Y, X_i) for each X_i @@ -130,16 +158,22 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): M = _cost_matrix(Y, X[i]) edges = _optimal_matching(M) matchings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) - #energy += total_cost + energy += sum([M[i,j] for i,j in enumerate(edges)]) - #energy /= m - _plot_barycenter(X, Y, matchings) - plt.show() + energy = energy/m return Y, matchings, energy else: return Y def _plot_barycenter(X, Y, matchings): + """ + :param X: list of persistence diagrams. + :param Y: numpy.array of (n x 2). Aims to be an estimate of the barycenter + returned by lagrangian_barycenter(X, verbose=True). + :param matchings: list of lists, such that L[k][i] = j if and only if + the i-th point of the barycenter is grouped with the j-th point of the k-th + diagram. + """ fig = plt.figure() ax = fig.add_subplot(111) @@ -176,7 +210,7 @@ def _plot_barycenter(X, Y, matchings): ax.set_xticks([]) ax.set_yticks([]) ax.set_aspect('equal', adjustable='box') - ax.set_title("example of (estimated) barycenter") + ax.set_title("Estimated barycenter") if __name__=="__main__": @@ -185,3 +219,5 @@ if __name__=="__main__": dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) X = [dg1, dg2, dg3] Y, a, e = lagrangian_barycenter(X, verbose=True) + _plot_barycenter(X, Y, a) + plt.show() -- cgit v1.2.3 From 80aa14d1b92d1a61366d798b07073289d4db4fda Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 5 Dec 2019 18:42:48 +0100 Subject: first version of barycenter for persistence diagrams --- src/python/doc/barycenter_sum.inc | 22 +++ src/python/doc/barycenter_user.rst | 51 ++++++ src/python/gudhi/barycenter.py | 322 +++++++++++++++++++++++++------------ 3 files changed, 292 insertions(+), 103 deletions(-) create mode 100644 src/python/doc/barycenter_sum.inc create mode 100644 src/python/doc/barycenter_user.rst (limited to 'src/python') diff --git a/src/python/doc/barycenter_sum.inc b/src/python/doc/barycenter_sum.inc new file mode 100644 index 00000000..7801a845 --- /dev/null +++ b/src/python/doc/barycenter_sum.inc @@ -0,0 +1,22 @@ +.. table:: + :widths: 30 50 20 + + +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ + | .. figure:: | A Frechet mean (or barycenter) is a generalization of the arithmetic | :Author: Theo Lacombe | + | ../../doc/Barycenter/barycenter.png | mean in a non linear space such as the one of persistence diagrams. | | + | :figclass: align-center | Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is | :Introduced in: GUDHI 3.1.0 | + | | defined as a minimizer of the variance functional, that is of | | + | Illustration of Frechet mean between persistence | :math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. | :Copyright: MIT | + | diagrams. | where :math:`d_2` denotes the Wasserstein-2 distance between persis- | | + | | tence diagrams. | | + | | It is known to exist and is generically unique. However, an exact | | + | | computation is in general untractable. Current implementation avai- | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | + | | -lable is based on [Turner et al, 2014], and uses an EM-scheme to | | + | | provide a local minimum of the variance functional (somewhat similar | | + | | to the Lloyd algorithm to estimate a solution to the k-means | | + | | problem). The combinatorial structure of the algorithm limits its | | + | | scaling on large scale problems (thousands of diagrams and of points | | + | | per diagram). | | + +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ + | * :doc:`barycenter_user` | | + +-----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst new file mode 100644 index 00000000..fae2854a --- /dev/null +++ b/src/python/doc/barycenter_user.rst @@ -0,0 +1,51 @@ +:orphan: + +.. To get rid of WARNING: document isn't included in any toctree + +Wasserstein distance user manual +================================ +Definition +---------- + +.. include:: wasserstein_distance_sum.inc + +This implementation is based on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport". + +Function +-------- +.. autofunction:: gudhi.barycenter.lagrangian_barycenter + + +Basic example +------------- + +This example computes the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. +It is initialized on the 4th diagram, which is the empty diagram. It is encoded by np.array([]). +Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. + +.. testcode:: + + import gudhi.barycenter + import numpy as np + + dg1 = np.array([[0.2, 0.5]]) + dg2 = np.array([[0.2, 0.7]]) + dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + dg4 = np.array([]) + + bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3)) + + message = "Wasserstein barycenter estimated:" + print(message) + print(bary) + +The output is: + +.. testoutput:: + + Wasserstein barycenter estimated: + [[0.27916667 0.55416667] + [0.7375 0.7625 ] + [0.2375 0.2625 ]] + + diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 85666631..3cd214a7 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -1,75 +1,105 @@ import ot import numpy as np -import matplotlib.pyplot as plt -from matplotlib.patches import Polygon +import scipy.spatial.distance as sc -def _proj_on_diag(x): - """ - :param x: numpy.array of length 2, encoding a point on the upper half plane. - :returns: numpy.array of length 2, orthogonal projection of the point onto - the diagonal. - """ - return np.array([(x[0] + x[1]) / 2, (x[0] + x[1]) / 2]) +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Theo Lacombe +# +# Copyright (C) 2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification -def _norm2(x, y): - """ - :param x: numpy.array of length 2, encoding a point on the upper half plane. - :param y: numpy.array of length 2, encoding a point on the upper half plane. - :returns: distance between the two points for the euclidean norm. - """ - return (y[0] - x[0])**2 + (y[1] - x[1])**2 +def _proj_on_diag(w): + ''' + Util function to project a point on the diag. + ''' + return np.array([(w[0] + w[1])/2 , (w[0] + w[1])/2]) -def _cost_matrix(X, Y): - """ - :param X: (n x 2) numpy.array encoding the first diagram - :param Y: (m x 2) numpy.array encoding the second diagram - :return: numpy.array with size (k x k) where k = |X| + |Y|, encoding the - cost matrix between points (including the diagonal, with repetition to - ensure one-to-one matchings. - """ - n, m = len(X), len(Y) - k = n + m - M = np.zeros((k, k)) - for i in range(n): # go throught X points - x_i = X[i] - p_x_i = _proj_on_diag(x_i) # proj of x_i on the diagonal - dist_x_delta = _norm2(x_i, p_x_i) # distance to the diagonal regarding the ground norm - for j in range(m): # go throught d_2 points - y_j = Y[j] - p_y_j = _proj_on_diag(y_j) - M[i, j] = _norm2(x_i, y_j) - dist_y_delta = _norm2(y_j, p_y_j) - for it in range(m): - M[n + it, j] = dist_y_delta - for it in range(n): - M[i, m + it] = dist_x_delta - - return M - - -def _optimal_matching(M): + +def _proj_on_diag_array(X): + ''' + :param X: (n x 2) array encoding the points of a persistent diagram. + :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal + ''' + Z = (X[:,0] + X[:,1]) / 2. + return np.array([Z , Z]).T + + +def _build_dist_matrix(X, Y, p=2., q=2.): + ''' + :param X: (n x 2) numpy.array encoding the (points of the) first diagram. + :param Y: (m x 2) numpy.array encoding the second diagram. + :param q: Ground metric (i.e. norm l_q). + :param p: exponent for the Wasserstein metric. + :returns: (n+1) x (m+1) np.array encoding the cost matrix C. + For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal proj onto the diagonal. + note also that C[n+1, m+1] = 0 (it costs nothing to move from the diagonal to the diagonal). + Note that for lagrangian_barycenter, one must use p=q=2. + ''' + Xdiag = _proj_on_diag_array(X) + Ydiag = _proj_on_diag_array(Y) + if np.isinf(q): + C = sc.cdist(X, Y, metric='chebyshev')**p + Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p + Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p + else: + C = sc.cdist(X,Y, metric='minkowski', p=q)**p + Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p + Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p + Cf = np.hstack((C, Cxd[:,None])) + Cdy = np.append(Cdy, 0) + + Cf = np.vstack((Cf, Cdy[None,:])) + + return Cf + + +def _optimal_matching(X, Y): """ - :param M: numpy.array of size (k x k), encoding the cost matrix between the - points of two diagrams. - :returns: list of length (k) such that L[i] = j if and only if P[i,j]=1 - where P is a bi-stochastic matrix that minimize . + :param X: numpy.array of size (n x 2) + :param Y: numpy.array of size (m x 2) + :returns: numpy.array of shape (k x 2) encoding the list of edges in the optimal matching. + That is, [[(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] + if i > len(X) or j > len(Y), it means they represent the diagonal. + """ - n = len(M) - # if input weights are empty lists, pot treats the uniform assignement - # problem and returns a bistochastic matrix (up to *n). - P = ot.emd(a=[], b=[], M=M) * n - # return the list of indices j such that L[i] = j iff P[i,j] = 1 - return np.nonzero(P)[1] + + n = len(X) + m = len(Y) + if X.size == 0: # X is empty + if Y.size == 0: # Y is empty + return np.array([[0,0]]) # the diagonal is matched to the diagonal and that's it... + else: + return np.column_stack([np.zeros(m+1, dtype=int), np.arange(m+1, dtype=int)]) # TO BE CORRECTED + elif Y.size == 0: # X is not empty but Y is empty + return np.column_stack([np.zeros(n+1, dtype=int), np.arange(n+1, dtype=int)]) # TO BE CORRECTED + + # we know X, Y are not empty diags now + M = _build_dist_matrix(X, Y) + + a = np.full(n+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. + a[-1] = a[-1] * m # normalized so that we have a probability measure, required by POT + b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. + b[-1] = b[-1] * n # so that we have a probability measure, required by POT + P = ot.emd(a=a, b=b, M=M)*(n+m) + # Note : it seems POT return a permutation matrix in this situation, + # ...guarantee...? + # It should be enough to check that the algorithm only iterates on vertices of the transportation polytope. + P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to be improved. + # return the list of (i,j) such that P[i,j] > 0, i.e. x_i is matched to y_j (should it be the diag). + res = np.nonzero(P) + return np.column_stack(res) def _mean(x, m): """ - :param x: a list of 2D-points, of diagonal, x_0... x_{k-1} + :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal - :returns: the weighted mean of x with (m-k) copies of Delta taken into - account. + :returns: the weighted mean of x with (m-k) copies of the diagonal """ k = len(x) if k > 0: @@ -88,44 +118,54 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): :param pdiagset: a list of size N containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. - :param init: The initial value for barycenter estimate. - If None, init is made on a random diagram from the dataset. - Otherwise, it must be a (n x 2) numpy.array enconding a persistence diagram with n points. - :param verbose: if True, returns additional information about the - barycenters (assignment and energy). - :returns: If not verbose (default), a numpy.array encoding + :param init: The initial value for barycenter estimate. + If None, init is made on a random diagram from the dataset. + Otherwise, it must be an int (then we init with diagset[init]) + or a (n x 2) numpy.array enconding a persistence diagram with n points. + :param verbose: if True, returns additional information about the + barycenters (assignment and energy). + :returns: If not verbose (default), a numpy.array encoding the barycenter estimate (local minima of the energy function). If verbose, returns a triplet (Y, a, e) where Y is the barycenter estimate, a is the assignments between the points of Y and thoses of the diagrams, and e is the energy value reached by the estimate. """ - m = len(pdiagset) # number of diagrams we are averaging - X = pdiagset # to shorten notations + X = pdiagset # to shorten notations, not a copy + m = len(X) # number of diagrams we are averaging + if m == 0: + print("Warning: computing barycenter of empty diag set. Returns None") + return None + nb_off_diag = np.array([len(X_i) for X_i in X]) # store the number of off-diagonal point for each of the X_i # Initialisation of barycenter if init is None: i0 = np.random.randint(m) # Index of first state for the barycenter - Y = X[i0].copy() + Y = X[i0].copy() #copy() ensure that we do not modify X[i0] else: - Y = init.copy() + if type(init)==int: + Y = X[init].copy() + else: + Y = init.copy() - not_converged = True # stoping criterion - while not_converged: + converged = False # stoping criterion + while not converged: K = len(Y) # current nb of points in Y (some might be on diagonal) - G = np.zeros((K, m)) # will store for each j, the (index) point matched in each other diagram (might be the diagonal). + G = np.zeros((K, m), dtype=int)-1 # will store for each j, the (index) point matched in each other diagram (might be the diagonal). + # that is G[j, i] = k <=> y_j is matched to + # x_k in the diagram i-th diagram X[i] updated_points = np.zeros((K, 2)) # will store the new positions of # the points of Y. # If points disappear, there thrown # on [0,0] by default. - new_created_points = [] # will store eventual new points. + new_created_points = [] # will store potential new points. # Step 1 : compute optimal matching (Y, X_i) for each X_i + # and create new points in Y if needed for i in range(m): - M = _cost_matrix(Y, X[i]) - indices = _optimal_matching(M) - for y_j, x_i_j in enumerate(indices): + indices = _optimal_matching(Y, X[i]) + for y_j, x_i_j in indices: if y_j < K: # we matched an off diagonal point to x_i_j... if x_i_j < nb_off_diag[i]: # ...which is also an off-diagonal point G[y_j, i] = x_i_j @@ -136,32 +176,40 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): new_y = _mean(np.array([X[i][x_i_j]]), m) # Average this point with (m-1) copies of Delta new_created_points.append(new_y) - # Step 2 : Compute new points (mean) + # Step 2 : Update current point position thanks to the groupings computed + + to_delete = [] for j in range(K): - matched_points = [X[i][int(G[j, i])] for i in range(m) if G[j, i] > -1] - updated_points[j] = _mean(matched_points, m) + matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] + new_y_j = _mean(matched_points, m) + if not np.array_equal(new_y_j, np.array([0,0])): + updated_points[j] = new_y_j + else: # this points is no longer of any use. + to_delete.append(j) + # we remove the point to be deleted now. + updated_points = np.delete(updated_points, to_delete, axis=0) # cannot be done in-place. - if new_created_points: + + if new_created_points: # we cannot converge if there have been new created points. Y = np.concatenate((updated_points, new_created_points)) else: + # Step 3 : we check convergence + if np.array_equal(updated_points, Y): + converged = True Y = updated_points - # Step 3 : we update our estimation of the barycenter - if len(new_created_points) == 0 and np.array_equal(updated_points, Y): - not_converged = False if verbose: matchings = [] - energy = 0 + #energy = 0 n_y = len(Y) for i in range(m): - M = _cost_matrix(Y, X[i]) - edges = _optimal_matching(M) + edges = _optimal_matching(Y, X[i]) matchings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) - energy += sum([M[i,j] for i,j in enumerate(edges)]) + # energy += sum([M[i,j] for i,j in enumerate(edges)]) - energy = energy/m - return Y, matchings, energy + # energy = energy/m + return Y, matchings #, energy else: return Y @@ -174,6 +222,11 @@ def _plot_barycenter(X, Y, matchings): the i-th point of the barycenter is grouped with the j-th point of the k-th diagram. """ + # import matplotlib now to avoid useless dependancies + + import matplotlib.pyplot as plt + from matplotlib.patches import Polygon + fig = plt.figure() ax = fig.add_subplot(111) @@ -182,7 +235,7 @@ def _plot_barycenter(X, Y, matchings): indices = matchings[i] n_i = len(X[i]) - for (y_j, x_i_j) in enumerate(indices): + for (y_j, x_i_j) in indices: y = Y[y_j] if y[0] != y[1]: if x_i_j < n_i: # not mapped with the diag @@ -192,16 +245,20 @@ def _plot_barycenter(X, Y, matchings): ax.plot([y[0], x[0]], [y[1], x[1]], c='black', linestyle="dashed") - ax.scatter(Y[:,0], Y[:,1], color='purple', marker='d') + ax.scatter(Y[:,0], Y[:,1], color='purple', marker='d', zorder=2) - for dgm in X: - ax.scatter(dgm[:,0], dgm[:,1], marker ='o') + for X_i in X: + if X_i.size > 0: + ax.scatter(X_i[:,0], X_i[:,1], marker ='o', zorder=2) shift = 0.1 # for improved rendering - xmin = min([np.min(x[:,0]) for x in X]) - shift - xmax = max([np.max(x[:,0]) for x in X]) + shift - ymin = min([np.max(x[:,1]) for x in X]) - shift - ymax = max([np.max(x[:,1]) for x in X]) + shift + try: + xmin = np.min(np.array([np.min(x[:,0]) for x in X if len(x) > 0]) - shift) + xmax = np.max(np.array([np.max(x[:,0]) for x in X if len(x) > 0]) + shift) + ymin = np.min(np.array([np.max(x[:,1]) for x in X if len(x) > 0]) - shift) + ymax = np.max(np.array([np.max(x[:,1]) for x in X if len(x) > 0]) + shift) + except ValueError: # to handle the pecular case where we only average empty diagrams. + xmin, xmax, ymin, ymax = 0, 1, 0, 1 themin = min(xmin, ymin) themax = max(xmax, ymax) ax.set_xlim(themin, themax) @@ -212,12 +269,71 @@ def _plot_barycenter(X, Y, matchings): ax.set_aspect('equal', adjustable='box') ax.set_title("Estimated barycenter") + plt.show() + + +def _test_perf(): + nb_repeat = 10 + nb_points_in_dgm = [5, 10, 20, 50, 100] + nb_dmg = [3, 5, 10, 20] + + from time import time + for m in nb_dmg: + for n in nb_points_in_dgm: + tstart = time() + for _ in range(nb_repeat): + X = [np.random.rand(n, 2) for _ in range(m)] + for diag in X: + #enforce having diagrams + diag[:,1] = diag[:,1] + diag[:,0] + _ = lagrangian_barycenter(X) + tend = time() + print("Computation of barycenter in %s sec, with k = %s diags and n = %s points per diag."%(np.round((tend - tstart)/nb_repeat, 2), m, n)) + print("********************") + + +def _sanity_check(verbose): + #dg1 = np.array([[0.2, 0.5]]) + #dg2 = np.array([[0.2, 0.7]]) + #dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + #dg4 = np.array([[0.72, 0.82]]) + #X = [dg1, dg2, dg3, dg4] + #Y, a = lagrangian_barycenter(X, verbose=verbose) + #_plot_barycenter(X, Y, a) + + #dg1 = np.array([[0.2, 0.5]]) + #dg2 = np.array([]) # The empty diagram + #dg3 = np.array([[0.4, 0.8]]) + #X = [dg1, dg2, dg3] + #Y, a = lagrangian_barycenter(X, verbose=verbose) + #_plot_barycenter(X, Y, a) + + #dg1 = np.array([]) + #dg2 = np.array([]) # The empty diagram + #dg3 = np.array([]) + #X = [dg1, dg2, dg3] + #Y, a = lagrangian_barycenter(X, verbose=verbose) + #_plot_barycenter(X, Y, a) + + #dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) + #dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) + #dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) + #X = [dg1, dg2, dg3] + #Y, a = lagrangian_barycenter(X, init=1, verbose=verbose) + #_plot_barycenter(X, Y, a) + + + dg1 = np.array([[0.2, 0.5]]) + dg2 = np.array([[0.2, 0.7]]) + dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + dg4 = np.array([]) + + bary = lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3) + + message = "Wasserstein barycenter estimated:" + print(message) + print(bary) if __name__=="__main__": - dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) - dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) - dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) - X = [dg1, dg2, dg3] - Y, a, e = lagrangian_barycenter(X, verbose=True) - _plot_barycenter(X, Y, a) - plt.show() + _sanity_check(verbose = True) + #_test_perf() -- cgit v1.2.3 From 56a9294ede73d0660ba724b4f448c02dcd5e3dcc Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 5 Dec 2019 18:52:16 +0100 Subject: added image for barycenter in the /img repository --- src/python/doc/barycenter_sum.inc | 6 ++++-- src/python/doc/img/barycenter.png | Bin 0 -> 12433 bytes src/python/gudhi/barycenter.py | 33 ++++++++++++++++----------------- 3 files changed, 20 insertions(+), 19 deletions(-) create mode 100644 src/python/doc/img/barycenter.png (limited to 'src/python') diff --git a/src/python/doc/barycenter_sum.inc b/src/python/doc/barycenter_sum.inc index 7801a845..afac07d7 100644 --- a/src/python/doc/barycenter_sum.inc +++ b/src/python/doc/barycenter_sum.inc @@ -3,7 +3,7 @@ +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | A Frechet mean (or barycenter) is a generalization of the arithmetic | :Author: Theo Lacombe | - | ../../doc/Barycenter/barycenter.png | mean in a non linear space such as the one of persistence diagrams. | | + | ./img/barycenter.png | mean in a non linear space such as the one of persistence diagrams. | | | :figclass: align-center | Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is | :Introduced in: GUDHI 3.1.0 | | | defined as a minimizer of the variance functional, that is of | | | Illustration of Frechet mean between persistence | :math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. | :Copyright: MIT | @@ -14,7 +14,9 @@ | | -lable is based on [Turner et al, 2014], and uses an EM-scheme to | | | | provide a local minimum of the variance functional (somewhat similar | | | | to the Lloyd algorithm to estimate a solution to the k-means | | - | | problem). The combinatorial structure of the algorithm limits its | | + | | problem). The local minimum returned depends on the initialization of| | + | | the barycenter. | | + | | The combinatorial structure of the algorithm limits its | | | | scaling on large scale problems (thousands of diagrams and of points | | | | per diagram). | | +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ diff --git a/src/python/doc/img/barycenter.png b/src/python/doc/img/barycenter.png new file mode 100644 index 00000000..cad6af70 Binary files /dev/null and b/src/python/doc/img/barycenter.png differ diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 3cd214a7..b4afdb6a 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -293,13 +293,12 @@ def _test_perf(): def _sanity_check(verbose): - #dg1 = np.array([[0.2, 0.5]]) - #dg2 = np.array([[0.2, 0.7]]) - #dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) - #dg4 = np.array([[0.72, 0.82]]) - #X = [dg1, dg2, dg3, dg4] - #Y, a = lagrangian_barycenter(X, verbose=verbose) - #_plot_barycenter(X, Y, a) + dg1 = np.array([[0.2, 0.5]]) + dg2 = np.array([[0.2, 0.7], [0.73, 0.88]]) + dg3 = np.array([[0.3, 0.6], [0.7, 0.85], [0.2, 0.3]]) + X = [dg1, dg2, dg3] + Y, a = lagrangian_barycenter(X, verbose=verbose) + _plot_barycenter(X, Y, a) #dg1 = np.array([[0.2, 0.5]]) #dg2 = np.array([]) # The empty diagram @@ -323,16 +322,16 @@ def _sanity_check(verbose): #_plot_barycenter(X, Y, a) - dg1 = np.array([[0.2, 0.5]]) - dg2 = np.array([[0.2, 0.7]]) - dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) - dg4 = np.array([]) - - bary = lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3) - - message = "Wasserstein barycenter estimated:" - print(message) - print(bary) + #dg1 = np.array([[0.2, 0.5]]) + #dg2 = np.array([[0.2, 0.7]]) + #dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + #dg4 = np.array([]) + # + #bary, a = lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=True) + #_plot_barycenter([dg1, dg2, dg3, dg4], bary, a) + #message = "Wasserstein barycenter estimated:" + #print(message) + #print(bary) if __name__=="__main__": _sanity_check(verbose = True) -- cgit v1.2.3 From aba9ad68394b0c5aae22c450cac7162733132002 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 5 Dec 2019 18:55:46 +0100 Subject: correction of bibliography --- src/python/doc/barycenter_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index fae2854a..1c4cb812 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -9,7 +9,7 @@ Definition .. include:: wasserstein_distance_sum.inc -This implementation is based on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport". +This implementation is based on ideas from "Frechet means for distribution of persistence diagrams", Turner et al. 2014. Function -------- -- cgit v1.2.3 From 5877b4d3b7aca645ba906dfe0be598b1881d8798 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Dec 2019 17:53:59 +0100 Subject: update CMakeLists and create test_wasserstein_bary --- src/python/CMakeLists.txt | 3 +++ src/python/gudhi/barycenter.py | 26 ++++++++++---------- src/python/test/test_wasserstein_barycenter.py | 33 ++++++++++++++++++++++++++ 3 files changed, 50 insertions(+), 12 deletions(-) create mode 100755 src/python/test/test_wasserstein_barycenter.py (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index 9af85eac..7f9ff38f 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -52,6 +52,7 @@ if(PYTHONINTERP_FOUND) # Modules that should not be auto-imported in __init__.py set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'representations', ") set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'wasserstein', ") + set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'barycenter', ") add_gudhi_debug_info("Python version ${PYTHON_VERSION_STRING}") add_gudhi_debug_info("Cython version ${CYTHON_VERSION}") @@ -210,6 +211,7 @@ if(PYTHONINTERP_FOUND) file(COPY "gudhi/persistence_graphical_tools.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") file(COPY "gudhi/representations" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi/") file(COPY "gudhi/wasserstein.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") + file(COPY "gudhi/barycenter.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") add_custom_command( OUTPUT gudhi.so @@ -385,6 +387,7 @@ if(PYTHONINTERP_FOUND) # Wasserstein if(OT_FOUND) add_gudhi_py_test(test_wasserstein_distance) + add_gudhi_py_test(test_wasserstein_barycenter) endif(OT_FOUND) # Representations diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index b4afdb6a..41418454 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -293,12 +293,12 @@ def _test_perf(): def _sanity_check(verbose): - dg1 = np.array([[0.2, 0.5]]) - dg2 = np.array([[0.2, 0.7], [0.73, 0.88]]) - dg3 = np.array([[0.3, 0.6], [0.7, 0.85], [0.2, 0.3]]) - X = [dg1, dg2, dg3] - Y, a = lagrangian_barycenter(X, verbose=verbose) - _plot_barycenter(X, Y, a) + #dg1 = np.array([[0.2, 0.5]]) + #dg2 = np.array([[0.2, 0.7], [0.73, 0.88]]) + #dg3 = np.array([[0.3, 0.6], [0.7, 0.85], [0.2, 0.3]]) + #X = [dg1, dg2, dg3] + #Y, a = lagrangian_barycenter(X, verbose=verbose) + #_plot_barycenter(X, Y, a) #dg1 = np.array([[0.2, 0.5]]) #dg2 = np.array([]) # The empty diagram @@ -313,13 +313,15 @@ def _sanity_check(verbose): #X = [dg1, dg2, dg3] #Y, a = lagrangian_barycenter(X, verbose=verbose) #_plot_barycenter(X, Y, a) + #print(Y) - #dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) - #dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) - #dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) - #X = [dg1, dg2, dg3] - #Y, a = lagrangian_barycenter(X, init=1, verbose=verbose) - #_plot_barycenter(X, Y, a) + dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) + dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) + dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) + X = [dg3] + Y, a = lagrangian_barycenter(X, verbose=verbose) + _plot_barycenter(X, Y, a) + print(Y) #dg1 = np.array([[0.2, 0.5]]) diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py new file mode 100755 index 00000000..6074f250 --- /dev/null +++ b/src/python/test/test_wasserstein_barycenter.py @@ -0,0 +1,33 @@ +from gudhi.barycenter import lagrangian_barycenter +import numpy as np + +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + Author(s): Theo Lacombe + + Copyright (C) 2019 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +__author__ = "Theo Lacombe" +__copyright__ = "Copyright (C) 2019 Inria" +__license__ = "MIT" + + +def test_lagrangian_barycenter(): + + dg1 = np.array([[0.2, 0.5]]) + dg2 = np.array([[0.2, 0.7]]) + dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + dg4 = np.array([]) + dg5 = np.array([]) + dg6 = np.array([]) + res = np.array([[0.27916667, 0.55416667], [0.7375, 0.7625], [0.2375, 0.2625]]) + + dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) + + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < 0.001 + assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.array([])) + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < 0.001 -- cgit v1.2.3 From b4fcc875393df12f42aea84b918b5b35f99f7283 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Dec 2019 18:11:27 +0100 Subject: correction of typo in _user.rst and of empty array shape in test_wasserstein_barycenter --- src/python/doc/barycenter_user.rst | 2 +- src/python/test/test_wasserstein_barycenter.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index 1c4cb812..5344583f 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -33,7 +33,7 @@ Note that persistence diagrams must be submitted as (n x 2) numpy arrays and mus dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) dg4 = np.array([]) - bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3)) + bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3) message = "Wasserstein barycenter estimated:" print(message) diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index 6074f250..ae3f6579 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -29,5 +29,5 @@ def test_lagrangian_barycenter(): dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < 0.001 - assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.array([])) + assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), shape=(0,2), np.array([])) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < 0.001 -- cgit v1.2.3 From 0c2fdc65cc1ea676fa8d11c24bba0d34eb5b7a3c Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Dec 2019 18:34:24 +0100 Subject: Correction of typo in barycenter_user --- src/python/doc/barycenter_user.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index 5344583f..714d807e 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -2,12 +2,12 @@ .. To get rid of WARNING: document isn't included in any toctree -Wasserstein distance user manual +Barycenter user manual ================================ Definition ---------- -.. include:: wasserstein_distance_sum.inc +.. include:: barycenter_sum.inc This implementation is based on ideas from "Frechet means for distribution of persistence diagrams", Turner et al. 2014. -- cgit v1.2.3 From 20047b94e693f31fd88ca142ba7256767ac753eb Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Dec 2019 18:34:55 +0100 Subject: correction of typo in test_wasserstein_barycenter --- src/python/test/test_wasserstein_barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index ae3f6579..dc82a57c 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -29,5 +29,5 @@ def test_lagrangian_barycenter(): dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < 0.001 - assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), shape=(0,2), np.array([])) + assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.array([], shape=(0,2))) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < 0.001 -- cgit v1.2.3 From b23813b90aaf1b0ce2b21bdfb33d2a6ea5bfe4cc Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Dec 2019 19:32:26 +0100 Subject: correction test --- src/python/gudhi/barycenter.py | 6 ++++-- src/python/test/test_wasserstein_barycenter.py | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 41418454..b76166c0 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -318,10 +318,12 @@ def _sanity_check(verbose): dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) - X = [dg3] + dg4 = np.array([]) + X = [dg4] Y, a = lagrangian_barycenter(X, verbose=verbose) - _plot_barycenter(X, Y, a) + #_plot_barycenter(X, Y, a) print(Y) + print(np.array_equal(Y, np.empty(shape=(0,2) ))) #dg1 = np.array([[0.2, 0.5]]) diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index dc82a57c..910d23ff 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -29,5 +29,5 @@ def test_lagrangian_barycenter(): dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < 0.001 - assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.array([], shape=(0,2))) + assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.empty(shape=(0,2))) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < 0.001 -- cgit v1.2.3 From d91585af64805a11a4d446d9e3f6467f3394d0c6 Mon Sep 17 00:00:00 2001 From: Théo Lacombe Date: Tue, 17 Dec 2019 18:58:48 +0100 Subject: Update src/python/gudhi/barycenter.py correction of typo Co-Authored-By: Marc Glisse --- src/python/gudhi/barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index b76166c0..43602a6e 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -114,7 +114,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): """ Compute the estimated barycenter computed with the algorithm provided by Turner et al (2014). - It is a local minima of the corresponding Frechet function. + It is a local minimum of the corresponding Frechet function. :param pdiagset: a list of size N containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. -- cgit v1.2.3 From 180add9067bc9bd0609362717972eeeb8d2f6713 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 19 Dec 2019 17:25:01 +0100 Subject: clean code and doc --- src/python/gudhi/barycenter.py | 129 ++++++++++++----------------------------- 1 file changed, 36 insertions(+), 93 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 43602a6e..c2173dba 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -58,12 +58,13 @@ def _build_dist_matrix(X, Y, p=2., q=2.): return Cf -def _optimal_matching(X, Y): +def _optimal_matching(X, Y, withcost=False): """ :param X: numpy.array of size (n x 2) :param Y: numpy.array of size (m x 2) + :param withcost: returns also the cost corresponding to this optimal matching :returns: numpy.array of shape (k x 2) encoding the list of edges in the optimal matching. - That is, [[(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] + That is, [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] if i > len(X) or j > len(Y), it means they represent the diagonal. """ @@ -74,10 +75,10 @@ def _optimal_matching(X, Y): if Y.size == 0: # Y is empty return np.array([[0,0]]) # the diagonal is matched to the diagonal and that's it... else: - return np.column_stack([np.zeros(m+1, dtype=int), np.arange(m+1, dtype=int)]) # TO BE CORRECTED + return np.column_stack([np.zeros(m+1, dtype=int), np.arange(m+1, dtype=int)]) elif Y.size == 0: # X is not empty but Y is empty - return np.column_stack([np.zeros(n+1, dtype=int), np.arange(n+1, dtype=int)]) # TO BE CORRECTED - + return np.column_stack([np.zeros(n+1, dtype=int), np.arange(n+1, dtype=int)]) + # we know X, Y are not empty diags now M = _build_dist_matrix(X, Y) @@ -86,12 +87,16 @@ def _optimal_matching(X, Y): b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. b[-1] = b[-1] * n # so that we have a probability measure, required by POT P = ot.emd(a=a, b=b, M=M)*(n+m) - # Note : it seems POT return a permutation matrix in this situation, - # ...guarantee...? - # It should be enough to check that the algorithm only iterates on vertices of the transportation polytope. + # Note : it seems POT return a permutation matrix in this situation, ie a vertex of the constraint set (generically true). + if withcost: + cost = np.sqrt(np.sum(np.multiply(P, M))) P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to be improved. # return the list of (i,j) such that P[i,j] > 0, i.e. x_i is matched to y_j (should it be the diag). res = np.nonzero(P) + + if withcost: + return np.column_stack(res), cost + return np.column_stack(res) @@ -123,13 +128,16 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): Otherwise, it must be an int (then we init with diagset[init]) or a (n x 2) numpy.array enconding a persistence diagram with n points. :param verbose: if True, returns additional information about the - barycenters (assignment and energy). + barycenter. :returns: If not verbose (default), a numpy.array encoding the barycenter estimate (local minima of the energy function). - If verbose, returns a triplet (Y, a, e) - where Y is the barycenter estimate, a is the assignments between the - points of Y and thoses of the diagrams, - and e is the energy value reached by the estimate. + If verbose, returns a couple (Y, log) + where Y is the barycenter estimate, + and log is a dict that contains additional informations: + - assigments, a list of list of pairs (i,j), + That is, a[k] = [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] + if i > len(X) or j > len(Y), it means they represent the diagonal. + - energy, a float representing the Frechet mean value obtained. """ X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging @@ -200,25 +208,29 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): if verbose: - matchings = [] - #energy = 0 + groupings = [] + energy = 0 + log = {} n_y = len(Y) for i in range(m): - edges = _optimal_matching(Y, X[i]) - matchings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) - # energy += sum([M[i,j] for i,j in enumerate(edges)]) - - # energy = energy/m - return Y, matchings #, energy + edges, cost = _optimal_matching(Y, X[i], withcost=True) + print(edges) + groupings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) + energy += cost + log["groupings"] = groupings + energy = energy/m + log["energy"] = energy + + return Y, log else: return Y -def _plot_barycenter(X, Y, matchings): +def _plot_barycenter(X, Y, groupings): """ :param X: list of persistence diagrams. :param Y: numpy.array of (n x 2). Aims to be an estimate of the barycenter returned by lagrangian_barycenter(X, verbose=True). - :param matchings: list of lists, such that L[k][i] = j if and only if + :param groupings: list of lists, such that L[k][i] = j if and only if the i-th point of the barycenter is grouped with the j-th point of the k-th diagram. """ @@ -232,7 +244,7 @@ def _plot_barycenter(X, Y, matchings): # n_y = len(Y.points) for i in range(len(X)): - indices = matchings[i] + indices = groupings[i] n_i = len(X[i]) for (y_j, x_i_j) in indices: @@ -271,72 +283,3 @@ def _plot_barycenter(X, Y, matchings): plt.show() - -def _test_perf(): - nb_repeat = 10 - nb_points_in_dgm = [5, 10, 20, 50, 100] - nb_dmg = [3, 5, 10, 20] - - from time import time - for m in nb_dmg: - for n in nb_points_in_dgm: - tstart = time() - for _ in range(nb_repeat): - X = [np.random.rand(n, 2) for _ in range(m)] - for diag in X: - #enforce having diagrams - diag[:,1] = diag[:,1] + diag[:,0] - _ = lagrangian_barycenter(X) - tend = time() - print("Computation of barycenter in %s sec, with k = %s diags and n = %s points per diag."%(np.round((tend - tstart)/nb_repeat, 2), m, n)) - print("********************") - - -def _sanity_check(verbose): - #dg1 = np.array([[0.2, 0.5]]) - #dg2 = np.array([[0.2, 0.7], [0.73, 0.88]]) - #dg3 = np.array([[0.3, 0.6], [0.7, 0.85], [0.2, 0.3]]) - #X = [dg1, dg2, dg3] - #Y, a = lagrangian_barycenter(X, verbose=verbose) - #_plot_barycenter(X, Y, a) - - #dg1 = np.array([[0.2, 0.5]]) - #dg2 = np.array([]) # The empty diagram - #dg3 = np.array([[0.4, 0.8]]) - #X = [dg1, dg2, dg3] - #Y, a = lagrangian_barycenter(X, verbose=verbose) - #_plot_barycenter(X, Y, a) - - #dg1 = np.array([]) - #dg2 = np.array([]) # The empty diagram - #dg3 = np.array([]) - #X = [dg1, dg2, dg3] - #Y, a = lagrangian_barycenter(X, verbose=verbose) - #_plot_barycenter(X, Y, a) - #print(Y) - - dg1 = np.array([[0.1, 0.12], [0.21, 0.7], [0.4, 0.5], [0.3, 0.4], [0.35, 0.7], [0.5, 0.55], [0.32, 0.42], [0.1, 0.4], [0.2, 0.4]]) - dg2 = np.array([[0.09, 0.11], [0.3, 0.43], [0.5, 0.61], [0.3, 0.7], [0.42, 0.5], [0.35, 0.41], [0.74, 0.9], [0.5, 0.95], [0.35, 0.45], [0.13, 0.48], [0.32, 0.45]]) - dg3 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) - dg4 = np.array([]) - X = [dg4] - Y, a = lagrangian_barycenter(X, verbose=verbose) - #_plot_barycenter(X, Y, a) - print(Y) - print(np.array_equal(Y, np.empty(shape=(0,2) ))) - - - #dg1 = np.array([[0.2, 0.5]]) - #dg2 = np.array([[0.2, 0.7]]) - #dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) - #dg4 = np.array([]) - # - #bary, a = lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=True) - #_plot_barycenter([dg1, dg2, dg3, dg4], bary, a) - #message = "Wasserstein barycenter estimated:" - #print(message) - #print(bary) - -if __name__=="__main__": - _sanity_check(verbose = True) - #_test_perf() -- cgit v1.2.3 From b7138871d42197c94c58b9938279455b75723606 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 19 Dec 2019 17:28:06 +0100 Subject: removed plot barycenter. Will be integrated in a tutorial --- src/python/gudhi/barycenter.py | 58 ------------------------------------------ 1 file changed, 58 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index c2173dba..11098afe 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -225,61 +225,3 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): else: return Y -def _plot_barycenter(X, Y, groupings): - """ - :param X: list of persistence diagrams. - :param Y: numpy.array of (n x 2). Aims to be an estimate of the barycenter - returned by lagrangian_barycenter(X, verbose=True). - :param groupings: list of lists, such that L[k][i] = j if and only if - the i-th point of the barycenter is grouped with the j-th point of the k-th - diagram. - """ - # import matplotlib now to avoid useless dependancies - - import matplotlib.pyplot as plt - from matplotlib.patches import Polygon - - fig = plt.figure() - ax = fig.add_subplot(111) - - # n_y = len(Y.points) - for i in range(len(X)): - indices = groupings[i] - n_i = len(X[i]) - - for (y_j, x_i_j) in indices: - y = Y[y_j] - if y[0] != y[1]: - if x_i_j < n_i: # not mapped with the diag - x = X[i][x_i_j] - else: # y_j is matched to the diagonal - x = _proj_on_diag(y) - ax.plot([y[0], x[0]], [y[1], x[1]], c='black', - linestyle="dashed") - - ax.scatter(Y[:,0], Y[:,1], color='purple', marker='d', zorder=2) - - for X_i in X: - if X_i.size > 0: - ax.scatter(X_i[:,0], X_i[:,1], marker ='o', zorder=2) - - shift = 0.1 # for improved rendering - try: - xmin = np.min(np.array([np.min(x[:,0]) for x in X if len(x) > 0]) - shift) - xmax = np.max(np.array([np.max(x[:,0]) for x in X if len(x) > 0]) + shift) - ymin = np.min(np.array([np.max(x[:,1]) for x in X if len(x) > 0]) - shift) - ymax = np.max(np.array([np.max(x[:,1]) for x in X if len(x) > 0]) + shift) - except ValueError: # to handle the pecular case where we only average empty diagrams. - xmin, xmax, ymin, ymax = 0, 1, 0, 1 - themin = min(xmin, ymin) - themax = max(xmax, ymax) - ax.set_xlim(themin, themax) - ax.set_ylim(themin, themax) - ax.add_patch(Polygon([[themin,themin], [themax,themin], [themax,themax]], fill=True, color='lightgrey')) - ax.set_xticks([]) - ax.set_yticks([]) - ax.set_aspect('equal', adjustable='box') - ax.set_title("Estimated barycenter") - - plt.show() - -- cgit v1.2.3 From 587a845289a4e29014f67d4c3379b2b4d6b1f102 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 14 Jan 2020 14:40:41 +0100 Subject: print errors to stderr --- ...lpha_complex_diagram_persistence_from_off_file_example.py | 3 ++- .../example/alpha_rips_persistence_bottleneck_distance.py | 3 ++- ...ness_complex_diagram_persistence_from_off_file_example.py | 3 ++- ...ness_complex_diagram_persistence_from_off_file_example.py | 3 ++- ..._complex_barcode_persistence_from_perseus_file_example.py | 3 ++- ...rips_complex_diagram_persistence_from_off_file_example.py | 3 ++- ...angential_complex_plain_homology_from_off_file_example.py | 3 ++- src/python/gudhi/alpha_complex.pyx | 2 ++ src/python/gudhi/cubical_complex.pyx | 9 ++++++--- src/python/gudhi/nerve_gic.pyx | 12 +++++++----- src/python/gudhi/off_reader.pyx | 4 +++- src/python/gudhi/periodic_cubical_complex.pyx | 8 +++++--- src/python/test/test_subsampling.py | 1 - 13 files changed, 37 insertions(+), 20 deletions(-) (limited to 'src/python') diff --git a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py index 4079a469..6afaf533 100755 --- a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -64,6 +65,6 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/example/alpha_rips_persistence_bottleneck_distance.py b/src/python/example/alpha_rips_persistence_bottleneck_distance.py index d5c33ec8..7b4aa3e7 100755 --- a/src/python/example/alpha_rips_persistence_bottleneck_distance.py +++ b/src/python/example/alpha_rips_persistence_bottleneck_distance.py @@ -3,6 +3,7 @@ import gudhi import argparse import math +import sys """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -100,6 +101,6 @@ with open(args.file, "r") as f: print(message) else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py index 4903667e..f61d692b 100755 --- a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -79,6 +80,6 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py index 339a8577..aaa03dad 100755 --- a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -78,6 +79,6 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py index c692e66f..97bfd49f 100755 --- a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py +++ b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -73,4 +74,4 @@ if is_file_perseus(args.file): gudhi.plot_persistence_barcode(diag) plot.show() else: - print(args.file, "is not a valid perseus style file") + print(args.file, "is not a valid perseus style file", file=sys.stderr) diff --git a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py index c757aca7..5d8f057b 100755 --- a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -68,6 +69,6 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py index f0df2189..77ac2ea7 100755 --- a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py +++ b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py @@ -2,6 +2,7 @@ import argparse import matplotlib.pyplot as plot +import sys import gudhi """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -60,6 +61,6 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file") + print(args.file, "is not a valid OFF file", file=sys.stderr) f.close() diff --git a/src/python/gudhi/alpha_complex.pyx b/src/python/gudhi/alpha_complex.pyx index db11416c..4ff37437 100644 --- a/src/python/gudhi/alpha_complex.pyx +++ b/src/python/gudhi/alpha_complex.pyx @@ -7,12 +7,14 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool from libc.stdint cimport intptr_t +import sys import os from gudhi.simplex_tree cimport * diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index 92ff6411..28913a32 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -7,11 +7,13 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool +import sys import os import numpy as np @@ -87,10 +89,11 @@ cdef class CubicalComplex: if os.path.isfile(perseus_file): self.thisptr = new Bitmap_cubical_complex_base_interface(str.encode(perseus_file)) else: - print("file " + perseus_file + " not found.") + print("file " + perseus_file + " not found.", file=sys.stderr) else: print("CubicalComplex can be constructed from dimensions and " - "top_dimensional_cells or from a Perseus-style file name.") + "top_dimensional_cells or from a Perseus-style file name.", + file=sys.stderr) def __dealloc__(self): if self.thisptr != NULL: @@ -199,5 +202,5 @@ cdef class CubicalComplex: intervals_result = self.pcohptr.intervals_in_dimension(dimension) else: print("intervals_in_dim function requires persistence function" - " to be launched first.") + " to be launched first.", file=sys.stderr) return np.array(intervals_result) diff --git a/src/python/gudhi/nerve_gic.pyx b/src/python/gudhi/nerve_gic.pyx index 68c06432..5eb9be0d 100644 --- a/src/python/gudhi/nerve_gic.pyx +++ b/src/python/gudhi/nerve_gic.pyx @@ -7,11 +7,13 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool +import sys import os from libc.stdint cimport intptr_t @@ -182,7 +184,7 @@ cdef class CoverComplex: if os.path.isfile(off_file): return self.thisptr.read_point_cloud(str.encode(off_file)) else: - print("file " + off_file + " not found.") + print("file " + off_file + " not found.", file=sys.stderr) return False def set_automatic_resolution(self): @@ -214,7 +216,7 @@ cdef class CoverComplex: if os.path.isfile(color_file_name): self.thisptr.set_color_from_file(str.encode(color_file_name)) else: - print("file " + color_file_name + " not found.") + print("file " + color_file_name + " not found.", file=sys.stderr) def set_color_from_range(self, color): """Computes the function used to color the nodes of the simplicial @@ -235,7 +237,7 @@ cdef class CoverComplex: if os.path.isfile(cover_file_name): self.thisptr.set_cover_from_file(str.encode(cover_file_name)) else: - print("file " + cover_file_name + " not found.") + print("file " + cover_file_name + " not found.", file=sys.stderr) def set_cover_from_function(self): """Creates a cover C from the preimages of the function f. @@ -268,7 +270,7 @@ cdef class CoverComplex: if os.path.isfile(func_file_name): self.thisptr.set_function_from_file(str.encode(func_file_name)) else: - print("file " + func_file_name + " not found.") + print("file " + func_file_name + " not found.", file=sys.stderr) def set_function_from_range(self, function): """Creates the function f from a vector stored in memory. @@ -309,7 +311,7 @@ cdef class CoverComplex: if os.path.isfile(graph_file_name): self.thisptr.set_graph_from_file(str.encode(graph_file_name)) else: - print("file " + graph_file_name + " not found.") + print("file " + graph_file_name + " not found.", file=sys.stderr) def set_graph_from_OFF(self): """Creates a graph G from the triangulation given by the input OFF diff --git a/src/python/gudhi/off_reader.pyx b/src/python/gudhi/off_reader.pyx index 58f05db8..ef8f420a 100644 --- a/src/python/gudhi/off_reader.pyx +++ b/src/python/gudhi/off_reader.pyx @@ -7,9 +7,11 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.string cimport string +import sys import os __author__ = "Vincent Rouvreau" @@ -32,6 +34,6 @@ def read_points_from_off_file(off_file=''): if os.path.isfile(off_file): return read_points_from_OFF_file(str.encode(off_file)) else: - print("file " + off_file + " not found.") + print("file " + off_file + " not found.", file=sys.stderr) return [] diff --git a/src/python/gudhi/periodic_cubical_complex.pyx b/src/python/gudhi/periodic_cubical_complex.pyx index b5dece10..4ec06524 100644 --- a/src/python/gudhi/periodic_cubical_complex.pyx +++ b/src/python/gudhi/periodic_cubical_complex.pyx @@ -7,11 +7,13 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool +import sys import os import numpy as np @@ -95,12 +97,12 @@ cdef class PeriodicCubicalComplex: if os.path.isfile(perseus_file): self.thisptr = new Periodic_cubical_complex_base_interface(str.encode(perseus_file)) else: - print("file " + perseus_file + " not found.") + print("file " + perseus_file + " not found.", file=sys.stderr) else: print("CubicalComplex can be constructed from dimensions, " "top_dimensional_cells and periodic_dimensions, or from " "top_dimensional_cells and periodic_dimensions or from " - "a Perseus-style file name.") + "a Perseus-style file name.", file=sys.stderr) def __dealloc__(self): if self.thisptr != NULL: @@ -209,5 +211,5 @@ cdef class PeriodicCubicalComplex: intervals_result = self.pcohptr.intervals_in_dimension(dimension) else: print("intervals_in_dim function requires persistence function" - " to be launched first.") + " to be launched first.", file=sys.stderr) return np.array(intervals_result) diff --git a/src/python/test/test_subsampling.py b/src/python/test/test_subsampling.py index fe0985fa..31f64e32 100755 --- a/src/python/test/test_subsampling.py +++ b/src/python/test/test_subsampling.py @@ -120,7 +120,6 @@ def test_simple_pick_n_random_points(): # Go furter than point set on purpose for iter in range(1, 10): sub_set = gudhi.pick_n_random_points(points=point_set, nb_points=iter) - print(5) for sub in sub_set: found = False for point in point_set: -- cgit v1.2.3 From 85ceea9512634a62664208cd2d0f1ce48bafa171 Mon Sep 17 00:00:00 2001 From: mathieu Date: Thu, 16 Jan 2020 17:02:55 -0500 Subject: added wasserstein class --- .../diagram_vectorizations_distances_kernels.py | 7 ++- src/python/gudhi/representations/metrics.py | 59 ++++++++++++++++++++++ 2 files changed, 65 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index 119072eb..66c32cc2 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -9,7 +9,7 @@ from gudhi.representations import DiagramSelector, Clamping, Landscape, Silhouet TopologicalVector, DiagramScaler, BirthPersistenceTransform,\ PersistenceImage, PersistenceWeightedGaussianKernel, Entropy, \ PersistenceScaleSpaceKernel, SlicedWassersteinDistance,\ - SlicedWassersteinKernel, BottleneckDistance, PersistenceFisherKernel + SlicedWassersteinKernel, BottleneckDistance, WassersteinDistance, PersistenceFisherKernel D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) diags = [D] @@ -117,6 +117,11 @@ X = SW.fit(diags) Y = SW.transform(diags2) print("SW kernel is " + str(Y[0][0])) +W = WassersteinDistance(order=2, internal_p=2) +X = W.fit(diags) +Y = W.transform(diags2) +print("Wasserstein distance is " + str(Y[0][0])) + W = BottleneckDistance(epsilon=.001) X = W.fit(diags) Y = W.transform(diags2) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 5f9ec6ab..290c1d07 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -10,6 +10,7 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances +from gudhi.wasserstein import wasserstein_distance try: from .. import bottleneck_distance USE_GUDHI = True @@ -145,6 +146,64 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): return Xfit +class WassersteinDistance(BaseEstimator, TransformerMixin): + """ + This is a class for computing the Wasserstein distance matrix from a list of persistence diagrams. + """ + def __init__(self, order=2, internal_p=2): + """ + Constructor for the WassersteinDistance class. + + Parameters: + order (int): exponent for Wasserstein, default value is 2., see :func:`gudhi.wasserstein.wasserstein_distance`. + internal_p (int): ground metric on the (upper-half) plane (i.e. norm l_p in R^2), default value is 2 (euclidean norm), see :func:`gudhi.wasserstein.wasserstein_distance`. + """ + self.order, self.internal_p = order, internal_p + + def fit(self, X, y=None): + """ + Fit the WassersteinDistance class on a list of persistence diagrams: persistence diagrams are stored in a numpy array called **diagrams**. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + y (n x 1 array): persistence diagram labels (unused). + """ + self.diagrams_ = X + return self + + def transform(self, X): + """ + Compute all Wasserstein distances between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. + + Parameters: + X (list of n x 2 numpy arrays): input persistence diagrams. + + Returns: + numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise Wasserstein distances. + """ + num_diag1 = len(X) + + #if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): + if X is self.diagrams_: + matrix = np.zeros((num_diag1, num_diag1)) + + for i in range(num_diag1): + for j in range(i+1, num_diag1): + matrix[i,j] = wasserstein_distance(X[i], X[j], self.order, self.internal_p) + matrix[j,i] = matrix[i,j] + + else: + num_diag2 = len(self.diagrams_) + matrix = np.zeros((num_diag1, num_diag2)) + + for i in range(num_diag1): + for j in range(num_diag2): + matrix[i,j] = wasserstein_distance(X[i], self.diagrams_[j], self.order, self.internal_p) + + Xfit = matrix + + return Xfit + class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the persistence Fisher distance matrix from a list of persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. -- cgit v1.2.3 From 6a6bed7ca21c1ffcf6de9ed09c2a6512ecb66585 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 17 Jan 2020 15:37:03 +0100 Subject: improving doc output --- src/python/doc/barycenter_sum.inc | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_sum.inc b/src/python/doc/barycenter_sum.inc index afac07d7..da2bdd84 100644 --- a/src/python/doc/barycenter_sum.inc +++ b/src/python/doc/barycenter_sum.inc @@ -7,11 +7,11 @@ | :figclass: align-center | Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is | :Introduced in: GUDHI 3.1.0 | | | defined as a minimizer of the variance functional, that is of | | | Illustration of Frechet mean between persistence | :math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. | :Copyright: MIT | - | diagrams. | where :math:`d_2` denotes the Wasserstein-2 distance between persis- | | - | | tence diagrams. | | + | diagrams. | where :math:`d_2` denotes the Wasserstein-2 distance between | | + | | persistence diagrams. | | | | It is known to exist and is generically unique. However, an exact | | - | | computation is in general untractable. Current implementation avai- | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | - | | -lable is based on [Turner et al, 2014], and uses an EM-scheme to | | + | | computation is in general untractable. Current implementation | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | + | | available is based on [Turner et al, 2014], and uses an EM-scheme to | | | | provide a local minimum of the variance functional (somewhat similar | | | | to the Lloyd algorithm to estimate a solution to the k-means | | | | problem). The local minimum returned depends on the initialization of| | -- cgit v1.2.3 From 4c0e6e4144dd3cf6da9600fd4b9bbcac5e664b73 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Sun, 26 Jan 2020 02:54:35 -0500 Subject: added extended persistence function --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 71 +++++++++++++++++++++++++++ src/python/gudhi/simplex_tree.pxd | 2 + src/python/gudhi/simplex_tree.pyx | 14 ++++++ 3 files changed, 87 insertions(+) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 76608008..4786b244 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -125,6 +125,8 @@ class Simplex_tree { private: typedef typename Dictionary::iterator Dictionary_it; typedef typename Dictionary_it::value_type Dit_value_t; + double minval_; + double maxval_; struct return_first { Vertex_handle operator()(const Dit_value_t& p_sh) const { @@ -1465,6 +1467,75 @@ class Simplex_tree { } } + /** \brief Retrieve good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. Need extend_filtration to be called first! + * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration and this->get_persistence. + * @return A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. + */ + std::vector>>> convert(const std::vector>>& dgm){ + std::vector>>> new_dgm(4); double x, y; + for(unsigned int i = 0; i < dgm.size(); i++){ int h = dgm[i].first; double px = dgm[i].second.first; double py = dgm[i].second.second; + if(std::isinf(py)) continue; + else{ + if ((px <= -1) & (py <= -1)){x = minval_ + (maxval_-minval_)*(px + 2); y = minval_ + (maxval_-minval_)*(py + 2); new_dgm[0].push_back(std::make_pair(h, std::make_pair(x,y))); } + if ((px >= 1) & (py >= 1)){x = minval_ - (maxval_-minval_)*(px - 2); y = minval_ - (maxval_-minval_)*(py - 2); new_dgm[1].push_back(std::make_pair(h, std::make_pair(x,y))); } + if ((px <= -1) & (py >= 1)){x = minval_ + (maxval_-minval_)*(px + 2); y = minval_ - (maxval_-minval_)*(py - 2); + if (x <= y) new_dgm[2].push_back(std::make_pair(h, std::make_pair(x,y))); + else new_dgm[3].push_back(std::make_pair(h, std::make_pair(x,y))); + } + } + } + return new_dgm; + } + + /** \brief Extend filtration for computing extended persistence. + */ + void extend_filtration() { + + // Compute maximum and minimum of filtration values + int maxvert = -std::numeric_limits::infinity(); + std::vector filt; + for (auto sh : this->complex_simplex_range()) {if (this->dimension(sh) == 0){filt.push_back(this->filtration(sh)); maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert);}} + minval_ = *std::min_element(filt.begin(), filt.end()); + maxval_ = *std::max_element(filt.begin(), filt.end()); + maxvert += 1; + + // Compute vectors of integers corresponding to the Simplex handles + std::vector > splxs; + for (auto sh : this->complex_simplex_range()) { + std::vector vr; for (auto vh : this->simplex_vertex_range(sh)){vr.push_back(vh);} + splxs.push_back(vr); + } + + // Add point for coning the simplicial complex + int count = this->num_simplices(); + std::vector cone; cone.push_back(maxvert); auto ins = this->insert_simplex(cone, -3); this->assign_key(ins.first, count); count++; + + // For each simplex + for (auto vr : splxs){ + // Create cone on simplex + auto sh = this->find(vr); vr.push_back(maxvert); + if (this->dimension(sh) == 0){ + // Assign ascending value between -2 and -1 to vertex + double v = this->filtration(sh); + this->assign_filtration(sh, -2 + (v-minval_)/(maxval_-minval_)); + // Assign descending value between 1 and 2 to cone on vertex + auto ins = this->insert_simplex(vr, 2 - (v-minval_)/(maxval_-minval_)); + this->assign_key(ins.first, count); + } + else{ + // Assign value -3 to simplex and cone on simplex + this->assign_filtration(sh, -3); + auto ins = this->insert_simplex(vr, -3); + this->assign_key(ins.first, count); + } + count++; + } + + this->make_filtration_non_decreasing(); this->initialize_filtration(); + + } + + private: Vertex_handle null_vertex_; /** \brief Total number of simplices in the complex, without the empty simplex.*/ diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 1066d44b..39f2a45f 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -43,6 +43,8 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": void remove_maximal_simplex(vector[int] simplex) bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() + void extend_filtration() + vector[vector[pair[int, pair[double, double]]]] convert(vector[pair[int, pair[double, double]]]) cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index b18627c4..cfab14f4 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -386,6 +386,20 @@ cdef class SimplexTree: """ return self.get_ptr().make_filtration_non_decreasing() + def extend_filtration(self): + """ This function extends filtration for computing extended persistence. + """ + return self.get_ptr().extend_filtration() + + def convert(self, dgm): + """This function retrieves good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. Need extend_filtration to be called first! + + :param dgm: Persistence diagram obtained after calling this->extend_filtration and this->get_persistence. + :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. + """ + return self.get_ptr().convert(dgm) + + def persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): """This function returns the persistence of the simplicial complex. -- cgit v1.2.3 From a064f5698fedbe13f6c343cb0b82e0f4d72caffb Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 27 Jan 2020 17:37:31 +0100 Subject: A first naive iterator implementation with yield --- src/Simplex_tree/example/simple_simplex_tree.cpp | 4 ++++ src/python/gudhi/simplex_tree.pxd | 8 ++++++- src/python/gudhi/simplex_tree.pyx | 18 +++++++-------- src/python/include/Simplex_tree_interface.h | 28 ++++++++++++++---------- 4 files changed, 37 insertions(+), 21 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/example/simple_simplex_tree.cpp b/src/Simplex_tree/example/simple_simplex_tree.cpp index 4353939f..92ab923b 100644 --- a/src/Simplex_tree/example/simple_simplex_tree.cpp +++ b/src/Simplex_tree/example/simple_simplex_tree.cpp @@ -165,6 +165,10 @@ int main(int argc, char* const argv[]) { // ++ GENERAL VARIABLE SET + //std::vector::const_iterator + std::vector::const_iterator begin = simplexTree.filtration_simplex_range().begin(); + auto end = simplexTree.filtration_simplex_range().end(); + std::cout << "********************************************************************\n"; // Display the Simplex_tree - Can not be done in the middle of 2 inserts std::cout << "* The complex contains " << simplexTree.num_simplices() << " simplices\n"; diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 96d14079..caf3c459 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -21,6 +21,9 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_options_full_featured: pass + cdef cppclass Simplex_tree_simplex_handle "Gudhi::Simplex_tree_interface::Simplex_handle": + pass + cdef cppclass Simplex_tree_interface_full_featured "Gudhi::Simplex_tree_interface": Simplex_tree() double simplex_filtration(vector[int] simplex) @@ -34,7 +37,6 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool find_simplex(vector[int] simplex) bool insert_simplex_and_subfaces(vector[int] simplex, double filtration) - vector[pair[vector[int], double]] get_filtration() vector[pair[vector[int], double]] get_skeleton(int dimension) vector[pair[vector[int], double]] get_star(vector[int] simplex) vector[pair[vector[int], double]] get_cofaces(vector[int] simplex, @@ -43,6 +45,10 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": void remove_maximal_simplex(vector[int] simplex) bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() + # Iterators over Simplex tree + pair[vector[int], double] get_simplex_filtration(Simplex_tree_simplex_handle f_simplex) + vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() + vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index b18627c4..478139de 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -7,6 +7,7 @@ # Modification(s): # - YYYY/MM Author: Description of the modification +from cython.operator import dereference, preincrement from libc.stdint cimport intptr_t from numpy import array as np_array cimport simplex_tree @@ -214,15 +215,14 @@ cdef class SimplexTree: :returns: The simplices sorted by increasing filtration values. :rtype: list of tuples(simplex, filtration) """ - cdef vector[pair[vector[int], double]] filtration \ - = self.get_ptr().get_filtration() - ct = [] - for filtered_complex in filtration: - v = [] - for vertex in filtered_complex.first: - v.append(vertex) - ct.append((v, filtered_complex.second)) - return ct + cdef vector[Simplex_tree_simplex_handle].const_iterator it = self.get_ptr().get_filtration_iterator_begin() + cdef vector[Simplex_tree_simplex_handle].const_iterator end = self.get_ptr().get_filtration_iterator_end() + + while True: + yield(self.get_ptr().get_simplex_filtration(dereference(it))) + preincrement(it) + if it == end: + raise StopIteration def get_skeleton(self, dimension): """This function returns the (simplices of the) skeleton of a maximum diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 06f31341..843966cd 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -33,7 +33,8 @@ class Simplex_tree_interface : public Simplex_tree { using Simplex_handle = typename Base::Simplex_handle; using Insertion_result = typename std::pair; using Simplex = std::vector; - using Filtered_simplices = std::vector>; + using Filtered_simplex = std::pair; + using Filtered_simplices = std::vector; public: bool find_simplex(const Simplex& vh) { @@ -82,17 +83,12 @@ class Simplex_tree_interface : public Simplex_tree { Base::initialize_filtration(); } - Filtered_simplices get_filtration() { - Base::initialize_filtration(); - Filtered_simplices filtrations; - for (auto f_simplex : Base::filtration_simplex_range()) { - Simplex simplex; - for (auto vertex : Base::simplex_vertex_range(f_simplex)) { - simplex.insert(simplex.begin(), vertex); - } - filtrations.push_back(std::make_pair(simplex, Base::filtration(f_simplex))); + Filtered_simplex get_simplex_filtration(Simplex_handle f_simplex) { + Simplex simplex; + for (auto vertex : Base::simplex_vertex_range(f_simplex)) { + simplex.insert(simplex.begin(), vertex); } - return filtrations; + return std::make_pair(simplex, Base::filtration(f_simplex)); } Filtered_simplices get_skeleton(int dimension) { @@ -135,6 +131,16 @@ class Simplex_tree_interface : public Simplex_tree { Base::initialize_filtration(); pcoh = new Gudhi::Persistent_cohomology_interface(*this); } + + // Iterator over the simplex tree + typename std::vector::const_iterator get_filtration_iterator_begin() { + Base::initialize_filtration(); + return Base::filtration_simplex_range().begin(); + } + + typename std::vector::const_iterator get_filtration_iterator_end() { + return Base::filtration_simplex_range().end(); + } }; } // namespace Gudhi -- cgit v1.2.3 From ef2c5b53e88321f07ad93496f00dde16dc20f018 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 28 Jan 2020 11:05:39 +0100 Subject: Code review: rename get_simplex_filtration with get_simplex_and_filtration. Remove exception raise. Fix failed tests. Reword documentation --- .../example/alpha_complex_from_points_example.py | 5 +- .../example/rips_complex_from_points_example.py | 5 +- src/python/example/simplex_tree_example.py | 5 +- src/python/gudhi/simplex_tree.pxd | 2 +- src/python/gudhi/simplex_tree.pyx | 10 +-- src/python/include/Simplex_tree_interface.h | 6 +- src/python/test/test_alpha_complex.py | 50 ++++++------ src/python/test/test_euclidean_witness_complex.py | 46 ++++++----- src/python/test/test_rips_complex.py | 53 +++++++------ src/python/test/test_simplex_tree.py | 90 +++++++++++----------- src/python/test/test_tangential_complex.py | 19 +++-- 11 files changed, 161 insertions(+), 130 deletions(-) (limited to 'src/python') diff --git a/src/python/example/alpha_complex_from_points_example.py b/src/python/example/alpha_complex_from_points_example.py index 844d7a82..465632eb 100755 --- a/src/python/example/alpha_complex_from_points_example.py +++ b/src/python/example/alpha_complex_from_points_example.py @@ -47,7 +47,10 @@ else: print("[4] Not found...") print("dimension=", simplex_tree.dimension()) -print("filtrations=", simplex_tree.get_filtration()) +print("filtrations=") +for simplex_with_filtration in simplex_tree.get_filtration(): + print("(%s, %.2f)" % tuple(simplex_with_filtration)) + print("star([0])=", simplex_tree.get_star([0])) print("coface([0], 1)=", simplex_tree.get_cofaces([0], 1)) diff --git a/src/python/example/rips_complex_from_points_example.py b/src/python/example/rips_complex_from_points_example.py index 59d8a261..c05703c6 100755 --- a/src/python/example/rips_complex_from_points_example.py +++ b/src/python/example/rips_complex_from_points_example.py @@ -22,6 +22,9 @@ rips = gudhi.RipsComplex(points=[[0, 0], [1, 0], [0, 1], [1, 1]], max_edge_lengt simplex_tree = rips.create_simplex_tree(max_dimension=1) -print("filtrations=", simplex_tree.get_filtration()) +print("filtrations=") +for simplex_with_filtration in simplex_tree.get_filtration(): + print("(%s, %.2f)" % tuple(simplex_with_filtration)) + print("star([0])=", simplex_tree.get_star([0])) print("coface([0], 1)=", simplex_tree.get_cofaces([0], 1)) diff --git a/src/python/example/simplex_tree_example.py b/src/python/example/simplex_tree_example.py index 30de00da..7f20c389 100755 --- a/src/python/example/simplex_tree_example.py +++ b/src/python/example/simplex_tree_example.py @@ -39,7 +39,10 @@ else: print("dimension=", st.dimension()) st.initialize_filtration() -print("filtration=", st.get_filtration()) +print("filtration=") +for simplex_with_filtration in st.get_filtration(): + print("(%s, %.2f)" % tuple(simplex_with_filtration)) + print("filtration[1, 2]=", st.filtration([1, 2])) print("filtration[4, 2]=", st.filtration([4, 2])) diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index caf3c459..1b0dc881 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -46,7 +46,7 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() # Iterators over Simplex tree - pair[vector[int], double] get_simplex_filtration(Simplex_tree_simplex_handle f_simplex) + pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 478139de..22978b6e 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -209,20 +209,18 @@ cdef class SimplexTree: filtration) def get_filtration(self): - """This function returns a list of all simplices with their given + """This function returns a generator with simplices and their given filtration values. :returns: The simplices sorted by increasing filtration values. - :rtype: list of tuples(simplex, filtration) + :rtype: generator with tuples(simplex, filtration) """ cdef vector[Simplex_tree_simplex_handle].const_iterator it = self.get_ptr().get_filtration_iterator_begin() cdef vector[Simplex_tree_simplex_handle].const_iterator end = self.get_ptr().get_filtration_iterator_end() - while True: - yield(self.get_ptr().get_simplex_filtration(dereference(it))) + while it != end: + yield(self.get_ptr().get_simplex_and_filtration(dereference(it))) preincrement(it) - if it == end: - raise StopIteration def get_skeleton(self, dimension): """This function returns the (simplices of the) skeleton of a maximum diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 843966cd..c0bbc3d9 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -33,8 +33,8 @@ class Simplex_tree_interface : public Simplex_tree { using Simplex_handle = typename Base::Simplex_handle; using Insertion_result = typename std::pair; using Simplex = std::vector; - using Filtered_simplex = std::pair; - using Filtered_simplices = std::vector; + using Simplex_and_filtration = std::pair; + using Filtered_simplices = std::vector; public: bool find_simplex(const Simplex& vh) { @@ -83,7 +83,7 @@ class Simplex_tree_interface : public Simplex_tree { Base::initialize_filtration(); } - Filtered_simplex get_simplex_filtration(Simplex_handle f_simplex) { + Simplex_and_filtration get_simplex_and_filtration(Simplex_handle f_simplex) { Simplex simplex; for (auto vertex : Base::simplex_vertex_range(f_simplex)) { simplex.insert(simplex.begin(), vertex); diff --git a/src/python/test/test_alpha_complex.py b/src/python/test/test_alpha_complex.py index 3761fe16..ceead919 100755 --- a/src/python/test/test_alpha_complex.py +++ b/src/python/test/test_alpha_complex.py @@ -40,19 +40,21 @@ def test_infinite_alpha(): assert simplex_tree.num_simplices() == 11 assert simplex_tree.num_vertices() == 4 - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([3], 0.0), - ([0, 1], 0.25), - ([0, 2], 0.25), - ([1, 3], 0.25), - ([2, 3], 0.25), - ([1, 2], 0.5), - ([0, 1, 2], 0.5), - ([1, 2, 3], 0.5), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([3], 0.0)) + assert(next(filtration_generator) == ([0, 1], 0.25)) + assert(next(filtration_generator) == ([0, 2], 0.25)) + assert(next(filtration_generator) == ([1, 3], 0.25)) + assert(next(filtration_generator) == ([2, 3], 0.25)) + assert(next(filtration_generator) == ([1, 2], 0.5)) + assert(next(filtration_generator) == ([0, 1, 2], 0.5)) + assert(next(filtration_generator) == ([1, 2, 3], 0.5)) + with pytest.raises(StopIteration): + next(filtration_generator) + assert simplex_tree.get_star([0]) == [ ([0], 0.0), ([0, 1], 0.25), @@ -105,16 +107,18 @@ def test_filtered_alpha(): else: assert False - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([3], 0.0), - ([0, 1], 0.25), - ([0, 2], 0.25), - ([1, 3], 0.25), - ([2, 3], 0.25), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([3], 0.0)) + assert(next(filtration_generator) == ([0, 1], 0.25)) + assert(next(filtration_generator) == ([0, 2], 0.25)) + assert(next(filtration_generator) == ([1, 3], 0.25)) + assert(next(filtration_generator) == ([2, 3], 0.25)) + with pytest.raises(StopIteration): + next(filtration_generator) + assert simplex_tree.get_star([0]) == [([0], 0.0), ([0, 1], 0.25), ([0, 2], 0.25)] assert simplex_tree.get_cofaces([0], 1) == [([0, 1], 0.25), ([0, 2], 0.25)] diff --git a/src/python/test/test_euclidean_witness_complex.py b/src/python/test/test_euclidean_witness_complex.py index c18d2484..16ff1ef4 100755 --- a/src/python/test/test_euclidean_witness_complex.py +++ b/src/python/test/test_euclidean_witness_complex.py @@ -9,6 +9,7 @@ """ import gudhi +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -40,15 +41,16 @@ def test_witness_complex(): assert landmarks[1] == euclidean_witness_complex.get_point(1) assert landmarks[2] == euclidean_witness_complex.get_point(2) - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([0, 1], 0.0), - ([2], 0.0), - ([0, 2], 0.0), - ([1, 2], 0.0), - ([0, 1, 2], 0.0), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([0, 1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([0, 2], 0.0)) + assert(next(filtration_generator) == ([1, 2], 0.0)) + assert(next(filtration_generator) == ([0, 1, 2], 0.0)) + with pytest.raises(StopIteration): + next(filtration_generator) def test_empty_euclidean_strong_witness_complex(): @@ -78,18 +80,24 @@ def test_strong_witness_complex(): assert landmarks[1] == euclidean_strong_witness_complex.get_point(1) assert landmarks[2] == euclidean_strong_witness_complex.get_point(2) - assert simplex_tree.get_filtration() == [([0], 0.0), ([1], 0.0), ([2], 0.0)] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + with pytest.raises(StopIteration): + next(filtration_generator) simplex_tree = euclidean_strong_witness_complex.create_simplex_tree( max_alpha_square=100.0 ) - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([1, 2], 15.0), - ([0, 2], 34.0), - ([0, 1], 37.0), - ([0, 1, 2], 37.0), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([1, 2], 15.0)) + assert(next(filtration_generator) == ([0, 2], 34.0)) + assert(next(filtration_generator) == ([0, 1], 37.0)) + assert(next(filtration_generator) == ([0, 1, 2], 37.0)) + with pytest.raises(StopIteration): + next(filtration_generator) diff --git a/src/python/test/test_rips_complex.py b/src/python/test/test_rips_complex.py index b02a68e1..bd31c47c 100755 --- a/src/python/test/test_rips_complex.py +++ b/src/python/test/test_rips_complex.py @@ -10,6 +10,7 @@ from gudhi import RipsComplex from math import sqrt +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -32,18 +33,20 @@ def test_rips_from_points(): assert simplex_tree.num_simplices() == 10 assert simplex_tree.num_vertices() == 4 - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([3], 0.0), - ([0, 1], 1.0), - ([0, 2], 1.0), - ([1, 3], 1.0), - ([2, 3], 1.0), - ([1, 2], 1.4142135623730951), - ([0, 3], 1.4142135623730951), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([3], 0.0)) + assert(next(filtration_generator) == ([0, 1], 1.0)) + assert(next(filtration_generator) == ([0, 2], 1.0)) + assert(next(filtration_generator) == ([1, 3], 1.0)) + assert(next(filtration_generator) == ([2, 3], 1.0)) + assert(next(filtration_generator) == ([1, 2], 1.4142135623730951)) + assert(next(filtration_generator) == ([0, 3], 1.4142135623730951)) + with pytest.raises(StopIteration): + next(filtration_generator) + assert simplex_tree.get_star([0]) == [ ([0], 0.0), ([0, 1], 1.0), @@ -95,18 +98,20 @@ def test_rips_from_distance_matrix(): assert simplex_tree.num_simplices() == 10 assert simplex_tree.num_vertices() == 4 - assert simplex_tree.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([3], 0.0), - ([0, 1], 1.0), - ([0, 2], 1.0), - ([1, 3], 1.0), - ([2, 3], 1.0), - ([1, 2], 1.4142135623730951), - ([0, 3], 1.4142135623730951), - ] + filtration_generator = simplex_tree.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([3], 0.0)) + assert(next(filtration_generator) == ([0, 1], 1.0)) + assert(next(filtration_generator) == ([0, 2], 1.0)) + assert(next(filtration_generator) == ([1, 3], 1.0)) + assert(next(filtration_generator) == ([2, 3], 1.0)) + assert(next(filtration_generator) == ([1, 2], 1.4142135623730951)) + assert(next(filtration_generator) == ([0, 3], 1.4142135623730951)) + with pytest.raises(StopIteration): + next(filtration_generator) + assert simplex_tree.get_star([0]) == [ ([0], 0.0), ([0, 1], 1.0), diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 1822c43b..0f3db7ac 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -9,6 +9,7 @@ """ from gudhi import SimplexTree +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -126,55 +127,58 @@ def test_expansion(): assert st.num_vertices() == 7 assert st.num_simplices() == 17 - assert st.get_filtration() == [ - ([2], 0.1), - ([3], 0.1), - ([2, 3], 0.1), - ([0], 0.2), - ([0, 2], 0.2), - ([1], 0.3), - ([0, 1], 0.3), - ([1, 3], 0.4), - ([1, 2], 0.5), - ([5], 0.6), - ([6], 0.6), - ([5, 6], 0.6), - ([4], 0.7), - ([2, 4], 0.7), - ([0, 3], 0.8), - ([4, 6], 0.9), - ([3, 6], 1.0), - ] + + filtration_generator = st.get_filtration() + assert(next(filtration_generator) == ([2], 0.1)) + assert(next(filtration_generator) == ([3], 0.1)) + assert(next(filtration_generator) == ([2, 3], 0.1)) + assert(next(filtration_generator) == ([0], 0.2)) + assert(next(filtration_generator) == ([0, 2], 0.2)) + assert(next(filtration_generator) == ([1], 0.3)) + assert(next(filtration_generator) == ([0, 1], 0.3)) + assert(next(filtration_generator) == ([1, 3], 0.4)) + assert(next(filtration_generator) == ([1, 2], 0.5)) + assert(next(filtration_generator) == ([5], 0.6)) + assert(next(filtration_generator) == ([6], 0.6)) + assert(next(filtration_generator) == ([5, 6], 0.6)) + assert(next(filtration_generator) == ([4], 0.7)) + assert(next(filtration_generator) == ([2, 4], 0.7)) + assert(next(filtration_generator) == ([0, 3], 0.8)) + assert(next(filtration_generator) == ([4, 6], 0.9)) + assert(next(filtration_generator) == ([3, 6], 1.0)) + with pytest.raises(StopIteration): + next(filtration_generator) st.expansion(3) assert st.num_vertices() == 7 assert st.num_simplices() == 22 st.initialize_filtration() - assert st.get_filtration() == [ - ([2], 0.1), - ([3], 0.1), - ([2, 3], 0.1), - ([0], 0.2), - ([0, 2], 0.2), - ([1], 0.3), - ([0, 1], 0.3), - ([1, 3], 0.4), - ([1, 2], 0.5), - ([0, 1, 2], 0.5), - ([1, 2, 3], 0.5), - ([5], 0.6), - ([6], 0.6), - ([5, 6], 0.6), - ([4], 0.7), - ([2, 4], 0.7), - ([0, 3], 0.8), - ([0, 1, 3], 0.8), - ([0, 2, 3], 0.8), - ([0, 1, 2, 3], 0.8), - ([4, 6], 0.9), - ([3, 6], 1.0), - ] + filtration_generator = st.get_filtration() + assert(next(filtration_generator) == ([2], 0.1)) + assert(next(filtration_generator) == ([3], 0.1)) + assert(next(filtration_generator) == ([2, 3], 0.1)) + assert(next(filtration_generator) == ([0], 0.2)) + assert(next(filtration_generator) == ([0, 2], 0.2)) + assert(next(filtration_generator) == ([1], 0.3)) + assert(next(filtration_generator) == ([0, 1], 0.3)) + assert(next(filtration_generator) == ([1, 3], 0.4)) + assert(next(filtration_generator) == ([1, 2], 0.5)) + assert(next(filtration_generator) == ([0, 1, 2], 0.5)) + assert(next(filtration_generator) == ([1, 2, 3], 0.5)) + assert(next(filtration_generator) == ([5], 0.6)) + assert(next(filtration_generator) == ([6], 0.6)) + assert(next(filtration_generator) == ([5, 6], 0.6)) + assert(next(filtration_generator) == ([4], 0.7)) + assert(next(filtration_generator) == ([2, 4], 0.7)) + assert(next(filtration_generator) == ([0, 3], 0.8)) + assert(next(filtration_generator) == ([0, 1, 3], 0.8)) + assert(next(filtration_generator) == ([0, 2, 3], 0.8)) + assert(next(filtration_generator) == ([0, 1, 2, 3], 0.8)) + assert(next(filtration_generator) == ([4, 6], 0.9)) + assert(next(filtration_generator) == ([3, 6], 1.0)) + with pytest.raises(StopIteration): + next(filtration_generator) def test_automatic_dimension(): diff --git a/src/python/test/test_tangential_complex.py b/src/python/test/test_tangential_complex.py index e650e99c..90e2c75b 100755 --- a/src/python/test/test_tangential_complex.py +++ b/src/python/test/test_tangential_complex.py @@ -9,6 +9,7 @@ """ from gudhi import TangentialComplex, SimplexTree +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -37,14 +38,16 @@ def test_tangential(): assert st.num_simplices() == 6 assert st.num_vertices() == 4 - assert st.get_filtration() == [ - ([0], 0.0), - ([1], 0.0), - ([2], 0.0), - ([0, 2], 0.0), - ([3], 0.0), - ([1, 3], 0.0), - ] + filtration_generator = st.get_filtration() + assert(next(filtration_generator) == ([0], 0.0)) + assert(next(filtration_generator) == ([1], 0.0)) + assert(next(filtration_generator) == ([2], 0.0)) + assert(next(filtration_generator) == ([0, 2], 0.0)) + assert(next(filtration_generator) == ([3], 0.0)) + assert(next(filtration_generator) == ([1, 3], 0.0)) + with pytest.raises(StopIteration): + next(filtration_generator) + assert st.get_cofaces([0], 1) == [([0, 2], 0.0)] assert point_list[0] == tc.get_point(0) -- cgit v1.2.3 From 68b6e3f3d641cd4a1e86f08bff96e417cc17ac59 Mon Sep 17 00:00:00 2001 From: takeshimeonerespect Date: Fri, 31 Jan 2020 08:08:43 +0100 Subject: timedelay added on fork --- src/python/CMakeLists.txt | 5 +++ src/python/doc/point_cloud.rst | 7 ++++ src/python/gudhi/point_cloud/timedelay.py | 56 +++++++++++++++++++++++++++++++ src/python/test/test_point_cloud.py | 35 +++++++++++++++++++ 4 files changed, 103 insertions(+) create mode 100644 src/python/gudhi/point_cloud/timedelay.py create mode 100755 src/python/test/test_point_cloud.py (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index b558d4c4..b23ec8a9 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -52,6 +52,7 @@ if(PYTHONINTERP_FOUND) # Modules that should not be auto-imported in __init__.py set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'representations', ") set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'wasserstein', ") + set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'point_cloud', ") add_gudhi_debug_info("Python version ${PYTHON_VERSION_STRING}") add_gudhi_debug_info("Cython version ${CYTHON_VERSION}") @@ -221,6 +222,7 @@ endif(CGAL_FOUND) file(COPY "gudhi/persistence_graphical_tools.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") file(COPY "gudhi/representations" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi/") file(COPY "gudhi/wasserstein.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") + file(COPY "gudhi/point_cloud" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") add_custom_command( OUTPUT gudhi.so @@ -399,6 +401,9 @@ endif(CGAL_FOUND) add_gudhi_py_test(test_representations) endif() + # Point cloud + add_gudhi_py_test(test_point_cloud) + # Documentation generation is available through sphinx - requires all modules if(SPHINX_PATH) if(MATPLOTLIB_FOUND) diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index d668428a..55c74ff3 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -20,3 +20,10 @@ Subsampling :members: :special-members: :show-inheritance: + +TimeDelayEmbedding +------------------ + +.. autoclass:: gudhi.point_cloud.timedelay.TimeDelayEmbedding + :members: + diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py new file mode 100644 index 00000000..5c7ba542 --- /dev/null +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -0,0 +1,56 @@ +import numpy as np + +class TimeDelayEmbedding: + """Point cloud transformation class. + + Embeds time-series data in the R^d according to Takens' Embedding Theorem + and obtains the coordinates of each point. + + Parameters + ---------- + dim : int, optional (default=3) + `d` of R^d to be embedded. + + delay : int, optional (default=1) + Time-Delay embedding. + + skip : int, optional (default=1) + How often to skip embedded points. + + """ + def __init__(self, dim=3, delay=1, skip=1): + self._dim = dim + self._delay = delay + self._skip = skip + + def __call__(self, *args, **kwargs): + return self.transform(*args, **kwargs) + + def _transform(self, ts): + """Guts of transform method.""" + return ts[ + np.add.outer( + np.arange(0, len(ts)-self._delay*(self._dim-1), self._skip), + np.arange(0, self._dim*self._delay, self._delay)) + ] + + def transform(self, ts): + """Transform method. + + Parameters + ---------- + ts : list[float] or list[list[float]] + A single or multiple time-series data. + + Returns + ------- + point clouds : list[list[float, float, float]] or list[list[list[float, float, float]]] + Makes point cloud every a single time-series data. + """ + ndts = np.array(ts) + if ndts.ndim == 1: + # for single. + return self._transform(ndts).tolist() + else: + # for multiple. + return np.apply_along_axis(self._transform, 1, ndts).tolist() diff --git a/src/python/test/test_point_cloud.py b/src/python/test/test_point_cloud.py new file mode 100755 index 00000000..2ee0c1fb --- /dev/null +++ b/src/python/test/test_point_cloud.py @@ -0,0 +1,35 @@ +from gudhi.point_cloud.timedelay import TimeDelayEmbedding + +def test_normal(): + # Sample array + ts = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] + # Normal case. + prep = TimeDelayEmbedding() + attractor = prep(ts) + assert (attractor[0] == [1, 2, 3]) + assert (attractor[1] == [2, 3, 4]) + assert (attractor[2] == [3, 4, 5]) + assert (attractor[3] == [4, 5, 6]) + assert (attractor[4] == [5, 6, 7]) + assert (attractor[5] == [6, 7, 8]) + assert (attractor[6] == [7, 8, 9]) + assert (attractor[7] == [8, 9, 10]) + # Delay = 3 + prep = TimeDelayEmbedding(delay=3) + attractor = prep(ts) + assert (attractor[0] == [1, 4, 7]) + assert (attractor[1] == [2, 5, 8]) + assert (attractor[2] == [3, 6, 9]) + assert (attractor[3] == [4, 7, 10]) + # Skip = 3 + prep = TimeDelayEmbedding(skip=3) + attractor = prep(ts) + assert (attractor[0] == [1, 2, 3]) + assert (attractor[1] == [4, 5, 6]) + assert (attractor[2] == [7, 8, 9]) + # Delay = 2 / Skip = 2 + prep = TimeDelayEmbedding(delay=2, skip=2) + attractor = prep(ts) + assert (attractor[0] == [1, 3, 5]) + assert (attractor[1] == [3, 5, 7]) + assert (attractor[2] == [5, 7, 9]) -- cgit v1.2.3 From a145c7168fdb3f4205cb68870f06fc5cb8e08dea Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Fri, 31 Jan 2020 14:49:59 -0500 Subject: factorization of distance and kernel computations --- src/python/gudhi/representations/kernel_methods.py | 131 +++++++---- src/python/gudhi/representations/metrics.py | 247 +++++++++------------ 2 files changed, 193 insertions(+), 185 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py index bfc83aff..bbbb7c31 100644 --- a/src/python/gudhi/representations/kernel_methods.py +++ b/src/python/gudhi/representations/kernel_methods.py @@ -9,13 +9,83 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin -from sklearn.metrics import pairwise_distances -from .metrics import SlicedWassersteinDistance, PersistenceFisherDistance +from sklearn.metrics import pairwise_distances, pairwise_kernels +from .metrics import SlicedWassersteinDistance, PersistenceFisherDistance, sklearn_wrapper, pairwise_persistence_diagram_distances, sliced_wasserstein_distance, persistence_fisher_distance +from .preprocessing import Padding ############################################# # Kernel methods ############################ ############################################# +def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_approx=None, bandwidth=1.): + """ + This is a function for computing the persistence weighted Gaussian kernel value from two persistence diagrams. The persistence weighted Gaussian kernel is computed by convolving the persistence diagram points with weighted Gaussian kernels. See http://proceedings.mlr.press/v48/kusano16.html for more details. + :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param D2: (m x 2) numpy.array encoding the second diagram. + :param bandwidth: bandwidth of the Gaussian kernel with which persistence diagrams will be convolved + :param weight: weight function for the persistence diagram points. This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. + :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + :returns: the persistence weighted Gaussian kernel value between persistence diagrams. + :rtype: float + """ + ws1 = np.array([weight(D1[j,:]) for j in range(len(D1))]) + ws2 = np.array([weight(D2[j,:]) for j in range(len(D2))]) + if kernel_approx is not None: + approx1 = np.sum(np.multiply(ws1[:,np.newaxis], kernel_approx.transform(D1)), axis=0) + approx2 = np.sum(np.multiply(ws2[:,np.newaxis], kernel_approx.transform(D2)), axis=0) + return (1./(np.sqrt(2*np.pi)*bandwidth)) * np.matmul(approx1, approx2.T) + else: + W = np.matmul(ws1[:,np.newaxis], ws2[np.newaxis,:]) + E = (1./(np.sqrt(2*np.pi)*bandwidth)) * np.exp(-np.square(pairwise_distances(D1,D2))/(2*bandwidth*bandwidth)) + return np.sum(np.multiply(W, E)) + +def persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): + """ + This is a function for computing the persistence scale space kernel value from two persistence diagrams. The persistence scale space kernel is computed by adding the symmetric to the diagonal of each point in each persistence diagram, with negative weight, and then convolving the points with a Gaussian kernel. See https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Reininghaus_A_Stable_Multi-Scale_2015_CVPR_paper.pdf for more details. + :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param D2: (m x 2) numpy.array encoding the second diagram. + :param bandwidth: bandwidth of the Gaussian kernel with which persistence diagrams will be convolved + :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + :returns: the persistence scale space kernel value between persistence diagrams. + :rtype: float + """ + DD1 = np.concatenate([D1, D1[:,[1,0]]], axis=0) + DD2 = np.concatenate([D2, D2[:,[1,0]]], axis=0) + weight_pss = lambda x: 1 if x[1] >= x[0] else -1 + return 0.5 * persistence_weighted_gaussian_kernel(DD1, DD2, weight=weight_pss, kernel_approx=kernel_approx, bandwidth=bandwidth) + +def pairwise_persistence_diagram_kernels(X, Y=None, metric="sliced_wasserstein", **kwargs): + """ + This function computes the kernel matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). + :param X: first list of persistence diagrams. + :param Y: second list of persistence diagrams (optional). If None, pairwise kernel values are computed from the first list only. + :param metric: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + :returns: kernel matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) + :rtype: float + """ + if Y is None: + YY = None + pX = Padding(use=True).fit_transform(X) + diag_len = len(pX[0]) + XX = np.reshape(np.vstack(pX), [-1, diag_len*3]) + else: + nX, nY = len(X), len(Y) + pD = Padding(use=True).fit_transform(X + Y) + diag_len = len(pD[0]) + XX = np.reshape(np.vstack(pD[:nX]), [-1, diag_len*3]) + YY = np.reshape(np.vstack(pD[nX:]), [-1, diag_len*3]) + + if metric == "sliced_wasserstein": + return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="sliced_wasserstein", num_directions=kwargs["num_directions"]) / kwargs["bandwidth"]) + elif metric == "persistence_fisher": + return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="persistence_fisher", kernel_approx=kwargs["kernel_approx"], bandwidth=kwargs["bandwidth"]) / kwargs["bandwidth_fisher"]) + elif metric == "persistence_scale_space": + return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_scale_space_kernel, **kwargs)) + elif metric == "persistence_weighted_gaussian": + return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_weighted_gaussian_kernel, **kwargs)) + else: + return pairwise_kernels(XX, YY, metric=sklearn_wrapper(metric, **kwargs)) + class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): """ This is a class for computing the sliced Wasserstein kernel matrix from a list of persistence diagrams. The sliced Wasserstein kernel is computed by exponentiating the corresponding sliced Wasserstein distance with a Gaussian kernel. See http://proceedings.mlr.press/v70/carriere17a.html for more details. @@ -29,7 +99,7 @@ class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the kernel computation (default 10). """ self.bandwidth = bandwidth - self.sw_ = SlicedWassersteinDistance(num_directions=num_directions) + self.num_directions = num_directions def fit(self, X, y=None): """ @@ -39,7 +109,7 @@ class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): X (list of n x 2 numpy arrays): input persistence diagrams. y (n x 1 array): persistence diagram labels (unused). """ - self.sw_.fit(X, y) + self.diagrams_ = X return self def transform(self, X): @@ -52,7 +122,7 @@ class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise sliced Wasserstein kernel values. """ - return np.exp(-self.sw_.transform(X)/self.bandwidth) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="sliced_wasserstein", bandwidth=self.bandwidth, num_directions=self.num_directions) class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): """ @@ -78,10 +148,7 @@ class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): X (list of n x 2 numpy arrays): input persistence diagrams. y (n x 1 array): persistence diagram labels (unused). """ - self.diagrams_ = list(X) - self.ws_ = [ np.array([self.weight(self.diagrams_[i][j,:]) for j in range(self.diagrams_[i].shape[0])]) for i in range(len(self.diagrams_)) ] - if self.kernel_approx is not None: - self.approx_ = np.concatenate([np.sum(np.multiply(self.ws_[i][:,np.newaxis], self.kernel_approx.transform(self.diagrams_[i])), axis=0)[np.newaxis,:] for i in range(len(self.diagrams_))]) + self.diagrams_ = X return self def transform(self, X): @@ -94,31 +161,7 @@ class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence weighted Gaussian kernel values. """ - Xp = list(X) - Xfit = np.zeros((len(Xp), len(self.diagrams_))) - if len(self.diagrams_) == len(Xp) and np.all([np.array_equal(self.diagrams_[i], Xp[i]) for i in range(len(Xp))]): - if self.kernel_approx is not None: - Xfit = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.matmul(self.approx_, self.approx_.T) - else: - for i in range(len(self.diagrams_)): - for j in range(i+1, len(self.diagrams_)): - W = np.matmul(self.ws_[i][:,np.newaxis], self.ws_[j][np.newaxis,:]) - E = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.exp(-np.square(pairwise_distances(self.diagrams_[i], self.diagrams_[j]))/(2*np.square(self.bandwidth))) - Xfit[i,j] = np.sum(np.multiply(W, E)) - Xfit[j,i] = Xfit[i,j] - else: - ws = [ np.array([self.weight(Xp[i][j,:]) for j in range(Xp[i].shape[0])]) for i in range(len(Xp)) ] - if self.kernel_approx is not None: - approx = np.concatenate([np.sum(np.multiply(ws[i][:,np.newaxis], self.kernel_approx.transform(Xp[i])), axis=0)[np.newaxis,:] for i in range(len(Xp))]) - Xfit = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.matmul(approx, self.approx_.T) - else: - for i in range(len(Xp)): - for j in range(len(self.diagrams_)): - W = np.matmul(ws[i][:,np.newaxis], self.ws_[j][np.newaxis,:]) - E = (1./(np.sqrt(2*np.pi)*self.bandwidth)) * np.exp(-np.square(pairwise_distances(Xp[i], self.diagrams_[j]))/(2*np.square(self.bandwidth))) - Xfit[i,j] = np.sum(np.multiply(W, E)) - - return Xfit + return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_weighted_gaussian", bandwidth=self.bandwidth, weight=self.weight, kernel_approx=self.kernel_approx) class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): """ @@ -132,7 +175,7 @@ class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved (default 1.) kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). """ - self.pwg_ = PersistenceWeightedGaussianKernel(bandwidth=bandwidth, weight=lambda x: 1 if x[1] >= x[0] else -1, kernel_approx=kernel_approx) + self.bandwidth, self.kernel_approx = bandwidth, kernel_approx def fit(self, X, y=None): """ @@ -142,11 +185,7 @@ class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): X (list of n x 2 numpy arrays): input persistence diagrams. y (n x 1 array): persistence diagram labels (unused). """ - self.diagrams_ = list(X) - for i in range(len(self.diagrams_)): - op_D = self.diagrams_[i][:,[1,0]] - self.diagrams_[i] = np.concatenate([self.diagrams_[i], op_D], axis=0) - self.pwg_.fit(X) + self.diagrams_ = X return self def transform(self, X): @@ -159,11 +198,7 @@ class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence scale space kernel values. """ - Xp = list(X) - for i in range(len(Xp)): - op_X = Xp[i][:,[1,0]] - Xp[i] = np.concatenate([Xp[i], op_X], axis=0) - return self.pwg_.transform(Xp) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_scale_space", bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) class PersistenceFisherKernel(BaseEstimator, TransformerMixin): """ @@ -179,7 +214,7 @@ class PersistenceFisherKernel(BaseEstimator, TransformerMixin): kernel_approx (class): kernel approximation class used to speed up computation (default None). Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). """ self.bandwidth = bandwidth - self.pf_ = PersistenceFisherDistance(bandwidth=bandwidth_fisher, kernel_approx=kernel_approx) + self.bandwidth_fisher, self.kernel_approx = bandwidth_fisher, kernel_approx def fit(self, X, y=None): """ @@ -189,7 +224,7 @@ class PersistenceFisherKernel(BaseEstimator, TransformerMixin): X (list of n x 2 numpy arrays): input persistence diagrams. y (n x 1 array): persistence diagram labels (unused). """ - self.pf_.fit(X, y) + self.diagrams_ = X return self def transform(self, X): @@ -202,5 +237,5 @@ class PersistenceFisherKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence Fisher kernel values. """ - return np.exp(-self.pf_.transform(X)/self.bandwidth) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_fisher", bandwidth=self.bandwidth, bandwidth_fisher=self.bandwidth_fisher, kernel_approx=self.kernel_approx) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 290c1d07..cc788994 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -11,6 +11,8 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances from gudhi.wasserstein import wasserstein_distance +from .preprocessing import Padding + try: from .. import bottleneck_distance USE_GUDHI = True @@ -22,6 +24,108 @@ except ImportError: # Metrics ################################### ############################################# +def sliced_wasserstein_distance(D1, D2, num_directions): + """ + This is a function for computing the sliced Wasserstein distance from two persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally integrating over all possible lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. + :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param D2: (m x 2) numpy.array encoding the second diagram. + :param num_directions: number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. + :returns: the sliced Wasserstein distance between persistence diagrams. + :rtype: float + """ + thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] + lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) + approx1 = np.matmul(D1, lines) + diag_proj1 = (1./2) * np.ones((2,2)) + approx_diag1 = np.matmul(np.matmul(D1, diag_proj1), lines) + approx2 = np.matmul(D2, lines) + diag_proj2 = (1./2) * np.ones((2,2)) + approx_diag2 = np.matmul(np.matmul(D2, diag_proj2), lines) + A = np.sort(np.concatenate([approx1, approx_diag2], axis=0), axis=0) + B = np.sort(np.concatenate([approx2, approx_diag1], axis=0), axis=0) + L1 = np.sum(np.abs(A-B), axis=0) + return np.mean(L1) + +def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): + """ + This is a function for computing the persistence Fisher distance from two persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. + :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param D2: (m x 2) numpy.array encoding the second diagram. + :param bandwidth: bandwidth of the Gaussian kernel used to turn persistence diagrams into probability distributions. + :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + :returns: the persistence Fisher distance between persistence diagrams. + :rtype: float + """ + projection = (1./2) * np.ones((2,2)) + diagonal_projections1 = np.matmul(D1, projection) + diagonal_projections2 = np.matmul(D2, projection) + if kernel_approx is not None: + approx1 = kernel_approx.transform(D1) + approx_diagonal1 = kernel_approx.transform(diagonal_projections1) + approx2 = kernel_approx.transform(D2) + approx_diagonal2 = kernel_approx.transform(diagonal_projections2) + Z = np.concatenate([approx1, approx_diagonal1, approx2, approx_diagonal2], axis=0) + U, V = np.sum(np.concatenate([approx1, approx_diagonal2], axis=0), axis=0), np.sum(np.concatenate([approx2, approx_diagonal1], axis=0), axis=0) + vectori, vectorj = np.abs(np.matmul(Z, U.T)), np.abs(np.matmul(Z, V.T)) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + return np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + else: + Z = np.concatenate([D1, diagonal_projections1, D2, diagonal_projections2], axis=0) + U, V = np.concatenate([D1, diagonal_projections2], axis=0), np.concatenate([D2, diagonal_projections1], axis=0) + vectori = np.sum(np.exp(-np.square(pairwise_distances(Z,U))/(2 * np.square(bandwidth)))/(bandwidth * np.sqrt(2*np.pi)), axis=1) + vectorj = np.sum(np.exp(-np.square(pairwise_distances(Z,V))/(2 * np.square(bandwidth)))/(bandwidth * np.sqrt(2*np.pi)), axis=1) + vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) + if vectori_sum != 0: + vectori = vectori/vectori_sum + if vectorj_sum != 0: + vectorj = vectorj/vectorj_sum + return np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) + +def sklearn_wrapper(metric, **kwargs): + """ + This function is a wrapper for any metric between two persistence diagrams that takes two numpy arrays of shapes (nx2) and (mx2) as arguments. It turns the metric into another that takes flattened and padded diagrams as inputs. + """ + def flat_metric(D1, D2): + DD1, DD2 = np.reshape(D1, [-1,3]), np.reshape(D2, [-1,3]) + return metric(DD1[DD1[:,2]==1,0:2], DD2[DD2[:,2]==1,0:2], **kwargs) + return flat_metric + +def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwargs): + """ + This function computes the distance matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). + :param X: first list of persistence diagrams. + :param Y: second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. + :param metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + :returns: distance matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) + :rtype: float + """ + if Y is None: + YY = None + pX = Padding(use=True).fit_transform(X) + diag_len = len(pX[0]) + XX = np.reshape(np.vstack(pX), [-1, diag_len*3]) + else: + nX, nY = len(X), len(Y) + pD = Padding(use=True).fit_transform(X + Y) + diag_len = len(pD[0]) + XX = np.reshape(np.vstack(pD[:nX]), [-1, diag_len*3]) + YY = np.reshape(np.vstack(pD[nX:]), [-1, diag_len*3]) + + if metric == "bottleneck": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, **kwargs)) + elif metric == "wasserstein": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(wasserstein_distance, **kwargs)) + elif metric == "sliced_wasserstein": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, **kwargs)) + elif metric == "persistence_fisher": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(persistence_fisher_distance, **kwargs)) + else: + return pairwise_distances(XX, YY, metric=sklearn_wrapper(metric, **kwargs)) + class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the sliced Wasserstein distance matrix from a list of persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally integrating over all possible lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. @@ -34,8 +138,6 @@ class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation (default 10). """ self.num_directions = num_directions - thetas = np.linspace(-np.pi/2, np.pi/2, num=self.num_directions+1)[np.newaxis,:-1] - self.lines_ = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) def fit(self, X, y=None): """ @@ -46,9 +148,6 @@ class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): y (n x 1 array): persistence diagram labels (unused). """ self.diagrams_ = X - self.approx_ = [np.matmul(X[i], self.lines_) for i in range(len(X))] - diag_proj = (1./2) * np.ones((2,2)) - self.approx_diag_ = [np.matmul(np.matmul(X[i], diag_proj), self.lines_) for i in range(len(X))] return self def transform(self, X): @@ -61,27 +160,7 @@ class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise sliced Wasserstein distances. """ - Xfit = np.zeros((len(X), len(self.approx_))) - if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): - for i in range(len(self.approx_)): - for j in range(i+1, len(self.approx_)): - A = np.sort(np.concatenate([self.approx_[i], self.approx_diag_[j]], axis=0), axis=0) - B = np.sort(np.concatenate([self.approx_[j], self.approx_diag_[i]], axis=0), axis=0) - L1 = np.sum(np.abs(A-B), axis=0) - Xfit[i,j] = np.mean(L1) - Xfit[j,i] = Xfit[i,j] - else: - diag_proj = (1./2) * np.ones((2,2)) - approx = [np.matmul(X[i], self.lines_) for i in range(len(X))] - approx_diag = [np.matmul(np.matmul(X[i], diag_proj), self.lines_) for i in range(len(X))] - for i in range(len(approx)): - for j in range(len(self.approx_)): - A = np.sort(np.concatenate([approx[i], self.approx_diag_[j]], axis=0), axis=0) - B = np.sort(np.concatenate([self.approx_[j], approx_diag[i]], axis=0), axis=0) - L1 = np.sum(np.abs(A-B), axis=0) - Xfit[i,j] = np.mean(L1) - - return Xfit + return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="sliced_wasserstein", num_directions=self.num_directions) class BottleneckDistance(BaseEstimator, TransformerMixin): """ @@ -117,33 +196,9 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise bottleneck distances. """ - num_diag1 = len(X) - - #if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): - if X is self.diagrams_: - matrix = np.zeros((num_diag1, num_diag1)) - - if USE_GUDHI: - for i in range(num_diag1): - for j in range(i+1, num_diag1): - matrix[i,j] = bottleneck_distance(X[i], X[j], self.epsilon) - matrix[j,i] = matrix[i,j] - else: - print("Gudhi built without CGAL: returning a null matrix") - - else: - num_diag2 = len(self.diagrams_) - matrix = np.zeros((num_diag1, num_diag2)) - - if USE_GUDHI: - for i in range(num_diag1): - for j in range(num_diag2): - matrix[i,j] = bottleneck_distance(X[i], self.diagrams_[j], self.epsilon) - else: - print("Gudhi built without CGAL: returning a null matrix") - - Xfit = matrix - + if not USE_GUDHI: + print("Gudhi built without CGAL: returning a null matrix") + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) if USE_GUDHI else np.zeros((len(X), len(self.diagrams_))) return Xfit class WassersteinDistance(BaseEstimator, TransformerMixin): @@ -181,28 +236,7 @@ class WassersteinDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise Wasserstein distances. """ - num_diag1 = len(X) - - #if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): - if X is self.diagrams_: - matrix = np.zeros((num_diag1, num_diag1)) - - for i in range(num_diag1): - for j in range(i+1, num_diag1): - matrix[i,j] = wasserstein_distance(X[i], X[j], self.order, self.internal_p) - matrix[j,i] = matrix[i,j] - - else: - num_diag2 = len(self.diagrams_) - matrix = np.zeros((num_diag1, num_diag2)) - - for i in range(num_diag1): - for j in range(num_diag2): - matrix[i,j] = wasserstein_distance(X[i], self.diagrams_[j], self.order, self.internal_p) - - Xfit = matrix - - return Xfit + return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="wasserstein", order=self.order, internal_p=self.internal_p) class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ @@ -227,11 +261,6 @@ class PersistenceFisherDistance(BaseEstimator, TransformerMixin): y (n x 1 array): persistence diagram labels (unused). """ self.diagrams_ = X - projection = (1./2) * np.ones((2,2)) - self.diagonal_projections_ = [np.matmul(X[i], projection) for i in range(len(X))] - if self.kernel_approx is not None: - self.approx_ = [self.kernel_approx.transform(X[i]) for i in range(len(X))] - self.approx_diagonal_ = [self.kernel_approx.transform(self.diagonal_projections_[i]) for i in range(len(X))] return self def transform(self, X): @@ -244,60 +273,4 @@ class PersistenceFisherDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence Fisher distances. """ - Xfit = np.zeros((len(X), len(self.diagrams_))) - if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): - for i in range(len(self.diagrams_)): - for j in range(i+1, len(self.diagrams_)): - if self.kernel_approx is not None: - Z = np.concatenate([self.approx_[i], self.approx_diagonal_[i], self.approx_[j], self.approx_diagonal_[j]], axis=0) - U, V = np.sum(np.concatenate([self.approx_[i], self.approx_diagonal_[j]], axis=0), axis=0), np.sum(np.concatenate([self.approx_[j], self.approx_diagonal_[i]], axis=0), axis=0) - vectori, vectorj = np.abs(np.matmul(Z, U.T)), np.abs(np.matmul(Z, V.T)) - vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) - if vectori_sum != 0: - vectori = vectori/vectori_sum - if vectorj_sum != 0: - vectorj = vectorj/vectorj_sum - Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) - Xfit[j,i] = Xfit[i,j] - else: - Z = np.concatenate([self.diagrams_[i], self.diagonal_projections_[i], self.diagrams_[j], self.diagonal_projections_[j]], axis=0) - U, V = np.concatenate([self.diagrams_[i], self.diagonal_projections_[j]], axis=0), np.concatenate([self.diagrams_[j], self.diagonal_projections_[i]], axis=0) - vectori = np.sum(np.exp(-np.square(pairwise_distances(Z,U))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) - vectorj = np.sum(np.exp(-np.square(pairwise_distances(Z,V))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) - vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) - if vectori_sum != 0: - vectori = vectori/vectori_sum - if vectorj_sum != 0: - vectorj = vectorj/vectorj_sum - Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) - Xfit[j,i] = Xfit[i,j] - else: - projection = (1./2) * np.ones((2,2)) - diagonal_projections = [np.matmul(X[i], projection) for i in range(len(X))] - if self.kernel_approx is not None: - approx = [self.kernel_approx.transform(X[i]) for i in range(len(X))] - approx_diagonal = [self.kernel_approx.transform(diagonal_projections[i]) for i in range(len(X))] - for i in range(len(X)): - for j in range(len(self.diagrams_)): - if self.kernel_approx is not None: - Z = np.concatenate([approx[i], approx_diagonal[i], self.approx_[j], self.approx_diagonal_[j]], axis=0) - U, V = np.sum(np.concatenate([approx[i], self.approx_diagonal_[j]], axis=0), axis=0), np.sum(np.concatenate([self.approx_[j], approx_diagonal[i]], axis=0), axis=0) - vectori, vectorj = np.abs(np.matmul(Z, U.T)), np.abs(np.matmul(Z, V.T)) - vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) - if vectori_sum != 0: - vectori = vectori/vectori_sum - if vectorj_sum != 0: - vectorj = vectorj/vectorj_sum - Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) - else: - Z = np.concatenate([X[i], diagonal_projections[i], self.diagrams_[j], self.diagonal_projections_[j]], axis=0) - U, V = np.concatenate([X[i], self.diagonal_projections_[j]], axis=0), np.concatenate([self.diagrams_[j], diagonal_projections[i]], axis=0) - vectori = np.sum(np.exp(-np.square(pairwise_distances(Z,U))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) - vectorj = np.sum(np.exp(-np.square(pairwise_distances(Z,V))/(2 * np.square(self.bandwidth)))/(self.bandwidth * np.sqrt(2*np.pi)), axis=1) - vectori_sum, vectorj_sum = np.sum(vectori), np.sum(vectorj) - if vectori_sum != 0: - vectori = vectori/vectori_sum - if vectorj_sum != 0: - vectorj = vectorj/vectorj_sum - Xfit[i,j] = np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) - return Xfit + return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="persistence_fisher", bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) -- cgit v1.2.3 From 1dd1c554a962db70809eadb470eb2eaa733970d4 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Fri, 31 Jan 2020 14:59:32 -0500 Subject: revert first commit --- .../diagram_vectorizations_distances_kernels.py | 7 +-- src/python/gudhi/representations/metrics.py | 59 ---------------------- 2 files changed, 1 insertion(+), 65 deletions(-) (limited to 'src/python') diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index 66c32cc2..119072eb 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -9,7 +9,7 @@ from gudhi.representations import DiagramSelector, Clamping, Landscape, Silhouet TopologicalVector, DiagramScaler, BirthPersistenceTransform,\ PersistenceImage, PersistenceWeightedGaussianKernel, Entropy, \ PersistenceScaleSpaceKernel, SlicedWassersteinDistance,\ - SlicedWassersteinKernel, BottleneckDistance, WassersteinDistance, PersistenceFisherKernel + SlicedWassersteinKernel, BottleneckDistance, PersistenceFisherKernel D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) diags = [D] @@ -117,11 +117,6 @@ X = SW.fit(diags) Y = SW.transform(diags2) print("SW kernel is " + str(Y[0][0])) -W = WassersteinDistance(order=2, internal_p=2) -X = W.fit(diags) -Y = W.transform(diags2) -print("Wasserstein distance is " + str(Y[0][0])) - W = BottleneckDistance(epsilon=.001) X = W.fit(diags) Y = W.transform(diags2) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 290c1d07..5f9ec6ab 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -10,7 +10,6 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances -from gudhi.wasserstein import wasserstein_distance try: from .. import bottleneck_distance USE_GUDHI = True @@ -146,64 +145,6 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): return Xfit -class WassersteinDistance(BaseEstimator, TransformerMixin): - """ - This is a class for computing the Wasserstein distance matrix from a list of persistence diagrams. - """ - def __init__(self, order=2, internal_p=2): - """ - Constructor for the WassersteinDistance class. - - Parameters: - order (int): exponent for Wasserstein, default value is 2., see :func:`gudhi.wasserstein.wasserstein_distance`. - internal_p (int): ground metric on the (upper-half) plane (i.e. norm l_p in R^2), default value is 2 (euclidean norm), see :func:`gudhi.wasserstein.wasserstein_distance`. - """ - self.order, self.internal_p = order, internal_p - - def fit(self, X, y=None): - """ - Fit the WassersteinDistance class on a list of persistence diagrams: persistence diagrams are stored in a numpy array called **diagrams**. - - Parameters: - X (list of n x 2 numpy arrays): input persistence diagrams. - y (n x 1 array): persistence diagram labels (unused). - """ - self.diagrams_ = X - return self - - def transform(self, X): - """ - Compute all Wasserstein distances between the persistence diagrams that were stored after calling the fit() method, and a given list of (possibly different) persistence diagrams. - - Parameters: - X (list of n x 2 numpy arrays): input persistence diagrams. - - Returns: - numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise Wasserstein distances. - """ - num_diag1 = len(X) - - #if len(self.diagrams_) == len(X) and np.all([np.array_equal(self.diagrams_[i], X[i]) for i in range(len(X))]): - if X is self.diagrams_: - matrix = np.zeros((num_diag1, num_diag1)) - - for i in range(num_diag1): - for j in range(i+1, num_diag1): - matrix[i,j] = wasserstein_distance(X[i], X[j], self.order, self.internal_p) - matrix[j,i] = matrix[i,j] - - else: - num_diag2 = len(self.diagrams_) - matrix = np.zeros((num_diag1, num_diag2)) - - for i in range(num_diag1): - for j in range(num_diag2): - matrix[i,j] = wasserstein_distance(X[i], self.diagrams_[j], self.order, self.internal_p) - - Xfit = matrix - - return Xfit - class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the persistence Fisher distance matrix from a list of persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. -- cgit v1.2.3 From d6afaa8300daa6204282a7d34df6bea33ea59fd2 Mon Sep 17 00:00:00 2001 From: takeshimeonerespect <58589594+takeshimeonerespect@users.noreply.github.com> Date: Mon, 3 Feb 2020 14:13:52 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index 5c7ba542..f283916d 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -1,3 +1,11 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Martin Royer, Yuichi Ike, Masatoshi Takenouchi +# +# Copyright (C) 2020 Inria, Copyright (C) 2020 Fujitsu Laboratories Ltd. +# Modification(s): +# - YYYY/MM Author: Description of the modification + import numpy as np class TimeDelayEmbedding: -- cgit v1.2.3 From eded147ffffe5b7143cad19ecd134fb7a63991a3 Mon Sep 17 00:00:00 2001 From: takenouchi Date: Tue, 4 Feb 2020 14:08:19 +0900 Subject: change a file name --- src/python/test/test_time_delay.py | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100755 src/python/test/test_time_delay.py (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py new file mode 100755 index 00000000..2ee0c1fb --- /dev/null +++ b/src/python/test/test_time_delay.py @@ -0,0 +1,35 @@ +from gudhi.point_cloud.timedelay import TimeDelayEmbedding + +def test_normal(): + # Sample array + ts = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] + # Normal case. + prep = TimeDelayEmbedding() + attractor = prep(ts) + assert (attractor[0] == [1, 2, 3]) + assert (attractor[1] == [2, 3, 4]) + assert (attractor[2] == [3, 4, 5]) + assert (attractor[3] == [4, 5, 6]) + assert (attractor[4] == [5, 6, 7]) + assert (attractor[5] == [6, 7, 8]) + assert (attractor[6] == [7, 8, 9]) + assert (attractor[7] == [8, 9, 10]) + # Delay = 3 + prep = TimeDelayEmbedding(delay=3) + attractor = prep(ts) + assert (attractor[0] == [1, 4, 7]) + assert (attractor[1] == [2, 5, 8]) + assert (attractor[2] == [3, 6, 9]) + assert (attractor[3] == [4, 7, 10]) + # Skip = 3 + prep = TimeDelayEmbedding(skip=3) + attractor = prep(ts) + assert (attractor[0] == [1, 2, 3]) + assert (attractor[1] == [4, 5, 6]) + assert (attractor[2] == [7, 8, 9]) + # Delay = 2 / Skip = 2 + prep = TimeDelayEmbedding(delay=2, skip=2) + attractor = prep(ts) + assert (attractor[0] == [1, 3, 5]) + assert (attractor[1] == [3, 5, 7]) + assert (attractor[2] == [5, 7, 9]) -- cgit v1.2.3 From 5ddb724824798fe194a66285e29ea4c5cc2713e2 Mon Sep 17 00:00:00 2001 From: takeshimeonerespect Date: Tue, 4 Feb 2020 14:24:27 +0900 Subject: Delete test_point_cloud.py --- src/python/test/test_point_cloud.py | 35 ----------------------------------- 1 file changed, 35 deletions(-) delete mode 100755 src/python/test/test_point_cloud.py (limited to 'src/python') diff --git a/src/python/test/test_point_cloud.py b/src/python/test/test_point_cloud.py deleted file mode 100755 index 2ee0c1fb..00000000 --- a/src/python/test/test_point_cloud.py +++ /dev/null @@ -1,35 +0,0 @@ -from gudhi.point_cloud.timedelay import TimeDelayEmbedding - -def test_normal(): - # Sample array - ts = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - # Normal case. - prep = TimeDelayEmbedding() - attractor = prep(ts) - assert (attractor[0] == [1, 2, 3]) - assert (attractor[1] == [2, 3, 4]) - assert (attractor[2] == [3, 4, 5]) - assert (attractor[3] == [4, 5, 6]) - assert (attractor[4] == [5, 6, 7]) - assert (attractor[5] == [6, 7, 8]) - assert (attractor[6] == [7, 8, 9]) - assert (attractor[7] == [8, 9, 10]) - # Delay = 3 - prep = TimeDelayEmbedding(delay=3) - attractor = prep(ts) - assert (attractor[0] == [1, 4, 7]) - assert (attractor[1] == [2, 5, 8]) - assert (attractor[2] == [3, 6, 9]) - assert (attractor[3] == [4, 7, 10]) - # Skip = 3 - prep = TimeDelayEmbedding(skip=3) - attractor = prep(ts) - assert (attractor[0] == [1, 2, 3]) - assert (attractor[1] == [4, 5, 6]) - assert (attractor[2] == [7, 8, 9]) - # Delay = 2 / Skip = 2 - prep = TimeDelayEmbedding(delay=2, skip=2) - attractor = prep(ts) - assert (attractor[0] == [1, 3, 5]) - assert (attractor[1] == [3, 5, 7]) - assert (attractor[2] == [5, 7, 9]) -- cgit v1.2.3 From 360cc2cc31e9e81b99f5c21aa2b4e79b066baabf Mon Sep 17 00:00:00 2001 From: mathieu Date: Tue, 4 Feb 2020 19:44:52 -0500 Subject: fixed Vincent's comments --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 74 ++++++++++++++++++----- src/python/gudhi/simplex_tree.pxd | 2 +- src/python/gudhi/simplex_tree.pyx | 14 +++-- src/python/test/test_simplex_tree.py | 86 +++++++++++++++++++++++++-- 4 files changed, 150 insertions(+), 26 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 301f7aae..42cf4246 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -1467,34 +1467,68 @@ class Simplex_tree { } } - /** \brief Retrieve good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. Need extend_filtration to be called first! - * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration and this->get_persistence. - * @return A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. + /** \brief Retrieve good values for extended persistence, and separate the + * diagrams into the ordinary, relative, extended+ and extended- subdiagrams. + * Need extend_filtration to be called first! + * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration + * and this->get_persistence. + * @return A vector of four persistence diagrams. The first one is Ordinary, the + * second one is Relative, the third one is Extended+ and the fourth one is Extended-. */ std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ - std::vector>>> new_dgm(4); double x, y; - for(unsigned int i = 0; i < dgm.size(); i++){ int h = dgm[i].first; double px = dgm[i].second.first; double py = dgm[i].second.second; + std::vector>>> new_dgm(4); + double x, y; + for(unsigned int i = 0; i < dgm.size(); i++){ + int h = dgm[i].first; + double px = dgm[i].second.first; + double py = dgm[i].second.second; if(std::isinf(py)) continue; else{ - if ((px <= -1) & (py <= -1)){x = minval_ + (maxval_-minval_)*(px + 2); y = minval_ + (maxval_-minval_)*(py + 2); new_dgm[0].push_back(std::make_pair(h, std::make_pair(x,y))); } - if ((px >= 1) & (py >= 1)){x = minval_ - (maxval_-minval_)*(px - 2); y = minval_ - (maxval_-minval_)*(py - 2); new_dgm[1].push_back(std::make_pair(h, std::make_pair(x,y))); } - if ((px <= -1) & (py >= 1)){x = minval_ + (maxval_-minval_)*(px + 2); y = minval_ - (maxval_-minval_)*(py - 2); - if (x <= y) new_dgm[2].push_back(std::make_pair(h, std::make_pair(x,y))); - else new_dgm[3].push_back(std::make_pair(h, std::make_pair(x,y))); + if ((px <= -1) & (py <= -1)){ + x = minval_ + (maxval_-minval_)*(px + 2); + y = minval_ + (maxval_-minval_)*(py + 2); + new_dgm[0].push_back(std::make_pair(h, std::make_pair(x,y))); + } + if ((px >= 1) & (py >= 1)){ + x = minval_ - (maxval_-minval_)*(px - 2); + y = minval_ - (maxval_-minval_)*(py - 2); + new_dgm[1].push_back(std::make_pair(h, std::make_pair(x,y))); + } + if ((px <= -1) & (py >= 1)){ + x = minval_ + (maxval_-minval_)*(px + 2); + y = minval_ - (maxval_-minval_)*(py - 2); + if (x <= y){ + new_dgm[2].push_back(std::make_pair(h, std::make_pair(x,y))); + } + else{ + new_dgm[3].push_back(std::make_pair(h, std::make_pair(x,y))); + } } } } return new_dgm; } - /** \brief Extend filtration for computing extended persistence. This function only uses the filtration values at the 0-dimensional simplices, and computes the extended persistence diagram induced by the lower-star filtration computed with these values. Note that after calling this function, the filtration values are actually modified. The function compute_extended_persistence_subdiagrams retrieves the original values and separates the extended persistence diagram points w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after computing the persistent homology of the extended simplicial complex. + /** \brief Extend filtration for computing extended persistence. + * This function only uses the filtration values at the 0-dimensional simplices, + * and computes the extended persistence diagram induced by the lower-star filtration + * computed with these values. Note that after calling this function, the filtration + * values are actually modified. The function compute_extended_persistence_subdiagrams + * retrieves the original values and separates the extended persistence diagram points + * w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after + * computing the persistent homology of the extended simplicial complex. */ void extend_filtration() { // Compute maximum and minimum of filtration values - int maxvert = -std::numeric_limits::infinity(); + int maxvert = -std::numeric_limits::infinity(); std::vector filt; - for (auto sh : this->complex_simplex_range()) {if (this->dimension(sh) == 0){filt.push_back(this->filtration(sh)); maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert);}} + for (auto sh : this->complex_simplex_range()) { + if (this->dimension(sh) == 0){ + filt.push_back(this->filtration(sh)); + maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert); + } + } minval_ = *std::min_element(filt.begin(), filt.end()); maxval_ = *std::max_element(filt.begin(), filt.end()); maxvert += 1; @@ -1502,13 +1536,20 @@ class Simplex_tree { // Compute vectors of integers corresponding to the Simplex handles std::vector > splxs; for (auto sh : this->complex_simplex_range()) { - std::vector vr; for (auto vh : this->simplex_vertex_range(sh)){vr.push_back(vh);} + std::vector vr; + for (auto vh : this->simplex_vertex_range(sh)){ + vr.push_back(vh); + } splxs.push_back(vr); } // Add point for coning the simplicial complex int count = this->num_simplices(); - std::vector cone; cone.push_back(maxvert); auto ins = this->insert_simplex(cone, -3); this->assign_key(ins.first, count); count++; + std::vector cone; + cone.push_back(maxvert); + auto ins = this->insert_simplex(cone, -3); + this->assign_key(ins.first, count); + count++; // For each simplex for (auto vr : splxs){ @@ -1531,7 +1572,8 @@ class Simplex_tree { count++; } - this->make_filtration_non_decreasing(); this->initialize_filtration(); + this->make_filtration_non_decreasing(); + this->initialize_filtration(); } diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 4393047f..7aa16926 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -44,7 +44,7 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() void extend_filtration() - vector[vector[pair[int, pair[double, double]]]] convert(vector[pair[int, pair[double, double]]]) + vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]]) cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index cfab14f4..e429e28a 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -387,17 +387,21 @@ cdef class SimplexTree: return self.get_ptr().make_filtration_non_decreasing() def extend_filtration(self): - """ This function extends filtration for computing extended persistence. + """ Extend filtration for computing extended persistence. This function only uses the filtration values at the 0-dimensional simplices, and computes the extended persistence diagram induced by the lower-star filtration computed with these values. Note that after calling this function, the filtration values are actually modified. The function :func:`compute_extended_persistence_subdiagrams()` retrieves the original values and separates the extended persistence diagram points w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after computing the persistent homology of the extended simplicial complex. """ return self.get_ptr().extend_filtration() - def convert(self, dgm): - """This function retrieves good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. Need extend_filtration to be called first! + def compute_extended_persistence_subdiagrams(self, dgm): + """This function retrieves good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. - :param dgm: Persistence diagram obtained after calling this->extend_filtration and this->get_persistence. + :param dgm: Persistence diagram obtained after calling :func:`extend_filtration()` and :func:`persistence()`. :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. + + .. note:: + + This function should be called only after calling :func:`extend_filtration()` and :func:`persistence()`. """ - return self.get_ptr().convert(dgm) + return self.get_ptr().compute_extended_persistence_subdiagrams(dgm) def persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 1822c43b..7e3d843e 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -244,7 +244,85 @@ def test_make_filtration_non_decreasing(): assert st.filtration([0, 1, 6]) == 1.0 assert st.filtration([0, 1]) == 1.0 assert st.filtration([0]) == 1.0 - assert st.filtration([1]) == 1.0 - assert st.filtration([3, 4, 5]) == 2.0 - assert st.filtration([3, 4]) == 2.0 - assert st.filtration([4, 5]) == 2.0 + +def test_extend_filtration(): + + # Inserted simplex: + # 5 4 + # o o + # / \ / + # o o + # /2\ /3 + # o o + # 1 0 + + st = SimplexTree() + st.insert([0,2]) + st.insert([1,2]) + st.insert([0,3]) + st.insert([2,5]) + st.insert([3,4]) + st.insert([3,5]) + st.assign_filtration([0], 1.) + st.assign_filtration([1], 2.) + st.assign_filtration([2], 3.) + st.assign_filtration([3], 4.) + st.assign_filtration([4], 5.) + st.assign_filtration([5], 6.) + + assert st.get_filtration() == [ + ([0, 2], 0.0), + ([1, 2], 0.0), + ([0, 3], 0.0), + ([3, 4], 0.0), + ([2, 5], 0.0), + ([3, 5], 0.0), + ([0], 1.0), + ([1], 2.0), + ([2], 3.0), + ([3], 4.0), + ([4], 5.0), + ([5], 6.0) + ] + + + st.extend_filtration() + + assert st.get_filtration() == [ + ([6], -3.0), + ([0], -2.0), + ([1], -1.8), + ([2], -1.6), + ([0, 2], -1.6), + ([1, 2], -1.6), + ([3], -1.4), + ([0, 3], -1.4), + ([4], -1.2), + ([3, 4], -1.2), + ([5], -1.0), + ([2, 5], -1.0), + ([3, 5], -1.0), + ([5, 6], 1.0), + ([4, 6], 1.2), + ([3, 6], 1.4), + ([3, 4, 6], 1.4), + ([3, 5, 6], 1.4), + ([2, 6], 1.6), + ([2, 5, 6], 1.6), + ([1, 6], 1.8), + ([1, 2, 6], 1.8), + ([0, 6], 2.0), + ([0, 2, 6], 2.0), + ([0, 3, 6], 2.0) + ] + + + dgm = st.persistence() + L = st.compute_extended_persistence_subdiagrams(dgm) + assert L == [ + [(0, (1.9999999999999998, 2.9999999999999996))], + [(1, (5.0, 4.0))], + [(0, (1.0, 6.0))], + [(1, (6.0, 1.0))] + ] + -- cgit v1.2.3 From 596355344e6205d02110e38a0cb7e0a94e8dbd27 Mon Sep 17 00:00:00 2001 From: takenouchi Date: Thu, 6 Feb 2020 16:00:47 +0900 Subject: modify CMakeLists.txt --- src/python/CMakeLists.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index b23ec8a9..798e2907 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -401,8 +401,8 @@ endif(CGAL_FOUND) add_gudhi_py_test(test_representations) endif() - # Point cloud - add_gudhi_py_test(test_point_cloud) + # Time Delay + add_gudhi_py_test(test_time_delay) # Documentation generation is available through sphinx - requires all modules if(SPHINX_PATH) -- cgit v1.2.3 From 24a76cc53c935dee93f2367f176143c015009e3f Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Thu, 6 Feb 2020 10:51:43 +0100 Subject: Use exceptions uinstead of error message for non existing files --- ...ex_diagram_persistence_from_off_file_example.py | 14 ++++++++----- .../alpha_rips_persistence_bottleneck_distance.py | 24 +++++++++++++--------- ...ex_diagram_persistence_from_off_file_example.py | 20 +++++++++++------- ...ex_diagram_persistence_from_off_file_example.py | 12 +++++++---- ...arcode_persistence_from_perseus_file_example.py | 17 +++++++++------ ...ex_diagram_persistence_from_off_file_example.py | 17 +++++++++------ ...complex_plain_homology_from_off_file_example.py | 19 ++++++++++------- src/python/gudhi/alpha_complex.pyx | 10 +++++---- src/python/gudhi/cubical_complex.pyx | 11 ++++++---- src/python/gudhi/off_reader.pyx | 12 ++++++----- 10 files changed, 98 insertions(+), 58 deletions(-) (limited to 'src/python') diff --git a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py index 6afaf533..727af4fa 100755 --- a/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/alpha_complex_diagram_persistence_from_off_file_example.py @@ -1,12 +1,15 @@ #!/usr/bin/env python import argparse +import errno +import os import matplotlib.pyplot as plot -import sys import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -42,7 +45,7 @@ args = parser.parse_args() with open(args.file, "r") as f: first_line = f.readline() if (first_line == "OFF\n") or (first_line == "nOFF\n"): - print("#####################################################################") + print("##############################################################") print("AlphaComplex creation from points read in a OFF file") message = "AlphaComplex with max_edge_length=" + repr(args.max_alpha_square) @@ -65,6 +68,7 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) f.close() diff --git a/src/python/example/alpha_rips_persistence_bottleneck_distance.py b/src/python/example/alpha_rips_persistence_bottleneck_distance.py index 7b4aa3e7..f156826d 100755 --- a/src/python/example/alpha_rips_persistence_bottleneck_distance.py +++ b/src/python/example/alpha_rips_persistence_bottleneck_distance.py @@ -3,10 +3,13 @@ import gudhi import argparse import math -import sys +import errno +import os -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -37,7 +40,7 @@ with open(args.file, "r") as f: first_line = f.readline() if (first_line == "OFF\n") or (first_line == "nOFF\n"): point_cloud = gudhi.read_points_from_off_file(off_file=args.file) - print("#####################################################################") + print("##############################################################") print("RipsComplex creation from points read in a OFF file") message = "RipsComplex with max_edge_length=" + repr(args.threshold) @@ -47,14 +50,15 @@ with open(args.file, "r") as f: points=point_cloud, max_edge_length=args.threshold ) - rips_stree = rips_complex.create_simplex_tree(max_dimension=args.max_dimension) + rips_stree = rips_complex.create_simplex_tree( + max_dimension=args.max_dimension) message = "Number of simplices=" + repr(rips_stree.num_simplices()) print(message) rips_diag = rips_stree.persistence() - print("#####################################################################") + print("##############################################################") print("AlphaComplex creation from points read in a OFF file") message = "AlphaComplex with max_edge_length=" + repr(args.threshold) @@ -94,13 +98,13 @@ with open(args.file, "r") as f: print(message) max_b_distance = max(bottleneck_distance, max_b_distance) - print( - "================================================================================" - ) + print("==============================================================") message = "Bottleneck distance is " + repr(max_b_distance) print(message) else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) + f.close() diff --git a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py index f61d692b..e1e572df 100755 --- a/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py @@ -1,12 +1,15 @@ #!/usr/bin/env python import argparse +import errno +import os import matplotlib.pyplot as plot -import sys import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -45,8 +48,9 @@ args = parser.parse_args() with open(args.file, "r") as f: first_line = f.readline() if (first_line == "OFF\n") or (first_line == "nOFF\n"): - print("#####################################################################") - print("EuclideanStrongWitnessComplex creation from points read in a OFF file") + print("##############################################################") + print("EuclideanStrongWitnessComplex creation from points read "\ + "in a OFF file") witnesses = gudhi.read_points_from_off_file(off_file=args.file) landmarks = gudhi.pick_n_random_points( @@ -65,7 +69,8 @@ with open(args.file, "r") as f: witnesses=witnesses, landmarks=landmarks ) simplex_tree = witness_complex.create_simplex_tree( - max_alpha_square=args.max_alpha_square, limit_dimension=args.limit_dimension + max_alpha_square=args.max_alpha_square, + limit_dimension=args.limit_dimension ) message = "Number of simplices=" + repr(simplex_tree.num_simplices()) @@ -80,6 +85,7 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) f.close() diff --git a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py index aaa03dad..58cb2bb5 100755 --- a/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py @@ -1,12 +1,15 @@ #!/usr/bin/env python import argparse +import errno +import os import matplotlib.pyplot as plot -import sys import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -79,6 +82,7 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) f.close() diff --git a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py index 97bfd49f..499171df 100755 --- a/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py +++ b/src/python/example/periodic_cubical_complex_barcode_persistence_from_perseus_file_example.py @@ -2,11 +2,14 @@ import argparse import matplotlib.pyplot as plot -import sys +import errno +import os import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -58,9 +61,10 @@ parser.add_argument( args = parser.parse_args() if is_file_perseus(args.file): - print("#####################################################################") + print("##################################################################") print("PeriodicCubicalComplex creation") - periodic_cubical_complex = gudhi.PeriodicCubicalComplex(perseus_file=args.file) + periodic_cubical_complex = gudhi.PeriodicCubicalComplex( + perseus_file=args.file) print("persistence(homology_coeff_field=3, min_persistence=0)=") diag = periodic_cubical_complex.persistence( @@ -74,4 +78,5 @@ if is_file_perseus(args.file): gudhi.plot_persistence_barcode(diag) plot.show() else: - print(args.file, "is not a valid perseus style file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) diff --git a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py index 5d8f057b..6f992508 100755 --- a/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py +++ b/src/python/example/rips_complex_diagram_persistence_from_off_file_example.py @@ -1,12 +1,15 @@ #!/usr/bin/env python import argparse +import errno +import os import matplotlib.pyplot as plot -import sys import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -43,10 +46,11 @@ args = parser.parse_args() with open(args.file, "r") as f: first_line = f.readline() if (first_line == "OFF\n") or (first_line == "nOFF\n"): - print("#####################################################################") + print("##############################################################") print("RipsComplex creation from points read in a OFF file") - message = "RipsComplex with max_edge_length=" + repr(args.max_edge_length) + message = "RipsComplex with max_edge_length=" + \ + repr(args.max_edge_length) print(message) point_cloud = gudhi.read_points_from_off_file(off_file=args.file) @@ -69,6 +73,7 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) f.close() diff --git a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py index 77ac2ea7..85bade4a 100755 --- a/src/python/example/tangential_complex_plain_homology_from_off_file_example.py +++ b/src/python/example/tangential_complex_plain_homology_from_off_file_example.py @@ -1,12 +1,15 @@ #!/usr/bin/env python import argparse +import errno +import os import matplotlib.pyplot as plot -import sys import gudhi -""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. - See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - + which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full + license details. Author(s): Vincent Rouvreau Copyright (C) 2016 Inria @@ -20,7 +23,7 @@ __copyright__ = "Copyright (C) 2016 Inria" __license__ = "MIT" parser = argparse.ArgumentParser( - description="TangentialComplex creation from " "points read in a OFF file.", + description="TangentialComplex creation from points read in a OFF file.", epilog="Example: " "example/tangential_complex_plain_homology_from_off_file_example.py " "-f ../data/points/tore3D_300.off -i 3" @@ -42,10 +45,11 @@ args = parser.parse_args() with open(args.file, "r") as f: first_line = f.readline() if (first_line == "OFF\n") or (first_line == "nOFF\n"): - print("#####################################################################") + print("##############################################################") print("TangentialComplex creation from points read in a OFF file") - tc = gudhi.TangentialComplex(intrisic_dim=args.intrisic_dim, off_file=args.file) + tc = gudhi.TangentialComplex(intrisic_dim=args.intrisic_dim, + off_file=args.file) tc.compute_tangential_complex() st = tc.create_simplex_tree() @@ -61,6 +65,7 @@ with open(args.file, "r") as f: gudhi.plot_persistence_diagram(diag, band=args.band) plot.show() else: - print(args.file, "is not a valid OFF file", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + args.file) f.close() diff --git a/src/python/gudhi/alpha_complex.pyx b/src/python/gudhi/alpha_complex.pyx index dab4b56f..e04dc652 100644 --- a/src/python/gudhi/alpha_complex.pyx +++ b/src/python/gudhi/alpha_complex.pyx @@ -1,5 +1,7 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - +# which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full +# license details. # Author(s): Vincent Rouvreau # # Copyright (C) 2016 Inria @@ -14,7 +16,6 @@ from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool from libc.stdint cimport intptr_t -import sys import os from gudhi.simplex_tree cimport * @@ -71,7 +72,8 @@ cdef class AlphaComplex: def __cinit__(self, points = None, off_file = ''): if off_file: if os.path.isfile(off_file): - self.thisptr = new Alpha_complex_interface(off_file.encode('utf-8'), True) + self.thisptr = new Alpha_complex_interface( + off_file.encode('utf-8'), True) else: print("file " + off_file + " not found.") else: diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index 1dd30b4e..463bd4ee 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -1,5 +1,7 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - +# which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full +# license details. # Author(s): Vincent Rouvreau # # Copyright (C) 2016 Inria @@ -13,7 +15,7 @@ from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool -import sys +import errno import os import numpy as np @@ -89,7 +91,8 @@ cdef class CubicalComplex: if os.path.isfile(perseus_file): self.thisptr = new Bitmap_cubical_complex_base_interface(perseus_file.encode('utf-8')) else: - print("file " + perseus_file + " not found.", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + perseus_file) else: print("CubicalComplex can be constructed from dimensions and " "top_dimensional_cells or from a Perseus-style file name.", diff --git a/src/python/gudhi/off_reader.pyx b/src/python/gudhi/off_reader.pyx index 0a828b83..a3200704 100644 --- a/src/python/gudhi/off_reader.pyx +++ b/src/python/gudhi/off_reader.pyx @@ -1,5 +1,7 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - +# which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full +# license details. # Author(s): Vincent Rouvreau # # Copyright (C) 2016 Inria @@ -11,7 +13,7 @@ from __future__ import print_function from cython cimport numeric from libcpp.vector cimport vector from libcpp.string cimport string -import sys +import errno import os __author__ = "Vincent Rouvreau" @@ -34,6 +36,6 @@ def read_points_from_off_file(off_file=''): if os.path.isfile(off_file): return read_points_from_OFF_file(off_file.encode('utf-8')) else: - print("file " + off_file + " not found.", file=sys.stderr) - return [] + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + off_file) -- cgit v1.2.3 From 26ef6e922c358f68d2bbee3aba20a1722c5150a1 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Thu, 6 Feb 2020 11:01:57 +0100 Subject: Use exceptions uinstead of error message for non existing files --- src/python/gudhi/cubical_complex.pyx | 4 ++-- src/python/gudhi/nerve_gic.pyx | 37 ++++++++++++++++++++++-------------- 2 files changed, 25 insertions(+), 16 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index 463bd4ee..31287d15 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -95,8 +95,8 @@ cdef class CubicalComplex: perseus_file) else: print("CubicalComplex can be constructed from dimensions and " - "top_dimensional_cells or from a Perseus-style file name.", - file=sys.stderr) + "top_dimensional_cells or from a Perseus-style file name.", + file=sys.stderr) def __dealloc__(self): if self.thisptr != NULL: diff --git a/src/python/gudhi/nerve_gic.pyx b/src/python/gudhi/nerve_gic.pyx index 022466c5..e291579b 100644 --- a/src/python/gudhi/nerve_gic.pyx +++ b/src/python/gudhi/nerve_gic.pyx @@ -1,5 +1,7 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - +# which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full +# license details. # Author(s): Vincent Rouvreau # # Copyright (C) 2018 Inria @@ -13,7 +15,7 @@ from libcpp.vector cimport vector from libcpp.utility cimport pair from libcpp.string cimport string from libcpp cimport bool -import sys +import errno import os from libc.stdint cimport intptr_t @@ -98,7 +100,8 @@ cdef class CoverComplex: return self.thisptr != NULL def set_point_cloud_from_range(self, cloud): - """ Reads and stores the input point cloud from a vector stored in memory. + """ Reads and stores the input point cloud from a vector stored in + memory. :param cloud: Input vector containing the point cloud. :type cloud: vector[vector[double]] @@ -106,7 +109,8 @@ cdef class CoverComplex: return self.thisptr.set_point_cloud_from_range(cloud) def set_distances_from_range(self, distance_matrix): - """ Reads and stores the input distance matrix from a vector stored in memory. + """ Reads and stores the input distance matrix from a vector stored in + memory. :param distance_matrix: Input vector containing the distance matrix. :type distance_matrix: vector[vector[double]] @@ -165,7 +169,8 @@ cdef class CoverComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - self.thisptr.create_simplex_tree(stree_int_ptr) + self.thisptr.create_simplex_tree( + stree_int_ptr) return stree def find_simplices(self): @@ -184,8 +189,8 @@ cdef class CoverComplex: if os.path.isfile(off_file): return self.thisptr.read_point_cloud(off_file.encode('utf-8')) else: - print("file " + off_file + " not found.", file=sys.stderr) - return False + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + off_file) def set_automatic_resolution(self): """Computes the optimal length of intervals (i.e. the smallest interval @@ -216,7 +221,8 @@ cdef class CoverComplex: if os.path.isfile(color_file_name): self.thisptr.set_color_from_file(color_file_name.encode('utf-8')) else: - print("file " + color_file_name + " not found.", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + color_file_name) def set_color_from_range(self, color): """Computes the function used to color the nodes of the simplicial @@ -237,7 +243,8 @@ cdef class CoverComplex: if os.path.isfile(cover_file_name): self.thisptr.set_cover_from_file(cover_file_name.encode('utf-8')) else: - print("file " + cover_file_name + " not found.", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + cover_file_name) def set_cover_from_function(self): """Creates a cover C from the preimages of the function f. @@ -270,7 +277,8 @@ cdef class CoverComplex: if os.path.isfile(func_file_name): self.thisptr.set_function_from_file(func_file_name.encode('utf-8')) else: - print("file " + func_file_name + " not found.", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + func_file_name) def set_function_from_range(self, function): """Creates the function f from a vector stored in memory. @@ -304,14 +312,15 @@ cdef class CoverComplex: """Creates a graph G from a file containing the edges. :param graph_file_name: Name of the input graph file. The graph file - contains one edge per line, each edge being represented by the IDs of - its two nodes. + contains one edge per line, each edge being represented by the IDs + of its two nodes. :type graph_file_name: string """ if os.path.isfile(graph_file_name): self.thisptr.set_graph_from_file(graph_file_name.encode('utf-8')) else: - print("file " + graph_file_name + " not found.", file=sys.stderr) + raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), + graph_file_name) def set_graph_from_OFF(self): """Creates a graph G from the triangulation given by the input OFF -- cgit v1.2.3 From 29e81d5038116aef0ec505e4d21d29f1c5920e34 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Fri, 7 Feb 2020 21:00:17 -0500 Subject: added sklearn trick --- src/python/gudhi/representations/kernel_methods.py | 20 +++--------- src/python/gudhi/representations/metrics.py | 37 +++++++++------------- 2 files changed, 20 insertions(+), 37 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py index bbbb7c31..d89f69ab 100644 --- a/src/python/gudhi/representations/kernel_methods.py +++ b/src/python/gudhi/representations/kernel_methods.py @@ -62,27 +62,17 @@ def pairwise_persistence_diagram_kernels(X, Y=None, metric="sliced_wasserstein", :param metric: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. :returns: kernel matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) :rtype: float - """ - if Y is None: - YY = None - pX = Padding(use=True).fit_transform(X) - diag_len = len(pX[0]) - XX = np.reshape(np.vstack(pX), [-1, diag_len*3]) - else: - nX, nY = len(X), len(Y) - pD = Padding(use=True).fit_transform(X + Y) - diag_len = len(pD[0]) - XX = np.reshape(np.vstack(pD[:nX]), [-1, diag_len*3]) - YY = np.reshape(np.vstack(pD[nX:]), [-1, diag_len*3]) - + """ + XX = np.reshape(np.arange(len(X)), [-1,1]) + YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) if metric == "sliced_wasserstein": return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="sliced_wasserstein", num_directions=kwargs["num_directions"]) / kwargs["bandwidth"]) elif metric == "persistence_fisher": return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="persistence_fisher", kernel_approx=kwargs["kernel_approx"], bandwidth=kwargs["bandwidth"]) / kwargs["bandwidth_fisher"]) elif metric == "persistence_scale_space": - return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_scale_space_kernel, **kwargs)) + return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_scale_space_kernel, X, Y, **kwargs)) elif metric == "persistence_weighted_gaussian": - return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_weighted_gaussian_kernel, **kwargs)) + return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_weighted_gaussian_kernel, X, Y, **kwargs)) else: return pairwise_kernels(XX, YY, metric=sklearn_wrapper(metric, **kwargs)) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index cc788994..fead8aa0 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -85,13 +85,16 @@ def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): vectorj = vectorj/vectorj_sum return np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) -def sklearn_wrapper(metric, **kwargs): +def sklearn_wrapper(metric, X, Y, **kwargs): """ - This function is a wrapper for any metric between two persistence diagrams that takes two numpy arrays of shapes (nx2) and (mx2) as arguments. It turns the metric into another that takes flattened and padded diagrams as inputs. + This function is a wrapper for any metric between two persistence diagrams that takes two numpy arrays of shapes (nx2) and (mx2) as arguments. """ - def flat_metric(D1, D2): - DD1, DD2 = np.reshape(D1, [-1,3]), np.reshape(D2, [-1,3]) - return metric(DD1[DD1[:,2]==1,0:2], DD2[DD2[:,2]==1,0:2], **kwargs) + if Y is None: + def flat_metric(a, b): + return metric(X[int(a[0])], X[int(b[0])], **kwargs) + else: + def flat_metric(a, b): + return metric(X[int(a[0])], Y[int(b[0])], **kwargs) return flat_metric def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwargs): @@ -103,28 +106,18 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa :returns: distance matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) :rtype: float """ - if Y is None: - YY = None - pX = Padding(use=True).fit_transform(X) - diag_len = len(pX[0]) - XX = np.reshape(np.vstack(pX), [-1, diag_len*3]) - else: - nX, nY = len(X), len(Y) - pD = Padding(use=True).fit_transform(X + Y) - diag_len = len(pD[0]) - XX = np.reshape(np.vstack(pD[:nX]), [-1, diag_len*3]) - YY = np.reshape(np.vstack(pD[nX:]), [-1, diag_len*3]) - + XX = np.reshape(np.arange(len(X)), [-1,1]) + YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) if metric == "bottleneck": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, **kwargs)) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) elif metric == "wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(wasserstein_distance, **kwargs)) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(wasserstein_distance, X, Y, **kwargs)) elif metric == "sliced_wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, **kwargs)) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, X, Y, **kwargs)) elif metric == "persistence_fisher": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(persistence_fisher_distance, **kwargs)) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(persistence_fisher_distance, X, Y, **kwargs)) else: - return pairwise_distances(XX, YY, metric=sklearn_wrapper(metric, **kwargs)) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(metric, X, Y, **kwargs)) class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): """ -- cgit v1.2.3 From 3253abd27129595f7fcd2be4c2285a93aea98690 Mon Sep 17 00:00:00 2001 From: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> Date: Tue, 11 Feb 2020 17:05:08 +0100 Subject: Update src/python/gudhi/simplex_tree.pyx Co-Authored-By: Marc Glisse --- src/python/gudhi/simplex_tree.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 22978b6e..308b3d2d 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -219,7 +219,7 @@ cdef class SimplexTree: cdef vector[Simplex_tree_simplex_handle].const_iterator end = self.get_ptr().get_filtration_iterator_end() while it != end: - yield(self.get_ptr().get_simplex_and_filtration(dereference(it))) + yield self.get_ptr().get_simplex_and_filtration(dereference(it)) preincrement(it) def get_skeleton(self, dimension): -- cgit v1.2.3 From 3ea44646f04648d1a456a0fb9526035101fc17ea Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 11 Feb 2020 17:20:24 +0100 Subject: Code review: non-optimal way to test filtration generator --- src/python/test/test_alpha_complex.py | 49 ++++++------- src/python/test/test_euclidean_witness_complex.py | 45 +++++------- src/python/test/test_rips_complex.py | 50 +++++++------ src/python/test/test_simplex_tree.py | 88 +++++++++++------------ src/python/test/test_tangential_complex.py | 17 +++-- 5 files changed, 117 insertions(+), 132 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_alpha_complex.py b/src/python/test/test_alpha_complex.py index ceead919..77121302 100755 --- a/src/python/test/test_alpha_complex.py +++ b/src/python/test/test_alpha_complex.py @@ -40,20 +40,19 @@ def test_infinite_alpha(): assert simplex_tree.num_simplices() == 11 assert simplex_tree.num_vertices() == 4 - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([3], 0.0)) - assert(next(filtration_generator) == ([0, 1], 0.25)) - assert(next(filtration_generator) == ([0, 2], 0.25)) - assert(next(filtration_generator) == ([1, 3], 0.25)) - assert(next(filtration_generator) == ([2, 3], 0.25)) - assert(next(filtration_generator) == ([1, 2], 0.5)) - assert(next(filtration_generator) == ([0, 1, 2], 0.5)) - assert(next(filtration_generator) == ([1, 2, 3], 0.5)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([3], 0.0), + ([0, 1], 0.25), + ([0, 2], 0.25), + ([1, 3], 0.25), + ([2, 3], 0.25), + ([1, 2], 0.5), + ([0, 1, 2], 0.5), + ([1, 2, 3], 0.5), + ] assert simplex_tree.get_star([0]) == [ ([0], 0.0), @@ -107,18 +106,16 @@ def test_filtered_alpha(): else: assert False - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([3], 0.0)) - assert(next(filtration_generator) == ([0, 1], 0.25)) - assert(next(filtration_generator) == ([0, 2], 0.25)) - assert(next(filtration_generator) == ([1, 3], 0.25)) - assert(next(filtration_generator) == ([2, 3], 0.25)) - with pytest.raises(StopIteration): - next(filtration_generator) - + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([3], 0.0), + ([0, 1], 0.25), + ([0, 2], 0.25), + ([1, 3], 0.25), + ([2, 3], 0.25), + ] assert simplex_tree.get_star([0]) == [([0], 0.0), ([0, 1], 0.25), ([0, 2], 0.25)] assert simplex_tree.get_cofaces([0], 1) == [([0, 1], 0.25), ([0, 2], 0.25)] diff --git a/src/python/test/test_euclidean_witness_complex.py b/src/python/test/test_euclidean_witness_complex.py index 16ff1ef4..47196a2a 100755 --- a/src/python/test/test_euclidean_witness_complex.py +++ b/src/python/test/test_euclidean_witness_complex.py @@ -41,16 +41,15 @@ def test_witness_complex(): assert landmarks[1] == euclidean_witness_complex.get_point(1) assert landmarks[2] == euclidean_witness_complex.get_point(2) - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([0, 1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([0, 2], 0.0)) - assert(next(filtration_generator) == ([1, 2], 0.0)) - assert(next(filtration_generator) == ([0, 1, 2], 0.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([0, 1], 0.0), + ([2], 0.0), + ([0, 2], 0.0), + ([1, 2], 0.0), + ([0, 1, 2], 0.0), + ] def test_empty_euclidean_strong_witness_complex(): @@ -80,24 +79,18 @@ def test_strong_witness_complex(): assert landmarks[1] == euclidean_strong_witness_complex.get_point(1) assert landmarks[2] == euclidean_strong_witness_complex.get_point(2) - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [([0], 0.0), ([1], 0.0), ([2], 0.0)] simplex_tree = euclidean_strong_witness_complex.create_simplex_tree( max_alpha_square=100.0 ) - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([1, 2], 15.0)) - assert(next(filtration_generator) == ([0, 2], 34.0)) - assert(next(filtration_generator) == ([0, 1], 37.0)) - assert(next(filtration_generator) == ([0, 1, 2], 37.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([1, 2], 15.0), + ([0, 2], 34.0), + ([0, 1], 37.0), + ([0, 1, 2], 37.0), + ] diff --git a/src/python/test/test_rips_complex.py b/src/python/test/test_rips_complex.py index bd31c47c..f5c086cb 100755 --- a/src/python/test/test_rips_complex.py +++ b/src/python/test/test_rips_complex.py @@ -33,19 +33,18 @@ def test_rips_from_points(): assert simplex_tree.num_simplices() == 10 assert simplex_tree.num_vertices() == 4 - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([3], 0.0)) - assert(next(filtration_generator) == ([0, 1], 1.0)) - assert(next(filtration_generator) == ([0, 2], 1.0)) - assert(next(filtration_generator) == ([1, 3], 1.0)) - assert(next(filtration_generator) == ([2, 3], 1.0)) - assert(next(filtration_generator) == ([1, 2], 1.4142135623730951)) - assert(next(filtration_generator) == ([0, 3], 1.4142135623730951)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([3], 0.0), + ([0, 1], 1.0), + ([0, 2], 1.0), + ([1, 3], 1.0), + ([2, 3], 1.0), + ([1, 2], 1.4142135623730951), + ([0, 3], 1.4142135623730951), + ] assert simplex_tree.get_star([0]) == [ ([0], 0.0), @@ -98,19 +97,18 @@ def test_rips_from_distance_matrix(): assert simplex_tree.num_simplices() == 10 assert simplex_tree.num_vertices() == 4 - filtration_generator = simplex_tree.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([3], 0.0)) - assert(next(filtration_generator) == ([0, 1], 1.0)) - assert(next(filtration_generator) == ([0, 2], 1.0)) - assert(next(filtration_generator) == ([1, 3], 1.0)) - assert(next(filtration_generator) == ([2, 3], 1.0)) - assert(next(filtration_generator) == ([1, 2], 1.4142135623730951)) - assert(next(filtration_generator) == ([0, 3], 1.4142135623730951)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(simplex_tree.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([3], 0.0), + ([0, 1], 1.0), + ([0, 2], 1.0), + ([1, 3], 1.0), + ([2, 3], 1.0), + ([1, 2], 1.4142135623730951), + ([0, 3], 1.4142135623730951), + ] assert simplex_tree.get_star([0]) == [ ([0], 0.0), diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 0f3db7ac..fa42f2ac 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -128,57 +128,55 @@ def test_expansion(): assert st.num_vertices() == 7 assert st.num_simplices() == 17 - filtration_generator = st.get_filtration() - assert(next(filtration_generator) == ([2], 0.1)) - assert(next(filtration_generator) == ([3], 0.1)) - assert(next(filtration_generator) == ([2, 3], 0.1)) - assert(next(filtration_generator) == ([0], 0.2)) - assert(next(filtration_generator) == ([0, 2], 0.2)) - assert(next(filtration_generator) == ([1], 0.3)) - assert(next(filtration_generator) == ([0, 1], 0.3)) - assert(next(filtration_generator) == ([1, 3], 0.4)) - assert(next(filtration_generator) == ([1, 2], 0.5)) - assert(next(filtration_generator) == ([5], 0.6)) - assert(next(filtration_generator) == ([6], 0.6)) - assert(next(filtration_generator) == ([5, 6], 0.6)) - assert(next(filtration_generator) == ([4], 0.7)) - assert(next(filtration_generator) == ([2, 4], 0.7)) - assert(next(filtration_generator) == ([0, 3], 0.8)) - assert(next(filtration_generator) == ([4, 6], 0.9)) - assert(next(filtration_generator) == ([3, 6], 1.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(st.get_filtration()) == [ + ([2], 0.1), + ([3], 0.1), + ([2, 3], 0.1), + ([0], 0.2), + ([0, 2], 0.2), + ([1], 0.3), + ([0, 1], 0.3), + ([1, 3], 0.4), + ([1, 2], 0.5), + ([5], 0.6), + ([6], 0.6), + ([5, 6], 0.6), + ([4], 0.7), + ([2, 4], 0.7), + ([0, 3], 0.8), + ([4, 6], 0.9), + ([3, 6], 1.0), + ] st.expansion(3) assert st.num_vertices() == 7 assert st.num_simplices() == 22 st.initialize_filtration() - filtration_generator = st.get_filtration() - assert(next(filtration_generator) == ([2], 0.1)) - assert(next(filtration_generator) == ([3], 0.1)) - assert(next(filtration_generator) == ([2, 3], 0.1)) - assert(next(filtration_generator) == ([0], 0.2)) - assert(next(filtration_generator) == ([0, 2], 0.2)) - assert(next(filtration_generator) == ([1], 0.3)) - assert(next(filtration_generator) == ([0, 1], 0.3)) - assert(next(filtration_generator) == ([1, 3], 0.4)) - assert(next(filtration_generator) == ([1, 2], 0.5)) - assert(next(filtration_generator) == ([0, 1, 2], 0.5)) - assert(next(filtration_generator) == ([1, 2, 3], 0.5)) - assert(next(filtration_generator) == ([5], 0.6)) - assert(next(filtration_generator) == ([6], 0.6)) - assert(next(filtration_generator) == ([5, 6], 0.6)) - assert(next(filtration_generator) == ([4], 0.7)) - assert(next(filtration_generator) == ([2, 4], 0.7)) - assert(next(filtration_generator) == ([0, 3], 0.8)) - assert(next(filtration_generator) == ([0, 1, 3], 0.8)) - assert(next(filtration_generator) == ([0, 2, 3], 0.8)) - assert(next(filtration_generator) == ([0, 1, 2, 3], 0.8)) - assert(next(filtration_generator) == ([4, 6], 0.9)) - assert(next(filtration_generator) == ([3, 6], 1.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(st.get_filtration()) == [ + ([2], 0.1), + ([3], 0.1), + ([2, 3], 0.1), + ([0], 0.2), + ([0, 2], 0.2), + ([1], 0.3), + ([0, 1], 0.3), + ([1, 3], 0.4), + ([1, 2], 0.5), + ([0, 1, 2], 0.5), + ([1, 2, 3], 0.5), + ([5], 0.6), + ([6], 0.6), + ([5, 6], 0.6), + ([4], 0.7), + ([2, 4], 0.7), + ([0, 3], 0.8), + ([0, 1, 3], 0.8), + ([0, 2, 3], 0.8), + ([0, 1, 2, 3], 0.8), + ([4, 6], 0.9), + ([3, 6], 1.0), + ] def test_automatic_dimension(): diff --git a/src/python/test/test_tangential_complex.py b/src/python/test/test_tangential_complex.py index 90e2c75b..fc500c45 100755 --- a/src/python/test/test_tangential_complex.py +++ b/src/python/test/test_tangential_complex.py @@ -38,15 +38,14 @@ def test_tangential(): assert st.num_simplices() == 6 assert st.num_vertices() == 4 - filtration_generator = st.get_filtration() - assert(next(filtration_generator) == ([0], 0.0)) - assert(next(filtration_generator) == ([1], 0.0)) - assert(next(filtration_generator) == ([2], 0.0)) - assert(next(filtration_generator) == ([0, 2], 0.0)) - assert(next(filtration_generator) == ([3], 0.0)) - assert(next(filtration_generator) == ([1, 3], 0.0)) - with pytest.raises(StopIteration): - next(filtration_generator) + assert list(st.get_filtration()) == [ + ([0], 0.0), + ([1], 0.0), + ([2], 0.0), + ([0, 2], 0.0), + ([3], 0.0), + ([1, 3], 0.0), + ] assert st.get_cofaces([0], 1) == [([0, 2], 0.0)] -- cgit v1.2.3 From 79de1437cb2fa0ab69465a2f2feabe09a12056eb Mon Sep 17 00:00:00 2001 From: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> Date: Tue, 11 Feb 2020 17:51:40 +0100 Subject: Update src/python/include/Simplex_tree_interface.h Co-Authored-By: Marc Glisse --- src/python/include/Simplex_tree_interface.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index c0bbc3d9..878919cc 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -88,7 +88,7 @@ class Simplex_tree_interface : public Simplex_tree { for (auto vertex : Base::simplex_vertex_range(f_simplex)) { simplex.insert(simplex.begin(), vertex); } - return std::make_pair(simplex, Base::filtration(f_simplex)); + return std::make_pair(std::move(simplex), Base::filtration(f_simplex)); } Filtered_simplices get_skeleton(int dimension) { -- cgit v1.2.3 From 73ad191a7dee054a58e9823c84dce9f1e71995f4 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Wed, 12 Feb 2020 10:24:25 +0100 Subject: Fix tests according to exception management --- src/python/gudhi/cubical_complex.pyx | 1 + src/python/test/test_cover_complex.py | 4 +++- src/python/test/test_cubical_complex.py | 6 +++--- 3 files changed, 7 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index 31287d15..d5ad1266 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -17,6 +17,7 @@ from libcpp.string cimport string from libcpp cimport bool import errno import os +import sys import numpy as np diff --git a/src/python/test/test_cover_complex.py b/src/python/test/test_cover_complex.py index 32bc5a26..260f6a5c 100755 --- a/src/python/test/test_cover_complex.py +++ b/src/python/test/test_cover_complex.py @@ -9,6 +9,7 @@ """ from gudhi import CoverComplex +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2018 Inria" @@ -24,7 +25,8 @@ def test_empty_constructor(): def test_non_existing_file_read(): # Try to open a non existing file cover = CoverComplex() - assert cover.read_point_cloud("pouetpouettralala.toubiloubabdou") == False + with pytest.raises(FileNotFoundError): + cover.read_point_cloud("pouetpouettralala.toubiloubabdou") def test_files_creation(): diff --git a/src/python/test/test_cubical_complex.py b/src/python/test/test_cubical_complex.py index 8c1b2600..fce4875c 100755 --- a/src/python/test/test_cubical_complex.py +++ b/src/python/test/test_cubical_complex.py @@ -10,6 +10,7 @@ from gudhi import CubicalComplex, PeriodicCubicalComplex import numpy as np +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -25,9 +26,8 @@ def test_empty_constructor(): def test_non_existing_perseus_file_constructor(): # Try to open a non existing file - cub = CubicalComplex(perseus_file="pouetpouettralala.toubiloubabdou") - assert cub.__is_defined() == False - assert cub.__is_persistence_defined() == False + with pytest.raises(FileNotFoundError): + cub = CubicalComplex(perseus_file="pouetpouettralala.toubiloubabdou") def test_dimension_or_perseus_file_constructor(): -- cgit v1.2.3 From 1edb818b38ace05b230319227e60838b796ddfc5 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Thu, 13 Feb 2020 11:08:44 +0100 Subject: simplex tree skeleton iterator --- src/python/gudhi/simplex_tree.pxd | 10 +++++++++- src/python/gudhi/simplex_tree.pyx | 15 ++++++--------- src/python/include/Simplex_tree_interface.h | 23 ++++++++++------------- src/python/test/test_simplex_tree.py | 8 ++++---- 4 files changed, 29 insertions(+), 27 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 1b0dc881..66c173a6 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -24,6 +24,13 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_simplex_handle "Gudhi::Simplex_tree_interface::Simplex_handle": pass + cdef cppclass Simplex_tree_skeleton_iterator "Gudhi::Simplex_tree_interface::Skeleton_simplex_iterator": + Simplex_tree_skeleton_iterator() + Simplex_tree_simplex_handle& operator*() + Simplex_tree_skeleton_iterator operator++() + bint operator!=(Simplex_tree_skeleton_iterator) + + cdef cppclass Simplex_tree_interface_full_featured "Gudhi::Simplex_tree_interface": Simplex_tree() double simplex_filtration(vector[int] simplex) @@ -37,7 +44,6 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool find_simplex(vector[int] simplex) bool insert_simplex_and_subfaces(vector[int] simplex, double filtration) - vector[pair[vector[int], double]] get_skeleton(int dimension) vector[pair[vector[int], double]] get_star(vector[int] simplex) vector[pair[vector[int], double]] get_cofaces(vector[int] simplex, int dimension) @@ -49,6 +55,8 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() + Simplex_tree_skeleton_iterator get_skeleton_iterator_begin(int dimension) + Simplex_tree_skeleton_iterator get_skeleton_iterator_end(int dimension) cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 308b3d2d..efac2d80 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -231,15 +231,12 @@ cdef class SimplexTree: :returns: The (simplices of the) skeleton of a maximum dimension. :rtype: list of tuples(simplex, filtration) """ - cdef vector[pair[vector[int], double]] skeleton \ - = self.get_ptr().get_skeleton(dimension) - ct = [] - for filtered_simplex in skeleton: - v = [] - for vertex in filtered_simplex.first: - v.append(vertex) - ct.append((v, filtered_simplex.second)) - return ct + cdef Simplex_tree_skeleton_iterator it = self.get_ptr().get_skeleton_iterator_begin(dimension) + cdef Simplex_tree_skeleton_iterator end = self.get_ptr().get_skeleton_iterator_end(dimension) + + while it != end: + yield self.get_ptr().get_simplex_and_filtration(dereference(it)) + preincrement(it) def get_star(self, simplex): """This function returns the star of a given N-simplex. diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 878919cc..55d5af97 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -35,6 +35,7 @@ class Simplex_tree_interface : public Simplex_tree { using Simplex = std::vector; using Simplex_and_filtration = std::pair; using Filtered_simplices = std::vector; + using Skeleton_simplex_iterator = typename Base::Skeleton_simplex_iterator; public: bool find_simplex(const Simplex& vh) { @@ -91,18 +92,6 @@ class Simplex_tree_interface : public Simplex_tree { return std::make_pair(std::move(simplex), Base::filtration(f_simplex)); } - Filtered_simplices get_skeleton(int dimension) { - Filtered_simplices skeletons; - for (auto f_simplex : Base::skeleton_simplex_range(dimension)) { - Simplex simplex; - for (auto vertex : Base::simplex_vertex_range(f_simplex)) { - simplex.insert(simplex.begin(), vertex); - } - skeletons.push_back(std::make_pair(simplex, Base::filtration(f_simplex))); - } - return skeletons; - } - Filtered_simplices get_star(const Simplex& simplex) { Filtered_simplices star; for (auto f_simplex : Base::star_simplex_range(Base::find(simplex))) { @@ -134,13 +123,21 @@ class Simplex_tree_interface : public Simplex_tree { // Iterator over the simplex tree typename std::vector::const_iterator get_filtration_iterator_begin() { - Base::initialize_filtration(); + // Base::initialize_filtration(); already performed in filtration_simplex_range return Base::filtration_simplex_range().begin(); } typename std::vector::const_iterator get_filtration_iterator_end() { return Base::filtration_simplex_range().end(); } + + Skeleton_simplex_iterator get_skeleton_iterator_begin(int dimension) { + return Base::skeleton_simplex_range(dimension).begin(); + } + + Skeleton_simplex_iterator get_skeleton_iterator_end(int dimension) { + return Base::skeleton_simplex_range(dimension).end(); + } }; } // namespace Gudhi diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index fa42f2ac..eca3807b 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -56,7 +56,7 @@ def test_insertion(): assert st.filtration([1]) == 0.0 # skeleton test - assert st.get_skeleton(2) == [ + assert list(st.get_skeleton(2)) == [ ([0, 1, 2], 4.0), ([0, 1], 0.0), ([0, 2], 4.0), @@ -65,7 +65,7 @@ def test_insertion(): ([1], 0.0), ([2], 4.0), ] - assert st.get_skeleton(1) == [ + assert list(st.get_skeleton(1)) == [ ([0, 1], 0.0), ([0, 2], 4.0), ([0], 0.0), @@ -73,12 +73,12 @@ def test_insertion(): ([1], 0.0), ([2], 4.0), ] - assert st.get_skeleton(0) == [([0], 0.0), ([1], 0.0), ([2], 4.0)] + assert list(st.get_skeleton(0)) == [([0], 0.0), ([1], 0.0), ([2], 4.0)] # remove_maximal_simplex test assert st.get_cofaces([0, 1, 2], 1) == [] st.remove_maximal_simplex([0, 1, 2]) - assert st.get_skeleton(2) == [ + assert list(st.get_skeleton(2)) == [ ([0, 1], 0.0), ([0, 2], 4.0), ([0], 0.0), -- cgit v1.2.3 From ef0f82ef2155440827e17c552abb49b509866fc7 Mon Sep 17 00:00:00 2001 From: mathieu Date: Thu, 13 Feb 2020 16:01:29 -0500 Subject: integrated hera --- .../diagram_vectorizations_distances_kernels.py | 7 ++++++- src/python/gudhi/representations/metrics.py | 23 ++++++++++++++++------ 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'src/python') diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index 66c32cc2..6352d2b5 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -117,7 +117,12 @@ X = SW.fit(diags) Y = SW.transform(diags2) print("SW kernel is " + str(Y[0][0])) -W = WassersteinDistance(order=2, internal_p=2) +W = WassersteinDistance(order=2, internal_p=2, mode="pot") +X = W.fit(diags) +Y = W.transform(diags2) +print("Wasserstein distance is " + str(Y[0][0])) + +W = WassersteinDistance(order=2, internal_p=2, mode="hera", delta=0.0001) X = W.fit(diags) Y = W.transform(diags2) print("Wasserstein distance is " + str(Y[0][0])) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index cc788994..ed998603 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -10,7 +10,8 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances -from gudhi.wasserstein import wasserstein_distance +from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance +from gudhi.hera import wasserstein_distance as hera_wasserstein_distance from .preprocessing import Padding try: @@ -117,8 +118,10 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa if metric == "bottleneck": return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, **kwargs)) - elif metric == "wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(wasserstein_distance, **kwargs)) + elif metric == "wasserstein" or metric == "pot_wasserstein": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, **kwargs)) + elif metric == "hera_wasserstein": + return pairwise_distances(XX, YY, metric=sklearn_wrapper(hera_wasserstein_distance, **kwargs)) elif metric == "sliced_wasserstein": return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, **kwargs)) elif metric == "persistence_fisher": @@ -205,15 +208,19 @@ class WassersteinDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the Wasserstein distance matrix from a list of persistence diagrams. """ - def __init__(self, order=2, internal_p=2): + def __init__(self, order=2, internal_p=2, mode="pot", delta=0.0001): """ Constructor for the WassersteinDistance class. Parameters: order (int): exponent for Wasserstein, default value is 2., see :func:`gudhi.wasserstein.wasserstein_distance`. internal_p (int): ground metric on the (upper-half) plane (i.e. norm l_p in R^2), default value is 2 (euclidean norm), see :func:`gudhi.wasserstein.wasserstein_distance`. + mode (str): method for computing Wasserstein distance. Either "pot" or "hera". + delta (float): relative error 1+delta. Used only if mode == "hera". """ - self.order, self.internal_p = order, internal_p + self.order, self.internal_p, self.mode = order, internal_p, mode + self.metric = "pot_wasserstein" if mode == "pot" else "hera_wasserstein" + self.delta = delta def fit(self, X, y=None): """ @@ -236,7 +243,11 @@ class WassersteinDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise Wasserstein distances. """ - return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="wasserstein", order=self.order, internal_p=self.internal_p) + if self.metric == "hera_wasserstein": + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric=self.metric, order=self.order, internal_p=self.internal_p, delta=self.delta) + else: + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric=self.metric, order=self.order, internal_p=self.internal_p) + return Xfit class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ -- cgit v1.2.3 From d9290a78741fc14dc0f87d395da967a4d561b34a Mon Sep 17 00:00:00 2001 From: mathieu Date: Thu, 13 Feb 2020 16:11:34 -0500 Subject: small modif on example file --- src/python/example/diagram_vectorizations_distances_kernels.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index 6352d2b5..507ead7c 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -120,12 +120,12 @@ print("SW kernel is " + str(Y[0][0])) W = WassersteinDistance(order=2, internal_p=2, mode="pot") X = W.fit(diags) Y = W.transform(diags2) -print("Wasserstein distance is " + str(Y[0][0])) +print("Wasserstein distance (POT) is " + str(Y[0][0])) W = WassersteinDistance(order=2, internal_p=2, mode="hera", delta=0.0001) X = W.fit(diags) Y = W.transform(diags2) -print("Wasserstein distance is " + str(Y[0][0])) +print("Wasserstein distance (hera) is " + str(Y[0][0])) W = BottleneckDistance(epsilon=.001) X = W.fit(diags) -- cgit v1.2.3 From a6a4f375822cf3e2ca1866d78472e4350140ddbc Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 11:02:56 +0900 Subject: Add __init__.py --- src/python/gudhi/point_cloud/__init__.py | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 src/python/gudhi/point_cloud/__init__.py (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/__init__.py b/src/python/gudhi/point_cloud/__init__.py new file mode 100644 index 00000000..e69de29b -- cgit v1.2.3 From 9cc9e1cf3cd9ea42908324d410ef68fa12e8e832 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 11:08:50 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 66 ++++++++++++++++++++++--------- 1 file changed, 48 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index f283916d..d899da67 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -10,30 +10,55 @@ import numpy as np class TimeDelayEmbedding: """Point cloud transformation class. - Embeds time-series data in the R^d according to Takens' Embedding Theorem and obtains the coordinates of each point. - Parameters ---------- dim : int, optional (default=3) `d` of R^d to be embedded. - delay : int, optional (default=1) Time-Delay embedding. - skip : int, optional (default=1) How often to skip embedded points. - + Given delay=3 and skip=2, an point cloud which is obtained by embedding + a single time-series data into R^3 is as follows. + + .. code-block:: none + + time-series = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] + point clouds = [[1, 4, 7], + [3, 6, 9]] + """ def __init__(self, dim=3, delay=1, skip=1): self._dim = dim self._delay = delay self._skip = skip - def __call__(self, *args, **kwargs): - return self.transform(*args, **kwargs) + def __call__(self, ts): + """Transform method for single time-series data. + Parameters + ---------- + ts : list[float] + A single time-series data. + Returns + ------- + point clouds : list[list[float, float, float]] + Makes point cloud every a single time-series data. + Raises + ------- + TypeError + If the parameter's type does not match the desired type. + """ + ndts = np.array(ts) + if ndts.ndim == 1: + return self._transform(ndts) + else: + raise TypeError("Expects 1-dimensional array.") + def fit(self, ts, y=None): + return self + def _transform(self, ts): """Guts of transform method.""" return ts[ @@ -43,22 +68,27 @@ class TimeDelayEmbedding: ] def transform(self, ts): - """Transform method. - + """Transform method for multiple time-series data. Parameters ---------- - ts : list[float] or list[list[float]] - A single or multiple time-series data. - + ts : list[list[float]] + Multiple time-series data. + Attributes + ---------- + ndts : + The ndts means that all time series need to have exactly + the same size. Returns ------- - point clouds : list[list[float, float, float]] or list[list[list[float, float, float]]] + point clouds : list[list[list[float, float, float]]] Makes point cloud every a single time-series data. + Raises + ------- + TypeError + If the parameter's type does not match the desired type. """ ndts = np.array(ts) - if ndts.ndim == 1: - # for single. - return self._transform(ndts).tolist() + if ndts.ndim == 2: + return np.apply_along_axis(self._transform, 1, ndts) else: - # for multiple. - return np.apply_along_axis(self._transform, 1, ndts).tolist() + raise TypeError("Expects 2-dimensional array.") -- cgit v1.2.3 From 2253fd03bb49aea455309f6d633a6edeb2362d79 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 17:52:07 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index 2ee0c1fb..d2ffbf40 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -6,30 +6,30 @@ def test_normal(): # Normal case. prep = TimeDelayEmbedding() attractor = prep(ts) - assert (attractor[0] == [1, 2, 3]) - assert (attractor[1] == [2, 3, 4]) - assert (attractor[2] == [3, 4, 5]) - assert (attractor[3] == [4, 5, 6]) - assert (attractor[4] == [5, 6, 7]) - assert (attractor[5] == [6, 7, 8]) - assert (attractor[6] == [7, 8, 9]) - assert (attractor[7] == [8, 9, 10]) + assert (attractor[0] == np.array[1, 2, 3]) + assert (attractor[1] == np.array[2, 3, 4]) + assert (attractor[2] == np.array[3, 4, 5]) + assert (attractor[3] == np.array[4, 5, 6]) + assert (attractor[4] == np.array[5, 6, 7]) + assert (attractor[5] == np.array[6, 7, 8]) + assert (attractor[6] == np.array[7, 8, 9]) + assert (attractor[7] == np.array[8, 9, 10]) # Delay = 3 prep = TimeDelayEmbedding(delay=3) attractor = prep(ts) - assert (attractor[0] == [1, 4, 7]) - assert (attractor[1] == [2, 5, 8]) - assert (attractor[2] == [3, 6, 9]) - assert (attractor[3] == [4, 7, 10]) + assert (attractor[0] == np.array[1, 4, 7]) + assert (attractor[1] == np.array[2, 5, 8]) + assert (attractor[2] == np.array[3, 6, 9]) + assert (attractor[3] == np.array[4, 7, 10]) # Skip = 3 prep = TimeDelayEmbedding(skip=3) attractor = prep(ts) - assert (attractor[0] == [1, 2, 3]) - assert (attractor[1] == [4, 5, 6]) - assert (attractor[2] == [7, 8, 9]) + assert (attractor[0] == np.array[1, 2, 3]) + assert (attractor[1] == np.array[4, 5, 6]) + assert (attractor[2] == np.array[7, 8, 9]) # Delay = 2 / Skip = 2 prep = TimeDelayEmbedding(delay=2, skip=2) attractor = prep(ts) - assert (attractor[0] == [1, 3, 5]) - assert (attractor[1] == [3, 5, 7]) - assert (attractor[2] == [5, 7, 9]) + assert (attractor[0] == np.array[1, 3, 5]) + assert (attractor[1] == np.array[3, 5, 7]) + assert (attractor[2] == np.array[5, 7, 9]) -- cgit v1.2.3 From f58a4120b70487aede3cb4e81fbb15171e34fa37 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 18:24:18 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index d2ffbf40..1cdf56f9 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -6,30 +6,30 @@ def test_normal(): # Normal case. prep = TimeDelayEmbedding() attractor = prep(ts) - assert (attractor[0] == np.array[1, 2, 3]) - assert (attractor[1] == np.array[2, 3, 4]) - assert (attractor[2] == np.array[3, 4, 5]) - assert (attractor[3] == np.array[4, 5, 6]) - assert (attractor[4] == np.array[5, 6, 7]) - assert (attractor[5] == np.array[6, 7, 8]) - assert (attractor[6] == np.array[7, 8, 9]) - assert (attractor[7] == np.array[8, 9, 10]) + assert (attractor[0] == np.array([1, 2, 3])) + assert (attractor[1] == np.array([2, 3, 4])) + assert (attractor[2] == np.array([3, 4, 5])) + assert (attractor[3] == np.array([4, 5, 6])) + assert (attractor[4] == np.array([5, 6, 7])) + assert (attractor[5] == np.array([6, 7, 8])) + assert (attractor[6] == np.array([7, 8, 9])) + assert (attractor[7] == np.array([8, 9, 10])) # Delay = 3 prep = TimeDelayEmbedding(delay=3) attractor = prep(ts) - assert (attractor[0] == np.array[1, 4, 7]) - assert (attractor[1] == np.array[2, 5, 8]) - assert (attractor[2] == np.array[3, 6, 9]) - assert (attractor[3] == np.array[4, 7, 10]) + assert (attractor[0] == np.array([1, 4, 7])) + assert (attractor[1] == np.array([2, 5, 8])) + assert (attractor[2] == np.array([3, 6, 9])) + assert (attractor[3] == np.array([4, 7, 10])) # Skip = 3 prep = TimeDelayEmbedding(skip=3) attractor = prep(ts) - assert (attractor[0] == np.array[1, 2, 3]) - assert (attractor[1] == np.array[4, 5, 6]) - assert (attractor[2] == np.array[7, 8, 9]) + assert (attractor[0] == np.array([1, 2, 3])) + assert (attractor[1] == np.array([4, 5, 6])) + assert (attractor[2] == np.array([7, 8, 9])) # Delay = 2 / Skip = 2 prep = TimeDelayEmbedding(delay=2, skip=2) attractor = prep(ts) - assert (attractor[0] == np.array[1, 3, 5]) - assert (attractor[1] == np.array[3, 5, 7]) - assert (attractor[2] == np.array[5, 7, 9]) + assert (attractor[0] == np.array([1, 3, 5])) + assert (attractor[1] == np.array([3, 5, 7])) + assert (attractor[2] == np.array([5, 7, 9])) -- cgit v1.2.3 From 1c0f48fb26bb2e606dfe0a22e62618357686e2c2 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 18:49:27 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index 1cdf56f9..3b586ad2 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -1,4 +1,5 @@ from gudhi.point_cloud.timedelay import TimeDelayEmbedding +import numpy as np def test_normal(): # Sample array -- cgit v1.2.3 From 39873c0cf43ca7352dddeab8c1cc6a3fc40a2e58 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 19:08:50 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index 3b586ad2..7b6562a5 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -7,7 +7,8 @@ def test_normal(): # Normal case. prep = TimeDelayEmbedding() attractor = prep(ts) - assert (attractor[0] == np.array([1, 2, 3])) + assert (attractor[0] == np.array([1, 2, 3]) + print(attractor[0].all())) assert (attractor[1] == np.array([2, 3, 4])) assert (attractor[2] == np.array([3, 4, 5])) assert (attractor[3] == np.array([4, 5, 6])) -- cgit v1.2.3 From 7c6966ee9821aaeb60d282616445a47071ac1fee Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 19:20:25 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index 7b6562a5..f652fc88 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -7,31 +7,30 @@ def test_normal(): # Normal case. prep = TimeDelayEmbedding() attractor = prep(ts) - assert (attractor[0] == np.array([1, 2, 3]) - print(attractor[0].all())) - assert (attractor[1] == np.array([2, 3, 4])) - assert (attractor[2] == np.array([3, 4, 5])) - assert (attractor[3] == np.array([4, 5, 6])) - assert (attractor[4] == np.array([5, 6, 7])) - assert (attractor[5] == np.array([6, 7, 8])) - assert (attractor[6] == np.array([7, 8, 9])) - assert (attractor[7] == np.array([8, 9, 10])) + assert (attractor[0].all() == np.array([1, 2, 3])) + assert (attractor[1].all() == np.array([2, 3, 4])) + assert (attractor[2].all() == np.array([3, 4, 5])) + assert (attractor[3].all() == np.array([4, 5, 6])) + assert (attractor[4].all() == np.array([5, 6, 7])) + assert (attractor[5].all() == np.array([6, 7, 8])) + assert (attractor[6].all() == np.array([7, 8, 9])) + assert (attractor[7].all() == np.array([8, 9, 10])) # Delay = 3 prep = TimeDelayEmbedding(delay=3) attractor = prep(ts) - assert (attractor[0] == np.array([1, 4, 7])) - assert (attractor[1] == np.array([2, 5, 8])) - assert (attractor[2] == np.array([3, 6, 9])) - assert (attractor[3] == np.array([4, 7, 10])) + assert (attractor[0].all() == np.array([1, 4, 7])) + assert (attractor[1].all() == np.array([2, 5, 8])) + assert (attractor[2].all() == np.array([3, 6, 9])) + assert (attractor[3].all() == np.array([4, 7, 10])) # Skip = 3 prep = TimeDelayEmbedding(skip=3) attractor = prep(ts) - assert (attractor[0] == np.array([1, 2, 3])) - assert (attractor[1] == np.array([4, 5, 6])) - assert (attractor[2] == np.array([7, 8, 9])) + assert (attractor[0].all() == np.array([1, 2, 3])) + assert (attractor[1].all() == np.array([4, 5, 6])) + assert (attractor[2].all() == np.array([7, 8, 9])) # Delay = 2 / Skip = 2 prep = TimeDelayEmbedding(delay=2, skip=2) attractor = prep(ts) - assert (attractor[0] == np.array([1, 3, 5])) - assert (attractor[1] == np.array([3, 5, 7])) - assert (attractor[2] == np.array([5, 7, 9])) + assert (attractor[0].all() == np.array([1, 3, 5])) + assert (attractor[1].all() == np.array([3, 5, 7])) + assert (attractor[2].all() == np.array([5, 7, 9])) -- cgit v1.2.3 From 5023aa0ff30474a96783152844e7fb0ed52e0c98 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Fri, 14 Feb 2020 20:25:14 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index f652fc88..5464a185 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -7,30 +7,30 @@ def test_normal(): # Normal case. prep = TimeDelayEmbedding() attractor = prep(ts) - assert (attractor[0].all() == np.array([1, 2, 3])) - assert (attractor[1].all() == np.array([2, 3, 4])) - assert (attractor[2].all() == np.array([3, 4, 5])) - assert (attractor[3].all() == np.array([4, 5, 6])) - assert (attractor[4].all() == np.array([5, 6, 7])) - assert (attractor[5].all() == np.array([6, 7, 8])) - assert (attractor[6].all() == np.array([7, 8, 9])) - assert (attractor[7].all() == np.array([8, 9, 10])) + assert (attractor[0] == np.array([1, 2, 3])).all() + assert (attractor[1] == np.array([2, 3, 4])).all() + assert (attractor[2] == np.array([3, 4, 5])).all() + assert (attractor[3] == np.array([4, 5, 6])).all() + assert (attractor[4] == np.array([5, 6, 7])).all() + assert (attractor[5] == np.array([6, 7, 8])).all() + assert (attractor[6] == np.array([7, 8, 9])).all() + assert (attractor[7] == np.array([8, 9, 10])).all() # Delay = 3 prep = TimeDelayEmbedding(delay=3) attractor = prep(ts) - assert (attractor[0].all() == np.array([1, 4, 7])) - assert (attractor[1].all() == np.array([2, 5, 8])) - assert (attractor[2].all() == np.array([3, 6, 9])) - assert (attractor[3].all() == np.array([4, 7, 10])) + assert (attractor[0] == np.array([1, 4, 7])).all() + assert (attractor[1] == np.array([2, 5, 8])).all() + assert (attractor[2] == np.array([3, 6, 9])).all() + assert (attractor[3] == np.array([4, 7, 10])).all() # Skip = 3 prep = TimeDelayEmbedding(skip=3) attractor = prep(ts) - assert (attractor[0].all() == np.array([1, 2, 3])) - assert (attractor[1].all() == np.array([4, 5, 6])) - assert (attractor[2].all() == np.array([7, 8, 9])) + assert (attractor[0] == np.array([1, 2, 3])).all() + assert (attractor[1] == np.array([4, 5, 6])).all() + assert (attractor[2] == np.array([7, 8, 9])).all() # Delay = 2 / Skip = 2 prep = TimeDelayEmbedding(delay=2, skip=2) attractor = prep(ts) - assert (attractor[0].all() == np.array([1, 3, 5])) - assert (attractor[1].all() == np.array([3, 5, 7])) - assert (attractor[2].all() == np.array([5, 7, 9])) + assert (attractor[0] == np.array([1, 3, 5])).all() + assert (attractor[1] == np.array([3, 5, 7])).all() + assert (attractor[2] == np.array([5, 7, 9])).all() -- cgit v1.2.3 From dc4442bc402ac25290eb529b57407607434bb7ae Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 14 Feb 2020 14:53:51 +0100 Subject: barycenter update, adding more tests and details about log (assigments, cost, nb iter) --- src/python/gudhi/barycenter.py | 125 +++++++++++-------------- src/python/test/test_wasserstein_barycenter.py | 15 ++- 2 files changed, 69 insertions(+), 71 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 11098afe..4a00c457 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -2,6 +2,7 @@ import ot import numpy as np import scipy.spatial.distance as sc +from wasserstein import _build_dist_matrix, _perstot # This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. # See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. @@ -20,42 +21,19 @@ def _proj_on_diag(w): return np.array([(w[0] + w[1])/2 , (w[0] + w[1])/2]) -def _proj_on_diag_array(X): - ''' - :param X: (n x 2) array encoding the points of a persistent diagram. - :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal - ''' - Z = (X[:,0] + X[:,1]) / 2. - return np.array([Z , Z]).T - - -def _build_dist_matrix(X, Y, p=2., q=2.): - ''' - :param X: (n x 2) numpy.array encoding the (points of the) first diagram. - :param Y: (m x 2) numpy.array encoding the second diagram. - :param q: Ground metric (i.e. norm l_q). - :param p: exponent for the Wasserstein metric. - :returns: (n+1) x (m+1) np.array encoding the cost matrix C. - For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal proj onto the diagonal. - note also that C[n+1, m+1] = 0 (it costs nothing to move from the diagonal to the diagonal). - Note that for lagrangian_barycenter, one must use p=q=2. - ''' - Xdiag = _proj_on_diag_array(X) - Ydiag = _proj_on_diag_array(Y) - if np.isinf(q): - C = sc.cdist(X, Y, metric='chebyshev')**p - Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p - Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p +def _mean(x, m): + """ + :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} + :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal + :returns: the weighted mean of x with (m-k) copies of the diagonal + """ + k = len(x) + if k > 0: + w = np.mean(x, axis=0) + w_delta = _proj_on_diag(w) + return (k * w + (m-k) * w_delta) / m else: - C = sc.cdist(X,Y, metric='minkowski', p=q)**p - Cxd = np.linalg.norm(X - Xdiag, ord=q, axis=1)**p - Cdy = np.linalg.norm(Y - Ydiag, ord=q, axis=1)**p - Cf = np.hstack((C, Cxd[:,None])) - Cdy = np.append(Cdy, 0) - - Cf = np.vstack((Cf, Cdy[None,:])) - - return Cf + return np.array([0, 0]) def _optimal_matching(X, Y, withcost=False): @@ -64,63 +42,63 @@ def _optimal_matching(X, Y, withcost=False): :param Y: numpy.array of size (m x 2) :param withcost: returns also the cost corresponding to this optimal matching :returns: numpy.array of shape (k x 2) encoding the list of edges in the optimal matching. - That is, [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] - if i > len(X) or j > len(Y), it means they represent the diagonal. - + That is, [[i, j] ...], where (i,j) indicates that X[i] is matched to Y[j] + if i >= len(X) or j >= len(Y), it means they represent the diagonal. + They will be encoded by -1 afterwards. """ n = len(X) m = len(Y) + # Start by handling empty diagrams. Could it be shorten? if X.size == 0: # X is empty if Y.size == 0: # Y is empty - return np.array([[0,0]]) # the diagonal is matched to the diagonal and that's it... - else: - return np.column_stack([np.zeros(m+1, dtype=int), np.arange(m+1, dtype=int)]) + res = np.array([[0,0]]) # the diagonal is matched to the diagonal and that's it... + if withcost: + return res, 0 + else: + return res + else: # X is empty but not Y + res = np.array([[0, i] for i in range(m)]) + cost = _perstot(Y, order=2, internal_p=2)**2 + if withcost: + return res, cost + else: + return res elif Y.size == 0: # X is not empty but Y is empty - return np.column_stack([np.zeros(n+1, dtype=int), np.arange(n+1, dtype=int)]) - + res = np.array([[i,0] for i in range(n)]) + cost = _perstot(X, order=2, internal_p=2)**2 + if withcost: + return res, cost + else: + return res + # we know X, Y are not empty diags now - M = _build_dist_matrix(X, Y) + M = _build_dist_matrix(X, Y, order=2, internal_p=2) a = np.full(n+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. a[-1] = a[-1] * m # normalized so that we have a probability measure, required by POT b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. b[-1] = b[-1] * n # so that we have a probability measure, required by POT P = ot.emd(a=a, b=b, M=M)*(n+m) - # Note : it seems POT return a permutation matrix in this situation, ie a vertex of the constraint set (generically true). + # Note : it seems POT returns a permutation matrix in this situation, ie a vertex of the constraint set (generically true). if withcost: - cost = np.sqrt(np.sum(np.multiply(P, M))) + cost = np.sum(np.multiply(P, M)) P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to be improved. - # return the list of (i,j) such that P[i,j] > 0, i.e. x_i is matched to y_j (should it be the diag). res = np.nonzero(P) + # return the list of (i,j) such that P[i,j] > 0, i.e. x_i is matched to y_j (should it be the diag). if withcost: return np.column_stack(res), cost return np.column_stack(res) -def _mean(x, m): - """ - :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} - :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal - :returns: the weighted mean of x with (m-k) copies of the diagonal - """ - k = len(x) - if k > 0: - w = np.mean(x, axis=0) - w_delta = _proj_on_diag(w) - return (k * w + (m-k) * w_delta) / m - else: - return np.array([0, 0]) - - def lagrangian_barycenter(pdiagset, init=None, verbose=False): """ Compute the estimated barycenter computed with the algorithm provided by Turner et al (2014). It is a local minimum of the corresponding Frechet function. - :param pdiagset: a list of size N containing numpy.array of shape (n x 2) + :param pdiagset: a list of size m containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. :param init: The initial value for barycenter estimate. @@ -134,10 +112,13 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): If verbose, returns a couple (Y, log) where Y is the barycenter estimate, and log is a dict that contains additional informations: - - assigments, a list of list of pairs (i,j), - That is, a[k] = [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] + - groupings, a list of list of pairs (i,j), + That is, G[k] = [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] if i > len(X) or j > len(Y), it means they represent the diagonal. - - energy, a float representing the Frechet mean value obtained. + - energy, a float representing the Frechet energy value obtained, + that is the mean of squared distances of observations to the output. + - nb_iter, integer representing the number of iterations performed before convergence + of the algorithm. """ X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging @@ -157,8 +138,11 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): else: Y = init.copy() + nb_iter = 0 + converged = False # stoping criterion while not converged: + nb_iter += 1 K = len(Y) # current nb of points in Y (some might be on diagonal) G = np.zeros((K, m), dtype=int)-1 # will store for each j, the (index) point matched in each other diagram (might be the diagonal). # that is G[j, i] = k <=> y_j is matched to @@ -185,7 +169,6 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): new_created_points.append(new_y) # Step 2 : Update current point position thanks to the groupings computed - to_delete = [] for j in range(K): matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] @@ -214,12 +197,16 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): n_y = len(Y) for i in range(m): edges, cost = _optimal_matching(Y, X[i], withcost=True) - print(edges) - groupings.append([x_i_j for (y_j, x_i_j) in enumerate(edges) if y_j < n_y]) + n_x = len(X[i]) + G = edges[np.where(edges[:,0]= n_x) + G[idx,1] = -1 # -1 will encode the diagonal + groupings.append(G) energy += cost log["groupings"] = groupings energy = energy/m log["energy"] = energy + log["nb_iter"] = nb_iter return Y, log else: diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index 910d23ff..07242582 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -27,7 +27,18 @@ def test_lagrangian_barycenter(): res = np.array([[0.27916667, 0.55416667], [0.7375, 0.7625], [0.2375, 0.2625]]) dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) + dg8 = np.array([[0., 4.]]) + + # error crit. + eps = 0.000001 - assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < 0.001 + + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < eps assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.empty(shape=(0,2))) - assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < 0.001 + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < eps + Y, log = lagrangian_barycenter(pdiagset=[dg4, dg8], verbose=True) + assert np.linalg.norm(Y - np.array([[1,3]])) < eps + assert np.abs(log["energy"] - 2) < eps + assert np.array_equal(log["groupings"][0] , np.array([[0, -1]])) + assert np.array_equal(log["groupings"][1] , np.array([[0, 0]])) + assert lagrangian_barycenter(pdiagset = []) is None -- cgit v1.2.3 From dc5c7ac2167bfa467b52d0a36ecb9999fe03ba91 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 14 Feb 2020 14:58:53 +0100 Subject: added two more tests for barycenter --- src/python/test/test_wasserstein_barycenter.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index 07242582..a58a4d62 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -41,4 +41,5 @@ def test_lagrangian_barycenter(): assert np.abs(log["energy"] - 2) < eps assert np.array_equal(log["groupings"][0] , np.array([[0, -1]])) assert np.array_equal(log["groupings"][1] , np.array([[0, 0]])) + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg8, dg4], init=np.array([[0.2, 0.6], [0.5, 0.7]]), verbose=False) - np.array([[1, 3]])) < eps assert lagrangian_barycenter(pdiagset = []) is None -- cgit v1.2.3 From 3eaba12b66518717e90ffb1e410b7f8d769719cf Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 14 Feb 2020 15:41:23 +0100 Subject: update import gudhi.wasserstein --- src/python/gudhi/barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 4a00c457..a2af7a58 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -2,7 +2,7 @@ import ot import numpy as np import scipy.spatial.distance as sc -from wasserstein import _build_dist_matrix, _perstot +from gudhi.wasserstein import _build_dist_matrix, _perstot # This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. # See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. -- cgit v1.2.3 From f8fe3fdb01f6161b57da732a1c3f0c14a8b359a6 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 14 Feb 2020 18:45:34 +0100 Subject: moved import after docstring + reduce lines < 80 char --- src/python/gudhi/barycenter.py | 99 +++++++++++++++++++++++++----------------- 1 file changed, 59 insertions(+), 40 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index a2af7a58..4a877b4a 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -1,9 +1,3 @@ -import ot -import numpy as np -import scipy.spatial.distance as sc - -from gudhi.wasserstein import _build_dist_matrix, _perstot - # This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. # See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. # Author(s): Theo Lacombe @@ -14,6 +8,13 @@ from gudhi.wasserstein import _build_dist_matrix, _perstot # - YYYY/MM Author: Description of the modification +import ot +import numpy as np +import scipy.spatial.distance as sc + +from gudhi.wasserstein import _build_dist_matrix, _perstot + + def _proj_on_diag(w): ''' Util function to project a point on the diag. @@ -24,7 +25,8 @@ def _proj_on_diag(w): def _mean(x, m): """ :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} - :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal + :param m: total amount of points taken into account, + that is we have (m-k) copies of diagonal :returns: the weighted mean of x with (m-k) copies of the diagonal """ k = len(x) @@ -40,11 +42,14 @@ def _optimal_matching(X, Y, withcost=False): """ :param X: numpy.array of size (n x 2) :param Y: numpy.array of size (m x 2) - :param withcost: returns also the cost corresponding to this optimal matching - :returns: numpy.array of shape (k x 2) encoding the list of edges in the optimal matching. - That is, [[i, j] ...], where (i,j) indicates that X[i] is matched to Y[j] - if i >= len(X) or j >= len(Y), it means they represent the diagonal. - They will be encoded by -1 afterwards. + :param withcost: returns also the cost corresponding to the optimal matching + :returns: numpy.array of shape (k x 2) encoding the list of edges + in the optimal matching. + That is, [[i, j] ...], where (i,j) indicates + that X[i] is matched to Y[j] + if i >= len(X) or j >= len(Y), it means they + represent the diagonal. + They will be encoded by -1 afterwards. """ n = len(X) @@ -52,7 +57,7 @@ def _optimal_matching(X, Y, withcost=False): # Start by handling empty diagrams. Could it be shorten? if X.size == 0: # X is empty if Y.size == 0: # Y is empty - res = np.array([[0,0]]) # the diagonal is matched to the diagonal and that's it... + res = np.array([[0,0]]) # the diagonal is matched to the diagonal if withcost: return res, 0 else: @@ -75,18 +80,20 @@ def _optimal_matching(X, Y, withcost=False): # we know X, Y are not empty diags now M = _build_dist_matrix(X, Y, order=2, internal_p=2) - a = np.full(n+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. - a[-1] = a[-1] * m # normalized so that we have a probability measure, required by POT - b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. - b[-1] = b[-1] * n # so that we have a probability measure, required by POT + a = np.full(n+1, 1. / (n + m) ) + a[-1] = a[-1] * m + b = np.full(m+1, 1. / (n + m) ) + b[-1] = b[-1] * n P = ot.emd(a=a, b=b, M=M)*(n+m) - # Note : it seems POT returns a permutation matrix in this situation, ie a vertex of the constraint set (generically true). + # Note : it seems POT returns a permutation matrix in this situation, + # ie a vertex of the constraint set (generically true). if withcost: cost = np.sum(np.multiply(P, M)) - P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to be improved. + P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to improve. res = np.nonzero(P) - # return the list of (i,j) such that P[i,j] > 0, i.e. x_i is matched to y_j (should it be the diag). + # return the list of (i,j) such that P[i,j] > 0, + #i.e. x_i is matched to y_j (should it be the diag). if withcost: return np.column_stack(res), cost @@ -103,31 +110,38 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): persistence diagrams with only finite coordinates. :param init: The initial value for barycenter estimate. If None, init is made on a random diagram from the dataset. - Otherwise, it must be an int (then we init with diagset[init]) - or a (n x 2) numpy.array enconding a persistence diagram with n points. + Otherwise, it must be an int + (then we init with diagset[init]) + or a (n x 2) numpy.array enconding + a persistence diagram with n points. :param verbose: if True, returns additional information about the barycenter. :returns: If not verbose (default), a numpy.array encoding - the barycenter estimate (local minima of the energy function). + the barycenter estimate + (local minima of the energy function). If verbose, returns a couple (Y, log) where Y is the barycenter estimate, and log is a dict that contains additional informations: - groupings, a list of list of pairs (i,j), - That is, G[k] = [(i, j) ...], where (i,j) indicates that X[i] is matched to Y[j] - if i > len(X) or j > len(Y), it means they represent the diagonal. - - energy, a float representing the Frechet energy value obtained, - that is the mean of squared distances of observations to the output. - - nb_iter, integer representing the number of iterations performed before convergence - of the algorithm. + That is, G[k] = [(i, j) ...], where (i,j) indicates + that X[i] is matched to Y[j] + if i > len(X) or j > len(Y), it means they + represent the diagonal. + - energy, a float representing the Frechet + energy value obtained, + that is the mean of squared distances + of observations to the output. + - nb_iter, integer representing the number of iterations + performed before convergence of the algorithm. """ X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging if m == 0: print("Warning: computing barycenter of empty diag set. Returns None") return None - - nb_off_diag = np.array([len(X_i) for X_i in X]) # store the number of off-diagonal point for each of the X_i - + + # store the number of off-diagonal point for each of the X_i + nb_off_diag = np.array([len(X_i) for X_i in X]) # Initialisation of barycenter if init is None: i0 = np.random.randint(m) # Index of first state for the barycenter @@ -144,7 +158,9 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): while not converged: nb_iter += 1 K = len(Y) # current nb of points in Y (some might be on diagonal) - G = np.zeros((K, m), dtype=int)-1 # will store for each j, the (index) point matched in each other diagram (might be the diagonal). + G = np.zeros((K, m), dtype=int)-1 # will store for each j, the (index) + # point matched in each other diagram + #(might be the diagonal). # that is G[j, i] = k <=> y_j is matched to # x_k in the diagram i-th diagram X[i] updated_points = np.zeros((K, 2)) # will store the new positions of @@ -159,16 +175,19 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): indices = _optimal_matching(Y, X[i]) for y_j, x_i_j in indices: if y_j < K: # we matched an off diagonal point to x_i_j... - if x_i_j < nb_off_diag[i]: # ...which is also an off-diagonal point + # ...which is also an off-diagonal point. + if x_i_j < nb_off_diag[i]: G[y_j, i] = x_i_j else: # ...which is a diagonal point G[y_j, i] = -1 # -1 stands for the diagonal (mask) else: # We matched a diagonal point to x_i_j... - if x_i_j < nb_off_diag[i]: # which is a off-diag point ! so we need to create a new point in Y - new_y = _mean(np.array([X[i][x_i_j]]), m) # Average this point with (m-1) copies of Delta + if x_i_j < nb_off_diag[i]: # which is a off-diag point ! + # need to create new point in Y + new_y = _mean(np.array([X[i][x_i_j]]), m) + # Average this point with (m-1) copies of Delta new_created_points.append(new_y) - # Step 2 : Update current point position thanks to the groupings computed + # Step 2 : Update current point position thanks to groupings computed to_delete = [] for j in range(K): matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] @@ -178,10 +197,10 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): else: # this points is no longer of any use. to_delete.append(j) # we remove the point to be deleted now. - updated_points = np.delete(updated_points, to_delete, axis=0) # cannot be done in-place. - + updated_points = np.delete(updated_points, to_delete, axis=0) - if new_created_points: # we cannot converge if there have been new created points. + # we cannot converge if there have been new created points. + if new_created_points: Y = np.concatenate((updated_points, new_created_points)) else: # Step 3 : we check convergence -- cgit v1.2.3 From 5e4bc93510f50dacdb59f1a7578aca72817c9631 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 17 Feb 2020 17:50:37 +0100 Subject: update doc + removed normalization + use argwhere --- src/python/doc/barycenter_user.rst | 7 ++++++- src/python/gudhi/barycenter.py | 29 ++++++++++++----------------- 2 files changed, 18 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index 714d807e..f81e9358 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -9,7 +9,8 @@ Definition .. include:: barycenter_sum.inc -This implementation is based on ideas from "Frechet means for distribution of persistence diagrams", Turner et al. 2014. +This implementation is based on ideas from "Frechet means for distribution of +persistence diagrams", Turner et al. 2014. Function -------- @@ -21,6 +22,10 @@ Basic example This example computes the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. It is initialized on the 4th diagram, which is the empty diagram. It is encoded by np.array([]). +As the algorithm is not convex, its output depends on the initialization and is only a local minimum of the objective function. +Initialization can be either given as an integer (in which case the i-th diagram of the list is used as initial estimate) +or as a diagram. +If None, it will randomly select one of the diagram of the list as initial estimate. Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. .. testcode:: diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 4a877b4a..c54066ec 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -15,12 +15,6 @@ import scipy.spatial.distance as sc from gudhi.wasserstein import _build_dist_matrix, _perstot -def _proj_on_diag(w): - ''' - Util function to project a point on the diag. - ''' - return np.array([(w[0] + w[1])/2 , (w[0] + w[1])/2]) - def _mean(x, m): """ @@ -32,7 +26,7 @@ def _mean(x, m): k = len(x) if k > 0: w = np.mean(x, axis=0) - w_delta = _proj_on_diag(w) + w_delta = (w[0] + w[1]) / 2 * np.ones(2) return (k * w + (m-k) * w_delta) / m else: return np.array([0, 0]) @@ -80,31 +74,32 @@ def _optimal_matching(X, Y, withcost=False): # we know X, Y are not empty diags now M = _build_dist_matrix(X, Y, order=2, internal_p=2) - a = np.full(n+1, 1. / (n + m) ) - a[-1] = a[-1] * m - b = np.full(m+1, 1. / (n + m) ) - b[-1] = b[-1] * n - P = ot.emd(a=a, b=b, M=M)*(n+m) + a = np.ones(n+1) + a[-1] = m + b = np.ones(m+1) + b[-1] = n + P = ot.emd(a=a, b=b, M=M) # Note : it seems POT returns a permutation matrix in this situation, # ie a vertex of the constraint set (generically true). if withcost: cost = np.sum(np.multiply(P, M)) P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to improve. - res = np.nonzero(P) + res = np.argwhere(P) # return the list of (i,j) such that P[i,j] > 0, #i.e. x_i is matched to y_j (should it be the diag). if withcost: - return np.column_stack(res), cost - - return np.column_stack(res) + return res, cost + return res def lagrangian_barycenter(pdiagset, init=None, verbose=False): """ - Compute the estimated barycenter computed with the algorithm provided + Returns the estimated barycenter computed with the algorithm provided by Turner et al (2014). + As the algorithm is not convex, the output depends on initialization. It is a local minimum of the corresponding Frechet function. + :param pdiagset: a list of size m containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. -- cgit v1.2.3 From 16e80e921e1edbc63398f7dbc342bd25d1f169de Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 17 Feb 2020 17:53:39 +0100 Subject: removed message about empty dgm --- src/python/doc/barycenter_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index f81e9358..59f758fa 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -21,7 +21,7 @@ Basic example ------------- This example computes the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. -It is initialized on the 4th diagram, which is the empty diagram. It is encoded by np.array([]). +It is initialized on the 4th diagram. As the algorithm is not convex, its output depends on the initialization and is only a local minimum of the objective function. Initialization can be either given as an integer (in which case the i-th diagram of the list is used as initial estimate) or as a diagram. -- cgit v1.2.3 From a9b0d8185ecab51428c1aeeb3bf78787420103b2 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 17 Feb 2020 17:54:01 +0100 Subject: specified that the alg returns None if input is empty --- src/python/gudhi/barycenter.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index c54066ec..dc9e8241 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -103,6 +103,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): :param pdiagset: a list of size m containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. + If empty, returns None. :param init: The initial value for barycenter estimate. If None, init is made on a random diagram from the dataset. Otherwise, it must be an int -- cgit v1.2.3 From 80d84e5d8f9a24de745d23f7d721ea3e62217ff4 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Wed, 19 Feb 2020 12:32:00 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index d899da67..6ad87cdc 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -43,7 +43,7 @@ class TimeDelayEmbedding: A single time-series data. Returns ------- - point clouds : list[list[float, float, float]] + point clouds : list of n x 2 numpy arrays Makes point cloud every a single time-series data. Raises ------- @@ -80,7 +80,7 @@ class TimeDelayEmbedding: the same size. Returns ------- - point clouds : list[list[list[float, float, float]]] + point clouds : list of n x 3 numpy arrays Makes point cloud every a single time-series data. Raises ------- -- cgit v1.2.3 From 59f046cd0f405b124a6e08f26ca7b0248f707374 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 24 Feb 2020 10:14:09 +0100 Subject: update doc for barycenter --- src/python/doc/index.rst | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'src/python') diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index 3387a64f..96cd3513 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -71,6 +71,11 @@ Wasserstein distance .. include:: wasserstein_distance_sum.inc +Barycenter +============ + +.. include:: barycenter_sum.inc + Persistence representations =========================== -- cgit v1.2.3 From 3e15e9fe5bffb0ffcf8f7f3a0dac1c331646630a Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 24 Feb 2020 10:14:31 +0100 Subject: changed double quote into simple quote to be consistent with wasserstein.py --- src/python/gudhi/barycenter.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index dc9e8241..4e132c23 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -17,12 +17,12 @@ from gudhi.wasserstein import _build_dist_matrix, _perstot def _mean(x, m): - """ + ''' :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal :returns: the weighted mean of x with (m-k) copies of the diagonal - """ + ''' k = len(x) if k > 0: w = np.mean(x, axis=0) @@ -33,7 +33,7 @@ def _mean(x, m): def _optimal_matching(X, Y, withcost=False): - """ + ''' :param X: numpy.array of size (n x 2) :param Y: numpy.array of size (m x 2) :param withcost: returns also the cost corresponding to the optimal matching @@ -44,7 +44,7 @@ def _optimal_matching(X, Y, withcost=False): if i >= len(X) or j >= len(Y), it means they represent the diagonal. They will be encoded by -1 afterwards. - """ + ''' n = len(X) m = len(Y) @@ -94,7 +94,7 @@ def _optimal_matching(X, Y, withcost=False): def lagrangian_barycenter(pdiagset, init=None, verbose=False): - """ + ''' Returns the estimated barycenter computed with the algorithm provided by Turner et al (2014). As the algorithm is not convex, the output depends on initialization. @@ -129,7 +129,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): of observations to the output. - nb_iter, integer representing the number of iterations performed before convergence of the algorithm. - """ + ''' X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging if m == 0: -- cgit v1.2.3 From 2dc7b150576d959b489d3f52890242fd6a492171 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 24 Feb 2020 13:18:38 +0100 Subject: changed doc for CI ? --- src/python/gudhi/barycenter.py | 5 ----- 1 file changed, 5 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 4e132c23..a41b5906 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -95,11 +95,6 @@ def _optimal_matching(X, Y, withcost=False): def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' - Returns the estimated barycenter computed with the algorithm provided - by Turner et al (2014). - As the algorithm is not convex, the output depends on initialization. - It is a local minimum of the corresponding Frechet function. - :param pdiagset: a list of size m containing numpy.array of shape (n x 2) (n can variate), encoding a set of persistence diagrams with only finite coordinates. -- cgit v1.2.3 From 88964b4ff10798d6d9c3d0a342c004ee6b8b1496 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Tue, 25 Feb 2020 13:21:55 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 89 +++++++++++++++---------------- 1 file changed, 44 insertions(+), 45 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index 6ad87cdc..d7a1dab7 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -8,10 +8,12 @@ import numpy as np + class TimeDelayEmbedding: """Point cloud transformation class. Embeds time-series data in the R^d according to Takens' Embedding Theorem and obtains the coordinates of each point. + Parameters ---------- dim : int, optional (default=3) @@ -20,16 +22,27 @@ class TimeDelayEmbedding: Time-Delay embedding. skip : int, optional (default=1) How often to skip embedded points. - Given delay=3 and skip=2, an point cloud which is obtained by embedding - a single time-series data into R^3 is as follows. - - .. code-block:: none - - time-series = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - point clouds = [[1, 4, 7], - [3, 6, 9]] - + + Example + ------- + + Given delay=3 and skip=2, a point cloud which is obtained by embedding + a scalar time-series into R^3 is as follows:: + + time-series = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] + point cloud = [[1, 4, 7], + [3, 6, 9]] + + Given delay=1 and skip=1, a point cloud which is obtained by embedding + a 2D vector time-series data into R^4 is as follows:: + + time-series = [[0, 1], [2, 3], [4, 5], [6, 7], [8, 9]] + point cloud = [[0, 1, 2, 3], + [2, 3, 4, 5], + [4, 5, 6, 7], + [6, 7, 8, 9]] """ + def __init__(self, dim=3, delay=1, skip=1): self._dim = dim self._delay = delay @@ -39,56 +52,42 @@ class TimeDelayEmbedding: """Transform method for single time-series data. Parameters ---------- - ts : list[float] - A single time-series data. + ts : Iterable[float] or Iterable[Iterable[float]] + A single time-series data, with scalar or vector values. + Returns ------- - point clouds : list of n x 2 numpy arrays - Makes point cloud every a single time-series data. - Raises - ------- - TypeError - If the parameter's type does not match the desired type. + point cloud : n x dim numpy arrays + Makes point cloud from a single time-series data. """ - ndts = np.array(ts) - if ndts.ndim == 1: - return self._transform(ndts) - else: - raise TypeError("Expects 1-dimensional array.") + return self._transform(np.array(ts)) def fit(self, ts, y=None): return self def _transform(self, ts): """Guts of transform method.""" - return ts[ - np.add.outer( - np.arange(0, len(ts)-self._delay*(self._dim-1), self._skip), - np.arange(0, self._dim*self._delay, self._delay)) - ] + if ts.ndim == 1: + repeat = self._dim + else: + assert self._dim % ts.shape[1] == 0 + repeat = self._dim // ts.shape[1] + end = len(ts) - self._delay * (repeat - 1) + short = np.arange(0, end, self._skip) + vertical = np.arange(0, repeat * self._delay, self._delay) + return ts[np.add.outer(short, vertical)].reshape(len(short), -1) def transform(self, ts): """Transform method for multiple time-series data. + Parameters ---------- - ts : list[list[float]] - Multiple time-series data. - Attributes - ---------- - ndts : - The ndts means that all time series need to have exactly - the same size. + ts : Iterable[Iterable[float]] or Iterable[Iterable[Iterable[float]]] + Multiple time-series data, with scalar or vector values. + Returns ------- - point clouds : list of n x 3 numpy arrays - Makes point cloud every a single time-series data. - Raises - ------- - TypeError - If the parameter's type does not match the desired type. + point clouds : list of n x dim numpy arrays + Makes point cloud from each time-series data. """ - ndts = np.array(ts) - if ndts.ndim == 2: - return np.apply_along_axis(self._transform, 1, ndts) - else: - raise TypeError("Expects 2-dimensional array.") + return [self._transform(np.array(s)) for s in ts] -- cgit v1.2.3 From 66c96498b994fea1fcaa6877121023410f4209f9 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Tue, 25 Feb 2020 13:24:48 +0900 Subject: Update test_time_delay.py --- src/python/test/test_time_delay.py | 51 ++++++++++++++++++++++---------------- 1 file changed, 29 insertions(+), 22 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_time_delay.py b/src/python/test/test_time_delay.py index 5464a185..1ead9bca 100755 --- a/src/python/test/test_time_delay.py +++ b/src/python/test/test_time_delay.py @@ -1,36 +1,43 @@ from gudhi.point_cloud.timedelay import TimeDelayEmbedding import numpy as np + def test_normal(): # Sample array ts = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] # Normal case. prep = TimeDelayEmbedding() - attractor = prep(ts) - assert (attractor[0] == np.array([1, 2, 3])).all() - assert (attractor[1] == np.array([2, 3, 4])).all() - assert (attractor[2] == np.array([3, 4, 5])).all() - assert (attractor[3] == np.array([4, 5, 6])).all() - assert (attractor[4] == np.array([5, 6, 7])).all() - assert (attractor[5] == np.array([6, 7, 8])).all() - assert (attractor[6] == np.array([7, 8, 9])).all() - assert (attractor[7] == np.array([8, 9, 10])).all() + pointclouds = prep(ts) + assert (pointclouds[0] == np.array([1, 2, 3])).all() + assert (pointclouds[1] == np.array([2, 3, 4])).all() + assert (pointclouds[2] == np.array([3, 4, 5])).all() + assert (pointclouds[3] == np.array([4, 5, 6])).all() + assert (pointclouds[4] == np.array([5, 6, 7])).all() + assert (pointclouds[5] == np.array([6, 7, 8])).all() + assert (pointclouds[6] == np.array([7, 8, 9])).all() + assert (pointclouds[7] == np.array([8, 9, 10])).all() # Delay = 3 prep = TimeDelayEmbedding(delay=3) - attractor = prep(ts) - assert (attractor[0] == np.array([1, 4, 7])).all() - assert (attractor[1] == np.array([2, 5, 8])).all() - assert (attractor[2] == np.array([3, 6, 9])).all() - assert (attractor[3] == np.array([4, 7, 10])).all() + pointclouds = prep(ts) + assert (pointclouds[0] == np.array([1, 4, 7])).all() + assert (pointclouds[1] == np.array([2, 5, 8])).all() + assert (pointclouds[2] == np.array([3, 6, 9])).all() + assert (pointclouds[3] == np.array([4, 7, 10])).all() # Skip = 3 prep = TimeDelayEmbedding(skip=3) - attractor = prep(ts) - assert (attractor[0] == np.array([1, 2, 3])).all() - assert (attractor[1] == np.array([4, 5, 6])).all() - assert (attractor[2] == np.array([7, 8, 9])).all() + pointclouds = prep(ts) + assert (pointclouds[0] == np.array([1, 2, 3])).all() + assert (pointclouds[1] == np.array([4, 5, 6])).all() + assert (pointclouds[2] == np.array([7, 8, 9])).all() # Delay = 2 / Skip = 2 prep = TimeDelayEmbedding(delay=2, skip=2) - attractor = prep(ts) - assert (attractor[0] == np.array([1, 3, 5])).all() - assert (attractor[1] == np.array([3, 5, 7])).all() - assert (attractor[2] == np.array([5, 7, 9])).all() + pointclouds = prep(ts) + assert (pointclouds[0] == np.array([1, 3, 5])).all() + assert (pointclouds[1] == np.array([3, 5, 7])).all() + assert (pointclouds[2] == np.array([5, 7, 9])).all() + + # Vector series + ts = np.arange(0, 10).reshape(-1, 2) + prep = TimeDelayEmbedding(dim=4) + prep.fit([ts]) + assert (prep.transform([ts])[0] == [[0, 1, 2, 3], [2, 3, 4, 5], [4, 5, 6, 7], [6, 7, 8, 9]]).all() -- cgit v1.2.3 From a74ec878560bbe5fa340b2650ca9c16471b685af Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Tue, 25 Feb 2020 13:27:03 +0900 Subject: Update point_cloud.rst --- src/python/doc/point_cloud.rst | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index 55c74ff3..c0d4b303 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -26,4 +26,5 @@ TimeDelayEmbedding .. autoclass:: gudhi.point_cloud.timedelay.TimeDelayEmbedding :members: + :special-members: __call__ -- cgit v1.2.3 From f25d0f86fcd4ac9ab2939b2919d7a66df8b21269 Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Tue, 25 Feb 2020 16:35:41 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index d7a1dab7..576f4386 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -50,6 +50,7 @@ class TimeDelayEmbedding: def __call__(self, ts): """Transform method for single time-series data. + Parameters ---------- ts : Iterable[float] or Iterable[Iterable[float]] -- cgit v1.2.3 From 2c1edeb7fd241c8718a22618438b482704703b4a Mon Sep 17 00:00:00 2001 From: mtakenouchi Date: Tue, 25 Feb 2020 17:46:28 +0900 Subject: Update timedelay.py --- src/python/gudhi/point_cloud/timedelay.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index 576f4386..f01df442 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -11,8 +11,9 @@ import numpy as np class TimeDelayEmbedding: """Point cloud transformation class. - Embeds time-series data in the R^d according to Takens' Embedding Theorem - and obtains the coordinates of each point. + Embeds time-series data in the R^d according to [Takens' Embedding Theorem] + (https://en.wikipedia.org/wiki/Takens%27s_theorem) and obtains the + coordinates of each point. Parameters ---------- -- cgit v1.2.3 From cbb350d81a8c4acadf31b604aaebde209f462e55 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Wed, 26 Feb 2020 09:32:32 +0100 Subject: Code review: remove import pytest leftovers --- src/python/test/test_euclidean_witness_complex.py | 1 - src/python/test/test_rips_complex.py | 1 - src/python/test/test_simplex_tree.py | 1 - src/python/test/test_tangential_complex.py | 1 - 4 files changed, 4 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_euclidean_witness_complex.py b/src/python/test/test_euclidean_witness_complex.py index 47196a2a..f3664d39 100755 --- a/src/python/test/test_euclidean_witness_complex.py +++ b/src/python/test/test_euclidean_witness_complex.py @@ -9,7 +9,6 @@ """ import gudhi -import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" diff --git a/src/python/test/test_rips_complex.py b/src/python/test/test_rips_complex.py index f5c086cb..b86e7498 100755 --- a/src/python/test/test_rips_complex.py +++ b/src/python/test/test_rips_complex.py @@ -10,7 +10,6 @@ from gudhi import RipsComplex from math import sqrt -import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index eca3807b..04b26e92 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -9,7 +9,6 @@ """ from gudhi import SimplexTree -import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" diff --git a/src/python/test/test_tangential_complex.py b/src/python/test/test_tangential_complex.py index fc500c45..8668a2e0 100755 --- a/src/python/test/test_tangential_complex.py +++ b/src/python/test/test_tangential_complex.py @@ -9,7 +9,6 @@ """ from gudhi import TangentialComplex, SimplexTree -import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" -- cgit v1.2.3 From f85742957276cbd15a2724c86cbc7a8279d62ef9 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Wed, 26 Feb 2020 11:11:32 +0100 Subject: Code review: add some comments about range.begin() and range.end() --- src/python/include/Simplex_tree_interface.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'src/python') diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 55d5af97..66ce5afd 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -124,18 +124,22 @@ class Simplex_tree_interface : public Simplex_tree { // Iterator over the simplex tree typename std::vector::const_iterator get_filtration_iterator_begin() { // Base::initialize_filtration(); already performed in filtration_simplex_range + // this specific case works because the range is just a pair of iterators - won't work if range was a vector return Base::filtration_simplex_range().begin(); } typename std::vector::const_iterator get_filtration_iterator_end() { + // this specific case works because the range is just a pair of iterators - won't work if range was a vector return Base::filtration_simplex_range().end(); } Skeleton_simplex_iterator get_skeleton_iterator_begin(int dimension) { + // this specific case works because the range is just a pair of iterators - won't work if range was a vector return Base::skeleton_simplex_range(dimension).begin(); } Skeleton_simplex_iterator get_skeleton_iterator_end(int dimension) { + // this specific case works because the range is just a pair of iterators - won't work if range was a vector return Base::skeleton_simplex_range(dimension).end(); } }; -- cgit v1.2.3 From 0998cecac7f15e3c68058d33acc21fb427f803e9 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 28 Feb 2020 11:18:59 +0100 Subject: shorten < 80 char the doc --- src/python/doc/barycenter_user.rst | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst index 59f758fa..83e9bebb 100644 --- a/src/python/doc/barycenter_user.rst +++ b/src/python/doc/barycenter_user.rst @@ -20,13 +20,17 @@ Function Basic example ------------- -This example computes the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. +This example computes the Frechet mean (aka Wasserstein barycenter) between +four persistence diagrams. It is initialized on the 4th diagram. -As the algorithm is not convex, its output depends on the initialization and is only a local minimum of the objective function. -Initialization can be either given as an integer (in which case the i-th diagram of the list is used as initial estimate) -or as a diagram. -If None, it will randomly select one of the diagram of the list as initial estimate. -Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. +As the algorithm is not convex, its output depends on the initialization and +is only a local minimum of the objective function. +Initialization can be either given as an integer (in which case the i-th +diagram of the list is used as initial estimate) or as a diagram. +If None, it will randomly select one of the diagram of the list +as initial estimate. +Note that persistence diagrams must be submitted as +(n x 2) numpy arrays and must not contain inf values. .. testcode:: @@ -37,8 +41,8 @@ Note that persistence diagrams must be submitted as (n x 2) numpy arrays and mus dg2 = np.array([[0.2, 0.7]]) dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) dg4 = np.array([]) - - bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3) + pdiagset = [dg1, dg2, dg3, dg4] + bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=pdiagset,init=3) message = "Wasserstein barycenter estimated:" print(message) -- cgit v1.2.3 From 8e4f3d151818b78a29d11cdc6ca171947bfd6dd9 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 3 Mar 2020 15:33:17 +0100 Subject: update wasserstein distance with pot so that it can return optimal matching now! --- src/python/doc/wasserstein_distance_user.rst | 24 ++++++++++ src/python/gudhi/wasserstein.py | 69 ++++++++++++++++++++++------ src/python/test/test_wasserstein_distance.py | 31 +++++++++---- 3 files changed, 102 insertions(+), 22 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 94b454e2..d3daa318 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -47,3 +47,27 @@ The output is: .. testoutput:: Wasserstein distance value = 1.45 + +We can also have access to the optimal matching by letting `matching=True`. +It is encoded as a list of indices (i,j), meaning that the i-th point in X +is mapped to the j-th point in Y. +An index of -1 represents the diagonal. + +.. testcode:: + + import gudhi.wasserstein + import numpy as np + + diag1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) + diag2 = np.array([[2.8, 4.45], [5, 6], [9.5, 14.1]]) + cost, matching = gudhi.wasserstein.wasserstein_distance(diag1, diag2, matching=True, order=1., internal_p=2.) + + message = "Wasserstein distance value = %.2f, optimal matching: %s" %(cost, matching) + print(message) + +The output is: + +.. testoutput:: + + Wasserstein distance value = 2.15, optimal matching: [(0, 0), (1, 2), (2, -1), (-1, 1)] + diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 13102094..ba0f7343 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -62,14 +62,39 @@ def _perstot(X, order, internal_p): return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) -def wasserstein_distance(X, Y, order=2., internal_p=2.): +def _clean_match(match, n, m): ''' - :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + :param match: a list of the form [(i,j) ...] + :param n: int, size of the first dgm + :param m: int, size of the second dgm + :return: a modified version of match where indices greater than n, m are replaced by -1, encoding the diagonal. + and (-1, -1) are removed + ''' + new_match = [] + for i,j in match: + if i >= n: + if j < m: + new_match.append((-1, j)) + elif j >= m: + if i < n: + new_match.append((i,-1)) + else: + new_match.append((i,j)) + return new_match + + +def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): + ''' + :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points + (i.e. with infinite coordinate). :param Y: (m x 2) numpy.array encoding the second diagram. + :param matching: if True, computes and returns the optimal matching between X and Y, encoded as... :param order: exponent for Wasserstein; Default value is 2. - :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). - :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with respect to the internal_p-norm as ground metric. - :rtype: float + :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); + Default value is 2 (Euclidean norm). + :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with + respect to the internal_p-norm as ground metric. + If matching is set to True, also returns the optimal matching between X and Y. ''' n = len(X) m = len(Y) @@ -77,21 +102,39 @@ def wasserstein_distance(X, Y, order=2., internal_p=2.): # handle empty diagrams if X.size == 0: if Y.size == 0: - return 0. + if not matching: + return 0. + else: + return 0., [] else: - return _perstot(Y, order, internal_p) + if not matching: + return _perstot(Y, order, internal_p) + else: + return _perstot(Y, order, internal_p), [(-1, j) for j in range(m)] elif Y.size == 0: - return _perstot(X, order, internal_p) + if not matching: + return _perstot(X, order, internal_p) + else: + return _perstot(X, order, internal_p), [(i, -1) for i in range(n)] M = _build_dist_matrix(X, Y, order=order, internal_p=internal_p) - a = np.full(n+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. - a[-1] = a[-1] * m # normalized so that we have a probability measure, required by POT - b = np.full(m+1, 1. / (n + m) ) # weight vector of the input diagram. Uniform here. - b[-1] = b[-1] * n # so that we have a probability measure, required by POT + a = np.ones(n+1) # weight vector of the input diagram. Uniform here. + a[-1] = m + b = np.ones(m+1) # weight vector of the input diagram. Uniform here. + b[-1] = n + + if matching: + P = ot.emd(a=a,b=b,M=M, numItermax=2000000) + ot_cost = np.sum(np.multiply(P,M)) + P[P < 0.5] = 0 # trick to avoid numerical issue, could it be improved? + match = np.argwhere(P) + # Now we turn to -1 points encoding the diagonal + match = _clean_match(match, n, m) + return ot_cost ** (1./order) , match # Comptuation of the otcost using the ot.emd2 library. # Note: it is the Wasserstein distance to the power q. # The default numItermax=100000 is not sufficient for some examples with 5000 points, what is a good value? - ot_cost = (n+m) * ot.emd2(a, b, M, numItermax=2000000) + ot_cost = ot.emd2(a, b, M, numItermax=2000000) return ot_cost ** (1./order) diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 6a6b217b..02a1d2c9 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -51,14 +51,27 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True): assert wasserstein_distance(diag3, diag4, internal_p=1., order=2.) == approx(np.sqrt(5)) assert wasserstein_distance(diag3, diag4, internal_p=4.5, order=2.) == approx(np.sqrt(5)) - if(not test_infinity): - return + if test_infinity: + diag5 = np.array([[0, 3], [4, np.inf]]) + diag6 = np.array([[7, 8], [4, 6], [3, np.inf]]) - diag5 = np.array([[0, 3], [4, np.inf]]) - diag6 = np.array([[7, 8], [4, 6], [3, np.inf]]) + assert wasserstein_distance(diag4, diag5) == np.inf + assert wasserstein_distance(diag5, diag6, order=1, internal_p=np.inf) == approx(4.) + + + if test_matching: + match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=1., order=2)[1] + assert match == [] + match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] + assert match == [] + match = wasserstein_distance(emptydiag, diag2, matching=True, internal_p=np.inf, order=2.)[1] + assert match == [(-1, 0), (-1, 1)] + match = wasserstein_distance(diag2, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] + assert match == [(0, -1), (1, -1)] + match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] + assert match == [(0, 0), (1, 1), (2, -1)] + - assert wasserstein_distance(diag4, diag5) == np.inf - assert wasserstein_distance(diag5, diag6, order=1, internal_p=np.inf) == approx(4.) def hera_wrap(delta): def fun(*kargs,**kwargs): @@ -66,8 +79,8 @@ def hera_wrap(delta): return fun def test_wasserstein_distance_pot(): - _basic_wasserstein(pot, 1e-15, test_infinity=False) + _basic_wasserstein(pot, 1e-15, test_infinity=False, test_matching=True) def test_wasserstein_distance_hera(): - _basic_wasserstein(hera_wrap(1e-12), 1e-12) - _basic_wasserstein(hera_wrap(.1), .1) + _basic_wasserstein(hera_wrap(1e-12), 1e-12, test_matching=False) + _basic_wasserstein(hera_wrap(.1), .1, test_matching=False) -- cgit v1.2.3 From 2141ef8adfee531f3eaf822cf4076b9b010e6f94 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 3 Mar 2020 16:22:48 +0100 Subject: correction missing arg in test_wasserstein_distance --- src/python/test/test_wasserstein_distance.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 02a1d2c9..d0f0323c 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -17,7 +17,7 @@ __author__ = "Theo Lacombe" __copyright__ = "Copyright (C) 2019 Inria" __license__ = "MIT" -def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True): +def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_matching=True): diag1 = np.array([[2.7, 3.7], [9.6, 14.0], [34.2, 34.974]]) diag2 = np.array([[2.8, 4.45], [9.5, 14.1]]) diag3 = np.array([[0, 2], [4, 6]]) -- cgit v1.2.3 From 570a9b83eb3f714bc52735dae289a5195874bf41 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Thu, 5 Mar 2020 15:40:45 +0100 Subject: completed as... --- src/python/gudhi/wasserstein.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index ba0f7343..aab0cb3c 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -30,7 +30,9 @@ def _build_dist_matrix(X, Y, order=2., internal_p=2.): :param order: exponent for the Wasserstein metric. :param internal_p: Ground metric (i.e. norm L^p). :returns: (n+1) x (m+1) np.array encoding the cost matrix C. - For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal proj onto the diagonal. + For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], + while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) + and its orthogonal proj onto the diagonal. note also that C[n+1, m+1] = 0 (it costs nothing to move from the diagonal to the diagonal). ''' Xdiag = _proj_on_diag(X) @@ -88,7 +90,9 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). :param Y: (m x 2) numpy.array encoding the second diagram. - :param matching: if True, computes and returns the optimal matching between X and Y, encoded as... + :param matching: if True, computes and returns the optimal matching between X and Y, encoded as + a list of tuple [...(i,j)...], meaning the i-th point in X is matched to + the j-th point in Y, with the convention (-1) represents the diagonal. :param order: exponent for Wasserstein; Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). -- cgit v1.2.3 From 64199fd8037556f135f90102ba8270cccf9d3e60 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 7 Mar 2020 01:08:10 +0100 Subject: persistence generators for lower-star and flag filtrations --- src/python/gudhi/simplex_tree.pxd | 2 + src/python/gudhi/simplex_tree.pyx | 55 ++++++++ .../include/Persistent_cohomology_interface.h | 138 ++++++++++++++++----- 3 files changed, 167 insertions(+), 28 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 96d14079..4e435c67 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -53,3 +53,5 @@ cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": vector[pair[double,double]] intervals_in_dimension(int dimension) void write_output_diagram(string diagram_file_name) vector[pair[vector[int], vector[int]]] persistence_pairs() + pair[vector[vector[int]], vector[vector[int]]] lower_star_generators() + pair[vector[vector[int]], vector[vector[int]]] flag_generators() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index b18627c4..1c9b9cf1 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -514,3 +514,58 @@ cdef class SimplexTree: else: print("intervals_in_dim function requires persistence function" " to be launched first.") + + def lower_star_persistence_generators(self): + """Assuming this is a lower-star filtration, this function returns the persistence pairs, + where each simplex is replaced with the vertex that gave it its filtration value. + + :returns: first the regular persistence pairs, grouped by dimension, with one vertex per extremity, + and second the essential features, grouped by dimension, with one vertex each + :rtype: Tuple[List[numpy.array[int] of shape (n,2)], List[numpy.array[int] of shape (m,)]] + + :note: intervals_in_dim function requires + :func:`persistence()` + function to be launched first. + """ + if self.pcohptr != NULL: + gen = self.pcohptr.lower_star_generators() + normal = [np_array(d).reshape(-1,2) for d in gen.first] + infinite = [np_array(d) for d in gen.second] + return (normal, infinite) + else: + print("lower_star_persistence_generators() requires that persistence() be called first.") + + def flag_persistence_generators(self): + """Assuming this is a flag complex, this function returns the persistence pairs, + where each simplex is replaced with the vertices of the edges that gave it its filtration value. + + :returns: first the regular persistence pairs of dimension 0, with one vertex for birth and two for death; + then the other regular persistence pairs, grouped by dimension, with 2 vertices per extremity; + then the connected components, with one vertex each; + finally the other essential features, grouped by dimension, with 2 vertices for birth. + :rtype: Tuple[List[numpy.array[int] of shape (n,3)], List[numpy.array[int] of shape (m,4)], List[numpy.array[int] of shape (l,)], List[numpy.array[int] of shape (k,2)]] + + :note: intervals_in_dim function requires + :func:`persistence()` + function to be launched first. + """ + if self.pcohptr != NULL: + gen = self.pcohptr.flag_generators() + if len(gen.first) == 0: + normal0 = np_array([]) + normals = np_array([]) + else: + l = iter(gen.first) + normal0 = np_array(next(l)).reshape(-1,3) + normals = [np_array(d).reshape(-1,4) for d in l] + if len(gen.second) == 0: + infinite0 = np_array([]) + infinites = np_array([]) + else: + l = iter(gen.second) + infinite0 = np_array(next(l)) + infinites = [np_array(d).reshape(-1,3) for d in l] + + return (normal0, normals, infinite0, infinites) + else: + print("lower_star_persistence_generators() requires that persistence() be called first.") diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 8c79e6f3..6e9aac52 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -23,61 +23,55 @@ template class Persistent_cohomology_interface : public persistent_cohomology::Persistent_cohomology { private: + typedef persistent_cohomology::Persistent_cohomology Base; /* * Compare two intervals by dimension, then by length. */ struct cmp_intervals_by_dim_then_length { - explicit cmp_intervals_by_dim_then_length(FilteredComplex * sc) - : sc_(sc) { } - template bool operator()(const Persistent_interval & p1, const Persistent_interval & p2) { - if (sc_->dimension(get < 0 > (p1)) == sc_->dimension(get < 0 > (p2))) - return (sc_->filtration(get < 1 > (p1)) - sc_->filtration(get < 0 > (p1)) - > sc_->filtration(get < 1 > (p2)) - sc_->filtration(get < 0 > (p2))); + if (std::get<0>(p1) == std::get<0>(p2)) { + auto& i1 = std::get<1>(p1); + auto& i2 = std::get<1>(p2); + return std::get<1>(i1) - std::get<0>(i1) > std::get<1>(i2) - std::get<0>(i2); + } else - return (sc_->dimension(get < 0 > (p1)) > sc_->dimension(get < 0 > (p2))); + return (std::get<0>(p1) > std::get<0>(p2)); + // Why does this sort by decreasing dimension? } - FilteredComplex* sc_; }; public: Persistent_cohomology_interface(FilteredComplex* stptr) - : persistent_cohomology::Persistent_cohomology(*stptr), + : Base(*stptr), stptr_(stptr) { } Persistent_cohomology_interface(FilteredComplex* stptr, bool persistence_dim_max) - : persistent_cohomology::Persistent_cohomology(*stptr, persistence_dim_max), + : Base(*stptr, persistence_dim_max), stptr_(stptr) { } std::vector>> get_persistence(int homology_coeff_field, double min_persistence) { - persistent_cohomology::Persistent_cohomology::init_coefficients(homology_coeff_field); - persistent_cohomology::Persistent_cohomology::compute_persistent_cohomology(min_persistence); - - // Custom sort and output persistence - cmp_intervals_by_dim_then_length cmp(stptr_); - auto persistent_pairs = persistent_cohomology::Persistent_cohomology::get_persistent_pairs(); - std::sort(std::begin(persistent_pairs), std::end(persistent_pairs), cmp); + Base::init_coefficients(homology_coeff_field); + Base::compute_persistent_cohomology(min_persistence); + auto const& persistent_pairs = Base::get_persistent_pairs(); std::vector>> persistence; + persistence.reserve(persistent_pairs.size()); for (auto pair : persistent_pairs) { - persistence.push_back(std::make_pair(stptr_->dimension(get<0>(pair)), - std::make_pair(stptr_->filtration(get<0>(pair)), - stptr_->filtration(get<1>(pair))))); + persistence.emplace_back(stptr_->dimension(get<0>(pair)), + std::make_pair(stptr_->filtration(get<0>(pair)), + stptr_->filtration(get<1>(pair)))); } + // Custom sort and output persistence + cmp_intervals_by_dim_then_length cmp; + std::sort(std::begin(persistence), std::end(persistence), cmp); return persistence; } std::vector, std::vector>> persistence_pairs() { - auto pairs = persistent_cohomology::Persistent_cohomology::get_persistent_pairs(); - std::vector, std::vector>> persistence_pairs; + auto const& pairs = Base::get_persistent_pairs(); persistence_pairs.reserve(pairs.size()); for (auto pair : pairs) { std::vector birth; @@ -89,16 +83,104 @@ persistent_cohomology::Persistent_cohomology death; if (get<1>(pair) != stptr_->null_simplex()) { + death.reserve(birth.size()+1); for (auto vertex : stptr_->simplex_vertex_range(get<1>(pair))) { death.push_back(vertex); } } - persistence_pairs.push_back(std::make_pair(birth, death)); + persistence_pairs.emplace_back(std::move(birth), std::move(death)); } return persistence_pairs; } + // TODO: (possibly at the python level) + // - an option to ignore intervals of length 0? + // - an option to return only some of those vectors? + typedef std::pair>, std::vector>> Generators; + + Generators lower_star_generators() { + Generators out; + // diags[i] should be interpreted as vector> + auto& diags = out.first; + // diagsinf[i] should be interpreted as vector + auto& diagsinf = out.second; + for (auto pair : Base::get_persistent_pairs()) { + auto s = std::get<0>(pair); + auto t = std::get<1>(pair); + int dim = stptr_->dimension(s); + auto v = stptr_->vertex_with_same_filtration(s); + if(t == stptr_->null_simplex()) { + while(diagsinf.size() < dim+1) diagsinf.emplace_back(); + diagsinf[dim].push_back(v); + } else { + while(diags.size() < dim+1) diags.emplace_back(); + auto w = stptr_->vertex_with_same_filtration(t); + diags[dim].push_back(v); + diags[dim].push_back(w); + } + } + return out; + } + + Generators flag_generators() { + Generators out; + // diags[0] should be interpreted as vector> and other diags[i] as vector> + auto& diags = out.first; + // diagsinf[0] should be interpreted as vector and other diagsinf[i] as vector> + auto& diagsinf = out.second; + for (auto pair : Base::get_persistent_pairs()) { + auto s = std::get<0>(pair); + auto t = std::get<1>(pair); + int dim = stptr_->dimension(s); + bool infinite = t == stptr_->null_simplex(); + if(infinite) { + if(dim == 0) { + auto v = *std::begin(stptr_->simplex_vertex_range(s)); + if(diagsinf.size()==0)diagsinf.emplace_back(); + diagsinf[0].push_back(v); + } else { + auto e = stptr_->edge_with_same_filtration(s); + auto&& e_vertices = stptr_->simplex_vertex_range(e); + auto i = std::begin(e_vertices); + auto v1 = *i; + auto v2 = *++i; + GUDHI_CHECK(++i==std::end(e_vertices), "must be an edge"); + while(diagsinf.size() < dim+1) diagsinf.emplace_back(); + diagsinf[dim].push_back(v1); + diagsinf[dim].push_back(v2); + } + } else { + auto et = stptr_->edge_with_same_filtration(t); + auto&& et_vertices = stptr_->simplex_vertex_range(et); + auto it = std::begin(et_vertices); + auto w1 = *it; + auto w2 = *++it; + GUDHI_CHECK(++it==std::end(et_vertices), "must be an edge"); + if(dim == 0) { + auto v = *std::begin(stptr_->simplex_vertex_range(s)); + if(diags.size()==0)diags.emplace_back(); + diags[0].push_back(v); + diags[0].push_back(w1); + diags[0].push_back(w2); + } else { + auto es = stptr_->edge_with_same_filtration(s); + auto&& es_vertices = stptr_->simplex_vertex_range(es); + auto is = std::begin(es_vertices); + auto v1 = *is; + auto v2 = *++is; + GUDHI_CHECK(++is==std::end(es_vertices), "must be an edge"); + while(diags.size() < dim+1) diags.emplace_back(); + diags[dim].push_back(v1); + diags[dim].push_back(v2); + diags[dim].push_back(w1); + diags[dim].push_back(w2); + } + } + } + return out; + } + private: // A copy FilteredComplex* stptr_; -- cgit v1.2.3 From 35e08b30836fb0c419c0377eaf51d2a3b16e7670 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 7 Mar 2020 14:05:05 +0100 Subject: min_persistence for generators --- src/python/gudhi/simplex_tree.pxd | 4 +-- src/python/gudhi/simplex_tree.pyx | 36 +++++++++++++--------- .../include/Persistent_cohomology_interface.h | 10 ++++-- 3 files changed, 30 insertions(+), 20 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 4e435c67..53e2bbc9 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -53,5 +53,5 @@ cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": vector[pair[double,double]] intervals_in_dimension(int dimension) void write_output_diagram(string diagram_file_name) vector[pair[vector[int], vector[int]]] persistence_pairs() - pair[vector[vector[int]], vector[vector[int]]] lower_star_generators() - pair[vector[vector[int]], vector[vector[int]]] flag_generators() + pair[vector[vector[int]], vector[vector[int]]] lower_star_generators(double) + pair[vector[vector[int]], vector[vector[int]]] flag_generators(double) diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 1c9b9cf1..3f582ac9 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -395,7 +395,7 @@ cdef class SimplexTree: :param min_persistence: The minimum persistence value to take into account (strictly greater than min_persistence). Default value is 0.0. - Sets min_persistence to -1.0 to see all values. + Set min_persistence to -1.0 to see all values. :type min_persistence: float. :param persistence_dim_max: If true, the persistent homology for the maximal dimension in the complex is computed. If false, it is @@ -515,42 +515,48 @@ cdef class SimplexTree: print("intervals_in_dim function requires persistence function" " to be launched first.") - def lower_star_persistence_generators(self): + def lower_star_persistence_generators(self, min_persistence=0.): """Assuming this is a lower-star filtration, this function returns the persistence pairs, where each simplex is replaced with the vertex that gave it its filtration value. - :returns: first the regular persistence pairs, grouped by dimension, with one vertex per extremity, + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Set min_persistence to -1.0 to see all values. + :type min_persistence: float. + :returns: First the regular persistence pairs, grouped by dimension, with one vertex per extremity, and second the essential features, grouped by dimension, with one vertex each :rtype: Tuple[List[numpy.array[int] of shape (n,2)], List[numpy.array[int] of shape (m,)]] - :note: intervals_in_dim function requires - :func:`persistence()` - function to be launched first. + :note: lower_star_persistence_generators requires that `persistence()` be called first. """ if self.pcohptr != NULL: - gen = self.pcohptr.lower_star_generators() + gen = self.pcohptr.lower_star_generators(min_persistence) normal = [np_array(d).reshape(-1,2) for d in gen.first] infinite = [np_array(d) for d in gen.second] return (normal, infinite) else: print("lower_star_persistence_generators() requires that persistence() be called first.") - def flag_persistence_generators(self): + def flag_persistence_generators(self, min_persistence=0.): """Assuming this is a flag complex, this function returns the persistence pairs, where each simplex is replaced with the vertices of the edges that gave it its filtration value. - :returns: first the regular persistence pairs of dimension 0, with one vertex for birth and two for death; + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Set min_persistence to -1.0 to see all values. + :type min_persistence: float. + :returns: First the regular persistence pairs of dimension 0, with one vertex for birth and two for death; then the other regular persistence pairs, grouped by dimension, with 2 vertices per extremity; then the connected components, with one vertex each; finally the other essential features, grouped by dimension, with 2 vertices for birth. - :rtype: Tuple[List[numpy.array[int] of shape (n,3)], List[numpy.array[int] of shape (m,4)], List[numpy.array[int] of shape (l,)], List[numpy.array[int] of shape (k,2)]] + :rtype: Tuple[numpy.array[int] of shape (n,3), List[numpy.array[int] of shape (m,4)], numpy.array[int] of shape (l,), List[numpy.array[int] of shape (k,2)]] - :note: intervals_in_dim function requires - :func:`persistence()` - function to be launched first. + :note: flag_persistence_generators requires that `persistence()` be called first. """ if self.pcohptr != NULL: - gen = self.pcohptr.flag_generators() + gen = self.pcohptr.flag_generators(min_persistence) if len(gen.first) == 0: normal0 = np_array([]) normals = np_array([]) @@ -568,4 +574,4 @@ cdef class SimplexTree: return (normal0, normals, infinite0, infinites) else: - print("lower_star_persistence_generators() requires that persistence() be called first.") + print("flag_persistence_generators() requires that persistence() be called first.") diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 6e9aac52..8e721fc0 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -95,11 +95,10 @@ persistent_cohomology::Persistent_cohomology>, std::vector>> Generators; - Generators lower_star_generators() { + Generators lower_star_generators(double min_persistence) { Generators out; // diags[i] should be interpreted as vector> auto& diags = out.first; @@ -108,6 +107,8 @@ persistent_cohomology::Persistent_cohomology(pair); auto t = std::get<1>(pair); + if(stptr_->filtration(t) - stptr_->filtration(s) <= min_persistence) + continue; int dim = stptr_->dimension(s); auto v = stptr_->vertex_with_same_filtration(s); if(t == stptr_->null_simplex()) { @@ -123,7 +124,8 @@ persistent_cohomology::Persistent_cohomology> and other diags[i] as vector> auto& diags = out.first; @@ -132,6 +134,8 @@ persistent_cohomology::Persistent_cohomology(pair); auto t = std::get<1>(pair); + if(stptr_->filtration(t) - stptr_->filtration(s) <= min_persistence) + continue; int dim = stptr_->dimension(s); bool infinite = t == stptr_->null_simplex(); if(infinite) { -- cgit v1.2.3 From 08be68c1fb3c05a35d738eab53712ec6cb4d1ad5 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 7 Mar 2020 14:14:45 +0100 Subject: [ci skip] Comment --- src/python/include/Persistent_cohomology_interface.h | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 8e721fc0..22d6f654 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -125,6 +125,7 @@ persistent_cohomology::Persistent_cohomology> and other diags[i] as vector> -- cgit v1.2.3 From 55c1385419edd4e152df219dfff596d2631367f1 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 8 Mar 2020 11:15:04 +0100 Subject: Typo in shape of array --- src/python/gudhi/simplex_tree.pyx | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 3f582ac9..d5f642d1 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -8,6 +8,7 @@ # - YYYY/MM Author: Description of the modification from libc.stdint cimport intptr_t +import numpy from numpy import array as np_array cimport simplex_tree @@ -558,19 +559,19 @@ cdef class SimplexTree: if self.pcohptr != NULL: gen = self.pcohptr.flag_generators(min_persistence) if len(gen.first) == 0: - normal0 = np_array([]) - normals = np_array([]) + normal0 = numpy.empty((0,3)) + normals = [] else: l = iter(gen.first) normal0 = np_array(next(l)).reshape(-1,3) normals = [np_array(d).reshape(-1,4) for d in l] if len(gen.second) == 0: - infinite0 = np_array([]) - infinites = np_array([]) + infinite0 = numpy.empty(0) + infinites = [] else: l = iter(gen.second) infinite0 = np_array(next(l)) - infinites = [np_array(d).reshape(-1,3) for d in l] + infinites = [np_array(d).reshape(-1,2) for d in l] return (normal0, normals, infinite0, infinites) else: -- cgit v1.2.3 From d1d25b4ae8d0f778f0e2b3f98449d7d13e466013 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 10 Mar 2020 09:04:45 +0100 Subject: Fix example - only fails on OSx --- src/python/example/alpha_complex_from_points_example.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'src/python') diff --git a/src/python/example/alpha_complex_from_points_example.py b/src/python/example/alpha_complex_from_points_example.py index 465632eb..73faf17c 100755 --- a/src/python/example/alpha_complex_from_points_example.py +++ b/src/python/example/alpha_complex_from_points_example.py @@ -46,6 +46,9 @@ if simplex_tree.find([4]): else: print("[4] Not found...") +# Some insertions, simplex_tree needs to initialize filtrations +simplex_tree.initialize_filtration() + print("dimension=", simplex_tree.dimension()) print("filtrations=") for simplex_with_filtration in simplex_tree.get_filtration(): -- cgit v1.2.3 From 2eca5c75b1fbd7157e2656b875e730dc5f00f373 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 15:45:45 +0100 Subject: removed P[P < 0.5] thresholding ; as it shouldn't happen anymore. --- src/python/gudhi/wasserstein.py | 1 - 1 file changed, 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index aab0cb3c..e28c63e6 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -130,7 +130,6 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): if matching: P = ot.emd(a=a,b=b,M=M, numItermax=2000000) ot_cost = np.sum(np.multiply(P,M)) - P[P < 0.5] = 0 # trick to avoid numerical issue, could it be improved? match = np.argwhere(P) # Now we turn to -1 points encoding the diagonal match = _clean_match(match, n, m) -- cgit v1.2.3 From 967ceab26b09ad74e0cff0d84429a766af267f6b Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 16:47:09 +0100 Subject: removed _clean_match and changed matching format, it is now a (n x 2) numpy array --- src/python/gudhi/wasserstein.py | 31 ++++++------------------------- 1 file changed, 6 insertions(+), 25 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index e28c63e6..9efa946e 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -64,34 +64,13 @@ def _perstot(X, order, internal_p): return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) -def _clean_match(match, n, m): - ''' - :param match: a list of the form [(i,j) ...] - :param n: int, size of the first dgm - :param m: int, size of the second dgm - :return: a modified version of match where indices greater than n, m are replaced by -1, encoding the diagonal. - and (-1, -1) are removed - ''' - new_match = [] - for i,j in match: - if i >= n: - if j < m: - new_match.append((-1, j)) - elif j >= m: - if i < n: - new_match.append((i,-1)) - else: - new_match.append((i,j)) - return new_match - - def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): ''' :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). :param Y: (m x 2) numpy.array encoding the second diagram. :param matching: if True, computes and returns the optimal matching between X and Y, encoded as - a list of tuple [...(i,j)...], meaning the i-th point in X is matched to + a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to the j-th point in Y, with the convention (-1) represents the diagonal. :param order: exponent for Wasserstein; Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); @@ -114,12 +93,12 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): if not matching: return _perstot(Y, order, internal_p) else: - return _perstot(Y, order, internal_p), [(-1, j) for j in range(m)] + return _perstot(Y, order, internal_p), np.array([[-1, j] for j in range(m)]) elif Y.size == 0: if not matching: return _perstot(X, order, internal_p) else: - return _perstot(X, order, internal_p), [(i, -1) for i in range(n)] + return _perstot(X, order, internal_p), np.array([[i, -1] for i in range(n)]) M = _build_dist_matrix(X, Y, order=order, internal_p=internal_p) a = np.ones(n+1) # weight vector of the input diagram. Uniform here. @@ -130,9 +109,11 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): if matching: P = ot.emd(a=a,b=b,M=M, numItermax=2000000) ot_cost = np.sum(np.multiply(P,M)) + P[-1, -1] = 0 # Remove matching corresponding to the diagonal match = np.argwhere(P) # Now we turn to -1 points encoding the diagonal - match = _clean_match(match, n, m) + match[:,0][match[:,0] >= n] = -1 + match[:,1][match[:,1] >= m] = -1 return ot_cost ** (1./order) , match # Comptuation of the otcost using the ot.emd2 library. -- cgit v1.2.3 From 4aea5deab6ce4cbb491f4c9c2b7e9f023efbbe01 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 17:41:38 +0100 Subject: changed output of matching as a (n x 2) array, adapted tests and doc --- src/python/doc/wasserstein_distance_user.rst | 2 +- src/python/gudhi/wasserstein.py | 2 +- src/python/test/test_wasserstein_distance.py | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index d3daa318..9519caa6 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -69,5 +69,5 @@ The output is: .. testoutput:: - Wasserstein distance value = 2.15, optimal matching: [(0, 0), (1, 2), (2, -1), (-1, 1)] + Wasserstein distance value = 2.15, optimal matching: [[0, 0], [1, 2], [2, -1], [-1, 1]] diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 9efa946e..9e4dc7d5 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -88,7 +88,7 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): if not matching: return 0. else: - return 0., [] + return 0., np.array([]) else: if not matching: return _perstot(Y, order, internal_p) diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index d0f0323c..ca9a4a61 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -61,15 +61,15 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat if test_matching: match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=1., order=2)[1] - assert match == [] + assert np.array_equal(match, np.array([])) match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] - assert match == [] + assert np.array_equal(match, np.array([])) match = wasserstein_distance(emptydiag, diag2, matching=True, internal_p=np.inf, order=2.)[1] - assert match == [(-1, 0), (-1, 1)] + assert np.array_equal(match , np.array([[-1, 0], [-1, 1]])) match = wasserstein_distance(diag2, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] - assert match == [(0, -1), (1, -1)] + assert np.array_equal(match , np.array([[0, -1], [1, -1]])) match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] - assert match == [(0, 0), (1, 1), (2, -1)] + assert np.array_equal(match, np.array_equal([[0, 0], [1, 1], [2, -1]])) -- cgit v1.2.3 From fc4e10863d103ee6bc22863f48548fe246a3ddd6 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 18:03:21 +0100 Subject: correction of typo in the doc --- src/python/gudhi/wasserstein.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 9e4dc7d5..12337780 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -30,10 +30,10 @@ def _build_dist_matrix(X, Y, order=2., internal_p=2.): :param order: exponent for the Wasserstein metric. :param internal_p: Ground metric (i.e. norm L^p). :returns: (n+1) x (m+1) np.array encoding the cost matrix C. - For 1 <= i <= n, 1 <= j <= m, C[i,j] encodes the distance between X[i] and Y[j], - while C[i, m+1] (resp. C[n+1, j]) encodes the distance (to the p) between X[i] (resp Y[j]) + For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], + while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal proj onto the diagonal. - note also that C[n+1, m+1] = 0 (it costs nothing to move from the diagonal to the diagonal). + note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). ''' Xdiag = _proj_on_diag(X) Ydiag = _proj_on_diag(Y) -- cgit v1.2.3 From 6c369a6aa566dfcb8cdb501d0c39eafb32219669 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 18:08:15 +0100 Subject: fix typo in test_wasserstein_distance --- src/python/test/test_wasserstein_distance.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index ca9a4a61..f92208c0 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -69,7 +69,7 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat match = wasserstein_distance(diag2, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] assert np.array_equal(match , np.array([[0, -1], [1, -1]])) match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] - assert np.array_equal(match, np.array_equal([[0, 0], [1, 1], [2, -1]])) + assert np.array_equal(match, np.array([[0, 0], [1, 1], [2, -1]])) -- cgit v1.2.3 From 753290475ab6e95c2de1baad97ee6f755a0ce19a Mon Sep 17 00:00:00 2001 From: Théo Lacombe Date: Tue, 10 Mar 2020 18:25:10 +0100 Subject: Update src/python/gudhi/wasserstein.py Co-Authored-By: Marc Glisse --- src/python/gudhi/wasserstein.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 12337780..83a682df 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -32,7 +32,7 @@ def _build_dist_matrix(X, Y, order=2., internal_p=2.): :returns: (n+1) x (m+1) np.array encoding the cost matrix C. For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) - and its orthogonal proj onto the diagonal. + and its orthogonal projection onto the diagonal. note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). ''' Xdiag = _proj_on_diag(X) -- cgit v1.2.3 From c9d6e27495c8927d736d593afb0450360b46ccc9 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 10 Mar 2020 18:55:19 +0100 Subject: fix indentation in wasserstein --- src/python/gudhi/wasserstein.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 83a682df..3dd993f9 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -70,13 +70,13 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): (i.e. with infinite coordinate). :param Y: (m x 2) numpy.array encoding the second diagram. :param matching: if True, computes and returns the optimal matching between X and Y, encoded as - a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to - the j-th point in Y, with the convention (-1) represents the diagonal. + a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to + the j-th point in Y, with the convention (-1) represents the diagonal. :param order: exponent for Wasserstein; Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); - Default value is 2 (Euclidean norm). + Default value is 2 (Euclidean norm). :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with - respect to the internal_p-norm as ground metric. + respect to the internal_p-norm as ground metric. If matching is set to True, also returns the optimal matching between X and Y. ''' n = len(X) -- cgit v1.2.3 From a47ace987876cb52351ae9223d335629aedbd71e Mon Sep 17 00:00:00 2001 From: mathieu Date: Tue, 10 Mar 2020 19:44:57 -0400 Subject: new fixes --- ext/hera | 2 +- src/python/gudhi/representations/metrics.py | 27 ++++++++++++--------------- 2 files changed, 13 insertions(+), 16 deletions(-) (limited to 'src/python') diff --git a/ext/hera b/ext/hera index cb1838e6..9a899718 160000 --- a/ext/hera +++ b/ext/hera @@ -1 +1 @@ -Subproject commit cb1838e682ec07f80720241cf9098400caeb83c7 +Subproject commit 9a89971855acefe39dce0e2adadf53b88ca8f683 diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index c5439a67..0659b457 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -10,17 +10,9 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances -from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance from gudhi.hera import wasserstein_distance as hera_wasserstein_distance from .preprocessing import Padding -try: - from .. import bottleneck_distance - USE_GUDHI = True -except ImportError: - USE_GUDHI = False - print("Gudhi built without CGAL: BottleneckDistance will return a null matrix") - ############################################# # Metrics ################################### ############################################# @@ -111,9 +103,13 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) if metric == "bottleneck": return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) - elif metric == "wasserstein" or metric == "pot_wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) - elif metric == "hera_wasserstein": + elif metric == "pot_wasserstein": + try: + from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance + return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) + except ImportError: + print("Gudhi built without POT") + elif metric == "wasserstein" or metric == "hera_wasserstein": return pairwise_distances(XX, YY, metric=sklearn_wrapper(hera_wasserstein_distance, X, Y, **kwargs)) elif metric == "sliced_wasserstein": return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, X, Y, **kwargs)) @@ -192,16 +188,17 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise bottleneck distances. """ - if not USE_GUDHI: - print("Gudhi built without CGAL: returning a null matrix") - Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) if USE_GUDHI else np.zeros((len(X), len(self.diagrams_))) + try: + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) + except ImportError: + print("Gudhi built without CGAL") return Xfit class WassersteinDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the Wasserstein distance matrix from a list of persistence diagrams. """ - def __init__(self, order=2, internal_p=2, mode="pot", delta=0.0001): + def __init__(self, order=2, internal_p=2, mode="pot", delta=0.01): """ Constructor for the WassersteinDistance class. -- cgit v1.2.3 From a17a09a2c58bba79e897d0ba00aada05da556967 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Wed, 11 Mar 2020 10:41:53 +0100 Subject: clean test_wasserstein from useless np.array --- src/python/test/test_wasserstein_distance.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index f92208c0..0d70e11a 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -61,15 +61,15 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat if test_matching: match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=1., order=2)[1] - assert np.array_equal(match, np.array([])) + assert np.array_equal(match, []) match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] - assert np.array_equal(match, np.array([])) + assert np.array_equal(match, []) match = wasserstein_distance(emptydiag, diag2, matching=True, internal_p=np.inf, order=2.)[1] - assert np.array_equal(match , np.array([[-1, 0], [-1, 1]])) + assert np.array_equal(match , [[-1, 0], [-1, 1]]) match = wasserstein_distance(diag2, emptydiag, matching=True, internal_p=np.inf, order=2.24)[1] - assert np.array_equal(match , np.array([[0, -1], [1, -1]])) + assert np.array_equal(match , [[0, -1], [1, -1]]) match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] - assert np.array_equal(match, np.array([[0, 0], [1, 1], [2, -1]])) + assert np.array_equal(match, [[0, 0], [1, 1], [2, -1]]) -- cgit v1.2.3 From 25e40a52ec7bc9e1bfe418fb1aa16e2a06994d1b Mon Sep 17 00:00:00 2001 From: mathieu Date: Wed, 11 Mar 2020 15:35:37 -0400 Subject: new fixes --- src/python/gudhi/representations/metrics.py | 63 +++++++++++++++++++++++------ 1 file changed, 50 insertions(+), 13 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 0659b457..f913f1fc 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -19,7 +19,7 @@ from .preprocessing import Padding def sliced_wasserstein_distance(D1, D2, num_directions): """ - This is a function for computing the sliced Wasserstein distance from two persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally integrating over all possible lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. + This is a function for computing the sliced Wasserstein distance from two persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). :param D2: (m x 2) numpy.array encoding the second diagram. :param num_directions: number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. @@ -39,6 +39,34 @@ def sliced_wasserstein_distance(D1, D2, num_directions): L1 = np.sum(np.abs(A-B), axis=0) return np.mean(L1) +def compute_persistence_diagram_projections(X, num_directions): + """ + This is a function for projecting the points of a list of persistence diagrams (as well as their diagonal projections) onto a fixed number of lines sampled uniformly on [-pi/2, pi/2]. This function can be used as a preprocessing step in order to speed up the running time for computing all pairwise sliced Wasserstein distances / kernel values on a list of persistence diagrams. + :param X: list of persistence diagrams. + :param num_directions: number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. + :returns: list of projected persistence diagrams. + :rtype: float + """ + thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] + lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) + XX = [np.vstack([np.matmul(D, lines), np.matmul(np.matmul(D, .5 * np.ones((2,2))), lines)]) for D in X] + return XX + +def sliced_wasserstein_distance_on_projections(D1, D2): + """ + This is a function for computing the sliced Wasserstein distance between two persistence diagrams that have already been projected onto some lines. It simply amounts to comparing the sorted projections with the 1-norm, and averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. + :param D1: (2n x number_of_lines) numpy.array containing the n projected points of the first diagram, and the n projections of their diagonal projections. + :param D2: (2m x number_of_lines) numpy.array containing the m projected points of the second diagram, and the m projections of their diagonal projections. + :returns: the sliced Wasserstein distance between the projected persistence diagrams. + :rtype: float + """ + lim1, lim2 = int(len(D1)/2), int(len(D2)/2) + approx1, approx_diag1, approx2, approx_diag2 = D1[:lim1], D1[lim1:], D2[:lim2], D2[lim2:] + A = np.sort(np.concatenate([approx1, approx_diag2], axis=0), axis=0) + B = np.sort(np.concatenate([approx2, approx_diag1], axis=0), axis=0) + L1 = np.sum(np.abs(A-B), axis=0) + return np.mean(L1) + def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence Fisher distance from two persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. @@ -90,31 +118,43 @@ def sklearn_wrapper(metric, X, Y, **kwargs): return metric(X[int(a[0])], Y[int(b[0])], **kwargs) return flat_metric +PAIRWISE_DISTANCE_FUNCTIONS = { + "wasserstein": hera_wasserstein_distance, + "hera_wasserstein": hera_wasserstein_distance, + "persistence_fisher": persistence_fisher_distance, +} + def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwargs): """ This function computes the distance matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). :param X: first list of persistence diagrams. :param Y: second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. - :param metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + :param metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. :returns: distance matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) :rtype: float """ XX = np.reshape(np.arange(len(X)), [-1,1]) YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) if metric == "bottleneck": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) + try: + from .. import bottleneck_distance + return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) + except ImportError: + print("Gudhi built without CGAL") + raise elif metric == "pot_wasserstein": try: from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) except ImportError: - print("Gudhi built without POT") - elif metric == "wasserstein" or metric == "hera_wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(hera_wasserstein_distance, X, Y, **kwargs)) + print("Gudhi built without POT. Please install POT or use metric='wasserstein' or metric='hera_wasserstein'") + raise elif metric == "sliced_wasserstein": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance, X, Y, **kwargs)) - elif metric == "persistence_fisher": - return pairwise_distances(XX, YY, metric=sklearn_wrapper(persistence_fisher_distance, X, Y, **kwargs)) + Xproj = compute_persistence_diagram_projections(X, **kwargs) + Yproj = None if Y is None else compute_persistence_diagram_projections(Y, **kwargs) + return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance_on_projections, Xproj, Yproj)) + elif type(metric) == str: + return pairwise_distances(XX, YY, metric=sklearn_wrapper(PAIRWISE_DISTANCE_FUNCTIONS[metric], X, Y, **kwargs)) else: return pairwise_distances(XX, YY, metric=sklearn_wrapper(metric, X, Y, **kwargs)) @@ -188,10 +228,7 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise bottleneck distances. """ - try: - Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) - except ImportError: - print("Gudhi built without CGAL") + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) return Xfit class WassersteinDistance(BaseEstimator, TransformerMixin): -- cgit v1.2.3 From 6552d09c3f290a25ee910e007084fe3809f8c8ed Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Thu, 12 Mar 2020 16:19:34 -0400 Subject: fixed error message --- src/python/gudhi/representations/metrics.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index f913f1fc..4070c321 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -147,7 +147,7 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) except ImportError: - print("Gudhi built without POT. Please install POT or use metric='wasserstein' or metric='hera_wasserstein'") + print("POT (Python Optimal Transport) is not installed. Please install POT or use metric='wasserstein' or metric='hera_wasserstein'") raise elif metric == "sliced_wasserstein": Xproj = compute_persistence_diagram_projections(X, **kwargs) -- cgit v1.2.3 From 4b546a43fe14178dcfb2b327e27a580fc9811499 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 13:16:04 +0100 Subject: update doc (indentation, mention of -1 for the diag) and added a few more tests --- src/python/gudhi/barycenter.py | 30 +++++++++++++------------- src/python/test/test_wasserstein_barycenter.py | 15 +++++++------ 2 files changed, 23 insertions(+), 22 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index a41b5906..3af12c14 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -96,9 +96,8 @@ def _optimal_matching(X, Y, withcost=False): def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' :param pdiagset: a list of size m containing numpy.array of shape (n x 2) - (n can variate), encoding a set of - persistence diagrams with only finite coordinates. - If empty, returns None. + (n can variate), encoding a set of + persistence diagrams with only finite coordinates. :param init: The initial value for barycenter estimate. If None, init is made on a random diagram from the dataset. Otherwise, it must be an int @@ -106,24 +105,25 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): or a (n x 2) numpy.array enconding a persistence diagram with n points. :param verbose: if True, returns additional information about the - barycenter. + barycenter. :returns: If not verbose (default), a numpy.array encoding - the barycenter estimate + the barycenter estimate of pdiagset (local minima of the energy function). + If pdiagset is empty, returns None. If verbose, returns a couple (Y, log) where Y is the barycenter estimate, and log is a dict that contains additional informations: - groupings, a list of list of pairs (i,j), - That is, G[k] = [(i, j) ...], where (i,j) indicates - that X[i] is matched to Y[j] - if i > len(X) or j > len(Y), it means they - represent the diagonal. + That is, G[k] = [(i, j) ...], where (i,j) indicates + that X[i] is matched to Y[j] + if i = -1 or j = -1, it means they + represent the diagonal. - energy, a float representing the Frechet - energy value obtained, - that is the mean of squared distances - of observations to the output. + energy value obtained, + that is the mean of squared distances + of observations to the output. - nb_iter, integer representing the number of iterations - performed before convergence of the algorithm. + performed before convergence of the algorithm. ''' X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging @@ -136,7 +136,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): # Initialisation of barycenter if init is None: i0 = np.random.randint(m) # Index of first state for the barycenter - Y = X[i0].copy() #copy() ensure that we do not modify X[i0] + Y = X[i0].copy() else: if type(init)==int: Y = X[init].copy() @@ -149,7 +149,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): while not converged: nb_iter += 1 K = len(Y) # current nb of points in Y (some might be on diagonal) - G = np.zeros((K, m), dtype=int)-1 # will store for each j, the (index) + G = np.full((K, m), -1, dtype=int) # will store for each j, the (index) # point matched in each other diagram #(might be the diagonal). # that is G[j, i] = k <=> y_j is matched to diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index a58a4d62..5167cb84 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -27,19 +27,20 @@ def test_lagrangian_barycenter(): res = np.array([[0.27916667, 0.55416667], [0.7375, 0.7625], [0.2375, 0.2625]]) dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) - dg8 = np.array([[0., 4.]]) + dg8 = np.array([[0., 4.], [4, 8]]) # error crit. - eps = 0.000001 + eps = 1e-7 assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < eps assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.empty(shape=(0,2))) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < eps Y, log = lagrangian_barycenter(pdiagset=[dg4, dg8], verbose=True) - assert np.linalg.norm(Y - np.array([[1,3]])) < eps - assert np.abs(log["energy"] - 2) < eps - assert np.array_equal(log["groupings"][0] , np.array([[0, -1]])) - assert np.array_equal(log["groupings"][1] , np.array([[0, 0]])) - assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg8, dg4], init=np.array([[0.2, 0.6], [0.5, 0.7]]), verbose=False) - np.array([[1, 3]])) < eps + assert np.linalg.norm(Y - np.array([[1,3], [5, 7]])) < eps + assert np.abs(log["energy"] - 4) < eps + assert np.array_equal(log["groupings"][0] , np.array([[0, -1], [1, -1]])) + assert np.array_equal(log["groupings"][1] , np.array([[0, 0], [1, 1]])) + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg8, dg4], init=np.array([[0.2, 0.6], [0.5, 0.7]]), verbose=False) - np.array([[1, 3], [5, 7]])) < eps assert lagrangian_barycenter(pdiagset = []) is None + -- cgit v1.2.3 From aa93247860bb01e3fc15926658dd9e6a95198f3d Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 13:18:58 +0100 Subject: added mention that _optimal matching should be removed at some point --- src/python/gudhi/barycenter.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 3af12c14..517cdb2f 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -44,6 +44,9 @@ def _optimal_matching(X, Y, withcost=False): if i >= len(X) or j >= len(Y), it means they represent the diagonal. They will be encoded by -1 afterwards. + + NOTE : this code will be removed for final merge, + and wasserstein.optimal_matching will be used instead. ''' n = len(X) -- cgit v1.2.3 From 6ed2a97421a223b4ebe31b91f48d779c2209f470 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 16 Mar 2020 13:38:18 +0100 Subject: Add get_simplices method - contrary to get_filtration method, sort is not performed --- src/Simplex_tree/example/simple_simplex_tree.cpp | 13 +++++++++++-- src/python/example/simplex_tree_example.py | 4 ++++ src/python/gudhi/simplex_tree.pxd | 8 ++++++++ src/python/gudhi/simplex_tree.pyx | 17 ++++++++++++++++- src/python/include/Simplex_tree_interface.h | 11 +++++++++++ src/python/test/test_simplex_tree.py | 12 ++++++++++++ 6 files changed, 62 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/example/simple_simplex_tree.cpp b/src/Simplex_tree/example/simple_simplex_tree.cpp index 4353939f..47ea7e36 100644 --- a/src/Simplex_tree/example/simple_simplex_tree.cpp +++ b/src/Simplex_tree/example/simple_simplex_tree.cpp @@ -166,10 +166,19 @@ int main(int argc, char* const argv[]) { // ++ GENERAL VARIABLE SET std::cout << "********************************************************************\n"; - // Display the Simplex_tree - Can not be done in the middle of 2 inserts std::cout << "* The complex contains " << simplexTree.num_simplices() << " simplices\n"; std::cout << " - dimension " << simplexTree.dimension() << "\n"; - std::cout << "* Iterator on Simplices in the filtration, with [filtration value]:\n"; + std::cout << "* Iterator on simplices, with [filtration value]:\n"; + for (Simplex_tree::Simplex_handle f_simplex : simplexTree.complex_simplex_range()) { + std::cout << " " + << "[" << simplexTree.filtration(f_simplex) << "] "; + for (auto vertex : simplexTree.simplex_vertex_range(f_simplex)) std::cout << "(" << vertex << ")"; + std::cout << std::endl; + } + + std::cout << "********************************************************************\n"; + // Can not be done in the middle of 2 inserts + std::cout << "* Iterator on simplices sorted by filtration values, with [filtration value]:\n"; for (auto f_simplex : simplexTree.filtration_simplex_range()) { std::cout << " " << "[" << simplexTree.filtration(f_simplex) << "] "; diff --git a/src/python/example/simplex_tree_example.py b/src/python/example/simplex_tree_example.py index 7f20c389..34833899 100755 --- a/src/python/example/simplex_tree_example.py +++ b/src/python/example/simplex_tree_example.py @@ -38,6 +38,10 @@ else: print("dimension=", st.dimension()) +print("simplices=") +for simplex_with_filtration in st.get_simplices(): + print("(%s, %.2f)" % tuple(simplex_with_filtration)) + st.initialize_filtration() print("filtration=") for simplex_with_filtration in st.get_filtration(): diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 66c173a6..82f155de 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -24,6 +24,12 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_simplex_handle "Gudhi::Simplex_tree_interface::Simplex_handle": pass + cdef cppclass Simplex_tree_simplices_iterator "Gudhi::Simplex_tree_interface::Complex_simplex_iterator": + Simplex_tree_simplices_iterator() + Simplex_tree_simplex_handle& operator*() + Simplex_tree_simplices_iterator operator++() + bint operator!=(Simplex_tree_simplices_iterator) + cdef cppclass Simplex_tree_skeleton_iterator "Gudhi::Simplex_tree_interface::Skeleton_simplex_iterator": Simplex_tree_skeleton_iterator() Simplex_tree_simplex_handle& operator*() @@ -53,6 +59,8 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool make_filtration_non_decreasing() # Iterators over Simplex tree pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) + Simplex_tree_simplices_iterator get_simplices_iterator_begin() + Simplex_tree_simplices_iterator get_simplices_iterator_end() vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() Simplex_tree_skeleton_iterator get_skeleton_iterator_begin(int dimension) diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index efac2d80..c01cc905 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -208,10 +208,25 @@ cdef class SimplexTree: return self.get_ptr().insert_simplex_and_subfaces(csimplex, filtration) - def get_filtration(self): + def get_simplices(self): """This function returns a generator with simplices and their given filtration values. + :returns: The simplices. + :rtype: generator with tuples(simplex, filtration) + """ + cdef Simplex_tree_simplices_iterator it = self.get_ptr().get_simplices_iterator_begin() + cdef Simplex_tree_simplices_iterator end = self.get_ptr().get_simplices_iterator_end() + cdef Simplex_tree_simplex_handle sh = dereference(it) + + while it != end: + yield self.get_ptr().get_simplex_and_filtration(dereference(it)) + preincrement(it) + + def get_filtration(self): + """This function returns a generator with simplices and their given + filtration values sorted by increasing filtration values. + :returns: The simplices sorted by increasing filtration values. :rtype: generator with tuples(simplex, filtration) """ diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 66ce5afd..4a7062d6 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -36,6 +36,7 @@ class Simplex_tree_interface : public Simplex_tree { using Simplex_and_filtration = std::pair; using Filtered_simplices = std::vector; using Skeleton_simplex_iterator = typename Base::Skeleton_simplex_iterator; + using Complex_simplex_iterator = typename Base::Complex_simplex_iterator; public: bool find_simplex(const Simplex& vh) { @@ -122,6 +123,16 @@ class Simplex_tree_interface : public Simplex_tree { } // Iterator over the simplex tree + Complex_simplex_iterator get_simplices_iterator_begin() { + // this specific case works because the range is just a pair of iterators - won't work if range was a vector + return Base::complex_simplex_range().begin(); + } + + Complex_simplex_iterator get_simplices_iterator_end() { + // this specific case works because the range is just a pair of iterators - won't work if range was a vector + return Base::complex_simplex_range().end(); + } + typename std::vector::const_iterator get_filtration_iterator_begin() { // Base::initialize_filtration(); already performed in filtration_simplex_range // this specific case works because the range is just a pair of iterators - won't work if range was a vector diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 04b26e92..f7848379 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -249,3 +249,15 @@ def test_make_filtration_non_decreasing(): assert st.filtration([3, 4, 5]) == 2.0 assert st.filtration([3, 4]) == 2.0 assert st.filtration([4, 5]) == 2.0 + +def test_simplices_iterator(): + st = SimplexTree() + + assert st.insert([0, 1, 2], filtration=4.0) == True + assert st.insert([2, 3, 4], filtration=2.0) == True + + for simplex in st.get_simplices(): + print("simplex is: ", simplex[0]) + assert st.find(simplex[0]) == True + print("filtration is: ", simplex[1]) + assert st.filtration(simplex[0]) == simplex[1] -- cgit v1.2.3 From 3099b2395fa143aa6c9b3df2c6087ccd017ff87c Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Mon, 16 Mar 2020 12:51:34 -0400 Subject: fixed doc --- src/python/gudhi/representations/kernel_methods.py | 45 +++++++++------- src/python/gudhi/representations/metrics.py | 63 +++++++++++++--------- 2 files changed, 66 insertions(+), 42 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py index d89f69ab..50186d63 100644 --- a/src/python/gudhi/representations/kernel_methods.py +++ b/src/python/gudhi/representations/kernel_methods.py @@ -20,13 +20,16 @@ from .preprocessing import Padding def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence weighted Gaussian kernel value from two persistence diagrams. The persistence weighted Gaussian kernel is computed by convolving the persistence diagram points with weighted Gaussian kernels. See http://proceedings.mlr.press/v48/kusano16.html for more details. - :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). - :param D2: (m x 2) numpy.array encoding the second diagram. - :param bandwidth: bandwidth of the Gaussian kernel with which persistence diagrams will be convolved - :param weight: weight function for the persistence diagram points. This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. - :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). - :returns: the persistence weighted Gaussian kernel value between persistence diagrams. - :rtype: float + + Parameters: + D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + D2: (m x 2) numpy.array encoding the second diagram. + bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved + weight: weight function for the persistence diagram points. This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. + kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + + Returns: + float: the persistence weighted Gaussian kernel value between persistence diagrams. """ ws1 = np.array([weight(D1[j,:]) for j in range(len(D1))]) ws2 = np.array([weight(D2[j,:]) for j in range(len(D2))]) @@ -42,12 +45,15 @@ def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_appr def persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence scale space kernel value from two persistence diagrams. The persistence scale space kernel is computed by adding the symmetric to the diagonal of each point in each persistence diagram, with negative weight, and then convolving the points with a Gaussian kernel. See https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Reininghaus_A_Stable_Multi-Scale_2015_CVPR_paper.pdf for more details. - :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). - :param D2: (m x 2) numpy.array encoding the second diagram. - :param bandwidth: bandwidth of the Gaussian kernel with which persistence diagrams will be convolved - :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). - :returns: the persistence scale space kernel value between persistence diagrams. - :rtype: float + + Parameters: + D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + D2: (m x 2) numpy.array encoding the second diagram. + bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved + kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + + Returns: + float: the persistence scale space kernel value between persistence diagrams. """ DD1 = np.concatenate([D1, D1[:,[1,0]]], axis=0) DD2 = np.concatenate([D2, D2[:,[1,0]]], axis=0) @@ -57,11 +63,14 @@ def persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): def pairwise_persistence_diagram_kernels(X, Y=None, metric="sliced_wasserstein", **kwargs): """ This function computes the kernel matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). - :param X: first list of persistence diagrams. - :param Y: second list of persistence diagrams (optional). If None, pairwise kernel values are computed from the first list only. - :param metric: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. - :returns: kernel matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) - :rtype: float + + Parameters: + X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. + Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise kernel values are computed from the first list only. + metric: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + + Returns: + numpy array of shape (nxm): kernel matrix. """ XX = np.reshape(np.arange(len(X)), [-1,1]) YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 4070c321..e2c30f8c 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -20,11 +20,14 @@ from .preprocessing import Padding def sliced_wasserstein_distance(D1, D2, num_directions): """ This is a function for computing the sliced Wasserstein distance from two persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. - :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). - :param D2: (m x 2) numpy.array encoding the second diagram. - :param num_directions: number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. - :returns: the sliced Wasserstein distance between persistence diagrams. - :rtype: float + + Parameters: + D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). + D2: (m x 2) numpy.array encoding the second diagram. + num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. + + Returns: + float: the sliced Wasserstein distance between persistence diagrams. """ thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) @@ -42,10 +45,13 @@ def sliced_wasserstein_distance(D1, D2, num_directions): def compute_persistence_diagram_projections(X, num_directions): """ This is a function for projecting the points of a list of persistence diagrams (as well as their diagonal projections) onto a fixed number of lines sampled uniformly on [-pi/2, pi/2]. This function can be used as a preprocessing step in order to speed up the running time for computing all pairwise sliced Wasserstein distances / kernel values on a list of persistence diagrams. - :param X: list of persistence diagrams. - :param num_directions: number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. - :returns: list of projected persistence diagrams. - :rtype: float + + Parameters: + X (list of n numpy arrays of shape (numx2)): list of persistence diagrams. + num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. + + Returns: + XX (list of n numpy arrays of shape (2*numx2)): list of projected persistence diagrams. """ thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) @@ -55,10 +61,13 @@ def compute_persistence_diagram_projections(X, num_directions): def sliced_wasserstein_distance_on_projections(D1, D2): """ This is a function for computing the sliced Wasserstein distance between two persistence diagrams that have already been projected onto some lines. It simply amounts to comparing the sorted projections with the 1-norm, and averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. - :param D1: (2n x number_of_lines) numpy.array containing the n projected points of the first diagram, and the n projections of their diagonal projections. - :param D2: (2m x number_of_lines) numpy.array containing the m projected points of the second diagram, and the m projections of their diagonal projections. - :returns: the sliced Wasserstein distance between the projected persistence diagrams. - :rtype: float + + Parameters: + D1: (2n x number_of_lines) numpy.array containing the n projected points of the first diagram, and the n projections of their diagonal projections. + D2: (2m x number_of_lines) numpy.array containing the m projected points of the second diagram, and the m projections of their diagonal projections. + + Returns: + float: the sliced Wasserstein distance between the projected persistence diagrams. """ lim1, lim2 = int(len(D1)/2), int(len(D2)/2) approx1, approx_diag1, approx2, approx_diag2 = D1[:lim1], D1[lim1:], D2[:lim2], D2[lim2:] @@ -70,12 +79,15 @@ def sliced_wasserstein_distance_on_projections(D1, D2): def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence Fisher distance from two persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. - :param D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). - :param D2: (m x 2) numpy.array encoding the second diagram. - :param bandwidth: bandwidth of the Gaussian kernel used to turn persistence diagrams into probability distributions. - :param kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). - :returns: the persistence Fisher distance between persistence diagrams. - :rtype: float + + Parameters: + D1: (n x 2) numpy.array encoding the (finite points of the) first diagram). Must not contain essential points (i.e. with infinite coordinate). + D2: (m x 2) numpy.array encoding the second diagram. + bandwidth (float): bandwidth of the Gaussian kernel used to turn persistence diagrams into probability distributions. + kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). + + Returns: + float: the persistence Fisher distance between persistence diagrams. """ projection = (1./2) * np.ones((2,2)) diagonal_projections1 = np.matmul(D1, projection) @@ -127,11 +139,14 @@ PAIRWISE_DISTANCE_FUNCTIONS = { def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwargs): """ This function computes the distance matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). - :param X: first list of persistence diagrams. - :param Y: second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. - :param metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. - :returns: distance matrix, i.e., numpy array of shape (num diagrams 1 x num diagrams 2) - :rtype: float + + Parameters: + X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. + Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. + metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + + Returns: + numpy array of shape (nxm): distance matrix """ XX = np.reshape(np.arange(len(X)), [-1,1]) YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) -- cgit v1.2.3 From 5c55e976606b4dd020bd4e21c93ae22143ef5348 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 18:01:16 +0100 Subject: changed doc of matchings for a more explicit (and hopefully sphinx-valid) version --- src/python/doc/wasserstein_distance_user.rst | 29 ++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 9519caa6..4c3b53dd 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -58,16 +58,29 @@ An index of -1 represents the diagonal. import gudhi.wasserstein import numpy as np - diag1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) - diag2 = np.array([[2.8, 4.45], [5, 6], [9.5, 14.1]]) - cost, matching = gudhi.wasserstein.wasserstein_distance(diag1, diag2, matching=True, order=1., internal_p=2.) - - message = "Wasserstein distance value = %.2f, optimal matching: %s" %(cost, matching) - print(message) + dgm1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) + dgm2 = np.array([[2.8, 4.45], [5, 6], [9.5, 14.1]]) + cost, matchings = gudhi.wasserstein.wasserstein_distance(diag1, diag2, matching=True, order=1., internal_p=2.) + + message_cost = "Wasserstein distance value = %.2f" %cost + print(message_cost) + dgm1_to_diagonal = matchings[np.where(matchings[:,0] == -1)][:,1] + dgm2_to_diagonal = matchings[np.where(matchings[:,1] == -1)][:,0] + off_diagonal_match = np.delete(matchings, np.where(matchings == -1)[0], axis=0) + + for i,j in off_diagonal_match: + print("point %s in dgm1 is matched to point %s in dgm2" %(i,j)) + for i in dgm1_to_diagonal: + print("point %s in dgm1 is matched to the diagonal" %i) + for j in dgm2_to_diagonal: + print("point %s in dgm2 is matched to the diagonal" %j) The output is: .. testoutput:: - Wasserstein distance value = 2.15, optimal matching: [[0, 0], [1, 2], [2, -1], [-1, 1]] - + Wasserstein distance value = 2.15 + point 0 in dgm1 is matched to point 0 in dgm2 + point 1 in dgm1 is matched to point 2 in dgm2 + point 2 in dgm1 is matched to the diagonal + point 1 in dgm2 is matched to the diagonal -- cgit v1.2.3 From 66f0b08a8f8d5006f8d29352c169525cc53a22e6 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 19:11:30 +0100 Subject: changed typo in doc (diag --> dgm), used integer for order and internal p, simplify th ecode --- src/python/doc/wasserstein_distance_user.rst | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 4c3b53dd..f43b2217 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -36,10 +36,10 @@ Note that persistence diagrams must be submitted as (n x 2) numpy arrays and mus import gudhi.wasserstein import numpy as np - diag1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) - diag2 = np.array([[2.8, 4.45],[9.5, 14.1]]) + dgm1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) + dgm2 = np.array([[2.8, 4.45],[9.5, 14.1]]) - message = "Wasserstein distance value = " + '%.2f' % gudhi.wasserstein.wasserstein_distance(diag1, diag2, order=1., internal_p=2.) + message = "Wasserstein distance value = " + '%.2f' % gudhi.wasserstein.wasserstein_distance(dgm1, dgm2, order=1., internal_p=2.) print(message) The output is: @@ -60,12 +60,12 @@ An index of -1 represents the diagonal. dgm1 = np.array([[2.7, 3.7],[9.6, 14.],[34.2, 34.974]]) dgm2 = np.array([[2.8, 4.45], [5, 6], [9.5, 14.1]]) - cost, matchings = gudhi.wasserstein.wasserstein_distance(diag1, diag2, matching=True, order=1., internal_p=2.) + cost, matchings = gudhi.wasserstein.wasserstein_distance(dgm1, dgm2, matching=True, order=1, internal_p=2) message_cost = "Wasserstein distance value = %.2f" %cost print(message_cost) - dgm1_to_diagonal = matchings[np.where(matchings[:,0] == -1)][:,1] - dgm2_to_diagonal = matchings[np.where(matchings[:,1] == -1)][:,0] + dgm1_to_diagonal = matching[matching[:,0] == -1, 1] + dgm2_to_diagonal = matching[matching[:,1] == -1, 0] off_diagonal_match = np.delete(matchings, np.where(matchings == -1)[0], axis=0) for i,j in off_diagonal_match: -- cgit v1.2.3 From a253c0c4f54a9a148740ed9c20457df0ea43c842 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 19:36:07 +0100 Subject: correction typo in usr.rst --- src/python/doc/wasserstein_distance_user.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index f43b2217..25e51d68 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -64,8 +64,8 @@ An index of -1 represents the diagonal. message_cost = "Wasserstein distance value = %.2f" %cost print(message_cost) - dgm1_to_diagonal = matching[matching[:,0] == -1, 1] - dgm2_to_diagonal = matching[matching[:,1] == -1, 0] + dgm1_to_diagonal = matchings[matchings[:,0] == -1, 1] + dgm2_to_diagonal = matchings[matchings[:,1] == -1, 0] off_diagonal_match = np.delete(matchings, np.where(matchings == -1)[0], axis=0) for i,j in off_diagonal_match: -- cgit v1.2.3 From 60d11e3f06e08b66e49997f389c4dc01b00b793f Mon Sep 17 00:00:00 2001 From: tlacombe Date: Mon, 16 Mar 2020 21:17:38 +0100 Subject: correction of typo in usr.rst --- src/python/doc/wasserstein_distance_user.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 25e51d68..a9b21fa5 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -64,8 +64,8 @@ An index of -1 represents the diagonal. message_cost = "Wasserstein distance value = %.2f" %cost print(message_cost) - dgm1_to_diagonal = matchings[matchings[:,0] == -1, 1] - dgm2_to_diagonal = matchings[matchings[:,1] == -1, 0] + dgm1_to_diagonal = matchings[matchings[:,1] == -1, 0] + dgm2_to_diagonal = matchings[matchings[:,0] == -1, 1] off_diagonal_match = np.delete(matchings, np.where(matchings == -1)[0], axis=0) for i,j in off_diagonal_match: -- cgit v1.2.3 From 6e289999fab86bf06cd69c5b7b846c4f26e0a525 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Tue, 17 Mar 2020 00:13:32 -0400 Subject: fixes --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 74 +++++++++++++++------------ src/python/test/test_simplex_tree.py | 12 ++--- 2 files changed, 47 insertions(+), 39 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 7be14bce..02f2c7e9 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -1354,6 +1354,7 @@ class Simplex_tree { // Replacing if(f=max)) would mean that if f is NaN, we replace it with the max of the children. // That seems more useful than keeping NaN. if (!(simplex.second.filtration() >= max_filt_border_value)) { + // Store the filtration modification information modified = true; simplex.second.assign_filtration(max_filt_border_value); @@ -1473,15 +1474,21 @@ class Simplex_tree { /** \brief Retrieve good values for extended persistence, and separate the * diagrams into the ordinary, relative, extended+ and extended- subdiagrams. - * Need extend_filtration to be called first! + * \post This function should be called only if extend_filtration has been called first! + * \post The coordinates of the persistence diagram points might be a little different than the + * original filtration values due to the internal transformation (scaling to [-2,-1]) that is + * performed on these values during the computation of extended persistence. * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration * and this->get_persistence. * @return A vector of four persistence diagrams. The first one is Ordinary, the * second one is Relative, the third one is Extended+ and the fourth one is Extended-. + * See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. */ std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ std::vector>>> new_dgm(4); double x, y; + double minval_ = this->minval_; + double maxval_ = this->maxval_; for(unsigned int i = 0; i < dgm.size(); i++){ int h = dgm[i].first; double px = dgm[i].second.first; @@ -1516,69 +1523,70 @@ class Simplex_tree { /** \brief Extend filtration for computing extended persistence. * This function only uses the filtration values at the 0-dimensional simplices, * and computes the extended persistence diagram induced by the lower-star filtration - * computed with these values. Note that after calling this function, the filtration + * computed with these values. + * \post Note that after calling this function, the filtration * values are actually modified. The function compute_extended_persistence_subdiagrams * retrieves the original values and separates the extended persistence diagram points * w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after * computing the persistent homology of the extended simplicial complex. + * \post Note that this code creates an extra vertex internally, so you should make sure that + * the Simplex tree does not contain a vertex with the largest Vertex_handle. */ void extend_filtration() { // Compute maximum and minimum of filtration values - int maxvert = -std::numeric_limits::infinity(); - std::vector filt; - for (auto sh : this->complex_simplex_range()) { - if (this->dimension(sh) == 0){ - filt.push_back(this->filtration(sh)); - maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert); - } + int maxvert = std::numeric_limits::min(); + this->minval_ = std::numeric_limits::max(); + this->maxval_ = std::numeric_limits::min(); + for (auto sh : this->skeleton_simplex_range(0)) { + double f = this->filtration(sh); + this->minval_ = std::min(this->minval_, f); + this->maxval_ = std::max(this->maxval_, f); + maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert); } - minval_ = *std::min_element(filt.begin(), filt.end()); - maxval_ = *std::max_element(filt.begin(), filt.end()); + + assert (maxvert < std::numeric_limits::max()); maxvert += 1; - // Compute vectors of integers corresponding to the Simplex handles - std::vector > splxs; - for (auto sh : this->complex_simplex_range()) { - std::vector vr; - for (auto vh : this->simplex_vertex_range(sh)){ - vr.push_back(vh); - } - splxs.push_back(vr); - } + Simplex_tree* st_copy = new Simplex_tree(*this); // Add point for coning the simplicial complex int count = this->num_simplices(); - std::vector cone; - cone.push_back(maxvert); - auto ins = this->insert_simplex(cone, -3); - this->assign_key(ins.first, count); + this->insert_simplex({maxvert}, -3); count++; // For each simplex - for (auto vr : splxs){ + for (auto sh_copy : st_copy->complex_simplex_range()){ + + // Locate simplex + std::vector vr; + for (auto vh : st_copy->simplex_vertex_range(sh_copy)){ + vr.push_back(vh); + } + auto sh = this->find(vr); + // Create cone on simplex - auto sh = this->find(vr); vr.push_back(maxvert); + vr.push_back(maxvert); if (this->dimension(sh) == 0){ // Assign ascending value between -2 and -1 to vertex double v = this->filtration(sh); - this->assign_filtration(sh, -2 + (v-minval_)/(maxval_-minval_)); + this->assign_filtration(sh, -2 + (v-this->minval_)/(this->maxval_-this->minval_)); // Assign descending value between 1 and 2 to cone on vertex - auto ins = this->insert_simplex(vr, 2 - (v-minval_)/(maxval_-minval_)); - this->assign_key(ins.first, count); + this->insert_simplex(vr, 2 - (v-this->minval_)/(this->maxval_-this->minval_)); } else{ // Assign value -3 to simplex and cone on simplex this->assign_filtration(sh, -3); - auto ins = this->insert_simplex(vr, -3); - this->assign_key(ins.first, count); + this->insert_simplex(vr, -3); } count++; } - this->make_filtration_non_decreasing(); - this->initialize_filtration(); + // Deallocate memory + delete st_copy; + // Automatically assign good values for simplices + this->make_filtration_non_decreasing(); } diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index caefeb9c..96ec4707 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -245,6 +245,10 @@ def test_make_filtration_non_decreasing(): assert st.filtration([0, 1, 6]) == 1.0 assert st.filtration([0, 1]) == 1.0 assert st.filtration([0]) == 1.0 + assert st.filtration([1]) == 1.0 + assert st.filtration([3, 4, 5]) == 2.0 + assert st.filtration([3, 4]) == 2.0 + assert st.filtration([4, 5]) == 2.0 def test_extend_filtration(): @@ -271,7 +275,7 @@ def test_extend_filtration(): st.assign_filtration([4], 5.) st.assign_filtration([5], 6.) - assert st.get_filtration() == [ + assert list(st.get_filtration()) == [ ([0, 2], 0.0), ([1, 2], 0.0), ([0, 3], 0.0), @@ -289,7 +293,7 @@ def test_extend_filtration(): st.extend_filtration() - assert st.get_filtration() == [ + assert list(st.get_filtration()) == [ ([6], -3.0), ([0], -2.0), ([1], -1.8), @@ -327,10 +331,6 @@ def test_extend_filtration(): [(1, (6.0, 1.0))] ] - assert st.filtration([1]) == 1.0 - assert st.filtration([3, 4, 5]) == 2.0 - assert st.filtration([3, 4]) == 2.0 - assert st.filtration([4, 5]) == 2.0 def test_simplices_iterator(): st = SimplexTree() -- cgit v1.2.3 From a52e84fdcdbf66f3542416499c26245d0435a8fb Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Tue, 17 Mar 2020 00:48:54 -0400 Subject: fix test --- src/python/test/test_simplex_tree.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 96ec4707..63eee9a5 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -292,6 +292,7 @@ def test_extend_filtration(): st.extend_filtration() + st.initialize_filtration() assert list(st.get_filtration()) == [ ([6], -3.0), -- cgit v1.2.3 From cdc57712ca159f3044453cef41e31ebc03617a1b Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 17 Mar 2020 10:55:14 +0100 Subject: removed _optimal_matching from barycenter as it is now handled by wasserstein_distance. --- src/python/gudhi/barycenter.py | 85 +++----------------------- src/python/test/test_wasserstein_barycenter.py | 2 +- 2 files changed, 9 insertions(+), 78 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 517cdb2f..0490fdd1 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -12,8 +12,7 @@ import ot import numpy as np import scipy.spatial.distance as sc -from gudhi.wasserstein import _build_dist_matrix, _perstot - +from gudhi.wasserstein import wasserstein_distance, _perstot def _mean(x, m): @@ -32,70 +31,6 @@ def _mean(x, m): return np.array([0, 0]) -def _optimal_matching(X, Y, withcost=False): - ''' - :param X: numpy.array of size (n x 2) - :param Y: numpy.array of size (m x 2) - :param withcost: returns also the cost corresponding to the optimal matching - :returns: numpy.array of shape (k x 2) encoding the list of edges - in the optimal matching. - That is, [[i, j] ...], where (i,j) indicates - that X[i] is matched to Y[j] - if i >= len(X) or j >= len(Y), it means they - represent the diagonal. - They will be encoded by -1 afterwards. - - NOTE : this code will be removed for final merge, - and wasserstein.optimal_matching will be used instead. - ''' - - n = len(X) - m = len(Y) - # Start by handling empty diagrams. Could it be shorten? - if X.size == 0: # X is empty - if Y.size == 0: # Y is empty - res = np.array([[0,0]]) # the diagonal is matched to the diagonal - if withcost: - return res, 0 - else: - return res - else: # X is empty but not Y - res = np.array([[0, i] for i in range(m)]) - cost = _perstot(Y, order=2, internal_p=2)**2 - if withcost: - return res, cost - else: - return res - elif Y.size == 0: # X is not empty but Y is empty - res = np.array([[i,0] for i in range(n)]) - cost = _perstot(X, order=2, internal_p=2)**2 - if withcost: - return res, cost - else: - return res - - # we know X, Y are not empty diags now - M = _build_dist_matrix(X, Y, order=2, internal_p=2) - - a = np.ones(n+1) - a[-1] = m - b = np.ones(m+1) - b[-1] = n - P = ot.emd(a=a, b=b, M=M) - # Note : it seems POT returns a permutation matrix in this situation, - # ie a vertex of the constraint set (generically true). - if withcost: - cost = np.sum(np.multiply(P, M)) - P[P < 0.5] = 0 # dirty trick to avoid some numerical issues... to improve. - res = np.argwhere(P) - - # return the list of (i,j) such that P[i,j] > 0, - #i.e. x_i is matched to y_j (should it be the diag). - if withcost: - return res, cost - return res - - def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' :param pdiagset: a list of size m containing numpy.array of shape (n x 2) @@ -166,16 +101,15 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): # Step 1 : compute optimal matching (Y, X_i) for each X_i # and create new points in Y if needed for i in range(m): - indices = _optimal_matching(Y, X[i]) + _, indices = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) for y_j, x_i_j in indices: - if y_j < K: # we matched an off diagonal point to x_i_j... - # ...which is also an off-diagonal point. - if x_i_j < nb_off_diag[i]: + if y_j >= 0: # we matched an off diagonal point to x_i_j... + if x_i_j >= 0: # ...which is also an off-diagonal point. G[y_j, i] = x_i_j else: # ...which is a diagonal point G[y_j, i] = -1 # -1 stands for the diagonal (mask) else: # We matched a diagonal point to x_i_j... - if x_i_j < nb_off_diag[i]: # which is a off-diag point ! + if x_i_j >= 0: # which is a off-diag point ! # need to create new point in Y new_y = _mean(np.array([X[i][x_i_j]]), m) # Average this point with (m-1) copies of Delta @@ -209,15 +143,12 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): log = {} n_y = len(Y) for i in range(m): - edges, cost = _optimal_matching(Y, X[i], withcost=True) - n_x = len(X[i]) - G = edges[np.where(edges[:,0]= n_x) - G[idx,1] = -1 # -1 will encode the diagonal - groupings.append(G) + cost, edges = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) + groupings.append(edges) energy += cost log["groupings"] = groupings energy = energy/m + print(energy) log["energy"] = energy log["nb_iter"] = nb_iter diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index 5167cb84..4d18616b 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -38,7 +38,7 @@ def test_lagrangian_barycenter(): assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < eps Y, log = lagrangian_barycenter(pdiagset=[dg4, dg8], verbose=True) assert np.linalg.norm(Y - np.array([[1,3], [5, 7]])) < eps - assert np.abs(log["energy"] - 4) < eps + assert np.abs(log["energy"] - 2) < eps assert np.array_equal(log["groupings"][0] , np.array([[0, -1], [1, -1]])) assert np.array_equal(log["groupings"][1] , np.array([[0, 0], [1, 1]])) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg8, dg4], init=np.array([[0.2, 0.6], [0.5, 0.7]]), verbose=False) - np.array([[1, 3], [5, 7]])) < eps -- cgit v1.2.3 From 58d923b13afb9b18a2d5b028c6575baee691d182 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Tue, 17 Mar 2020 12:14:49 -0400 Subject: update python doc --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 8 +++---- src/python/gudhi/simplex_tree.pyx | 34 +++++++++++++++++++++++---- 2 files changed, 33 insertions(+), 9 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 02f2c7e9..f661f687 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -1478,8 +1478,8 @@ class Simplex_tree { * \post The coordinates of the persistence diagram points might be a little different than the * original filtration values due to the internal transformation (scaling to [-2,-1]) that is * performed on these values during the computation of extended persistence. - * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration - * and this->get_persistence. + * @param[in] dgm Persistence diagram obtained after calling this->extend_filtration, + * this->initialize_filtration, and this->compute_persistent_cohomology. * @return A vector of four persistence diagrams. The first one is Ordinary, the * second one is Relative, the third one is Extended+ and the fourth one is Extended-. * See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. @@ -1538,14 +1538,14 @@ class Simplex_tree { int maxvert = std::numeric_limits::min(); this->minval_ = std::numeric_limits::max(); this->maxval_ = std::numeric_limits::min(); - for (auto sh : this->skeleton_simplex_range(0)) { + for (auto sh = root_.members().begin(); sh != root_.members().end(); ++sh){ double f = this->filtration(sh); this->minval_ = std::min(this->minval_, f); this->maxval_ = std::max(this->maxval_, f); maxvert = std::max(*this->simplex_vertex_range(sh).begin(), maxvert); } - assert (maxvert < std::numeric_limits::max()); + GUDHI_CHECK(maxvert < std::numeric_limits::max(), std::invalid_argument("Simplex_tree contains a vertex with the largest Vertex_handle")); maxvert += 1; Simplex_tree* st_copy = new Simplex_tree(*this); diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 733ecb97..7af44683 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -397,19 +397,43 @@ cdef class SimplexTree: return self.get_ptr().make_filtration_non_decreasing() def extend_filtration(self): - """ Extend filtration for computing extended persistence. This function only uses the filtration values at the 0-dimensional simplices, and computes the extended persistence diagram induced by the lower-star filtration computed with these values. Note that after calling this function, the filtration values are actually modified. The function :func:`compute_extended_persistence_subdiagrams()` retrieves the original values and separates the extended persistence diagram points w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after computing the persistent homology of the extended simplicial complex. + """ Extend filtration for computing extended persistence. This function only uses the + filtration values at the 0-dimensional simplices, and computes the extended persistence + diagram induced by the lower-star filtration computed with these values. + + .. note:: + + Note that after calling this function, the filtration + values are actually modified within the Simplex_tree. + The function :func:`compute_extended_persistence_subdiagrams()` + retrieves the original values. + + .. note:: + + Note that this code creates an extra vertex internally, so you should make sure that + the Simplex_tree does not contain a vertex with the largest Vertex_handle. """ return self.get_ptr().extend_filtration() def compute_extended_persistence_subdiagrams(self, dgm): - """This function retrieves good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. + """This function retrieves good values for extended persistence, and separate the diagrams + into the ordinary, relative, extended+ and extended- subdiagrams. + + :param dgm: Persistence diagram obtained after calling :func:`extend_filtration()`, :func:`initialize_filtration()`, and :func:`persistence()`. + + :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + + .. note:: - :param dgm: Persistence diagram obtained after calling :func:`extend_filtration()` and :func:`persistence()`. - :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. + This function should be called only if :func:`extend_filtration()`, + :func:`initialize_filtration()`, + and :func:`persistence()` have been called first! .. note:: - This function should be called only after calling :func:`extend_filtration()` and :func:`persistence()`. + The coordinates of the persistence diagram points might be a little different than the + original filtration values due to the internal transformation (scaling to [-2,-1]) that is + performed on these values during the computation of extended persistence. """ return self.get_ptr().compute_extended_persistence_subdiagrams(dgm) -- cgit v1.2.3 From b262406b0a75e39276c11f70ef1174981aa31b51 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 17 Mar 2020 17:57:17 +0100 Subject: Remove thread_local workaround --- src/Alpha_complex/include/gudhi/Alpha_complex_3d.h | 5 +-- src/Nerve_GIC/include/gudhi/GIC.h | 14 +------- .../include/gudhi/Persistent_cohomology.h | 5 +-- src/Simplex_tree/include/gudhi/Simplex_tree.h | 12 ++----- src/cmake/modules/GUDHI_compilation_flags.cmake | 37 ---------------------- src/python/CMakeLists.txt | 10 ------ 6 files changed, 5 insertions(+), 78 deletions(-) (limited to 'src/python') diff --git a/src/Alpha_complex/include/gudhi/Alpha_complex_3d.h b/src/Alpha_complex/include/gudhi/Alpha_complex_3d.h index 7f96c94c..1486cefd 100644 --- a/src/Alpha_complex/include/gudhi/Alpha_complex_3d.h +++ b/src/Alpha_complex/include/gudhi/Alpha_complex_3d.h @@ -61,10 +61,7 @@ namespace Gudhi { namespace alpha_complex { -#ifdef GUDHI_CAN_USE_CXX11_THREAD_LOCAL -thread_local -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL - double RELATIVE_PRECISION_OF_TO_DOUBLE = 0.00001; +thread_local double RELATIVE_PRECISION_OF_TO_DOUBLE = 0.00001; // Value_from_iterator returns the filtration value from an iterator on alpha shapes values // diff --git a/src/Nerve_GIC/include/gudhi/GIC.h b/src/Nerve_GIC/include/gudhi/GIC.h index 2a6d4788..9a4c813d 100644 --- a/src/Nerve_GIC/include/gudhi/GIC.h +++ b/src/Nerve_GIC/include/gudhi/GIC.h @@ -139,19 +139,9 @@ class Cover_complex { for (boost::tie(ei, ei_end) = boost::edges(G); ei != ei_end; ++ei) boost::remove_edge(*ei, G); } - // Thread local is not available on XCode version < V.8 - // If not available, random engine is a class member. -#ifndef GUDHI_CAN_USE_CXX11_THREAD_LOCAL - std::default_random_engine re; -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL - // Find random number in [0,1]. double GetUniform() { - // Thread local is not available on XCode version < V.8 - // If available, random engine is defined for each thread. -#ifdef GUDHI_CAN_USE_CXX11_THREAD_LOCAL thread_local std::default_random_engine re; -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL std::uniform_real_distribution Dist(0, 1); return Dist(re); } @@ -456,9 +446,7 @@ class Cover_complex { if (distances.size() == 0) compute_pairwise_distances(distance); - // This cannot be parallelized if thread_local is not defined - // thread_local is not defined for XCode < v.8 - #if defined(GUDHI_USE_TBB) && defined(GUDHI_CAN_USE_CXX11_THREAD_LOCAL) + #ifdef GUDHI_USE_TBB std::mutex deltamutex; tbb::parallel_for(0, N, [&](int i){ std::vector samples(m); diff --git a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h index b1ded5ae..ca4bc10d 100644 --- a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h +++ b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h @@ -288,10 +288,7 @@ class Persistent_cohomology { // with multiplicity. We used to sum the coefficients directly in // annotations_in_boundary by using a map, we now do it later. typedef std::pair annotation_t; -#ifdef GUDHI_CAN_USE_CXX11_THREAD_LOCAL - thread_local -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL - std::vector annotations_in_boundary; + thread_local std::vector annotations_in_boundary; annotations_in_boundary.clear(); int sign = 1 - 2 * (dim_sigma % 2); // \in {-1,1} provides the sign in the // alternate sum in the boundary. diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index b7fb9002..2adc8354 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -765,12 +765,7 @@ class Simplex_tree { if (first == last) return { null_simplex(), true }; // FIXME: false would make more sense to me. - // Copy before sorting - // Thread local is not available on XCode version < V.8 - It will slow down computation -#ifdef GUDHI_CAN_USE_CXX11_THREAD_LOCAL - thread_local -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL - std::vector copy; + thread_local std::vector copy; copy.clear(); copy.insert(copy.end(), first, last); std::sort(copy.begin(), copy.end()); @@ -1133,10 +1128,7 @@ class Simplex_tree { Dictionary_it next = siblings->members().begin(); ++next; -#ifdef GUDHI_CAN_USE_CXX11_THREAD_LOCAL - thread_local -#endif // GUDHI_CAN_USE_CXX11_THREAD_LOCAL - std::vector > inter; + thread_local std::vector > inter; for (Dictionary_it s_h = siblings->members().begin(); s_h != siblings->members().end(); ++s_h, ++next) { Simplex_handle root_sh = find_vertex(s_h->first); diff --git a/src/cmake/modules/GUDHI_compilation_flags.cmake b/src/cmake/modules/GUDHI_compilation_flags.cmake index 34c2e065..567fbc40 100644 --- a/src/cmake/modules/GUDHI_compilation_flags.cmake +++ b/src/cmake/modules/GUDHI_compilation_flags.cmake @@ -1,7 +1,6 @@ # This files manage compilation flags required by GUDHI include(TestCXXAcceptsFlag) -include(CheckCXXSourceCompiles) # add a compiler flag only if it is accepted macro(add_cxx_compiler_flag _flag) @@ -12,32 +11,6 @@ macro(add_cxx_compiler_flag _flag) endif() endmacro() -function(can_cgal_use_cxx11_thread_local) - # This is because of https://github.com/CGAL/cgal/blob/master/Installation/include/CGAL/tss.h - # CGAL is using boost thread if thread_local is not ready (requires XCode 8 for Mac). - # The test in https://github.com/CGAL/cgal/blob/master/Installation/include/CGAL/config.h - # #if __has_feature(cxx_thread_local) || \ - # ( (__GNUC__ * 100 + __GNUC_MINOR__) >= 408 && __cplusplus >= 201103L ) || \ - # ( _MSC_VER >= 1900 ) - # #define CGAL_CAN_USE_CXX11_THREAD_LOCAL - # #endif - set(CGAL_CAN_USE_CXX11_THREAD_LOCAL " - int main() { - #ifndef __has_feature - #define __has_feature(x) 0 // Compatibility with non-clang compilers. - #endif - #if __has_feature(cxx_thread_local) || \ - ( (__GNUC__ * 100 + __GNUC_MINOR__) >= 408 && __cplusplus >= 201103L ) || \ - ( _MSC_VER >= 1900 ) - bool has_feature_thread_local = true; - #else - // Explicit error of compilation for CMake test purpose - has_feature_thread_local is not defined - #endif - bool result = has_feature_thread_local; - } ") - check_cxx_source_compiles("${CGAL_CAN_USE_CXX11_THREAD_LOCAL}" CGAL_CAN_USE_CXX11_THREAD_LOCAL_RESULT) -endfunction() - set (CMAKE_CXX_STANDARD 14) enable_testing() @@ -58,16 +31,6 @@ if (DEBUG_TRACES) add_definitions(-DDEBUG_TRACES) endif() -set(GUDHI_CAN_USE_CXX11_THREAD_LOCAL " - int main() { - thread_local int result = 0; - return result; - } ") -check_cxx_source_compiles("${GUDHI_CAN_USE_CXX11_THREAD_LOCAL}" GUDHI_CAN_USE_CXX11_THREAD_LOCAL_RESULT) -if (GUDHI_CAN_USE_CXX11_THREAD_LOCAL_RESULT) - add_definitions(-DGUDHI_CAN_USE_CXX11_THREAD_LOCAL) -endif() - if(CMAKE_BUILD_TYPE MATCHES Debug) message("++ Debug compilation flags are: ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_DEBUG}") else() diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index 22af3ec9..f00966a5 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -128,16 +128,6 @@ if(PYTHONINTERP_FOUND) endif () if(CGAL_FOUND) - can_cgal_use_cxx11_thread_local() - if (NOT CGAL_CAN_USE_CXX11_THREAD_LOCAL_RESULT) - if(CMAKE_BUILD_TYPE MATCHES Debug) - add_GUDHI_PYTHON_lib("${Boost_THREAD_LIBRARY_DEBUG}") - else() - add_GUDHI_PYTHON_lib("${Boost_THREAD_LIBRARY_RELEASE}") - endif() - message("** Add Boost ${Boost_LIBRARY_DIRS}") - set(GUDHI_PYTHON_LIBRARY_DIRS "${GUDHI_PYTHON_LIBRARY_DIRS}'${Boost_LIBRARY_DIRS}', ") - endif() # Add CGAL compilation args if(CGAL_HEADER_ONLY) add_gudhi_debug_info("CGAL header only version ${CGAL_VERSION}") -- cgit v1.2.3 From e1c8edc4b148331083f53c7c3d34766190bb6d99 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Tue, 17 Mar 2020 22:16:23 +0100 Subject: Another proposal to fix #248 --- src/python/doc/alpha_complex_sum.inc | 2 +- src/python/doc/bottleneck_distance_sum.inc | 2 +- src/python/doc/cubical_complex_sum.inc | 2 +- src/python/doc/nerve_gic_complex_sum.inc | 2 +- src/python/doc/persistence_graphical_tools_sum.inc | 2 +- src/python/doc/persistent_cohomology_sum.inc | 2 +- src/python/doc/point_cloud_sum.inc | 2 +- src/python/doc/representations_sum.inc | 2 +- src/python/doc/rips_complex_sum.inc | 2 +- src/python/doc/simplex_tree_sum.inc | 2 +- src/python/doc/tangential_complex_sum.inc | 2 +- src/python/doc/wasserstein_distance_sum.inc | 2 +- src/python/doc/witness_complex_sum.inc | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_sum.inc b/src/python/doc/alpha_complex_sum.inc index b5af0d27..00c35155 100644 --- a/src/python/doc/alpha_complex_sum.inc +++ b/src/python/doc/alpha_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | diff --git a/src/python/doc/bottleneck_distance_sum.inc b/src/python/doc/bottleneck_distance_sum.inc index 6eb0ac19..a01e7f04 100644 --- a/src/python/doc/bottleneck_distance_sum.inc +++ b/src/python/doc/bottleneck_distance_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | Bottleneck distance measures the similarity between two persistence | :Author: François Godi | diff --git a/src/python/doc/cubical_complex_sum.inc b/src/python/doc/cubical_complex_sum.inc index f200e695..ab6388e5 100644 --- a/src/python/doc/cubical_complex_sum.inc +++ b/src/python/doc/cubical_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +--------------------------------------------------------------------------+----------------------------------------------------------------------+-----------------------------+ | .. figure:: | The cubical complex is an example of a structured complex useful in | :Author: Pawel Dlotko | diff --git a/src/python/doc/nerve_gic_complex_sum.inc b/src/python/doc/nerve_gic_complex_sum.inc index d633c4ff..d5356eca 100644 --- a/src/python/doc/nerve_gic_complex_sum.inc +++ b/src/python/doc/nerve_gic_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | Nerves and Graph Induced Complexes are cover complexes, i.e. | :Author: Mathieu Carrière | diff --git a/src/python/doc/persistence_graphical_tools_sum.inc b/src/python/doc/persistence_graphical_tools_sum.inc index ef376802..723c0f78 100644 --- a/src/python/doc/persistence_graphical_tools_sum.inc +++ b/src/python/doc/persistence_graphical_tools_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | diff --git a/src/python/doc/persistent_cohomology_sum.inc b/src/python/doc/persistent_cohomology_sum.inc index 4d7b077e..9c29bfaa 100644 --- a/src/python/doc/persistent_cohomology_sum.inc +++ b/src/python/doc/persistent_cohomology_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | The theory of homology consists in attaching to a topological space | :Author: Clément Maria | diff --git a/src/python/doc/point_cloud_sum.inc b/src/python/doc/point_cloud_sum.inc index 85d52de7..77245e86 100644 --- a/src/python/doc/point_cloud_sum.inc +++ b/src/python/doc/point_cloud_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, etc. | :Author: Vincent Rouvreau | diff --git a/src/python/doc/representations_sum.inc b/src/python/doc/representations_sum.inc index 700828f1..edb8a448 100644 --- a/src/python/doc/representations_sum.inc +++ b/src/python/doc/representations_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | diff --git a/src/python/doc/rips_complex_sum.inc b/src/python/doc/rips_complex_sum.inc index 857c6893..a1f0e469 100644 --- a/src/python/doc/rips_complex_sum.inc +++ b/src/python/doc/rips_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+----------------------------------------------------------------------+ | .. figure:: | Rips complex is a simplicial complex constructed from a one skeleton | :Authors: Clément Maria, Pawel Dlotko, Vincent Rouvreau, Marc Glisse | diff --git a/src/python/doc/simplex_tree_sum.inc b/src/python/doc/simplex_tree_sum.inc index 5ba58d2b..3c637b8c 100644 --- a/src/python/doc/simplex_tree_sum.inc +++ b/src/python/doc/simplex_tree_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------+ | .. figure:: | The simplex tree is an efficient and flexible data structure for | :Author: Clément Maria | diff --git a/src/python/doc/tangential_complex_sum.inc b/src/python/doc/tangential_complex_sum.inc index d84aa433..ddc3e609 100644 --- a/src/python/doc/tangential_complex_sum.inc +++ b/src/python/doc/tangential_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | A Tangential Delaunay complex is a simplicial complex designed to | :Author: Clément Jamin | diff --git a/src/python/doc/wasserstein_distance_sum.inc b/src/python/doc/wasserstein_distance_sum.inc index a97f428d..1632befa 100644 --- a/src/python/doc/wasserstein_distance_sum.inc +++ b/src/python/doc/wasserstein_distance_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | The q-Wasserstein distance measures the similarity between two | :Author: Theo Lacombe | diff --git a/src/python/doc/witness_complex_sum.inc b/src/python/doc/witness_complex_sum.inc index 71b65a71..f9c009ab 100644 --- a/src/python/doc/witness_complex_sum.inc +++ b/src/python/doc/witness_complex_sum.inc @@ -1,5 +1,5 @@ .. table:: - :widths: 30 50 20 + :widths: 30 40 30 +-------------------------------------------------------------------+----------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | Witness complex :math:`Wit(W,L)` is a simplicial complex defined on | :Author: Siargey Kachanovich | -- cgit v1.2.3 From 61691b0081cb868645335c0b1433ddcc0bcbf9e3 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Thu, 19 Mar 2020 13:09:59 -0400 Subject: new fixes --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 45 ++++++++++++++++----------- src/python/gudhi/simplex_tree.pxd | 4 +-- src/python/gudhi/simplex_tree.pyx | 32 ++++++++++++++----- src/python/include/Simplex_tree_interface.h | 13 ++++++++ src/python/test/test_simplex_tree.py | 18 ++++++----- 5 files changed, 77 insertions(+), 35 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 697afe26..50b8e582 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -100,6 +100,12 @@ class Simplex_tree { void assign_key(Simplex_key); Simplex_key key() const; }; + struct Extended_filtration_data { + Filtration_value minval; + Filtration_value maxval; + Extended_filtration_data(){} + Extended_filtration_data(Filtration_value vmin, Filtration_value vmax){ minval = vmin; maxval = vmax; } + }; typedef typename std::conditional::type Key_simplex_base; @@ -126,8 +132,6 @@ class Simplex_tree { private: typedef typename Dictionary::iterator Dictionary_it; typedef typename Dictionary_it::value_type Dit_value_t; - Filtration_value minval_; - Filtration_value maxval_; struct return_first { Vertex_handle operator()(const Dit_value_t& p_sh) const { @@ -1490,15 +1494,16 @@ class Simplex_tree { * performed on these values during the computation of extended persistence. * @param[in] dgm Persistence diagram obtained after calling `extend_filtration()`, * `initialize_filtration()`, and `Gudhi::persistent_cohomology::Persistent_cohomology< FilteredComplex, CoefficientField >::compute_persistent_cohomology()`. + * @param[in] efd Structure containing the minimum and maximum values of the original filtration * @return A vector of four persistence diagrams. The first one is Ordinary, the * second one is Relative, the third one is Extended+ and the fourth one is Extended-. * See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. */ - std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ + std::vector>>> extended_persistence_subdiagrams(const std::vector>>& dgm, const Extended_filtration_data& efd){ std::vector>>> new_dgm(4); Filtration_value x, y; - Filtration_value minval_ = this->minval_; - Filtration_value maxval_ = this->maxval_; + Filtration_value minval = efd.minval; + Filtration_value maxval = efd.maxval; for(unsigned int i = 0; i < dgm.size(); i++){ int h = dgm[i].first; Filtration_value px = dgm[i].second.first; @@ -1506,18 +1511,18 @@ class Simplex_tree { if(std::isinf(py)) continue; else{ if ((px <= -1) & (py <= -1)){ - x = minval_ + (maxval_-minval_)*(px + 2); - y = minval_ + (maxval_-minval_)*(py + 2); + x = minval + (maxval-minval)*(px + 2); + y = minval + (maxval-minval)*(py + 2); new_dgm[0].push_back(std::make_pair(h, std::make_pair(x,y))); } else if ((px >= 1) & (py >= 1)){ - x = minval_ - (maxval_-minval_)*(px - 2); - y = minval_ - (maxval_-minval_)*(py - 2); + x = minval - (maxval-minval)*(px - 2); + y = minval - (maxval-minval)*(py - 2); new_dgm[1].push_back(std::make_pair(h, std::make_pair(x,y))); } else { - x = minval_ + (maxval_-minval_)*(px + 2); - y = minval_ - (maxval_-minval_)*(py - 2); + x = minval + (maxval-minval)*(px + 2); + y = minval - (maxval-minval)*(py - 2); if (x <= y){ new_dgm[2].push_back(std::make_pair(h, std::make_pair(x,y))); } @@ -1535,23 +1540,23 @@ class Simplex_tree { * and computes the extended persistence diagram induced by the lower-star filtration * computed with these values. * \post Note that after calling this function, the filtration - * values are actually modified. The function `compute_extended_persistence_subdiagrams()` + * values are actually modified. The function `extended_persistence_subdiagrams()` * retrieves the original values and separates the extended persistence diagram points * w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after * computing the persistent homology of the extended simplicial complex. * \pre Note that this code creates an extra vertex internally, so you should make sure that * the Simplex tree does not contain a vertex with the largest Vertex_handle. */ - void extend_filtration() { + Extended_filtration_data extend_filtration() { // Compute maximum and minimum of filtration values Vertex_handle maxvert = std::numeric_limits::min(); - this->minval_ = std::numeric_limits::infinity(); - this->maxval_ = -std::numeric_limits::infinity(); + Filtration_value minval = std::numeric_limits::infinity(); + Filtration_value maxval = -std::numeric_limits::infinity(); for (auto sh = root_.members().begin(); sh != root_.members().end(); ++sh){ Filtration_value f = this->filtration(sh); - this->minval_ = std::min(this->minval_, f); - this->maxval_ = std::max(this->maxval_, f); + minval = std::min(minval, f); + maxval = std::max(maxval, f); maxvert = std::max(sh->first, maxvert); } @@ -1578,7 +1583,7 @@ class Simplex_tree { vr.push_back(maxvert); if (this->dimension(sh) == 0){ Filtration_value v = this->filtration(sh); - Filtration_value scaled_v = (v-this->minval_)/(this->maxval_-this->minval_); + Filtration_value scaled_v = (v-minval)/(maxval-minval); // Assign ascending value between -2 and -1 to vertex this->assign_filtration(sh, -2 + scaled_v); // Assign descending value between 1 and 2 to cone on vertex @@ -1593,6 +1598,10 @@ class Simplex_tree { // Automatically assign good values for simplices this->make_filtration_non_decreasing(); + + // Return the filtration data + Extended_filtration_data efd(minval, maxval); + return efd; } /** \brief Returns a vertex of `sh` that has the same filtration value as `sh` if it exists, and `null_vertex()` otherwise. diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index ae32eb82..b6284af4 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -57,8 +57,8 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": void remove_maximal_simplex(vector[int] simplex) bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() - void extend_filtration() - vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]]) + void compute_extended_filtration() + vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]] dgm) # Iterators over Simplex tree pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) Simplex_tree_simplices_iterator get_simplices_iterator_begin() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 7af44683..3502000a 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -405,7 +405,7 @@ cdef class SimplexTree: Note that after calling this function, the filtration values are actually modified within the Simplex_tree. - The function :func:`compute_extended_persistence_subdiagrams()` + The function :func:`extended_persistence()` retrieves the original values. .. note:: @@ -413,21 +413,31 @@ cdef class SimplexTree: Note that this code creates an extra vertex internally, so you should make sure that the Simplex_tree does not contain a vertex with the largest Vertex_handle. """ - return self.get_ptr().extend_filtration() + return self.get_ptr().compute_extended_filtration() - def compute_extended_persistence_subdiagrams(self, dgm): + def extended_persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): """This function retrieves good values for extended persistence, and separate the diagrams into the ordinary, relative, extended+ and extended- subdiagrams. - :param dgm: Persistence diagram obtained after calling :func:`extend_filtration()`, :func:`initialize_filtration()`, and :func:`persistence()`. - + :param homology_coeff_field: The homology coefficient field. Must be a + prime number. Default value is 11. + :type homology_coeff_field: int. + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Sets min_persistence to -1.0 to see all values. + :type min_persistence: float. + :param persistence_dim_max: If true, the persistent homology for the + maximal dimension in the complex is computed. If false, it is + ignored. Default is false. + :type persistence_dim_max: bool :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: This function should be called only if :func:`extend_filtration()`, :func:`initialize_filtration()`, - and :func:`persistence()` have been called first! + and (optionally) :func:`persistence()` have been called first! .. note:: @@ -435,7 +445,15 @@ cdef class SimplexTree: original filtration values due to the internal transformation (scaling to [-2,-1]) that is performed on these values during the computation of extended persistence. """ - return self.get_ptr().compute_extended_persistence_subdiagrams(dgm) + cdef vector[pair[int, pair[double, double]]] persistence_result + if self.pcohptr == NULL: + self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) + if self.pcohptr != NULL: + self.pcohptr.get_persistence(homology_coeff_field, min_persistence) + if self.pcohptr != NULL: + pairs = self.pcohptr.persistence_pairs() + persistence_result = [(len(splx1)-1, [self.filtration(splx1), self.filtration(splx2)]) for [splx1, splx2] in pairs] + return self.get_ptr().compute_extended_persistence_subdiagrams(persistence_result) def persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 4a7062d6..50ed58d0 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -37,8 +37,12 @@ class Simplex_tree_interface : public Simplex_tree { using Filtered_simplices = std::vector; using Skeleton_simplex_iterator = typename Base::Skeleton_simplex_iterator; using Complex_simplex_iterator = typename Base::Complex_simplex_iterator; + using Extended_filtration_data = typename Base::Extended_filtration_data; public: + + Extended_filtration_data efd; + bool find_simplex(const Simplex& vh) { return (Base::find(vh) != Base::null_simplex()); } @@ -117,6 +121,15 @@ class Simplex_tree_interface : public Simplex_tree { return cofaces; } + void compute_extended_filtration() { + this->efd = this->extend_filtration(); + return; + } + + std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ + return this->extended_persistence_subdiagrams(dgm, this->efd); + } + void create_persistence(Gudhi::Persistent_cohomology_interface* pcoh) { Base::initialize_filtration(); pcoh = new Gudhi::Persistent_cohomology_interface(*this); diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 63eee9a5..20f6aabf 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -9,6 +9,7 @@ """ from gudhi import SimplexTree +import pytest __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" @@ -322,15 +323,16 @@ def test_extend_filtration(): ([0, 3, 6], 2.0) ] + dgms = st.extended_persistence() - dgm = st.persistence() - L = st.compute_extended_persistence_subdiagrams(dgm) - assert L == [ - [(0, (1.9999999999999998, 2.9999999999999996))], - [(1, (5.0, 4.0))], - [(0, (1.0, 6.0))], - [(1, (6.0, 1.0))] - ] + assert dgms[0][0][1][0] == pytest.approx(2.) + assert dgms[0][0][1][1] == pytest.approx(3.) + assert dgms[1][0][1][0] == pytest.approx(5.) + assert dgms[1][0][1][1] == pytest.approx(4.) + assert dgms[2][0][1][0] == pytest.approx(1.) + assert dgms[2][0][1][1] == pytest.approx(6.) + assert dgms[3][0][1][0] == pytest.approx(6.) + assert dgms[3][0][1][1] == pytest.approx(1.) def test_simplices_iterator(): -- cgit v1.2.3 From 361abfcfa9ec18c76837f847f8e2e3a060cf7db7 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Thu, 19 Mar 2020 17:02:55 -0400 Subject: added decoding function --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 82 +++++++++++---------------- src/python/gudhi/simplex_tree.pyx | 10 +--- src/python/include/Simplex_tree_interface.h | 27 ++++++++- 3 files changed, 63 insertions(+), 56 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 50b8e582..9008c5f2 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -87,6 +87,8 @@ class Simplex_tree { /* \brief Set of nodes sharing a same parent in the simplex tree. */ typedef Simplex_tree_siblings Siblings; + enum Extended_simplex_type {UP, DOWN, EXTRA}; + struct Key_simplex_base_real { Key_simplex_base_real() : key_(-1) {} void assign_key(Simplex_key k) { key_ = k; } @@ -1486,66 +1488,50 @@ class Simplex_tree { } } - /** \brief Retrieve good values for extended persistence, and separate the - * diagrams into the ordinary, relative, extended+ and extended- subdiagrams. + /** \brief Retrieve the original filtration value for a given simplex in the Simplex_tree. Since the + * computation of extended persistence requires modifying the filtration values, this function can be used + * to recover the original values. Moreover, computing extended persistence requires adding new simplices + * in the Simplex_tree. Hence, this function also outputs the type of each simplex. It can be either UP (which means + * that the simplex was present originally, and is thus part of the ascending extended filtration), DOWN (which means + * that the simplex is the cone of an original simplex, and is thus part of the descending extended filtration) or + * EXTRA (which means the simplex is the cone point). Note that if the simplex type is DOWN, the original filtration value + * is set to be the original filtration value of the corresponding (not coned) original simplex. * \pre This function should be called only if `extend_filtration()` has been called first! - * \post The coordinates of the persistence diagram points might be a little different than the - * original filtration values due to the internal transformation (scaling to [-2,-1]) that is - * performed on these values during the computation of extended persistence. - * @param[in] dgm Persistence diagram obtained after calling `extend_filtration()`, - * `initialize_filtration()`, and `Gudhi::persistent_cohomology::Persistent_cohomology< FilteredComplex, CoefficientField >::compute_persistent_cohomology()`. - * @param[in] efd Structure containing the minimum and maximum values of the original filtration - * @return A vector of four persistence diagrams. The first one is Ordinary, the - * second one is Relative, the third one is Extended+ and the fourth one is Extended-. - * See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + * \post The output filtration value is supposed to be the same, but might be a little different, than the + * original filtration value, due to the internal transformation (scaling to [-2,-1]) that is + * performed on the original filtration values during the computation of extended persistence. + * @param[in] f Filtration value of the simplex in the extended (i.e., modified) filtration. + * @param[in] efd Structure containing the minimum and maximum values of the original filtration. This the output of `extend_filtration()`. + * @return A pair containing the original filtration value of the simplex as well as the simplex type. */ - std::vector>>> extended_persistence_subdiagrams(const std::vector>>& dgm, const Extended_filtration_data& efd){ - std::vector>>> new_dgm(4); - Filtration_value x, y; + std::pair decode_extended_filtration(Filtration_value f, const Extended_filtration_data& efd){ + std::pair p; Filtration_value minval = efd.minval; Filtration_value maxval = efd.maxval; - for(unsigned int i = 0; i < dgm.size(); i++){ - int h = dgm[i].first; - Filtration_value px = dgm[i].second.first; - Filtration_value py = dgm[i].second.second; - if(std::isinf(py)) continue; - else{ - if ((px <= -1) & (py <= -1)){ - x = minval + (maxval-minval)*(px + 2); - y = minval + (maxval-minval)*(py + 2); - new_dgm[0].push_back(std::make_pair(h, std::make_pair(x,y))); - } - else if ((px >= 1) & (py >= 1)){ - x = minval - (maxval-minval)*(px - 2); - y = minval - (maxval-minval)*(py - 2); - new_dgm[1].push_back(std::make_pair(h, std::make_pair(x,y))); - } - else { - x = minval + (maxval-minval)*(px + 2); - y = minval - (maxval-minval)*(py - 2); - if (x <= y){ - new_dgm[2].push_back(std::make_pair(h, std::make_pair(x,y))); - } - else{ - new_dgm[3].push_back(std::make_pair(h, std::make_pair(x,y))); - } - } - } + if (f >= -2 && f <= -1){ + p.first = minval + (maxval-minval)*(f + 2); p.second = UP; } - return new_dgm; - } + else if (f >= 1 && f <= 2){ + p.first = minval - (maxval-minval)*(f - 2); p.second = DOWN; + } + else{ + p.first = -3; p.second = EXTRA; + } + return p; + }; /** \brief Extend filtration for computing extended persistence. * This function only uses the filtration values at the 0-dimensional simplices, * and computes the extended persistence diagram induced by the lower-star filtration * computed with these values. * \post Note that after calling this function, the filtration - * values are actually modified. The function `extended_persistence_subdiagrams()` - * retrieves the original values and separates the extended persistence diagram points - * w.r.t. their types (Ord, Rel, Ext+, Ext-) and should always be called after - * computing the persistent homology of the extended simplicial complex. + * values are actually modified. The function `decode_extended_filtration()` + * retrieves the original values and outputs the extended simplex type. * \pre Note that this code creates an extra vertex internally, so you should make sure that - * the Simplex tree does not contain a vertex with the largest Vertex_handle. + * the Simplex tree does not contain a vertex with the largest Vertex_handle. + * @return A data structure containing the maximum and minimum values of the original filtration. + * It is meant to be provided as input to `decode_extended_filtration()` in order to retrieve + * the original filtration values for each simplex. */ Extended_filtration_data extend_filtration() { diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 3502000a..2cd81c14 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -415,9 +415,9 @@ cdef class SimplexTree: """ return self.get_ptr().compute_extended_filtration() - def extended_persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): + def extended_persistence(self, homology_coeff_field=11, min_persistence=0): """This function retrieves good values for extended persistence, and separate the diagrams - into the ordinary, relative, extended+ and extended- subdiagrams. + into the Ordinary, Relative, Extended+ and Extended- subdiagrams. :param homology_coeff_field: The homology coefficient field. Must be a prime number. Default value is 11. @@ -427,10 +427,6 @@ cdef class SimplexTree: 0.0. Sets min_persistence to -1.0 to see all values. :type min_persistence: float. - :param persistence_dim_max: If true, the persistent homology for the - maximal dimension in the complex is computed. If false, it is - ignored. Default is false. - :type persistence_dim_max: bool :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: @@ -447,7 +443,7 @@ cdef class SimplexTree: """ cdef vector[pair[int, pair[double, double]]] persistence_result if self.pcohptr == NULL: - self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) + self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), True) if self.pcohptr != NULL: self.pcohptr.get_persistence(homology_coeff_field, min_persistence) if self.pcohptr != NULL: diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 50ed58d0..a6b1a06e 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -38,6 +38,7 @@ class Simplex_tree_interface : public Simplex_tree { using Skeleton_simplex_iterator = typename Base::Skeleton_simplex_iterator; using Complex_simplex_iterator = typename Base::Complex_simplex_iterator; using Extended_filtration_data = typename Base::Extended_filtration_data; + using Extended_simplex_type = typename Base::Extended_simplex_type; public: @@ -127,7 +128,31 @@ class Simplex_tree_interface : public Simplex_tree { } std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ - return this->extended_persistence_subdiagrams(dgm, this->efd); + std::vector>>> new_dgm(4); + for (unsigned int i = 0; i < dgm.size(); i++){ + std::pair px = this->decode_extended_filtration(dgm[i].second.first, this->efd); + std::pair py = this->decode_extended_filtration(dgm[i].second.second, this->efd); + std::pair> pd_point = std::make_pair(dgm[i].first, std::make_pair(px.first, py.first)); + //Ordinary + if (px.second == Base::UP && py.second == Base::UP){ + new_dgm[0].push_back(pd_point); + } + // Relative + else if (px.second == Base::DOWN && py.second == Base::DOWN){ + new_dgm[1].push_back(pd_point); + } + else{ + // Extended+ + if (px.first < py.first){ + new_dgm[2].push_back(pd_point); + } + //Extended- + else{ + new_dgm[3].push_back(pd_point); + } + } + } + return new_dgm; } void create_persistence(Gudhi::Persistent_cohomology_interface* pcoh) { -- cgit v1.2.3 From 1e0e378ab442672ef569e93c4114b0e99ea70f6e Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Fri, 20 Mar 2020 12:47:13 -0400 Subject: small fix --- src/python/gudhi/simplex_tree.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 2cd81c14..5b850462 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -443,7 +443,7 @@ cdef class SimplexTree: """ cdef vector[pair[int, pair[double, double]]] persistence_result if self.pcohptr == NULL: - self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), True) + self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), False) if self.pcohptr != NULL: self.pcohptr.get_persistence(homology_coeff_field, min_persistence) if self.pcohptr != NULL: -- cgit v1.2.3 From cf29f4a485d06469d17c6d12d306901fa3c5ab36 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 23 Mar 2020 18:11:15 +0100 Subject: Shorter headers in sphinx: Introduced in -> Since and Copyright -> License --- src/python/doc/alpha_complex_sum.inc | 4 ++-- src/python/doc/bottleneck_distance_sum.inc | 4 ++-- src/python/doc/cubical_complex_sum.inc | 4 ++-- src/python/doc/cubical_complex_user.rst | 2 +- src/python/doc/nerve_gic_complex_sum.inc | 4 ++-- src/python/doc/persistence_graphical_tools_sum.inc | 4 ++-- src/python/doc/persistent_cohomology_sum.inc | 4 ++-- src/python/doc/persistent_cohomology_user.rst | 2 +- src/python/doc/point_cloud_sum.inc | 4 ++-- src/python/doc/representations_sum.inc | 4 ++-- src/python/doc/rips_complex_sum.inc | 4 ++-- src/python/doc/rips_complex_user.rst | 2 +- src/python/doc/simplex_tree_sum.inc | 4 ++-- src/python/doc/tangential_complex_sum.inc | 4 ++-- src/python/doc/wasserstein_distance_sum.inc | 4 ++-- src/python/doc/witness_complex_sum.inc | 4 ++-- 16 files changed, 29 insertions(+), 29 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_sum.inc b/src/python/doc/alpha_complex_sum.inc index 00c35155..9e6414d0 100644 --- a/src/python/doc/alpha_complex_sum.inc +++ b/src/python/doc/alpha_complex_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | | ../../doc/Alpha_complex/alpha_complex_representation.png | cells of a Delaunay Triangulation. | | - | :alt: Alpha complex representation | | :Introduced in: GUDHI 2.0.0 | + | :alt: Alpha complex representation | | :Since: GUDHI 2.0.0 | | :figclass: align-center | The filtration value of each simplex is computed as the **square** of | | - | | the circumradius of the simplex if the circumsphere is empty (the | :Copyright: MIT (`GPL v3 `_) | + | | the circumradius of the simplex if the circumsphere is empty (the | :License: MIT (`GPL v3 `_) | | | simplex is then said to be Gabriel), and as the minimum of the | | | | filtration values of the codimension 1 cofaces that make it not | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | | | Gabriel otherwise. | | diff --git a/src/python/doc/bottleneck_distance_sum.inc b/src/python/doc/bottleneck_distance_sum.inc index a01e7f04..0de4625c 100644 --- a/src/python/doc/bottleneck_distance_sum.inc +++ b/src/python/doc/bottleneck_distance_sum.inc @@ -4,9 +4,9 @@ +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | Bottleneck distance measures the similarity between two persistence | :Author: François Godi | | ../../doc/Bottleneck_distance/perturb_pd.png | diagrams. It's the shortest distance b for which there exists a | | - | :figclass: align-center | perfect matching between the points of the two diagrams (+ all the | :Introduced in: GUDHI 2.0.0 | + | :figclass: align-center | perfect matching between the points of the two diagrams (+ all the | :Since: GUDHI 2.0.0 | | | diagonal points) such that any couple of matched points are at | | - | Bottleneck distance is the length of | distance at most b, where the distance between points is the sup | :Copyright: MIT (`GPL v3 `_) | + | Bottleneck distance is the length of | distance at most b, where the distance between points is the sup | :License: MIT (`GPL v3 `_) | | the longest edge | norm in :math:`\mathbb{R}^2`. | | | | | :Requires: `CGAL `__ :math:`\geq` 4.11.0 | +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ diff --git a/src/python/doc/cubical_complex_sum.inc b/src/python/doc/cubical_complex_sum.inc index ab6388e5..28bf8e94 100644 --- a/src/python/doc/cubical_complex_sum.inc +++ b/src/python/doc/cubical_complex_sum.inc @@ -4,9 +4,9 @@ +--------------------------------------------------------------------------+----------------------------------------------------------------------+-----------------------------+ | .. figure:: | The cubical complex is an example of a structured complex useful in | :Author: Pawel Dlotko | | ../../doc/Bitmap_cubical_complex/Cubical_complex_representation.png | computational mathematics (specially rigorous numerics) and image | | - | :alt: Cubical complex representation | analysis. | :Introduced in: GUDHI 2.0.0 | + | :alt: Cubical complex representation | analysis. | :Since: GUDHI 2.0.0 | | :figclass: align-center | | | - | | | :Copyright: MIT | + | | | :License: MIT | | | | | +--------------------------------------------------------------------------+----------------------------------------------------------------------+-----------------------------+ | * :doc:`cubical_complex_user` | * :doc:`cubical_complex_ref` | diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index 56cf0170..93ca6b24 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -8,7 +8,7 @@ Definition ---------- ===================================== ===================================== ===================================== -:Author: Pawel Dlotko :Introduced in: GUDHI PYTHON 2.0.0 :Copyright: GPL v3 +:Author: Pawel Dlotko :Since: GUDHI PYTHON 2.0.0 :License: GPL v3 ===================================== ===================================== ===================================== +---------------------------------------------+----------------------------------------------------------------------+ diff --git a/src/python/doc/nerve_gic_complex_sum.inc b/src/python/doc/nerve_gic_complex_sum.inc index d5356eca..7fe55aff 100644 --- a/src/python/doc/nerve_gic_complex_sum.inc +++ b/src/python/doc/nerve_gic_complex_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | Nerves and Graph Induced Complexes are cover complexes, i.e. | :Author: Mathieu Carrière | | ../../doc/Nerve_GIC/gicvisu.jpg | simplicial complexes that provably contain topological information | | - | :alt: Graph Induced Complex of a point cloud. | about the input data. They can be computed with a cover of the data, | :Introduced in: GUDHI 2.3.0 | + | :alt: Graph Induced Complex of a point cloud. | about the input data. They can be computed with a cover of the data, | :Since: GUDHI 2.3.0 | | :figclass: align-center | that comes i.e. from the preimage of a family of intervals covering | | - | | the image of a scalar-valued function defined on the data. | :Copyright: MIT (`GPL v3 `_) | + | | the image of a scalar-valued function defined on the data. | :License: MIT (`GPL v3 `_) | | | | | | | | :Requires: `CGAL `__ :math:`\geq` 4.11.0 | | | | | diff --git a/src/python/doc/persistence_graphical_tools_sum.inc b/src/python/doc/persistence_graphical_tools_sum.inc index 723c0f78..b68d3d7e 100644 --- a/src/python/doc/persistence_graphical_tools_sum.inc +++ b/src/python/doc/persistence_graphical_tools_sum.inc @@ -4,9 +4,9 @@ +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | | img/graphical_tools_representation.png | the user to display easily persistence barcode, diagram or density. | | - | | | :Introduced in: GUDHI 2.0.0 | + | | | :Since: GUDHI 2.0.0 | | | Note that these functions return the matplotlib axis, allowing | | - | | for further modifications (title, aspect, etc.) | :Copyright: MIT | + | | for further modifications (title, aspect, etc.) | :License: MIT | | | | | | | | :Requires: matplotlib, numpy and scipy | +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ diff --git a/src/python/doc/persistent_cohomology_sum.inc b/src/python/doc/persistent_cohomology_sum.inc index 9c29bfaa..0effb50f 100644 --- a/src/python/doc/persistent_cohomology_sum.inc +++ b/src/python/doc/persistent_cohomology_sum.inc @@ -4,9 +4,9 @@ +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | The theory of homology consists in attaching to a topological space | :Author: Clément Maria | | ../../doc/Persistent_cohomology/3DTorus_poch.png | a sequence of (homology) groups, capturing global topological | | - | :figclass: align-center | features like connected components, holes, cavities, etc. Persistent | :Introduced in: GUDHI 2.0.0 | + | :figclass: align-center | features like connected components, holes, cavities, etc. Persistent | :Since: GUDHI 2.0.0 | | | homology studies the evolution -- birth, life and death -- of these | | - | Rips Persistent Cohomology on a 3D | features when the topological space is changing. Consequently, the | :Copyright: MIT | + | Rips Persistent Cohomology on a 3D | features when the topological space is changing. Consequently, the | :License: MIT | | Torus | theory is essentially composed of three elements: topological spaces, | | | | their homology groups and an evolution scheme. | | | | | | diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index de83cda1..5f931b3a 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -7,7 +7,7 @@ Persistent cohomology user manual Definition ---------- ===================================== ===================================== ===================================== -:Author: Clément Maria :Introduced in: GUDHI PYTHON 2.0.0 :Copyright: GPL v3 +:Author: Clément Maria :Since: GUDHI PYTHON 2.0.0 :License: GPL v3 ===================================== ===================================== ===================================== +-----------------------------------------------------------------+-----------------------------------------------------------------------+ diff --git a/src/python/doc/point_cloud_sum.inc b/src/python/doc/point_cloud_sum.inc index 77245e86..0a159680 100644 --- a/src/python/doc/point_cloud_sum.inc +++ b/src/python/doc/point_cloud_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, etc. | :Author: Vincent Rouvreau | | | :math:`(y_1, y_2, \ldots, y_d)` | | | - | | | :Introduced in: GUDHI 2.0.0 | + | | | :Since: GUDHI 2.0.0 | | | | | - | | | :Copyright: MIT (`GPL v3 `_) | + | | | :License: MIT (`GPL v3 `_) | | | Parts of this package require CGAL. | | | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | | | | | diff --git a/src/python/doc/representations_sum.inc b/src/python/doc/representations_sum.inc index edb8a448..eac89b9d 100644 --- a/src/python/doc/representations_sum.inc +++ b/src/python/doc/representations_sum.inc @@ -4,9 +4,9 @@ +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | - | | | :Introduced in: GUDHI 3.1.0 | + | | | :Since: GUDHI 3.1.0 | | | | | - | | | :Copyright: MIT | + | | | :License: MIT | | | | | | | | :Requires: scikit-learn | +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ diff --git a/src/python/doc/rips_complex_sum.inc b/src/python/doc/rips_complex_sum.inc index a1f0e469..6feb74cd 100644 --- a/src/python/doc/rips_complex_sum.inc +++ b/src/python/doc/rips_complex_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+----------------------------------------------------------------------+ | .. figure:: | Rips complex is a simplicial complex constructed from a one skeleton | :Authors: Clément Maria, Pawel Dlotko, Vincent Rouvreau, Marc Glisse | | ../../doc/Rips_complex/rips_complex_representation.png | graph. | | - | :figclass: align-center | | :Introduced in: GUDHI 2.0.0 | + | :figclass: align-center | | :Since: GUDHI 2.0.0 | | | The filtration value of each edge is computed from a user-given | | - | | distance function and is inserted until a user-given threshold | :Copyright: MIT | + | | distance function and is inserted until a user-given threshold | :License: MIT | | | value. | | | | | | | | This complex can be built from a point cloud and a distance function, | | diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index a27573e8..8efb12e6 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -8,7 +8,7 @@ Definition ---------- ==================================================================== ================================ ====================== -:Authors: Clément Maria, Pawel Dlotko, Vincent Rouvreau, Marc Glisse :Introduced in: GUDHI 2.0.0 :Copyright: GPL v3 +:Authors: Clément Maria, Pawel Dlotko, Vincent Rouvreau, Marc Glisse :Since: GUDHI 2.0.0 :License: GPL v3 ==================================================================== ================================ ====================== +-------------------------------------------+----------------------------------------------------------------------+ diff --git a/src/python/doc/simplex_tree_sum.inc b/src/python/doc/simplex_tree_sum.inc index 3c637b8c..a8858f16 100644 --- a/src/python/doc/simplex_tree_sum.inc +++ b/src/python/doc/simplex_tree_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------+ | .. figure:: | The simplex tree is an efficient and flexible data structure for | :Author: Clément Maria | | ../../doc/Simplex_tree/Simplex_tree_representation.png | representing general (filtered) simplicial complexes. | | - | :alt: Simplex tree representation | | :Introduced in: GUDHI 2.0.0 | + | :alt: Simplex tree representation | | :Since: GUDHI 2.0.0 | | :figclass: align-center | The data structure is described in | | - | | :cite:`boissonnatmariasimplextreealgorithmica` | :Copyright: MIT | + | | :cite:`boissonnatmariasimplextreealgorithmica` | :License: MIT | | | | | +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------+ | * :doc:`simplex_tree_user` | * :doc:`simplex_tree_ref` | diff --git a/src/python/doc/tangential_complex_sum.inc b/src/python/doc/tangential_complex_sum.inc index ddc3e609..45ce2a66 100644 --- a/src/python/doc/tangential_complex_sum.inc +++ b/src/python/doc/tangential_complex_sum.inc @@ -4,9 +4,9 @@ +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | A Tangential Delaunay complex is a simplicial complex designed to | :Author: Clément Jamin | | ../../doc/Tangential_complex/tc_examples.png | reconstruct a :math:`k`-dimensional manifold embedded in :math:`d`- | | - | :figclass: align-center | dimensional Euclidean space. The input is a point sample coming from | :Introduced in: GUDHI 2.0.0 | + | :figclass: align-center | dimensional Euclidean space. The input is a point sample coming from | :Since: GUDHI 2.0.0 | | | an unknown manifold. The running time depends only linearly on the | | - | | extrinsic dimension :math:`d` and exponentially on the intrinsic | :Copyright: MIT (`GPL v3 `_) | + | | extrinsic dimension :math:`d` and exponentially on the intrinsic | :License: MIT (`GPL v3 `_) | | | dimension :math:`k`. | | | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/wasserstein_distance_sum.inc b/src/python/doc/wasserstein_distance_sum.inc index 1632befa..0ff22035 100644 --- a/src/python/doc/wasserstein_distance_sum.inc +++ b/src/python/doc/wasserstein_distance_sum.inc @@ -4,9 +4,9 @@ +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | The q-Wasserstein distance measures the similarity between two | :Author: Theo Lacombe | | ../../doc/Bottleneck_distance/perturb_pd.png | persistence diagrams. It's the minimum value c that can be achieved | | - | :figclass: align-center | by a perfect matching between the points of the two diagrams (+ all | :Introduced in: GUDHI 3.1.0 | + | :figclass: align-center | by a perfect matching between the points of the two diagrams (+ all | :Since: GUDHI 3.1.0 | | | diagonal points), where the value of a matching is defined as the | | - | Wasserstein distance is the q-th root of the sum of the | q-th root of the sum of all edge lengths to the power q. Edge lengths| :Copyright: MIT | + | Wasserstein distance is the q-th root of the sum of the | q-th root of the sum of all edge lengths to the power q. Edge lengths| :License: MIT | | edge lengths to the power q. | are measured in norm p, for :math:`1 \leq p \leq \infty`. | | | | | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ diff --git a/src/python/doc/witness_complex_sum.inc b/src/python/doc/witness_complex_sum.inc index f9c009ab..34d4df4a 100644 --- a/src/python/doc/witness_complex_sum.inc +++ b/src/python/doc/witness_complex_sum.inc @@ -4,9 +4,9 @@ +-------------------------------------------------------------------+----------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------+ | .. figure:: | Witness complex :math:`Wit(W,L)` is a simplicial complex defined on | :Author: Siargey Kachanovich | | ../../doc/Witness_complex/Witness_complex_representation.png | two sets of points in :math:`\mathbb{R}^D`. | | - | :alt: Witness complex representation | | :Introduced in: GUDHI 2.0.0 | + | :alt: Witness complex representation | | :Since: GUDHI 2.0.0 | | :figclass: align-center | The data structure is described in | | - | | :cite:`boissonnatmariasimplextreealgorithmica`. | :Copyright: MIT (`GPL v3 `_ for Euclidean versions only) | + | | :cite:`boissonnatmariasimplextreealgorithmica`. | :License: MIT (`GPL v3 `_ for Euclidean versions only) | | | | | | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 for Euclidean versions only | +-------------------------------------------------------------------+----------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------+ -- cgit v1.2.3 From 0b4eddeb0d53d465016d5eb913b382123bc5b891 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 23 Mar 2020 18:35:07 +0100 Subject: Avoid consecutive push_back --- src/python/include/Persistent_cohomology_interface.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'src/python') diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 22d6f654..89ff5137 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -117,8 +117,8 @@ persistent_cohomology::Persistent_cohomologyvertex_with_same_filtration(t); - diags[dim].push_back(v); - diags[dim].push_back(w); + auto& d = diags[dim]; + d.insert(d.end(), { v, w }); } } return out; @@ -152,8 +152,8 @@ persistent_cohomology::Persistent_cohomologyedge_with_same_filtration(t); @@ -165,9 +165,8 @@ persistent_cohomology::Persistent_cohomologysimplex_vertex_range(s)); if(diags.size()==0)diags.emplace_back(); - diags[0].push_back(v); - diags[0].push_back(w1); - diags[0].push_back(w2); + auto& d = diags[0]; + d.insert(d.end(), { v, w1, w2 }); } else { auto es = stptr_->edge_with_same_filtration(s); auto&& es_vertices = stptr_->simplex_vertex_range(es); @@ -176,10 +175,8 @@ persistent_cohomology::Persistent_cohomology Date: Mon, 23 Mar 2020 18:52:49 +0100 Subject: Reuse vector Reuse + copy should be slightly faster than regrowing each time (and moving) --- src/python/include/Persistent_cohomology_interface.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 89ff5137..3ce40af5 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -73,15 +73,17 @@ persistent_cohomology::Persistent_cohomology, std::vector>> persistence_pairs; auto const& pairs = Base::get_persistent_pairs(); persistence_pairs.reserve(pairs.size()); + std::vector birth; + std::vector death; for (auto pair : pairs) { - std::vector birth; + birth.clear(); if (get<0>(pair) != stptr_->null_simplex()) { for (auto vertex : stptr_->simplex_vertex_range(get<0>(pair))) { birth.push_back(vertex); } } - std::vector death; + death.clear(); if (get<1>(pair) != stptr_->null_simplex()) { death.reserve(birth.size()+1); for (auto vertex : stptr_->simplex_vertex_range(get<1>(pair))) { @@ -89,7 +91,7 @@ persistent_cohomology::Persistent_cohomology Date: Mon, 23 Mar 2020 21:54:56 +0100 Subject: Add test --- src/python/test/test_simplex_generators.py | 57 ++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100755 src/python/test/test_simplex_generators.py (limited to 'src/python') diff --git a/src/python/test/test_simplex_generators.py b/src/python/test/test_simplex_generators.py new file mode 100755 index 00000000..efb5f8e3 --- /dev/null +++ b/src/python/test/test_simplex_generators.py @@ -0,0 +1,57 @@ +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + Author(s): Marc Glisse + + Copyright (C) 2020 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +import gudhi +import numpy as np + + +def test_flag_generators(): + pts = np.array([[0, 0], [0, 1.01], [1, 0], [1.02, 1.03], [100, 0], [100, 3.01], [103, 0], [103.02, 3.03]]) + r = gudhi.RipsComplex(pts, max_edge_length=4) + st = r.create_simplex_tree(max_dimension=50) + st.persistence() + g = st.flag_persistence_generators() + assert np.array_equal(g[0], [[2, 2, 0], [1, 1, 0], [3, 3, 1], [6, 6, 4], [5, 5, 4], [7, 7, 5]]) + assert len(g[1]) == 1 + assert np.array_equal(g[1][0], [[3, 2, 2, 1]]) + assert np.array_equal(g[2], [0, 4]) + assert len(g[3]) == 1 + assert np.array_equal(g[3][0], [[7, 6]]) + + +def test_lower_star_generators(): + st = gudhi.SimplexTree() + st.insert([0, 1, 2], -10) + st.insert([0, 3], -10) + st.insert([1, 3], -10) + st.assign_filtration([2], -1) + st.assign_filtration([3], 0) + st.assign_filtration([0], 1) + st.assign_filtration([1], 2) + st.make_filtration_non_decreasing() + st.persistence(min_persistence=-1) + g = st.lower_star_persistence_generators(min_persistence=-1) + assert len(g[0]) == 2 + assert np.array_equal(g[0][0], [[0, 0], [3, 0], [1, 1]]) + assert np.array_equal(g[0][1], [[1, 1]]) + assert len(g[1]) == 2 + assert np.array_equal(g[1][0], [2]) + assert np.array_equal(g[1][1], [1]) + + +def test_empty(): + st = gudhi.SimplexTree() + st.persistence() + assert st.lower_star_persistence_generators() == ([], []) + g = st.flag_persistence_generators() + assert np.array_equal(g[0], np.empty((0, 3))) + assert g[1] == [] + assert np.array_equal(g[2], []) + assert g[3] == [] -- cgit v1.2.3 From bc223c3cc7cb9e9c0bb3573af720fce9c5380b94 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Mon, 23 Mar 2020 21:22:16 -0400 Subject: new fixes --- src/Simplex_tree/include/gudhi/Simplex_tree.h | 25 +++++++++++++++----- src/python/gudhi/simplex_tree.pxd | 2 +- src/python/gudhi/simplex_tree.pyx | 21 +++++++---------- src/python/include/Simplex_tree_interface.h | 34 ++++++++++++++------------- src/python/test/test_simplex_tree.py | 7 ++---- 5 files changed, 48 insertions(+), 41 deletions(-) (limited to 'src/python') diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index 9008c5f2..de97d6f2 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -42,6 +42,20 @@ namespace Gudhi { +/** + * \class Extended_simplex_type Simplex_tree.h gudhi/Simplex_tree.h + * \brief Extended simplex type data structure for representing the type of simplices in an extended filtration. + * + * \details The extended simplex type can be either UP (which means + * that the simplex was present originally, and is thus part of the ascending extended filtration), DOWN (which means + * that the simplex is the cone of an original simplex, and is thus part of the descending extended filtration) or + * EXTRA (which means the simplex is the cone point). + * + * Details may be found in section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z. + * + */ +enum class Extended_simplex_type {UP, DOWN, EXTRA}; + struct Simplex_tree_options_full_featured; /** @@ -87,7 +101,7 @@ class Simplex_tree { /* \brief Set of nodes sharing a same parent in the simplex tree. */ typedef Simplex_tree_siblings Siblings; - enum Extended_simplex_type {UP, DOWN, EXTRA}; + struct Key_simplex_base_real { Key_simplex_base_real() : key_(-1) {} @@ -106,7 +120,7 @@ class Simplex_tree { Filtration_value minval; Filtration_value maxval; Extended_filtration_data(){} - Extended_filtration_data(Filtration_value vmin, Filtration_value vmax){ minval = vmin; maxval = vmax; } + Extended_filtration_data(Filtration_value vmin, Filtration_value vmax): minval(vmin), maxval(vmax) {} }; typedef typename std::conditional::type Key_simplex_base; @@ -1370,7 +1384,6 @@ class Simplex_tree { // Replacing if(f=max)) would mean that if f is NaN, we replace it with the max of the children. // That seems more useful than keeping NaN. if (!(simplex.second.filtration() >= max_filt_border_value)) { - // Store the filtration modification information modified = true; simplex.second.assign_filtration(max_filt_border_value); @@ -1509,13 +1522,13 @@ class Simplex_tree { Filtration_value minval = efd.minval; Filtration_value maxval = efd.maxval; if (f >= -2 && f <= -1){ - p.first = minval + (maxval-minval)*(f + 2); p.second = UP; + p.first = minval + (maxval-minval)*(f + 2); p.second = Extended_simplex_type::UP; } else if (f >= 1 && f <= 2){ - p.first = minval - (maxval-minval)*(f - 2); p.second = DOWN; + p.first = minval - (maxval-minval)*(f - 2); p.second = Extended_simplex_type::DOWN; } else{ - p.first = -3; p.second = EXTRA; + p.first = std::numeric_limits::quiet_NaN(); p.second = Extended_simplex_type::EXTRA; } return p; }; diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index b6284af4..595f22bb 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -58,7 +58,7 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": bool prune_above_filtration(double filtration) bool make_filtration_non_decreasing() void compute_extended_filtration() - vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]] dgm) + vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]] dgm, double min_persistence) # Iterators over Simplex tree pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) Simplex_tree_simplices_iterator get_simplices_iterator_begin() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 5b850462..bcb1578d 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -411,7 +411,7 @@ cdef class SimplexTree: .. note:: Note that this code creates an extra vertex internally, so you should make sure that - the Simplex_tree does not contain a vertex with the largest Vertex_handle. + the Simplex_tree does not contain a vertex with the largest possible value (i.e., 4294967295). """ return self.get_ptr().compute_extended_filtration() @@ -422,18 +422,16 @@ cdef class SimplexTree: :param homology_coeff_field: The homology coefficient field. Must be a prime number. Default value is 11. :type homology_coeff_field: int. - :param min_persistence: The minimum persistence value to take into + :param min_persistence: The minimum persistence value (i.e., the absolute value of the difference between the persistence diagram point coordinates) to take into account (strictly greater than min_persistence). Default value is 0.0. Sets min_persistence to -1.0 to see all values. :type min_persistence: float. - :returns: A vector of four persistence diagrams. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: - This function should be called only if :func:`extend_filtration()`, - :func:`initialize_filtration()`, - and (optionally) :func:`persistence()` have been called first! + This function should be called only if :func:`extend_filtration()` has been called first! .. note:: @@ -442,14 +440,11 @@ cdef class SimplexTree: performed on these values during the computation of extended persistence. """ cdef vector[pair[int, pair[double, double]]] persistence_result - if self.pcohptr == NULL: - self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), False) - if self.pcohptr != NULL: - self.pcohptr.get_persistence(homology_coeff_field, min_persistence) if self.pcohptr != NULL: - pairs = self.pcohptr.persistence_pairs() - persistence_result = [(len(splx1)-1, [self.filtration(splx1), self.filtration(splx2)]) for [splx1, splx2] in pairs] - return self.get_ptr().compute_extended_persistence_subdiagrams(persistence_result) + del self.pcohptr + self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), False) + persistence_result = self.pcohptr.get_persistence(homology_coeff_field, -1.) + return self.get_ptr().compute_extended_persistence_subdiagrams(persistence_result, min_persistence) def persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index a6b1a06e..1a18aed6 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -38,7 +38,6 @@ class Simplex_tree_interface : public Simplex_tree { using Skeleton_simplex_iterator = typename Base::Skeleton_simplex_iterator; using Complex_simplex_iterator = typename Base::Complex_simplex_iterator; using Extended_filtration_data = typename Base::Extended_filtration_data; - using Extended_simplex_type = typename Base::Extended_simplex_type; public: @@ -124,31 +123,34 @@ class Simplex_tree_interface : public Simplex_tree { void compute_extended_filtration() { this->efd = this->extend_filtration(); + this->initialize_filtration(); return; } - std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm){ + std::vector>>> compute_extended_persistence_subdiagrams(const std::vector>>& dgm, Filtration_value min_persistence){ std::vector>>> new_dgm(4); for (unsigned int i = 0; i < dgm.size(); i++){ std::pair px = this->decode_extended_filtration(dgm[i].second.first, this->efd); std::pair py = this->decode_extended_filtration(dgm[i].second.second, this->efd); std::pair> pd_point = std::make_pair(dgm[i].first, std::make_pair(px.first, py.first)); - //Ordinary - if (px.second == Base::UP && py.second == Base::UP){ - new_dgm[0].push_back(pd_point); - } - // Relative - else if (px.second == Base::DOWN && py.second == Base::DOWN){ - new_dgm[1].push_back(pd_point); - } - else{ - // Extended+ - if (px.first < py.first){ - new_dgm[2].push_back(pd_point); + if(std::abs(px.first - py.first) > min_persistence){ + //Ordinary + if (px.second == Extended_simplex_type::UP && py.second == Extended_simplex_type::UP){ + new_dgm[0].push_back(pd_point); + } + // Relative + else if (px.second == Extended_simplex_type::DOWN && py.second == Extended_simplex_type::DOWN){ + new_dgm[1].push_back(pd_point); } - //Extended- else{ - new_dgm[3].push_back(pd_point); + // Extended+ + if (px.first < py.first){ + new_dgm[2].push_back(pd_point); + } + //Extended- + else{ + new_dgm[3].push_back(pd_point); + } } } } diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 20f6aabf..70b26e97 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -291,10 +291,8 @@ def test_extend_filtration(): ([5], 6.0) ] - st.extend_filtration() - st.initialize_filtration() - + assert list(st.get_filtration()) == [ ([6], -3.0), ([0], -2.0), @@ -323,7 +321,7 @@ def test_extend_filtration(): ([0, 3, 6], 2.0) ] - dgms = st.extended_persistence() + dgms = st.extended_persistence(min_persistence=-1.) assert dgms[0][0][1][0] == pytest.approx(2.) assert dgms[0][0][1][1] == pytest.approx(3.) @@ -334,7 +332,6 @@ def test_extend_filtration(): assert dgms[3][0][1][0] == pytest.approx(6.) assert dgms[3][0][1][1] == pytest.approx(1.) - def test_simplices_iterator(): st = SimplexTree() -- cgit v1.2.3 From ec4a9583adaa73c01b05a4b30425581ed7256379 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 24 Mar 2020 14:50:53 +0100 Subject: Remove min_persistence from generators It is supposed to be handled in persistence() already. --- src/python/CMakeLists.txt | 1 + src/python/gudhi/simplex_tree.pxd | 4 ++-- src/python/gudhi/simplex_tree.pyx | 18 ++++-------------- src/python/include/Persistent_cohomology_interface.h | 8 ++------ src/python/test/test_simplex_generators.py | 2 +- 5 files changed, 10 insertions(+), 23 deletions(-) (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index f00966a5..fb219884 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -374,6 +374,7 @@ if(PYTHONINTERP_FOUND) ${PYTHON_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/example/simplex_tree_example.py) add_gudhi_py_test(test_simplex_tree) + add_gudhi_py_test(test_simplex_generators) # Witness add_test(NAME witness_complex_from_nearest_landmark_table_py_test diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 44789365..4038b41d 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -75,5 +75,5 @@ cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": vector[pair[double,double]] intervals_in_dimension(int dimension) void write_output_diagram(string diagram_file_name) vector[pair[vector[int], vector[int]]] persistence_pairs() - pair[vector[vector[int]], vector[vector[int]]] lower_star_generators(double) - pair[vector[vector[int]], vector[vector[int]]] flag_generators(double) + pair[vector[vector[int]], vector[vector[int]]] lower_star_generators() + pair[vector[vector[int]], vector[vector[int]]] flag_generators() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index faa9f9d8..beb40bc4 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -526,15 +526,10 @@ cdef class SimplexTree: print("intervals_in_dim function requires persistence function" " to be launched first.") - def lower_star_persistence_generators(self, min_persistence=0.): + def lower_star_persistence_generators(self): """Assuming this is a lower-star filtration, this function returns the persistence pairs, where each simplex is replaced with the vertex that gave it its filtration value. - :param min_persistence: The minimum persistence value to take into - account (strictly greater than min_persistence). Default value is - 0.0. - Set min_persistence to -1.0 to see all values. - :type min_persistence: float. :returns: First the regular persistence pairs, grouped by dimension, with one vertex per extremity, and second the essential features, grouped by dimension, with one vertex each :rtype: Tuple[List[numpy.array[int] of shape (n,2)], List[numpy.array[int] of shape (m,)]] @@ -542,22 +537,17 @@ cdef class SimplexTree: :note: lower_star_persistence_generators requires that `persistence()` be called first. """ if self.pcohptr != NULL: - gen = self.pcohptr.lower_star_generators(min_persistence) + gen = self.pcohptr.lower_star_generators() normal = [np_array(d).reshape(-1,2) for d in gen.first] infinite = [np_array(d) for d in gen.second] return (normal, infinite) else: print("lower_star_persistence_generators() requires that persistence() be called first.") - def flag_persistence_generators(self, min_persistence=0.): + def flag_persistence_generators(self): """Assuming this is a flag complex, this function returns the persistence pairs, where each simplex is replaced with the vertices of the edges that gave it its filtration value. - :param min_persistence: The minimum persistence value to take into - account (strictly greater than min_persistence). Default value is - 0.0. - Set min_persistence to -1.0 to see all values. - :type min_persistence: float. :returns: First the regular persistence pairs of dimension 0, with one vertex for birth and two for death; then the other regular persistence pairs, grouped by dimension, with 2 vertices per extremity; then the connected components, with one vertex each; @@ -567,7 +557,7 @@ cdef class SimplexTree: :note: flag_persistence_generators requires that `persistence()` be called first. """ if self.pcohptr != NULL: - gen = self.pcohptr.flag_generators(min_persistence) + gen = self.pcohptr.flag_generators() if len(gen.first) == 0: normal0 = numpy.empty((0,3)) normals = [] diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 3ce40af5..3074389c 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -100,7 +100,7 @@ persistent_cohomology::Persistent_cohomology>, std::vector>> Generators; - Generators lower_star_generators(double min_persistence) { + Generators lower_star_generators() { Generators out; // diags[i] should be interpreted as vector> auto& diags = out.first; @@ -109,8 +109,6 @@ persistent_cohomology::Persistent_cohomology(pair); auto t = std::get<1>(pair); - if(stptr_->filtration(t) - stptr_->filtration(s) <= min_persistence) - continue; int dim = stptr_->dimension(s); auto v = stptr_->vertex_with_same_filtration(s); if(t == stptr_->null_simplex()) { @@ -128,7 +126,7 @@ persistent_cohomology::Persistent_cohomology> and other diags[i] as vector> auto& diags = out.first; @@ -137,8 +135,6 @@ persistent_cohomology::Persistent_cohomology(pair); auto t = std::get<1>(pair); - if(stptr_->filtration(t) - stptr_->filtration(s) <= min_persistence) - continue; int dim = stptr_->dimension(s); bool infinite = t == stptr_->null_simplex(); if(infinite) { diff --git a/src/python/test/test_simplex_generators.py b/src/python/test/test_simplex_generators.py index efb5f8e3..e3bdc094 100755 --- a/src/python/test/test_simplex_generators.py +++ b/src/python/test/test_simplex_generators.py @@ -37,7 +37,7 @@ def test_lower_star_generators(): st.assign_filtration([1], 2) st.make_filtration_non_decreasing() st.persistence(min_persistence=-1) - g = st.lower_star_persistence_generators(min_persistence=-1) + g = st.lower_star_persistence_generators() assert len(g[0]) == 2 assert np.array_equal(g[0][0], [[0, 0], [3, 0], [1, 1]]) assert np.array_equal(g[0][1], [[1, 1]]) -- cgit v1.2.3 From d5c8dc1ba4d00ead5875b97e164d07f6180526b0 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 24 Mar 2020 20:31:05 +0100 Subject: print -> assert --- src/python/gudhi/simplex_tree.pyx | 47 +++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 26 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index beb40bc4..dcf1b46e 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -536,13 +536,11 @@ cdef class SimplexTree: :note: lower_star_persistence_generators requires that `persistence()` be called first. """ - if self.pcohptr != NULL: - gen = self.pcohptr.lower_star_generators() - normal = [np_array(d).reshape(-1,2) for d in gen.first] - infinite = [np_array(d) for d in gen.second] - return (normal, infinite) - else: - print("lower_star_persistence_generators() requires that persistence() be called first.") + assert self.pcohptr != NULL, "lower_star_persistence_generators() requires that persistence() be called first." + gen = self.pcohptr.lower_star_generators() + normal = [np_array(d).reshape(-1,2) for d in gen.first] + infinite = [np_array(d) for d in gen.second] + return (normal, infinite) def flag_persistence_generators(self): """Assuming this is a flag complex, this function returns the persistence pairs, @@ -556,23 +554,20 @@ cdef class SimplexTree: :note: flag_persistence_generators requires that `persistence()` be called first. """ - if self.pcohptr != NULL: - gen = self.pcohptr.flag_generators() - if len(gen.first) == 0: - normal0 = numpy.empty((0,3)) - normals = [] - else: - l = iter(gen.first) - normal0 = np_array(next(l)).reshape(-1,3) - normals = [np_array(d).reshape(-1,4) for d in l] - if len(gen.second) == 0: - infinite0 = numpy.empty(0) - infinites = [] - else: - l = iter(gen.second) - infinite0 = np_array(next(l)) - infinites = [np_array(d).reshape(-1,2) for d in l] - - return (normal0, normals, infinite0, infinites) + assert self.pcohptr != NULL, "flag_persistence_generators() requires that persistence() be called first." + gen = self.pcohptr.flag_generators() + if len(gen.first) == 0: + normal0 = numpy.empty((0,3)) + normals = [] + else: + l = iter(gen.first) + normal0 = np_array(next(l)).reshape(-1,3) + normals = [np_array(d).reshape(-1,4) for d in l] + if len(gen.second) == 0: + infinite0 = numpy.empty(0) + infinites = [] else: - print("flag_persistence_generators() requires that persistence() be called first.") + l = iter(gen.second) + infinite0 = np_array(next(l)) + infinites = [np_array(d).reshape(-1,2) for d in l] + return (normal0, normals, infinite0, infinites) -- cgit v1.2.3 From 20ba972d2a7fd14e564ce4adb3921f3f8190fc71 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Wed, 25 Mar 2020 13:00:58 -0400 Subject: update biblio --- biblio/bibliography.bib | 36 +++++++++++++++++++-------- src/Simplex_tree/include/gudhi/Simplex_tree.h | 4 +-- src/python/gudhi/simplex_tree.pyx | 2 +- 3 files changed, 29 insertions(+), 13 deletions(-) (limited to 'src/python') diff --git a/biblio/bibliography.bib b/biblio/bibliography.bib index 3bbe7960..b017a07e 100644 --- a/biblio/bibliography.bib +++ b/biblio/bibliography.bib @@ -7,11 +7,13 @@ } @article{Carriere17c, - author = {Carri\`ere, Mathieu and Michel, Bertrand and Oudot, Steve}, - title = {{Statistical Analysis and Parameter Selection for Mapper}}, - journal = {CoRR}, - volume = {abs/1706.00204}, - year = {2017} +author = {Carri{\`{e}}re, Mathieu and Michel, Bertrand and Oudot, Steve}, +journal = {Journal of Machine Learning Research}, +pages = {1--39}, +publisher = {JMLR.org}, +title = {{Statistical analysis and parameter selection for Mapper}}, +volume = {19}, +year = {2018} } @inproceedings{Dey13, @@ -23,11 +25,14 @@ } @article{Carriere16, - title={{Structure and Stability of the 1-Dimensional Mapper}}, - author={Carri\`ere, Mathieu and Oudot, Steve}, - journal={CoRR}, - volume= {abs/1511.05823}, - year={2015} +author = {Carri{\`{e}}re, Mathieu and Oudot, Steve}, +journal = {Foundations of Computational Mathematics}, +number = {6}, +pages = {1333--1396}, +publisher = {Springer-Verlag}, +title = {{Structure and stability of the one-dimensional Mapper}}, +volume = {18}, +year = {2017} } @inproceedings{zigzag_reflection, @@ -36,6 +41,17 @@ year = {2014 $\ \ \ \ \ \ \ \ \ \ \ $ \emph{In Preparation}}, } +@article{Cohen-Steiner2009, +author = {Cohen-Steiner, David and Edelsbrunner, Herbert and Harer, John}, +journal = {Foundations of Computational Mathematics}, +number = {1}, +pages = {79--103}, +publisher = {Springer-Verlag}, +title = {{Extending persistence using Poincar{\'{e}} and Lefschetz duality}}, +volume = {9}, +year = {2009} +} + @misc{gudhi_stpcoh, author = {Cl\'ement Maria}, title = "\textsc{Gudhi}, Simplex Tree and Persistent Cohomology Packages", diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index de97d6f2..60720567 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -51,7 +51,7 @@ namespace Gudhi { * that the simplex is the cone of an original simplex, and is thus part of the descending extended filtration) or * EXTRA (which means the simplex is the cone point). * - * Details may be found in section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z. + * Details may be found in \cite Cohen-Steiner2009 and section 2.2 in \cite Carriere16. * */ enum class Extended_simplex_type {UP, DOWN, EXTRA}; @@ -1507,7 +1507,7 @@ class Simplex_tree { * in the Simplex_tree. Hence, this function also outputs the type of each simplex. It can be either UP (which means * that the simplex was present originally, and is thus part of the ascending extended filtration), DOWN (which means * that the simplex is the cone of an original simplex, and is thus part of the descending extended filtration) or - * EXTRA (which means the simplex is the cone point). Note that if the simplex type is DOWN, the original filtration value + * EXTRA (which means the simplex is the cone point). See the definition of Extended_simplex_type. Note that if the simplex type is DOWN, the original filtration value * is set to be the original filtration value of the corresponding (not coned) original simplex. * \pre This function should be called only if `extend_filtration()` has been called first! * \post The output filtration value is supposed to be the same, but might be a little different, than the diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index bcb1578d..6bb22171 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -427,7 +427,7 @@ cdef class SimplexTree: 0.0. Sets min_persistence to -1.0 to see all values. :type min_persistence: float. - :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See and https://link.springer.com/article/10.1007/s10208-008-9027-z and section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: -- cgit v1.2.3 From b2a549c055c2796fe4eb1e4e4265cdd718753416 Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Wed, 25 Mar 2020 15:10:35 -0400 Subject: fix biblio --- src/python/gudhi/simplex_tree.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 6bb22171..cc3753e1 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -427,7 +427,7 @@ cdef class SimplexTree: 0.0. Sets min_persistence to -1.0 to see all values. :type min_persistence: float. - :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See and https://link.springer.com/article/10.1007/s10208-008-9027-z and section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See https://link.springer.com/article/10.1007/s10208-008-9027-z and/or section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: -- cgit v1.2.3 From c8c942c43643131a7ef9899826a7095e497150fe Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 26 Mar 2020 22:10:26 +0100 Subject: cmake --- .../modules/GUDHI_third_party_libraries.cmake | 3 + src/python/CMakeLists.txt | 14 ++ src/python/gudhi/point_cloud/dtm.py | 40 +++++ src/python/gudhi/point_cloud/knn.py | 193 +++++++++++++++++++++ src/python/test/test_dtm.py | 32 ++++ 5 files changed, 282 insertions(+) create mode 100644 src/python/gudhi/point_cloud/dtm.py create mode 100644 src/python/gudhi/point_cloud/knn.py create mode 100755 src/python/test/test_dtm.py (limited to 'src/python') diff --git a/src/cmake/modules/GUDHI_third_party_libraries.cmake b/src/cmake/modules/GUDHI_third_party_libraries.cmake index 2d010483..c2039674 100644 --- a/src/cmake/modules/GUDHI_third_party_libraries.cmake +++ b/src/cmake/modules/GUDHI_third_party_libraries.cmake @@ -160,6 +160,9 @@ if( PYTHONINTERP_FOUND ) find_python_module("sklearn") find_python_module("ot") find_python_module("pybind11") + find_python_module("torch") + find_python_module("hnswlib") + find_python_module("pykeops") endif() if(NOT GUDHI_PYTHON_PATH) diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index f00966a5..d26d3e6e 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -78,6 +78,15 @@ if(PYTHONINTERP_FOUND) if(OT_FOUND) add_gudhi_debug_info("POT version ${OT_VERSION}") endif() + if(HNSWLIB_FOUND) + add_gudhi_debug_info("HNSWlib version ${OT_VERSION}") + endif() + if(TORCH_FOUND) + add_gudhi_debug_info("PyTorch version ${OT_VERSION}") + endif() + if(PYKEOPS_FOUND) + add_gudhi_debug_info("PyKeOps version ${OT_VERSION}") + endif() set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_RESULT_OF_USE_DECLTYPE', ") set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_ALL_NO_LIB', ") @@ -399,6 +408,11 @@ if(PYTHONINTERP_FOUND) # Time Delay add_gudhi_py_test(test_time_delay) + # DTM + if(SCIPY_FOUND AND SKLEARN_FOUND AND TORCH_FOUND AND HNSWLIB_FOUND AND PYKEOPS_FOUND) + add_gudhi_py_test(test_dtm) + endif() + # Documentation generation is available through sphinx - requires all modules if(SPHINX_PATH) if(MATPLOTLIB_FOUND) diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py new file mode 100644 index 00000000..08f9ea60 --- /dev/null +++ b/src/python/gudhi/point_cloud/dtm.py @@ -0,0 +1,40 @@ +from .knn import KNN + + +class DTM: + def __init__(self, k, q=2, **kwargs): + """ + Args: + q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if input_type is 'distance_matrix'. + kwargs: Same parameters as KNN, except that metric="neighbors" means that transform() expects an array with the distances to the k nearest neighbors. + """ + self.k = k + self.q = q + self.params = kwargs + + def fit_transform(self, X, y=None): + return self.fit(X).transform(X) + + def fit(self, X, y=None): + """ + Args: + X (numpy.array): coordinates for mass points + """ + if self.params.setdefault("metric", "euclidean") != "neighbors": + self.knn = KNN(self.k, return_index=False, return_distance=True, **self.params) + self.knn.fit(X) + return self + + def transform(self, X): + """ + Args: + X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed", or distances to the k nearest neighbors if metric is "neighbors" (if the array has more than k columns, the remaining ones are ignored). + """ + if self.params["metric"] == "neighbors": + distances = X[:, : self.k] + else: + distances = self.knn.transform(X) + distances = distances ** self.q + dtm = distances.sum(-1) / self.k + dtm = dtm ** (1.0 / self.q) + return dtm diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py new file mode 100644 index 00000000..57078f1e --- /dev/null +++ b/src/python/gudhi/point_cloud/knn.py @@ -0,0 +1,193 @@ +import numpy + + +class KNN: + def __init__(self, k, return_index=True, return_distance=False, metric="euclidean", **kwargs): + """ + Args: + k (int): number of neighbors (including the point itself). + return_index (bool): if True, return the index of each neighbor. + return_distance (bool): if True, return the distance to each neighbor. + implementation (str): Choice of the library that does the real work. + + * 'keops' for a brute-force, CUDA implementation through pykeops. Useful when the dimension becomes + large (10+) but the number of points remains low (less than a million). + Only "minkowski" and its aliases are supported. + * 'ckdtree' for scipy's cKDTree. Only "minkowski" and its aliases are supported. + * 'sklearn' for scikit-learn's NearestNeighbors. + Note that this provides in particular an option algorithm="brute". + * 'hnsw' for hnswlib.Index. It is very fast but does not provide guarantees. + Only supports "euclidean" for now. + * None will try to select a sensible one (scipy if possible, scikit-learn otherwise). + metric (str): see `sklearn.neighbors.NearestNeighbors`. + eps (float): relative error when computing nearest neighbors with the cKDTree. + p (float): norm L^p on input points (including numpy.inf) if metric is "minkowski". Defaults to 2. + n_jobs (int): Number of jobs to schedule for parallel processing of nearest neighbors on the CPU. + If -1 is given all processors are used. Default: 1. + + Additional parameters are forwarded to the backends. + """ + self.k = k + self.return_index = return_index + self.return_distance = return_distance + self.metric = metric + self.params = kwargs + # canonicalize + if metric == "euclidean": + self.params["p"] = 2 + self.metric = "minkowski" + elif metric == "manhattan": + self.params["p"] = 1 + self.metric = "minkowski" + elif metric == "chebyshev": + self.params["p"] = numpy.inf + self.metric = "minkowski" + elif metric == "minkowski": + self.params["p"] = kwargs.get("p", 2) + if self.params.get("implementation") in {"keops", "ckdtree"}: + assert self.metric == "minkowski" + if self.params.get("implementation") == "hnsw": + assert self.metric == "minkowski" and self.params["p"] == 2 + if not self.params.get("implementation"): + if self.metric == "minkowski": + self.params["implementation"] = "ckdtree" + else: + self.params["implementation"] = "sklearn" + + def fit_transform(self, X, y=None): + return self.fit(X).transform(X) + + def fit(self, X, y=None): + """ + Args: + X (numpy.array): coordinates for reference points + """ + self.ref_points = X + if self.params.get("implementation") == "ckdtree": + # sklearn could handle this, but it is much slower + from scipy.spatial import cKDTree + self.kdtree = cKDTree(X) + + if self.params.get("implementation") == "sklearn" and self.metric != "precomputed": + # FIXME: sklearn badly handles "precomputed" + from sklearn.neighbors import NearestNeighbors + + nargs = {k: v for k, v in self.params.items() if k in {"p", "n_jobs", "metric_params", "algorithm", "leaf_size"}} + self.nn = NearestNeighbors(self.k, metric=self.metric, **nargs) + self.nn.fit(X) + + if self.params.get("implementation") == "hnsw": + import hnswlib + self.graph = hnswlib.Index("l2", len(X[0])) # Actually returns squared distances + self.graph.init_index(len(X), **{k:v for k,v in self.params.items() if k in {"ef_construction", "M", "random_seed"}}) + n = self.params.get("num_threads") + if n is None: + n = self.params.get("n_jobs", 1) + self.params["num_threads"] = n + self.graph.add_items(X, num_threads=n) + + return self + + def transform(self, X): + """ + Args: + X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed" + """ + metric = self.metric + k = self.k + + if metric == "precomputed": + # scikit-learn could handle that, but they insist on calling fit() with an unused square array, which is too unnatural. + X = numpy.array(X) + if self.return_index: + neighbors = numpy.argpartition(X, k - 1)[:, 0:k] + distances = numpy.take_along_axis(X, neighbors, axis=-1) + ngb_order = numpy.argsort(distances, axis=-1) + neighbors = numpy.take_along_axis(neighbors, ngb_order, axis=-1) + if self.return_distance: + distances = numpy.take_along_axis(distances, ngb_order, axis=-1) + return neighbors, distances + else: + return neighbors + if self.return_distance: + distances = numpy.partition(X, k - 1)[:, 0:k] + # partition is not guaranteed to sort the lower half, although it often does + distances.sort(axis=-1) + return distances + return None + + if self.params.get("implementation") == "hnsw": + ef = self.params.get("ef") + if ef is not None: + self.graph.set_ef(ef) + neighbors, distances = self.graph.knn_query(X, k, num_threads=self.params["num_threads"]) + # The k nearest neighbors are always sorted. I couldn't find it in the doc, but the code calls searchKnn, + # which returns a priority_queue, and then fills the return array backwards with top/pop on the queue. + if self.return_index: + if self.return_distance: + return neighbors, numpy.sqrt(distances) + else: + return neighbors + if self.return_distance: + return numpy.sqrt(distances) + return None + + if self.params.get("implementation") == "keops": + import torch + from pykeops.torch import LazyTensor + + # 'float64' is slow except on super expensive GPUs. Allow it with some param? + XX = torch.tensor(X, dtype=torch.float32) + if X is self.ref_points: + YY = XX + else: + YY = torch.tensor(self.ref_points, dtype=torch.float32) + + p = self.params["p"] + if p == numpy.inf: + # Requires a version of pykeops strictly more recent than 1.3 + mat = (LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])).abs().max(-1) + elif p == 2: # Any even integer? + mat = ((LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])) ** p).sum(-1) + else: + mat = ((LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])).abs() ** p).sum(-1) + + if self.return_index: + if self.return_distance: + distances, neighbors = mat.Kmin_argKmin(k, dim=1) + if p != numpy.inf: + distances = distances ** (1.0 / p) + return neighbors, distances + else: + neighbors = mat.argKmin(k, dim=1) + return neighbors + if self.return_distance: + distances = mat.Kmin(k, dim=1) + if p != numpy.inf: + distances = distances ** (1.0 / p) + return distances + return None + # FIXME: convert everything back to numpy arrays or not? + + if hasattr(self, "kdtree"): + qargs = {key: val for key, val in self.params.items() if key in {"p", "eps", "n_jobs"}} + distances, neighbors = self.kdtree.query(X, k=self.k, **qargs) + if self.return_index: + if self.return_distance: + return neighbors, distances + else: + return neighbors + if self.return_distance: + return distances + return None + + if self.return_distance: + distances, neighbors = self.nn.kneighbors(X, return_distance=True) + if self.return_index: + return neighbors, distances + else: + return distances + if self.return_index: + neighbors = self.nn.kneighbors(X, return_distance=False) + return neighbors + return None diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py new file mode 100755 index 00000000..57fdd131 --- /dev/null +++ b/src/python/test/test_dtm.py @@ -0,0 +1,32 @@ +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + Author(s): Marc Glisse + + Copyright (C) 2020 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +from gudhi.point_cloud.dtm import DTM +import numpy + + +def test_dtm_euclidean(): + pts = numpy.random.rand(1000,4) + k = 3 + dtm = DTM(k,implementation="ckdtree") + print(dtm.fit_transform(pts)) + dtm = DTM(k,implementation="sklearn") + print(dtm.fit_transform(pts)) + dtm = DTM(k,implementation="sklearn",algorithm="brute") + print(dtm.fit_transform(pts)) + dtm = DTM(k,implementation="hnsw") + print(dtm.fit_transform(pts)) + from scipy.spatial.distance import cdist + d = cdist(pts,pts) + dtm = DTM(k,metric="precomputed") + print(dtm.fit_transform(d)) + dtm = DTM(k,implementation="keops") + print(dtm.fit_transform(pts)) + -- cgit v1.2.3 From 5c4c398b99fe1b157d64cd43a4977ce1504ca795 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 26 Mar 2020 22:25:28 +0100 Subject: HNSWlib doesn't define __version__ --- src/cmake/modules/GUDHI_third_party_libraries.cmake | 21 ++++++++++++++++++++- src/python/CMakeLists.txt | 7 ++++--- 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/cmake/modules/GUDHI_third_party_libraries.cmake b/src/cmake/modules/GUDHI_third_party_libraries.cmake index c2039674..a931b3a1 100644 --- a/src/cmake/modules/GUDHI_third_party_libraries.cmake +++ b/src/cmake/modules/GUDHI_third_party_libraries.cmake @@ -150,6 +150,25 @@ function( find_python_module PYTHON_MODULE_NAME ) endif() endfunction( find_python_module ) +# For modules that do not define module.__version__ +function( find_python_module_no_version PYTHON_MODULE_NAME ) + string(TOUPPER ${PYTHON_MODULE_NAME} PYTHON_MODULE_NAME_UP) + execute_process( + COMMAND ${PYTHON_EXECUTABLE} -c "import ${PYTHON_MODULE_NAME}" + RESULT_VARIABLE PYTHON_MODULE_RESULT + ERROR_VARIABLE PYTHON_MODULE_ERROR) + if(PYTHON_MODULE_RESULT EQUAL 0) + # Remove carriage return + message ("++ Python module ${PYTHON_MODULE_NAME} found") + set(${PYTHON_MODULE_NAME_UP}_FOUND TRUE PARENT_SCOPE) + else() + message ("PYTHON_MODULE_NAME = ${PYTHON_MODULE_NAME} + - PYTHON_MODULE_RESULT = ${PYTHON_MODULE_RESULT} + - PYTHON_MODULE_ERROR = ${PYTHON_MODULE_ERROR}") + set(${PYTHON_MODULE_NAME_UP}_FOUND FALSE PARENT_SCOPE) + endif() +endfunction( find_python_module_no_version ) + if( PYTHONINTERP_FOUND ) find_python_module("cython") find_python_module("pytest") @@ -161,8 +180,8 @@ if( PYTHONINTERP_FOUND ) find_python_module("ot") find_python_module("pybind11") find_python_module("torch") - find_python_module("hnswlib") find_python_module("pykeops") + find_python_module_no_version("hnswlib") endif() if(NOT GUDHI_PYTHON_PATH) diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index d26d3e6e..ec0ab1ca 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -79,13 +79,14 @@ if(PYTHONINTERP_FOUND) add_gudhi_debug_info("POT version ${OT_VERSION}") endif() if(HNSWLIB_FOUND) - add_gudhi_debug_info("HNSWlib version ${OT_VERSION}") + # Does not have a version number... + add_gudhi_debug_info("HNSWlib found") endif() if(TORCH_FOUND) - add_gudhi_debug_info("PyTorch version ${OT_VERSION}") + add_gudhi_debug_info("PyTorch version ${TORCH_VERSION}") endif() if(PYKEOPS_FOUND) - add_gudhi_debug_info("PyKeOps version ${OT_VERSION}") + add_gudhi_debug_info("PyKeOps version ${PYKEOPS_VERSION}") endif() set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_RESULT_OF_USE_DECLTYPE', ") -- cgit v1.2.3 From 7ddad8220fdd34fd3ed91e16882feaa3961b2d67 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 26 Mar 2020 22:59:20 +0100 Subject: license --- src/python/gudhi/point_cloud/dtm.py | 9 +++++++++ src/python/gudhi/point_cloud/knn.py | 9 +++++++++ 2 files changed, 18 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 08f9ea60..839e7452 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -1,3 +1,12 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Marc Glisse +# +# Copyright (C) 2020 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + from .knn import KNN diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 57078f1e..943d4e9f 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -1,3 +1,12 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Marc Glisse +# +# Copyright (C) 2020 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + import numpy -- cgit v1.2.3 From 7120b186471828a9570fdeef37900bd8b98d0d31 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 26 Mar 2020 23:06:06 +0100 Subject: license --- src/python/doc/point_cloud_sum.inc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/point_cloud_sum.inc b/src/python/doc/point_cloud_sum.inc index 0a159680..ecc18951 100644 --- a/src/python/doc/point_cloud_sum.inc +++ b/src/python/doc/point_cloud_sum.inc @@ -6,7 +6,7 @@ | | :math:`(y_1, y_2, \ldots, y_d)` | | | | | | :Since: GUDHI 2.0.0 | | | | | - | | | :License: MIT (`GPL v3 `_) | + | | | :License: MIT (`GPL v3 `_, BSD-3-Clause, Apache-2.0) | | | Parts of this package require CGAL. | | | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | | | | | -- cgit v1.2.3 From af35ea5b4ce631ae826f1db1940798f254aba658 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 26 Mar 2020 23:39:59 +0100 Subject: clean-up use of "implementation" --- src/python/gudhi/point_cloud/knn.py | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 943d4e9f..a4ea3acd 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -72,12 +72,12 @@ class KNN: X (numpy.array): coordinates for reference points """ self.ref_points = X - if self.params.get("implementation") == "ckdtree": + if self.params["implementation"] == "ckdtree": # sklearn could handle this, but it is much slower from scipy.spatial import cKDTree self.kdtree = cKDTree(X) - if self.params.get("implementation") == "sklearn" and self.metric != "precomputed": + if self.params["implementation"] == "sklearn" and self.metric != "precomputed": # FIXME: sklearn badly handles "precomputed" from sklearn.neighbors import NearestNeighbors @@ -85,7 +85,7 @@ class KNN: self.nn = NearestNeighbors(self.k, metric=self.metric, **nargs) self.nn.fit(X) - if self.params.get("implementation") == "hnsw": + if self.params["implementation"] == "hnsw": import hnswlib self.graph = hnswlib.Index("l2", len(X[0])) # Actually returns squared distances self.graph.init_index(len(X), **{k:v for k,v in self.params.items() if k in {"ef_construction", "M", "random_seed"}}) @@ -125,7 +125,7 @@ class KNN: return distances return None - if self.params.get("implementation") == "hnsw": + if self.params["implementation"] == "hnsw": ef = self.params.get("ef") if ef is not None: self.graph.set_ef(ef) @@ -141,7 +141,7 @@ class KNN: return numpy.sqrt(distances) return None - if self.params.get("implementation") == "keops": + if self.params["implementation"] == "keops": import torch from pykeops.torch import LazyTensor @@ -178,7 +178,7 @@ class KNN: return None # FIXME: convert everything back to numpy arrays or not? - if hasattr(self, "kdtree"): + if self.params["implementation"] == "ckdtree": qargs = {key: val for key, val in self.params.items() if key in {"p", "eps", "n_jobs"}} distances, neighbors = self.kdtree.query(X, k=self.k, **qargs) if self.return_index: @@ -190,6 +190,7 @@ class KNN: return distances return None + assert self.params["implementation"] == "sklearn" if self.return_distance: distances, neighbors = self.nn.kneighbors(X, return_distance=True) if self.return_index: -- cgit v1.2.3 From f74c71ca8e474ff927cae029ea63329d30293582 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 27 Mar 2020 13:43:58 +0100 Subject: Improve coverage --- src/python/gudhi/point_cloud/dtm.py | 2 ++ src/python/test/test_dtm.py | 48 +++++++++++++++++++++++++------------ 2 files changed, 35 insertions(+), 15 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 839e7452..541b74a6 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -30,6 +30,8 @@ class DTM: X (numpy.array): coordinates for mass points """ if self.params.setdefault("metric", "euclidean") != "neighbors": + # KNN gives sorted distances, which is unnecessary here. + # Maybe add a parameter to say we don't need sorting? self.knn = KNN(self.k, return_index=False, return_distance=True, **self.params) self.knn.fit(X) return self diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 57fdd131..841f8c3c 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -10,23 +10,41 @@ from gudhi.point_cloud.dtm import DTM import numpy +import pytest -def test_dtm_euclidean(): - pts = numpy.random.rand(1000,4) +def test_dtm_compare_euclidean(): + pts = numpy.random.rand(1000, 4) k = 3 - dtm = DTM(k,implementation="ckdtree") - print(dtm.fit_transform(pts)) - dtm = DTM(k,implementation="sklearn") - print(dtm.fit_transform(pts)) - dtm = DTM(k,implementation="sklearn",algorithm="brute") - print(dtm.fit_transform(pts)) - dtm = DTM(k,implementation="hnsw") - print(dtm.fit_transform(pts)) + dtm = DTM(k, implementation="ckdtree") + r0 = dtm.fit_transform(pts) + dtm = DTM(k, implementation="sklearn") + r1 = dtm.fit_transform(pts) + assert r1 == pytest.approx(r0) + dtm = DTM(k, implementation="sklearn", algorithm="brute") + r2 = dtm.fit_transform(pts) + assert r2 == pytest.approx(r0) + dtm = DTM(k, implementation="hnsw") + r3 = dtm.fit_transform(pts) + assert r3 == pytest.approx(r0) from scipy.spatial.distance import cdist - d = cdist(pts,pts) - dtm = DTM(k,metric="precomputed") - print(dtm.fit_transform(d)) - dtm = DTM(k,implementation="keops") - print(dtm.fit_transform(pts)) + d = cdist(pts, pts) + dtm = DTM(k, metric="precomputed") + r4 = dtm.fit_transform(d) + assert r4 == pytest.approx(r0) + dtm = DTM(k, implementation="keops") + r5 = dtm.fit_transform(pts) + assert r5 == pytest.approx(r0) + + +def test_dtm_precomputed(): + dist = numpy.array([[1.0, 3, 8], [1, 5, 5], [0, 2, 3]]) + dtm = DTM(2, q=1, metric="neighbors") + r = dtm.fit_transform(dist) + assert r == pytest.approx([2.0, 3, 1]) + + dist = numpy.array([[2.0, 2], [0, 1], [3, 4]]) + dtm = DTM(2, q=2, metric="neighbors") + r = dtm.fit_transform(dist) + assert r == pytest.approx([2.0, .707, 3.5355], rel=.01) -- cgit v1.2.3 From 03376ffe0f6060864ee8908893297f8800b7b8d1 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 27 Mar 2020 20:27:10 +0100 Subject: doc --- src/python/doc/point_cloud.rst | 17 +++++++++++++++-- src/python/gudhi/point_cloud/dtm.py | 6 +++++- src/python/gudhi/point_cloud/knn.py | 31 ++++++++++++++++++------------- src/python/test/test_dtm.py | 2 +- 4 files changed, 39 insertions(+), 17 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index c0d4b303..351b0786 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -21,10 +21,23 @@ Subsampling :special-members: :show-inheritance: -TimeDelayEmbedding ------------------- +Time Delay Embedding +-------------------- .. autoclass:: gudhi.point_cloud.timedelay.TimeDelayEmbedding :members: :special-members: __call__ +Nearest neighbors +----------------- + +.. automodule:: gudhi.point_cloud.knn + :members: + :special-members: __init__ + +Distance to measure +------------------- + +.. automodule:: gudhi.point_cloud.dtm + :members: + :special-members: __init__ diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 541b74a6..e4096c5e 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -11,11 +11,15 @@ from .knn import KNN class DTM: + """ + Class to compute the distance to the empirical measure defined by a point set. + """ + def __init__(self, k, q=2, **kwargs): """ Args: q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if input_type is 'distance_matrix'. - kwargs: Same parameters as KNN, except that metric="neighbors" means that transform() expects an array with the distances to the k nearest neighbors. + kwargs: Same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. """ self.k = k self.q = q diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index a4ea3acd..02448530 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -11,6 +11,10 @@ import numpy class KNN: + """ + Class wrapping several implementations for computing the k nearest neighbors in a point set. + """ + def __init__(self, k, return_index=True, return_distance=False, metric="euclidean", **kwargs): """ Args: @@ -19,22 +23,17 @@ class KNN: return_distance (bool): if True, return the distance to each neighbor. implementation (str): Choice of the library that does the real work. - * 'keops' for a brute-force, CUDA implementation through pykeops. Useful when the dimension becomes - large (10+) but the number of points remains low (less than a million). - Only "minkowski" and its aliases are supported. + * 'keops' for a brute-force, CUDA implementation through pykeops. Useful when the dimension becomes large (10+) but the number of points remains low (less than a million). Only "minkowski" and its aliases are supported. * 'ckdtree' for scipy's cKDTree. Only "minkowski" and its aliases are supported. - * 'sklearn' for scikit-learn's NearestNeighbors. - Note that this provides in particular an option algorithm="brute". - * 'hnsw' for hnswlib.Index. It is very fast but does not provide guarantees. - Only supports "euclidean" for now. + * 'sklearn' for scikit-learn's NearestNeighbors. Note that this provides in particular an option algorithm="brute". + * 'hnsw' for hnswlib.Index. It can be very fast but does not provide guarantees. Only supports "euclidean" for now. * None will try to select a sensible one (scipy if possible, scikit-learn otherwise). metric (str): see `sklearn.neighbors.NearestNeighbors`. eps (float): relative error when computing nearest neighbors with the cKDTree. p (float): norm L^p on input points (including numpy.inf) if metric is "minkowski". Defaults to 2. n_jobs (int): Number of jobs to schedule for parallel processing of nearest neighbors on the CPU. If -1 is given all processors are used. Default: 1. - - Additional parameters are forwarded to the backends. + kwargs: additional parameters are forwarded to the backends. """ self.k = k self.return_index = return_index @@ -75,20 +74,26 @@ class KNN: if self.params["implementation"] == "ckdtree": # sklearn could handle this, but it is much slower from scipy.spatial import cKDTree + self.kdtree = cKDTree(X) if self.params["implementation"] == "sklearn" and self.metric != "precomputed": # FIXME: sklearn badly handles "precomputed" from sklearn.neighbors import NearestNeighbors - nargs = {k: v for k, v in self.params.items() if k in {"p", "n_jobs", "metric_params", "algorithm", "leaf_size"}} + nargs = { + k: v for k, v in self.params.items() if k in {"p", "n_jobs", "metric_params", "algorithm", "leaf_size"} + } self.nn = NearestNeighbors(self.k, metric=self.metric, **nargs) self.nn.fit(X) if self.params["implementation"] == "hnsw": import hnswlib - self.graph = hnswlib.Index("l2", len(X[0])) # Actually returns squared distances - self.graph.init_index(len(X), **{k:v for k,v in self.params.items() if k in {"ef_construction", "M", "random_seed"}}) + + self.graph = hnswlib.Index("l2", len(X[0])) # Actually returns squared distances + self.graph.init_index( + len(X), **{k: v for k, v in self.params.items() if k in {"ef_construction", "M", "random_seed"}} + ) n = self.params.get("num_threads") if n is None: n = self.params.get("n_jobs", 1) @@ -154,7 +159,7 @@ class KNN: p = self.params["p"] if p == numpy.inf: - # Requires a version of pykeops strictly more recent than 1.3 + # Requires pykeops 1.4 or later mat = (LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])).abs().max(-1) elif p == 2: # Any even integer? mat = ((LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])) ** p).sum(-1) diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 841f8c3c..93b13e1a 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -47,4 +47,4 @@ def test_dtm_precomputed(): dist = numpy.array([[2.0, 2], [0, 1], [3, 4]]) dtm = DTM(2, q=2, metric="neighbors") r = dtm.fit_transform(dist) - assert r == pytest.approx([2.0, .707, 3.5355], rel=.01) + assert r == pytest.approx([2.0, 0.707, 3.5355], rel=0.01) -- cgit v1.2.3 From 68839b95e7751afd04155cd2565cc53362f01fa2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 10:41:50 +0100 Subject: Missing test --- src/python/CMakeLists.txt | 1 + src/python/test/test_knn.py | 82 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) create mode 100755 src/python/test/test_knn.py (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index ec0ab1ca..d7a6a4db 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -411,6 +411,7 @@ if(PYTHONINTERP_FOUND) # DTM if(SCIPY_FOUND AND SKLEARN_FOUND AND TORCH_FOUND AND HNSWLIB_FOUND AND PYKEOPS_FOUND) + add_gudhi_py_test(test_knn) add_gudhi_py_test(test_dtm) endif() diff --git a/src/python/test/test_knn.py b/src/python/test/test_knn.py new file mode 100755 index 00000000..e455fb48 --- /dev/null +++ b/src/python/test/test_knn.py @@ -0,0 +1,82 @@ +""" This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + Author(s): Marc Glisse + + Copyright (C) 2020 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +from gudhi.point_cloud.knn import KNN +import numpy as np +import pytest + + +def test_knn_explicit(): + base = np.array([[1.0, 1], [1, 2], [4, 2], [4, 3]]) + query = np.array([[1.0, 1], [2, 2], [4, 4]]) + knn = KNN(2, metric="manhattan", return_distance=True, return_index=True) + knn.fit(base) + r = knn.transform(query) + assert r[0] == pytest.approx(np.array([[0, 1], [1, 0], [3, 2]])) + assert r[1] == pytest.approx(np.array([[0.0, 1], [1, 2], [1, 2]])) + + knn = KNN(2, metric="chebyshev", return_distance=True, return_index=False) + knn.fit(base) + r = knn.transform(query) + assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) + r = ( + KNN(2, metric="chebyshev", return_distance=True, return_index=False, implementation="keops") + .fit(base) + .transform(query) + ) + assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) + + knn = KNN(2, metric="minkowski", p=3, return_distance=False, return_index=True) + knn.fit(base) + r = knn.transform(query) + assert np.array_equal(r, [[0, 1], [1, 0], [3, 2]]) + r = ( + KNN(2, metric="minkowski", p=3, return_distance=False, return_index=True, implementation="keops") + .fit(base) + .transform(query) + ) + assert np.array_equal(r, [[0, 1], [1, 0], [3, 2]]) + + dist = np.array([[0.0, 3, 8], [1, 0, 5], [1, 2, 0]]) + knn = KNN(2, metric="precomputed", return_index=True, return_distance=False) + r = knn.fit_transform(dist) + assert np.array_equal(r, [[0, 1], [1, 0], [2, 0]]) + knn = KNN(2, metric="precomputed", return_index=True, return_distance=True) + r = knn.fit_transform(dist) + assert np.array_equal(r[0], [[0, 1], [1, 0], [2, 0]]) + assert np.array_equal(r[1], [[0, 3], [0, 1], [0, 1]]) + + +def test_knn_compare(): + base = np.array([[1.0, 1], [1, 2], [4, 2], [4, 3]]) + query = np.array([[1.0, 1], [2, 2], [4, 4]]) + r0 = KNN(2, implementation="ckdtree", return_index=True, return_distance=False).fit(base).transform(query) + r1 = KNN(2, implementation="sklearn", return_index=True, return_distance=False).fit(base).transform(query) + r2 = KNN(2, implementation="hnsw", return_index=True, return_distance=False).fit(base).transform(query) + r3 = KNN(2, implementation="keops", return_index=True, return_distance=False).fit(base).transform(query) + assert np.array_equal(r0, r1) and np.array_equal(r0, r2) and np.array_equal(r0, r3) + + r0 = KNN(2, implementation="ckdtree", return_index=True, return_distance=True).fit(base).transform(query) + r1 = KNN(2, implementation="sklearn", return_index=True, return_distance=True).fit(base).transform(query) + r2 = KNN(2, implementation="hnsw", return_index=True, return_distance=True).fit(base).transform(query) + r3 = KNN(2, implementation="keops", return_index=True, return_distance=True).fit(base).transform(query) + assert np.array_equal(r0[0], r1[0]) and np.array_equal(r0[0], r2[0]) and np.array_equal(r0[0], r3[0]) + d0 = pytest.approx(r0[1]) + assert r1[1] == d0 and r2[1] == d0 and r3[1] == d0 + + +def test_knn_nop(): + # This doesn't look super useful... + p = np.array([[0.0]]) + assert None is KNN(k=1, return_index=False, return_distance=False, implementation="sklearn").fit_transform(p) + assert None is KNN(k=1, return_index=False, return_distance=False, implementation="ckdtree").fit_transform(p) + assert None is KNN(k=1, return_index=False, return_distance=False, implementation="hnsw", ef=5).fit_transform(p) + assert None is KNN(k=1, return_index=False, return_distance=False, implementation="keops").fit_transform(p) + assert None is KNN(k=1, return_index=False, return_distance=False, metric="precomputed").fit_transform(p) -- cgit v1.2.3 From 35a12b553c85af8ce31629b90a27a7071b0cc379 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 11:48:43 +0100 Subject: Doc tweaks, default DTM exponent --- src/python/doc/point_cloud.rst | 6 ++++-- src/python/doc/point_cloud_sum.inc | 4 ++-- src/python/gudhi/point_cloud/dtm.py | 17 ++++++++++++----- src/python/gudhi/point_cloud/knn.py | 6 +++--- 4 files changed, 21 insertions(+), 12 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index 351b0786..192f70db 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -28,11 +28,12 @@ Time Delay Embedding :members: :special-members: __call__ -Nearest neighbors ------------------ +K nearest neighbors +------------------- .. automodule:: gudhi.point_cloud.knn :members: + :undoc-members: :special-members: __init__ Distance to measure @@ -40,4 +41,5 @@ Distance to measure .. automodule:: gudhi.point_cloud.dtm :members: + :undoc-members: :special-members: __init__ diff --git a/src/python/doc/point_cloud_sum.inc b/src/python/doc/point_cloud_sum.inc index ecc18951..d4761aba 100644 --- a/src/python/doc/point_cloud_sum.inc +++ b/src/python/doc/point_cloud_sum.inc @@ -2,8 +2,8 @@ :widths: 30 40 30 +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, etc. | :Author: Vincent Rouvreau | - | | :math:`(y_1, y_2, \ldots, y_d)` | | | + | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, | :Authors: Vincent Rouvreau, Marc Glisse, Masatoshi Takenouchi | + | | :math:`(y_1, y_2, \ldots, y_d)` | find neighbors, embed time series in higher dimension, etc. | | | | | :Since: GUDHI 2.0.0 | | | | | | | | :License: MIT (`GPL v3 `_, BSD-3-Clause, Apache-2.0) | diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index e4096c5e..520cbea8 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -15,10 +15,11 @@ class DTM: Class to compute the distance to the empirical measure defined by a point set. """ - def __init__(self, k, q=2, **kwargs): + def __init__(self, k, q=None, **kwargs): """ Args: - q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if input_type is 'distance_matrix'. + k (int): number of neighbors (possibly including the point itself). + q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if metric is "neighbors" or "distance_matrix". kwargs: Same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. """ self.k = k @@ -31,7 +32,7 @@ class DTM: def fit(self, X, y=None): """ Args: - X (numpy.array): coordinates for mass points + X (numpy.array): coordinates for mass points. """ if self.params.setdefault("metric", "euclidean") != "neighbors": # KNN gives sorted distances, which is unnecessary here. @@ -45,11 +46,17 @@ class DTM: Args: X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed", or distances to the k nearest neighbors if metric is "neighbors" (if the array has more than k columns, the remaining ones are ignored). """ + q = self.q + if q is None: + if self.params["metric"] in {"neighbors", "precomputed"}: + q = 2 + else: + q = len(X[0]) if self.params["metric"] == "neighbors": distances = X[:, : self.k] else: distances = self.knn.transform(X) - distances = distances ** self.q + distances = distances ** q dtm = distances.sum(-1) / self.k - dtm = dtm ** (1.0 / self.q) + dtm = dtm ** (1.0 / q) return dtm diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 02448530..31e4fc9f 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -18,7 +18,7 @@ class KNN: def __init__(self, k, return_index=True, return_distance=False, metric="euclidean", **kwargs): """ Args: - k (int): number of neighbors (including the point itself). + k (int): number of neighbors (possibly including the point itself). return_index (bool): if True, return the index of each neighbor. return_distance (bool): if True, return the distance to each neighbor. implementation (str): Choice of the library that does the real work. @@ -68,7 +68,7 @@ class KNN: def fit(self, X, y=None): """ Args: - X (numpy.array): coordinates for reference points + X (numpy.array): coordinates for reference points. """ self.ref_points = X if self.params["implementation"] == "ckdtree": @@ -105,7 +105,7 @@ class KNN: def transform(self, X): """ Args: - X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed" + X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed". """ metric = self.metric k = self.k -- cgit v1.2.3 From a911f9707d44259a38ae3dbb6fbcec75779fc639 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 12:17:29 +0100 Subject: doc --- src/python/gudhi/point_cloud/dtm.py | 2 +- src/python/gudhi/point_cloud/knn.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 520cbea8..3ac69f31 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -20,7 +20,7 @@ class DTM: Args: k (int): number of neighbors (possibly including the point itself). q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if metric is "neighbors" or "distance_matrix". - kwargs: Same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. + kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. """ self.k = k self.q = q diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 31e4fc9f..bb7757f2 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -21,7 +21,7 @@ class KNN: k (int): number of neighbors (possibly including the point itself). return_index (bool): if True, return the index of each neighbor. return_distance (bool): if True, return the distance to each neighbor. - implementation (str): Choice of the library that does the real work. + implementation (str): choice of the library that does the real work. * 'keops' for a brute-force, CUDA implementation through pykeops. Useful when the dimension becomes large (10+) but the number of points remains low (less than a million). Only "minkowski" and its aliases are supported. * 'ckdtree' for scipy's cKDTree. Only "minkowski" and its aliases are supported. @@ -31,7 +31,7 @@ class KNN: metric (str): see `sklearn.neighbors.NearestNeighbors`. eps (float): relative error when computing nearest neighbors with the cKDTree. p (float): norm L^p on input points (including numpy.inf) if metric is "minkowski". Defaults to 2. - n_jobs (int): Number of jobs to schedule for parallel processing of nearest neighbors on the CPU. + n_jobs (int): number of jobs to schedule for parallel processing of nearest neighbors on the CPU. If -1 is given all processors are used. Default: 1. kwargs: additional parameters are forwarded to the backends. """ -- cgit v1.2.3 From 990d54f2f13e116f97c1d0f35cbb751015d863fe Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 12:20:57 +0100 Subject: Fix test --- src/python/test/test_dtm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 93b13e1a..1d080ab4 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -30,7 +30,7 @@ def test_dtm_compare_euclidean(): from scipy.spatial.distance import cdist d = cdist(pts, pts) - dtm = DTM(k, metric="precomputed") + dtm = DTM(k, q=2, metric="precomputed") r4 = dtm.fit_transform(d) assert r4 == pytest.approx(r0) dtm = DTM(k, implementation="keops") -- cgit v1.2.3 From 40f4b6fb1fe20c3843b1fd80f99996e6d25c9426 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 12:26:36 +0100 Subject: Comment --- src/python/gudhi/point_cloud/dtm.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 3ac69f31..ba011eaf 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -59,4 +59,6 @@ class DTM: distances = distances ** q dtm = distances.sum(-1) / self.k dtm = dtm ** (1.0 / q) + # We compute too many powers, 1/p in knn then q in dtm, 1/q in dtm then q or some log in the caller. + # Add option to skip the final root? return dtm -- cgit v1.2.3 From 7f323484acdeafca93efdd9bdd20ed428f8fb95b Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 12:45:00 +0100 Subject: Optional sort_results --- src/python/gudhi/point_cloud/dtm.py | 4 +--- src/python/gudhi/point_cloud/knn.py | 19 +++++++++++++------ 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index ba011eaf..678524f2 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -35,9 +35,7 @@ class DTM: X (numpy.array): coordinates for mass points. """ if self.params.setdefault("metric", "euclidean") != "neighbors": - # KNN gives sorted distances, which is unnecessary here. - # Maybe add a parameter to say we don't need sorting? - self.knn = KNN(self.k, return_index=False, return_distance=True, **self.params) + self.knn = KNN(self.k, return_index=False, return_distance=True, sort_results=False, **self.params) self.knn.fit(X) return self diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index bb7757f2..8369f1f8 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -33,6 +33,9 @@ class KNN: p (float): norm L^p on input points (including numpy.inf) if metric is "minkowski". Defaults to 2. n_jobs (int): number of jobs to schedule for parallel processing of nearest neighbors on the CPU. If -1 is given all processors are used. Default: 1. + sort_results (bool): if True, then distances and indices of each point are + sorted on return, so that the first column contains the closest points. + Otherwise, neighbors are returned in an arbitrary order. Defaults to True. kwargs: additional parameters are forwarded to the backends. """ self.k = k @@ -115,18 +118,22 @@ class KNN: X = numpy.array(X) if self.return_index: neighbors = numpy.argpartition(X, k - 1)[:, 0:k] - distances = numpy.take_along_axis(X, neighbors, axis=-1) - ngb_order = numpy.argsort(distances, axis=-1) - neighbors = numpy.take_along_axis(neighbors, ngb_order, axis=-1) + if self.params.get("sort_results", True): + X = numpy.take_along_axis(X, neighbors, axis=-1) + ngb_order = numpy.argsort(X, axis=-1) + neighbors = numpy.take_along_axis(neighbors, ngb_order, axis=-1) + else: + ngb_order = neighbors if self.return_distance: - distances = numpy.take_along_axis(distances, ngb_order, axis=-1) + distances = numpy.take_along_axis(X, ngb_order, axis=-1) return neighbors, distances else: return neighbors if self.return_distance: distances = numpy.partition(X, k - 1)[:, 0:k] - # partition is not guaranteed to sort the lower half, although it often does - distances.sort(axis=-1) + if self.params.get("sort_results"): + # partition is not guaranteed to sort the lower half, although it often does + distances.sort(axis=-1) return distances return None -- cgit v1.2.3 From 75286efcf311f0c7c46a7039970d663f60953e14 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 12:59:01 +0100 Subject: Fix test --- src/python/test/test_dtm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 1d080ab4..33b2f3a2 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -30,7 +30,7 @@ def test_dtm_compare_euclidean(): from scipy.spatial.distance import cdist d = cdist(pts, pts) - dtm = DTM(k, q=2, metric="precomputed") + dtm = DTM(k, q=4, metric="precomputed") r4 = dtm.fit_transform(d) assert r4 == pytest.approx(r0) dtm = DTM(k, implementation="keops") -- cgit v1.2.3 From dd9457649d0d197bbed6402200e0f2f55655680e Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 28 Mar 2020 15:39:15 +0100 Subject: Default param of 2 for DTM --- src/python/gudhi/point_cloud/dtm.py | 14 ++++---------- src/python/test/test_dtm.py | 2 +- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 678524f2..c26ba844 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -15,11 +15,11 @@ class DTM: Class to compute the distance to the empirical measure defined by a point set. """ - def __init__(self, k, q=None, **kwargs): + def __init__(self, k, q=2, **kwargs): """ Args: k (int): number of neighbors (possibly including the point itself). - q (float): order used to compute the distance to measure. Defaults to the dimension, or 2 if metric is "neighbors" or "distance_matrix". + q (float): order used to compute the distance to measure. Defaults to 2. kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. """ self.k = k @@ -44,19 +44,13 @@ class DTM: Args: X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed", or distances to the k nearest neighbors if metric is "neighbors" (if the array has more than k columns, the remaining ones are ignored). """ - q = self.q - if q is None: - if self.params["metric"] in {"neighbors", "precomputed"}: - q = 2 - else: - q = len(X[0]) if self.params["metric"] == "neighbors": distances = X[:, : self.k] else: distances = self.knn.transform(X) - distances = distances ** q + distances = distances ** self.q dtm = distances.sum(-1) / self.k - dtm = dtm ** (1.0 / q) + dtm = dtm ** (1.0 / self.q) # We compute too many powers, 1/p in knn then q in dtm, 1/q in dtm then q or some log in the caller. # Add option to skip the final root? return dtm diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 33b2f3a2..93b13e1a 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -30,7 +30,7 @@ def test_dtm_compare_euclidean(): from scipy.spatial.distance import cdist d = cdist(pts, pts) - dtm = DTM(k, q=4, metric="precomputed") + dtm = DTM(k, metric="precomputed") r4 = dtm.fit_transform(d) assert r4 == pytest.approx(r0) dtm = DTM(k, implementation="keops") -- cgit v1.2.3 From 8d06fbeae596a0372bf9a921de7d04cc734eaa3b Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 30 Mar 2020 08:14:46 +0200 Subject: Biblio --- biblio/bibliography.bib | 15 +++++++++++++++ src/python/gudhi/point_cloud/dtm.py | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/biblio/bibliography.bib b/biblio/bibliography.bib index 3bbe7960..f9d43638 100644 --- a/biblio/bibliography.bib +++ b/biblio/bibliography.bib @@ -1192,3 +1192,18 @@ numpages = {11}, location = {Montr\'{e}al, Canada}, series = {NIPS’18} } +@Article{dtm, +author={Chazal, Fr{\'e}d{\'e}ric +and Cohen-Steiner, David +and M{\'e}rigot, Quentin}, +title={Geometric Inference for Probability Measures}, +journal={Foundations of Computational Mathematics}, +year={2011}, +volume={11}, +number={6}, +pages={733-751}, +abstract={Data often comes in the form of a point cloud sampled from an unknown compact subset of Euclidean space. The general goal of geometric inference is then to recover geometric and topological features (e.g., Betti numbers, normals) of this subset from the approximating point cloud data. It appears that the study of distance functions allows one to address many of these questions successfully. However, one of the main limitations of this framework is that it does not cope well with outliers or with background noise. In this paper, we show how to extend the framework of distance functions to overcome this problem. Replacing compact subsets by measures, we introduce a notion of distance function to a probability distribution in Rd. These functions share many properties with classical distance functions, which make them suitable for inference purposes. In particular, by considering appropriate level sets of these distance functions, we show that it is possible to reconstruct offsets of sampled shapes with topological guarantees even in the presence of outliers. Moreover, in settings where empirical measures are considered, these functions can be easily evaluated, making them of particular practical interest.}, +issn={1615-3383}, +doi={10.1007/s10208-011-9098-0}, +url={https://doi.org/10.1007/s10208-011-9098-0} +} diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index c26ba844..23c36b88 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -12,7 +12,7 @@ from .knn import KNN class DTM: """ - Class to compute the distance to the empirical measure defined by a point set. + Class to compute the distance to the empirical measure defined by a point set, as introduced in :cite:`dtm`. """ def __init__(self, k, q=2, **kwargs): -- cgit v1.2.3 From c5c565dfd92ce1ad5b318dca40edf9429d6334c2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 30 Mar 2020 20:46:56 +0200 Subject: Streamline initialize_filtration --- src/Alpha_complex/test/Alpha_complex_unit_test.cpp | 3 -- .../utilities/alpha_complex_3d_persistence.cpp | 3 -- .../utilities/alpha_complex_persistence.cpp | 3 -- .../alpha_rips_persistence_bottleneck_distance.cpp | 6 --- .../example/custom_persistence_sort.cpp | 3 -- .../example/persistence_from_file.cpp | 3 -- .../example/plain_homology.cpp | 3 -- .../example/rips_multifield_persistence.cpp | 3 -- .../example/rips_persistence_step_by_step.cpp | 3 -- .../include/gudhi/Persistent_cohomology.h | 2 - .../rips_correlation_matrix_persistence.cpp | 3 -- .../utilities/rips_distance_matrix_persistence.cpp | 3 -- src/Rips_complex/utilities/rips_persistence.cpp | 3 -- .../utilities/sparse_rips_persistence.cpp | 3 -- src/Simplex_tree/include/gudhi/Simplex_tree.h | 56 ++++++++++++++-------- src/python/doc/simplex_tree_ref.rst | 1 - .../example/alpha_complex_from_points_example.py | 3 -- src/python/example/simplex_tree_example.py | 1 - src/python/gudhi/simplex_tree.pxd | 3 +- src/python/gudhi/simplex_tree.pyx | 50 ++----------------- src/python/include/Alpha_complex_interface.h | 1 - .../Euclidean_strong_witness_complex_interface.h | 2 - .../include/Euclidean_witness_complex_interface.h | 2 - src/python/include/Nerve_gic_interface.h | 1 - src/python/include/Rips_complex_interface.h | 1 - src/python/include/Simplex_tree_interface.h | 15 +++--- .../include/Strong_witness_complex_interface.h | 2 - src/python/include/Tangential_complex_interface.h | 1 - src/python/include/Witness_complex_interface.h | 2 - src/python/test/test_simplex_tree.py | 3 -- 30 files changed, 48 insertions(+), 140 deletions(-) (limited to 'src/python') diff --git a/src/Alpha_complex/test/Alpha_complex_unit_test.cpp b/src/Alpha_complex/test/Alpha_complex_unit_test.cpp index da1d8004..4b37e4bd 100644 --- a/src/Alpha_complex/test/Alpha_complex_unit_test.cpp +++ b/src/Alpha_complex/test/Alpha_complex_unit_test.cpp @@ -188,9 +188,6 @@ BOOST_AUTO_TEST_CASE(Alpha_complex_from_points) { // Test after prune_above_filtration bool modified = simplex_tree.prune_above_filtration(0.6); - if (modified) { - simplex_tree.initialize_filtration(); - } BOOST_CHECK(modified); // Another way to check num_simplices diff --git a/src/Alpha_complex/utilities/alpha_complex_3d_persistence.cpp b/src/Alpha_complex/utilities/alpha_complex_3d_persistence.cpp index e93c412e..91899040 100644 --- a/src/Alpha_complex/utilities/alpha_complex_3d_persistence.cpp +++ b/src/Alpha_complex/utilities/alpha_complex_3d_persistence.cpp @@ -222,9 +222,6 @@ int main(int argc, char **argv) { break; } - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - std::clog << "Simplex_tree dim: " << simplex_tree.dimension() << std::endl; // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree, true); diff --git a/src/Alpha_complex/utilities/alpha_complex_persistence.cpp b/src/Alpha_complex/utilities/alpha_complex_persistence.cpp index be60ff78..7c898dfd 100644 --- a/src/Alpha_complex/utilities/alpha_complex_persistence.cpp +++ b/src/Alpha_complex/utilities/alpha_complex_persistence.cpp @@ -75,9 +75,6 @@ int main(int argc, char **argv) { std::clog << "Simplicial complex is of dimension " << simplex.dimension() << " - " << simplex.num_simplices() << " simplices - " << simplex.num_vertices() << " vertices." << std::endl; - // Sort the simplices in the order of the filtration - simplex.initialize_filtration(); - std::clog << "Simplex_tree dim: " << simplex.dimension() << std::endl; // Compute the persistence diagram of the complex Gudhi::persistent_cohomology::Persistent_cohomology pcoh( diff --git a/src/Bottleneck_distance/example/alpha_rips_persistence_bottleneck_distance.cpp b/src/Bottleneck_distance/example/alpha_rips_persistence_bottleneck_distance.cpp index 4769eca3..ceb9e226 100644 --- a/src/Bottleneck_distance/example/alpha_rips_persistence_bottleneck_distance.cpp +++ b/src/Bottleneck_distance/example/alpha_rips_persistence_bottleneck_distance.cpp @@ -71,9 +71,6 @@ int main(int argc, char * argv[]) { std::clog << "The Rips complex contains " << rips_stree.num_simplices() << " simplices and has dimension " << rips_stree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - rips_stree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology rips_pcoh(rips_stree); // initializes the coefficient field for homology @@ -92,9 +89,6 @@ int main(int argc, char * argv[]) { std::clog << "The Alpha complex contains " << alpha_stree.num_simplices() << " simplices and has dimension " << alpha_stree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - alpha_stree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology alpha_pcoh(alpha_stree); // initializes the coefficient field for homology diff --git a/src/Persistent_cohomology/example/custom_persistence_sort.cpp b/src/Persistent_cohomology/example/custom_persistence_sort.cpp index 87e9c207..410cd987 100644 --- a/src/Persistent_cohomology/example/custom_persistence_sort.cpp +++ b/src/Persistent_cohomology/example/custom_persistence_sort.cpp @@ -86,9 +86,6 @@ int main(int argc, char **argv) { " - " << simplex.num_simplices() << " simplices - " << simplex.num_vertices() << " vertices." << std::endl; - // Sort the simplices in the order of the filtration - simplex.initialize_filtration(); - std::clog << "Simplex_tree dim: " << simplex.dimension() << std::endl; Persistent_cohomology pcoh(simplex); diff --git a/src/Persistent_cohomology/example/persistence_from_file.cpp b/src/Persistent_cohomology/example/persistence_from_file.cpp index 79108730..38c44514 100644 --- a/src/Persistent_cohomology/example/persistence_from_file.cpp +++ b/src/Persistent_cohomology/example/persistence_from_file.cpp @@ -59,9 +59,6 @@ int main(int argc, char * argv[]) { std::clog << std::endl; }*/ - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology< Simplex_tree<>, Field_Zp > pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Persistent_cohomology/example/plain_homology.cpp b/src/Persistent_cohomology/example/plain_homology.cpp index 4d329020..236b67de 100644 --- a/src/Persistent_cohomology/example/plain_homology.cpp +++ b/src/Persistent_cohomology/example/plain_homology.cpp @@ -59,9 +59,6 @@ int main() { st.insert_simplex_and_subfaces(edge35); st.insert_simplex(vertex4); - // Sort the simplices in the order of the filtration - st.initialize_filtration(); - // Class for homology computation // By default, since the complex has dimension 1, only 0-dimensional homology would be computed. // Here we also want persistent homology to be computed for the maximal dimension in the complex (persistence_dim_max = true) diff --git a/src/Persistent_cohomology/example/rips_multifield_persistence.cpp b/src/Persistent_cohomology/example/rips_multifield_persistence.cpp index e2e2c0a5..2edf5bc4 100644 --- a/src/Persistent_cohomology/example/rips_multifield_persistence.cpp +++ b/src/Persistent_cohomology/example/rips_multifield_persistence.cpp @@ -59,9 +59,6 @@ int main(int argc, char * argv[]) { std::clog << "The complex contains " << simplex_tree.num_simplices() << " simplices \n"; std::clog << " and has dimension " << simplex_tree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Persistent_cohomology/example/rips_persistence_step_by_step.cpp b/src/Persistent_cohomology/example/rips_persistence_step_by_step.cpp index 7da9f15d..a503d983 100644 --- a/src/Persistent_cohomology/example/rips_persistence_step_by_step.cpp +++ b/src/Persistent_cohomology/example/rips_persistence_step_by_step.cpp @@ -76,9 +76,6 @@ int main(int argc, char * argv[]) { std::clog << "The complex contains " << st.num_simplices() << " simplices \n"; std::clog << " and has dimension " << st.dimension() << " \n"; - // Sort the simplices in the order of the filtration - st.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(st); // initializes the coefficient field for homology diff --git a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h index ca4bc10d..bc111f94 100644 --- a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h +++ b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h @@ -561,7 +561,6 @@ class Persistent_cohomology { void output_diagram(std::ostream& ostream = std::cout) { cmp_intervals_by_length cmp(cpx_); std::sort(std::begin(persistent_pairs_), std::end(persistent_pairs_), cmp); - bool has_infinity = std::numeric_limits::has_infinity; for (auto pair : persistent_pairs_) { ostream << get<2>(pair) << " " << cpx_->dimension(get<0>(pair)) << " " << cpx_->filtration(get<0>(pair)) << " " @@ -573,7 +572,6 @@ class Persistent_cohomology { std::ofstream diagram_out(diagram_name.c_str()); cmp_intervals_by_length cmp(cpx_); std::sort(std::begin(persistent_pairs_), std::end(persistent_pairs_), cmp); - bool has_infinity = std::numeric_limits::has_infinity; for (auto pair : persistent_pairs_) { diagram_out << cpx_->dimension(get<0>(pair)) << " " << cpx_->filtration(get<0>(pair)) << " " diff --git a/src/Rips_complex/utilities/rips_correlation_matrix_persistence.cpp b/src/Rips_complex/utilities/rips_correlation_matrix_persistence.cpp index 67f921a6..b473738e 100644 --- a/src/Rips_complex/utilities/rips_correlation_matrix_persistence.cpp +++ b/src/Rips_complex/utilities/rips_correlation_matrix_persistence.cpp @@ -71,9 +71,6 @@ int main(int argc, char* argv[]) { std::clog << "The complex contains " << simplex_tree.num_simplices() << " simplices \n"; std::clog << " and has dimension " << simplex_tree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Rips_complex/utilities/rips_distance_matrix_persistence.cpp b/src/Rips_complex/utilities/rips_distance_matrix_persistence.cpp index 4ad19675..6306755d 100644 --- a/src/Rips_complex/utilities/rips_distance_matrix_persistence.cpp +++ b/src/Rips_complex/utilities/rips_distance_matrix_persistence.cpp @@ -50,9 +50,6 @@ int main(int argc, char* argv[]) { std::clog << "The complex contains " << simplex_tree.num_simplices() << " simplices \n"; std::clog << " and has dimension " << simplex_tree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Rips_complex/utilities/rips_persistence.cpp b/src/Rips_complex/utilities/rips_persistence.cpp index 4cc63d3c..9d7490b3 100644 --- a/src/Rips_complex/utilities/rips_persistence.cpp +++ b/src/Rips_complex/utilities/rips_persistence.cpp @@ -52,9 +52,6 @@ int main(int argc, char* argv[]) { std::clog << "The complex contains " << simplex_tree.num_simplices() << " simplices \n"; std::clog << " and has dimension " << simplex_tree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Rips_complex/utilities/sparse_rips_persistence.cpp b/src/Rips_complex/utilities/sparse_rips_persistence.cpp index 40606158..ac935b41 100644 --- a/src/Rips_complex/utilities/sparse_rips_persistence.cpp +++ b/src/Rips_complex/utilities/sparse_rips_persistence.cpp @@ -54,9 +54,6 @@ int main(int argc, char* argv[]) { std::clog << "The complex contains " << simplex_tree.num_simplices() << " simplices \n"; std::clog << " and has dimension " << simplex_tree.dimension() << " \n"; - // Sort the simplices in the order of the filtration - simplex_tree.initialize_filtration(); - // Compute the persistence diagram of the complex Persistent_cohomology pcoh(simplex_tree); // initializes the coefficient field for homology diff --git a/src/Simplex_tree/include/gudhi/Simplex_tree.h b/src/Simplex_tree/include/gudhi/Simplex_tree.h index b455ae31..43250795 100644 --- a/src/Simplex_tree/include/gudhi/Simplex_tree.h +++ b/src/Simplex_tree/include/gudhi/Simplex_tree.h @@ -142,7 +142,10 @@ class Simplex_tree { public: /** \brief Handle type to a simplex contained in the simplicial complex represented - * by the simplex tree. */ + * by the simplex tree. + * + * They are essentially pointers into internal vectors, and any insertion or removal + * of a simplex may invalidate any other Simplex_handle in the complex. */ typedef typename Dictionary::iterator Simplex_handle; private: @@ -255,11 +258,9 @@ class Simplex_tree { * * The filtration must be valid. If the filtration has not been initialized yet, the * method initializes it (i.e. order the simplices). If the complex has changed since the last time the filtration - * was initialized, please call `initialize_filtration()` to recompute it. */ + * was initialized, please call `clear_filtration()` or `initialize_filtration()` to recompute it. */ Filtration_simplex_range const& filtration_simplex_range(Indexing_tag = Indexing_tag()) { - if (filtration_vect_.empty()) { - initialize_filtration(); - } + maybe_initialize_filtration(); return filtration_vect_; } @@ -877,15 +878,13 @@ class Simplex_tree { } public: - /** \brief Initializes the filtrations, i.e. sort the - * simplices according to their order in the filtration and initializes all Simplex_keys. + /** \brief Initializes the filtration cache, i.e. sorts the + * simplices according to their order in the filtration. * - * After calling this method, filtration_simplex_range() becomes valid, and each simplex is - * assigned a Simplex_key corresponding to its order in the filtration (from 0 to m-1 for a - * simplicial complex with m simplices). + * It always recomputes the cache, even if one already exists. * - * Will be automatically called when calling filtration_simplex_range() - * if the filtration has never been initialized yet. */ + * Any insertion, deletion or change of filtration value invalidates this cache, + * which can be cleared with clear_filtration(). */ void initialize_filtration() { filtration_vect_.clear(); filtration_vect_.reserve(num_simplices()); @@ -907,6 +906,21 @@ class Simplex_tree { std::stable_sort(filtration_vect_.begin(), filtration_vect_.end(), is_before_in_filtration(this)); #endif } + /** \brief Initializes the filtration cache if it isn't initialized yet. + * + * Automatically called by filtration_simplex_range(). */ + void maybe_initialize_filtration() { + if (filtration_vect_.empty()) { + initialize_filtration(); + } + } + /** \brief Clears the filtration cache produced by initialize_filtration(). + * + * Useful when initialize_filtration() has already been called and we perform an operation + * (say an insertion) that invalidates the cache. */ + void clear_filtration() { + filtration_vect_.clear(); + } private: /** Recursive search of cofaces @@ -1128,6 +1142,7 @@ class Simplex_tree { * 1 when calling the method. */ void expansion(int max_dim) { if (max_dim <= 1) return; + clear_filtration(); // Drop the cache. dimension_ = max_dim; for (Dictionary_it root_it = root_.members_.begin(); root_it != root_.members_.end(); ++root_it) { @@ -1338,9 +1353,6 @@ class Simplex_tree { /** \brief This function ensures that each simplex has a higher filtration value than its faces by increasing the * filtration values. * @return True if any filtration value was modified, false if the filtration was already non-decreasing. - * \post Some simplex tree functions require the filtration to be valid. `make_filtration_non_decreasing()` - * function is not launching `initialize_filtration()` but returns the filtration modification information. If the - * complex has changed , please call `initialize_filtration()` to recompute it. * * If a simplex has a `NaN` filtration value, it is considered lower than any other defined filtration value. */ @@ -1352,6 +1364,8 @@ class Simplex_tree { modified |= rec_make_filtration_non_decreasing(simplex.second.children()); } } + if(modified) + clear_filtration(); // Drop the cache. return modified; } @@ -1391,16 +1405,16 @@ class Simplex_tree { public: /** \brief Prune above filtration value given as parameter. * @param[in] filtration Maximum threshold value. - * @return The filtration modification information. - * \post Some simplex tree functions require the filtration to be valid. `prune_above_filtration()` - * function is not launching `initialize_filtration()` but returns the filtration modification information. If the - * complex has changed , please call `initialize_filtration()` to recompute it. + * @return True if any simplex was removed, false if all simplices already had a value below the threshold. * \post Note that the dimension of the simplicial complex may be lower after calling `prune_above_filtration()` * than it was before. However, `upper_bound_dimension()` will return the old value, which remains a valid upper * bound. If you care, you can call `dimension()` to recompute the exact dimension. */ bool prune_above_filtration(Filtration_value filtration) { - return rec_prune_above_filtration(root(), filtration); + bool modified = rec_prune_above_filtration(root(), filtration); + if(modified) + clear_filtration(); // Drop the cache. + return modified; } private: @@ -1467,7 +1481,6 @@ class Simplex_tree { * @param[in] sh Simplex handle on the maximal simplex to remove. * \pre Please check the simplex has no coface before removing it. * \exception std::invalid_argument In debug mode, if sh has children. - * \post Be aware that removing is shifting data in a flat_map (initialize_filtration to be done). * \post Note that the dimension of the simplicial complex may be lower after calling `remove_maximal_simplex()` * than it was before. However, `upper_bound_dimension()` will return the old value, which remains a valid upper * bound. If you care, you can call `dimension()` to recompute the exact dimension. @@ -1539,6 +1552,7 @@ class Simplex_tree { * the original filtration values for each simplex. */ Extended_filtration_data extend_filtration() { + clear_filtration(); // Drop the cache. // Compute maximum and minimum of filtration values Vertex_handle maxvert = std::numeric_limits::min(); diff --git a/src/python/doc/simplex_tree_ref.rst b/src/python/doc/simplex_tree_ref.rst index 9eb8c199..46b2c1e5 100644 --- a/src/python/doc/simplex_tree_ref.rst +++ b/src/python/doc/simplex_tree_ref.rst @@ -8,7 +8,6 @@ Simplex tree reference manual .. autoclass:: gudhi.SimplexTree :members: - :undoc-members: :show-inheritance: .. automethod:: gudhi.SimplexTree.__init__ diff --git a/src/python/example/alpha_complex_from_points_example.py b/src/python/example/alpha_complex_from_points_example.py index 73faf17c..465632eb 100755 --- a/src/python/example/alpha_complex_from_points_example.py +++ b/src/python/example/alpha_complex_from_points_example.py @@ -46,9 +46,6 @@ if simplex_tree.find([4]): else: print("[4] Not found...") -# Some insertions, simplex_tree needs to initialize filtrations -simplex_tree.initialize_filtration() - print("dimension=", simplex_tree.dimension()) print("filtrations=") for simplex_with_filtration in simplex_tree.get_filtration(): diff --git a/src/python/example/simplex_tree_example.py b/src/python/example/simplex_tree_example.py index 34833899..c4635dc5 100755 --- a/src/python/example/simplex_tree_example.py +++ b/src/python/example/simplex_tree_example.py @@ -42,7 +42,6 @@ print("simplices=") for simplex_with_filtration in st.get_simplices(): print("(%s, %.2f)" % tuple(simplex_with_filtration)) -st.initialize_filtration() print("filtration=") for simplex_with_filtration in st.get_filtration(): print("(%s, %.2f)" % tuple(simplex_with_filtration)) diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 595f22bb..7e3bba2b 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -48,8 +48,7 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": int dimension() int upper_bound_dimension() bool find_simplex(vector[int] simplex) - bool insert_simplex_and_subfaces(vector[int] simplex, - double filtration) + bool insert(vector[int] simplex, double filtration) vector[pair[vector[int], double]] get_star(vector[int] simplex) vector[pair[vector[int], double]] get_cofaces(vector[int] simplex, int dimension) diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index cc3753e1..a709980f 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -90,7 +90,7 @@ cdef class SimplexTree: (with more :meth:`assign_filtration` or :meth:`make_filtration_non_decreasing` for instance) before calling any function that relies on the filtration property, like - :meth:`initialize_filtration`. + :meth:`persistence`. """ self.get_ptr().assign_simplex_filtration(simplex, filtration) @@ -98,16 +98,7 @@ cdef class SimplexTree: """This function initializes and sorts the simplicial complex filtration vector. - .. note:: - - This function must be launched before - :func:`persistence()`, - :func:`betti_numbers()`, - :func:`persistent_betti_numbers()`, - or :func:`get_filtration()` - after :func:`inserting` or - :func:`removing` - simplices. + .. deprecated:: 3.2.0 """ self.get_ptr().initialize_filtration() @@ -182,10 +173,7 @@ cdef class SimplexTree: :returns: true if the simplex was found, false otherwise. :rtype: bool """ - cdef vector[int] csimplex - for i in simplex: - csimplex.push_back(i) - return self.get_ptr().find_simplex(csimplex) + return self.get_ptr().find_simplex(simplex) def insert(self, simplex, filtration=0.0): """This function inserts the given N-simplex and its subfaces with the @@ -202,11 +190,7 @@ cdef class SimplexTree: otherwise (whatever its original filtration value). :rtype: bool """ - cdef vector[int] csimplex - for i in simplex: - csimplex.push_back(i) - return self.get_ptr().insert_simplex_and_subfaces(csimplex, - filtration) + return self.get_ptr().insert(simplex, filtration) def get_simplices(self): """This function returns a generator with simplices and their given @@ -306,11 +290,6 @@ cdef class SimplexTree: :param simplex: The N-simplex, represented by a list of vertex. :type simplex: list of int. - .. note:: - - Be aware that removing is shifting data in a flat_map - (:func:`initialize_filtration()` to be done). - .. note:: The dimension of the simplicial complex may be lower after calling @@ -332,16 +311,6 @@ cdef class SimplexTree: :rtype: bool - .. note:: - - Some simplex tree functions require the filtration to be valid. - prune_above_filtration function is not launching - :func:`initialize_filtration()` - but returns the filtration modification - information. If the complex has changed , please call - :func:`initialize_filtration()` - to recompute it. - .. note:: Note that the dimension of the simplicial complex may be lower @@ -382,17 +351,6 @@ cdef class SimplexTree: :returns: True if any filtration value was modified, False if the filtration was already non-decreasing. :rtype: bool - - - .. note:: - - Some simplex tree functions require the filtration to be valid. - make_filtration_non_decreasing function is not launching - :func:`initialize_filtration()` - but returns the filtration modification - information. If the complex has changed , please call - :func:`initialize_filtration()` - to recompute it. """ return self.get_ptr().make_filtration_non_decreasing() diff --git a/src/python/include/Alpha_complex_interface.h b/src/python/include/Alpha_complex_interface.h index 8614eee3..40de88f3 100644 --- a/src/python/include/Alpha_complex_interface.h +++ b/src/python/include/Alpha_complex_interface.h @@ -58,7 +58,6 @@ class Alpha_complex_interface { void create_simplex_tree(Simplex_tree_interface<>* simplex_tree, double max_alpha_square) { alpha_complex_->create_complex(*simplex_tree, max_alpha_square); - simplex_tree->initialize_filtration(); } private: diff --git a/src/python/include/Euclidean_strong_witness_complex_interface.h b/src/python/include/Euclidean_strong_witness_complex_interface.h index c1c72737..f94c51ef 100644 --- a/src/python/include/Euclidean_strong_witness_complex_interface.h +++ b/src/python/include/Euclidean_strong_witness_complex_interface.h @@ -50,12 +50,10 @@ class Euclidean_strong_witness_complex_interface { void create_simplex_tree(Gudhi::Simplex_tree<>* simplex_tree, double max_alpha_square, std::size_t limit_dimension) { witness_complex_->create_complex(*simplex_tree, max_alpha_square, limit_dimension); - simplex_tree->initialize_filtration(); } void create_simplex_tree(Gudhi::Simplex_tree<>* simplex_tree, double max_alpha_square) { witness_complex_->create_complex(*simplex_tree, max_alpha_square); - simplex_tree->initialize_filtration(); } std::vector get_point(unsigned vh) { diff --git a/src/python/include/Euclidean_witness_complex_interface.h b/src/python/include/Euclidean_witness_complex_interface.h index 5d7dbdc2..4411ae79 100644 --- a/src/python/include/Euclidean_witness_complex_interface.h +++ b/src/python/include/Euclidean_witness_complex_interface.h @@ -49,12 +49,10 @@ class Euclidean_witness_complex_interface { void create_simplex_tree(Gudhi::Simplex_tree<>* simplex_tree, double max_alpha_square, std::size_t limit_dimension) { witness_complex_->create_complex(*simplex_tree, max_alpha_square, limit_dimension); - simplex_tree->initialize_filtration(); } void create_simplex_tree(Gudhi::Simplex_tree<>* simplex_tree, double max_alpha_square) { witness_complex_->create_complex(*simplex_tree, max_alpha_square); - simplex_tree->initialize_filtration(); } std::vector get_point(unsigned vh) { diff --git a/src/python/include/Nerve_gic_interface.h b/src/python/include/Nerve_gic_interface.h index 5e7f8ae6..ab14c318 100644 --- a/src/python/include/Nerve_gic_interface.h +++ b/src/python/include/Nerve_gic_interface.h @@ -29,7 +29,6 @@ class Nerve_gic_interface : public Cover_complex> { public: void create_simplex_tree(Simplex_tree_interface<>* simplex_tree) { create_complex(*simplex_tree); - simplex_tree->initialize_filtration(); } void set_cover_from_Euclidean_Voronoi(int m) { set_cover_from_Voronoi(Gudhi::Euclidean_distance(), m); diff --git a/src/python/include/Rips_complex_interface.h b/src/python/include/Rips_complex_interface.h index a66b0e5b..d98b0226 100644 --- a/src/python/include/Rips_complex_interface.h +++ b/src/python/include/Rips_complex_interface.h @@ -53,7 +53,6 @@ class Rips_complex_interface { rips_complex_->create_complex(*simplex_tree, dim_max); else sparse_rips_complex_->create_complex(*simplex_tree, dim_max); - simplex_tree->initialize_filtration(); } private: diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 1a18aed6..5b456baa 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -43,16 +43,19 @@ class Simplex_tree_interface : public Simplex_tree { Extended_filtration_data efd; - bool find_simplex(const Simplex& vh) { - return (Base::find(vh) != Base::null_simplex()); + bool find_simplex(const Simplex& simplex) { + return (Base::find(simplex) != Base::null_simplex()); } - void assign_simplex_filtration(const Simplex& vh, Filtration_value filtration) { - Base::assign_filtration(Base::find(vh), filtration); + void assign_simplex_filtration(const Simplex& simplex, Filtration_value filtration) { + Base::assign_filtration(Base::find(simplex), filtration); + Base::clear_filtration(); } bool insert(const Simplex& simplex, Filtration_value filtration = 0) { Insertion_result result = Base::insert_simplex_and_subfaces(simplex, filtration); + if (result.first != Base::null_simplex()) + Base::clear_filtration(); return (result.second); } @@ -86,7 +89,7 @@ class Simplex_tree_interface : public Simplex_tree { void remove_maximal_simplex(const Simplex& simplex) { Base::remove_maximal_simplex(Base::find(simplex)); - Base::initialize_filtration(); + Base::clear_filtration(); } Simplex_and_filtration get_simplex_and_filtration(Simplex_handle f_simplex) { @@ -123,7 +126,6 @@ class Simplex_tree_interface : public Simplex_tree { void compute_extended_filtration() { this->efd = this->extend_filtration(); - this->initialize_filtration(); return; } @@ -158,7 +160,6 @@ class Simplex_tree_interface : public Simplex_tree { } void create_persistence(Gudhi::Persistent_cohomology_interface* pcoh) { - Base::initialize_filtration(); pcoh = new Gudhi::Persistent_cohomology_interface(*this); } diff --git a/src/python/include/Strong_witness_complex_interface.h b/src/python/include/Strong_witness_complex_interface.h index cda5b514..e9ab0c7b 100644 --- a/src/python/include/Strong_witness_complex_interface.h +++ b/src/python/include/Strong_witness_complex_interface.h @@ -41,13 +41,11 @@ class Strong_witness_complex_interface { void create_simplex_tree(Simplex_tree_interface<>* simplex_tree, double max_alpha_square, std::size_t limit_dimension) { witness_complex_->create_complex(*simplex_tree, max_alpha_square, limit_dimension); - simplex_tree->initialize_filtration(); } void create_simplex_tree(Simplex_tree_interface<>* simplex_tree, double max_alpha_square) { witness_complex_->create_complex(*simplex_tree, max_alpha_square); - simplex_tree->initialize_filtration(); } private: diff --git a/src/python/include/Tangential_complex_interface.h b/src/python/include/Tangential_complex_interface.h index 698226cc..b1afce94 100644 --- a/src/python/include/Tangential_complex_interface.h +++ b/src/python/include/Tangential_complex_interface.h @@ -90,7 +90,6 @@ class Tangential_complex_interface { void create_simplex_tree(Simplex_tree<>* simplex_tree) { tangential_complex_->create_complex>(*simplex_tree); - simplex_tree->initialize_filtration(); } void set_max_squared_edge_length(double max_squared_edge_length) { diff --git a/src/python/include/Witness_complex_interface.h b/src/python/include/Witness_complex_interface.h index 45e14253..76947e53 100644 --- a/src/python/include/Witness_complex_interface.h +++ b/src/python/include/Witness_complex_interface.h @@ -41,13 +41,11 @@ class Witness_complex_interface { void create_simplex_tree(Simplex_tree_interface<>* simplex_tree, double max_alpha_square, std::size_t limit_dimension) { witness_complex_->create_complex(*simplex_tree, max_alpha_square, limit_dimension); - simplex_tree->initialize_filtration(); } void create_simplex_tree(Simplex_tree_interface<>* simplex_tree, double max_alpha_square) { witness_complex_->create_complex(*simplex_tree, max_alpha_square); - simplex_tree->initialize_filtration(); } private: diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index 70b26e97..2137d822 100755 --- a/src/python/test/test_simplex_tree.py +++ b/src/python/test/test_simplex_tree.py @@ -46,7 +46,6 @@ def test_insertion(): assert st.find([2, 3]) == False # filtration test - st.initialize_filtration() assert st.filtration([0, 1, 2]) == 4.0 assert st.filtration([0, 2]) == 4.0 assert st.filtration([1, 2]) == 4.0 @@ -93,7 +92,6 @@ def test_insertion(): assert st.find([1]) == True assert st.find([2]) == True - st.initialize_filtration() assert st.persistence(persistence_dim_max=True) == [ (1, (4.0, float("inf"))), (0, (0.0, float("inf"))), @@ -151,7 +149,6 @@ def test_expansion(): st.expansion(3) assert st.num_vertices() == 7 assert st.num_simplices() == 22 - st.initialize_filtration() assert list(st.get_filtration()) == [ ([2], 0.1), -- cgit v1.2.3 From 4cdc7f03fb5917134ba8886b026c8990f56bcfeb Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 11:21:27 +0200 Subject: merged doc from barycenters to wasserstein distance --- src/python/doc/wasserstein_distance_sum.inc | 10 +-- src/python/doc/wasserstein_distance_user.rst | 91 ++++++++++++++++++++++++++-- 2 files changed, 92 insertions(+), 9 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_sum.inc b/src/python/doc/wasserstein_distance_sum.inc index a97f428d..09424de2 100644 --- a/src/python/doc/wasserstein_distance_sum.inc +++ b/src/python/doc/wasserstein_distance_sum.inc @@ -3,11 +3,11 @@ +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | The q-Wasserstein distance measures the similarity between two | :Author: Theo Lacombe | - | ../../doc/Bottleneck_distance/perturb_pd.png | persistence diagrams. It's the minimum value c that can be achieved | | - | :figclass: align-center | by a perfect matching between the points of the two diagrams (+ all | :Introduced in: GUDHI 3.1.0 | - | | diagonal points), where the value of a matching is defined as the | | - | Wasserstein distance is the q-th root of the sum of the | q-th root of the sum of all edge lengths to the power q. Edge lengths| :Copyright: MIT | - | edge lengths to the power q. | are measured in norm p, for :math:`1 \leq p \leq \infty`. | | + | ../../doc/Bottleneck_distance/perturb_pd.png | persistence diagrams using the sum of all edges lengths (instead of | | + | :figclass: align-center | the maximum). It allows to define sophisticated objects such as | :Introduced in: GUDHI 3.1.0 | + | | barycenters of a family of persistence diagrams. | | + | Wasserstein distance is the q-th root of the sum of the | | :Copyright: MIT | + | edge lengths to the power q. | | | | | | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | * :doc:`wasserstein_distance_user` | | diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index a9b21fa5..6de05afc 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -9,10 +9,16 @@ Definition .. include:: wasserstein_distance_sum.inc -Functions ---------- -This implementation uses the Python Optimal Transport library and is based on -ideas from "Large Scale Computation of Means and Cluster for Persistence +The q-Wasserstein distance is defined as the minimal value +by a perfect matching between the points of the two diagrams (+ all +diagonal points), where the value of a matching is defined as the +q-th root of the sum of all edge lengths to the power q. Edge lengths +are measured in norm p, for :math:`1 \leq p \leq \infty`. + +Distance Functions +------------------ +This first implementation uses the Python Optimal Transport library and is based +on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport" :cite:`10.5555/3327546.3327645`. .. autofunction:: gudhi.wasserstein.wasserstein_distance @@ -84,3 +90,80 @@ The output is: point 1 in dgm1 is matched to point 2 in dgm2 point 2 in dgm1 is matched to the diagonal point 1 in dgm2 is matched to the diagonal + + +Barycenters +----------- + +A Frechet mean (or barycenter) is a generalization of the arithmetic +mean in a non linear space such as the one of persistence diagrams. +Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is +defined as a minimizer of the variance functional, that is of +:math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. +where :math:`d_2` denotes the Wasserstein-2 distance between +persistence diagrams. +It is known to exist and is generically unique. However, an exact +computation is in general untractable. Current implementation +available is based on (Turner et al., 2014), +:cite:`turner2014frechet` +and uses an EM-scheme to +provide a local minimum of the variance functional (somewhat similar +to the Lloyd algorithm to estimate a solution to the k-means +problem). The local minimum returned depends on the initialization of +the barycenter. +The combinatorial structure of the algorithm limits its +scaling on large scale problems (thousands of diagrams and of points +per diagram). + +.. figure:: + ./img/barycenter.png + :figclass: align-center + + Illustration of Frechet mean between persistence + diagrams. + + +.. autofunction:: gudhi.barycenter.lagrangian_barycenter + +Basic example +------------- + +This example computes the Frechet mean (aka Wasserstein barycenter) between +four persistence diagrams. +It is initialized on the 4th diagram. +As the algorithm is not convex, its output depends on the initialization and +is only a local minimum of the objective function. +Initialization can be either given as an integer (in which case the i-th +diagram of the list is used as initial estimate) or as a diagram. +If None, it will randomly select one of the diagram of the list +as initial estimate. +Note that persistence diagrams must be submitted as +(n x 2) numpy arrays and must not contain inf values. + + +.. testcode:: + + import gudhi.barycenter + import numpy as np + + dg1 = np.array([[0.2, 0.5]]) + dg2 = np.array([[0.2, 0.7]]) + dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) + dg4 = np.array([]) + pdiagset = [dg1, dg2, dg3, dg4] + bary = gudhi.wasserstein.barycenter.lagrangian_barycenter(pdiagset=pdiagset,init=3) + + message = "Wasserstein barycenter estimated:" + print(message) + print(bary) + +The output is: + +.. testoutput:: + + Wasserstein barycenter estimated: + [[0.27916667 0.55416667] + [0.7375 0.7625 ] + [0.2375 0.2625 ]] + + -- cgit v1.2.3 From 4adbdcf16f311b0b5151311f77cfead5bf065bf4 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 11:22:50 +0200 Subject: removed barycenters specific doc files as those are included in wasserstein distance now --- src/python/doc/barycenter_sum.inc | 24 --------------- src/python/doc/barycenter_user.rst | 60 -------------------------------------- 2 files changed, 84 deletions(-) delete mode 100644 src/python/doc/barycenter_sum.inc delete mode 100644 src/python/doc/barycenter_user.rst (limited to 'src/python') diff --git a/src/python/doc/barycenter_sum.inc b/src/python/doc/barycenter_sum.inc deleted file mode 100644 index da2bdd84..00000000 --- a/src/python/doc/barycenter_sum.inc +++ /dev/null @@ -1,24 +0,0 @@ -.. table:: - :widths: 30 50 20 - - +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ - | .. figure:: | A Frechet mean (or barycenter) is a generalization of the arithmetic | :Author: Theo Lacombe | - | ./img/barycenter.png | mean in a non linear space such as the one of persistence diagrams. | | - | :figclass: align-center | Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is | :Introduced in: GUDHI 3.1.0 | - | | defined as a minimizer of the variance functional, that is of | | - | Illustration of Frechet mean between persistence | :math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. | :Copyright: MIT | - | diagrams. | where :math:`d_2` denotes the Wasserstein-2 distance between | | - | | persistence diagrams. | | - | | It is known to exist and is generically unique. However, an exact | | - | | computation is in general untractable. Current implementation | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | - | | available is based on [Turner et al, 2014], and uses an EM-scheme to | | - | | provide a local minimum of the variance functional (somewhat similar | | - | | to the Lloyd algorithm to estimate a solution to the k-means | | - | | problem). The local minimum returned depends on the initialization of| | - | | the barycenter. | | - | | The combinatorial structure of the algorithm limits its | | - | | scaling on large scale problems (thousands of diagrams and of points | | - | | per diagram). | | - +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ - | * :doc:`barycenter_user` | | - +-----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/barycenter_user.rst b/src/python/doc/barycenter_user.rst deleted file mode 100644 index 83e9bebb..00000000 --- a/src/python/doc/barycenter_user.rst +++ /dev/null @@ -1,60 +0,0 @@ -:orphan: - -.. To get rid of WARNING: document isn't included in any toctree - -Barycenter user manual -================================ -Definition ----------- - -.. include:: barycenter_sum.inc - -This implementation is based on ideas from "Frechet means for distribution of -persistence diagrams", Turner et al. 2014. - -Function --------- -.. autofunction:: gudhi.barycenter.lagrangian_barycenter - - -Basic example -------------- - -This example computes the Frechet mean (aka Wasserstein barycenter) between -four persistence diagrams. -It is initialized on the 4th diagram. -As the algorithm is not convex, its output depends on the initialization and -is only a local minimum of the objective function. -Initialization can be either given as an integer (in which case the i-th -diagram of the list is used as initial estimate) or as a diagram. -If None, it will randomly select one of the diagram of the list -as initial estimate. -Note that persistence diagrams must be submitted as -(n x 2) numpy arrays and must not contain inf values. - -.. testcode:: - - import gudhi.barycenter - import numpy as np - - dg1 = np.array([[0.2, 0.5]]) - dg2 = np.array([[0.2, 0.7]]) - dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) - dg4 = np.array([]) - pdiagset = [dg1, dg2, dg3, dg4] - bary = gudhi.barycenter.lagrangian_barycenter(pdiagset=pdiagset,init=3) - - message = "Wasserstein barycenter estimated:" - print(message) - print(bary) - -The output is: - -.. testoutput:: - - Wasserstein barycenter estimated: - [[0.27916667 0.55416667] - [0.7375 0.7625 ] - [0.2375 0.2625 ]] - - -- cgit v1.2.3 From 9f55afbb17494c67709d9be58bf8bb876f704524 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 11:24:21 +0200 Subject: added import barycenter on top of the file so that we can call for gudhi.wasserstein.barycenter --- src/python/gudhi/wasserstein.py | 1 + 1 file changed, 1 insertion(+) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 3dd993f9..8f03039b 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -9,6 +9,7 @@ import numpy as np import scipy.spatial.distance as sc +import barycenter try: import ot except ImportError: -- cgit v1.2.3 From 7721ac6181fc394ae0136ee176d63210e727f06f Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 11:40:46 +0200 Subject: modified import in test to get consistent with gudhi.wasserstein.barycenter --- src/python/test/test_wasserstein_barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index 4d18616b..f686aef5 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -1,4 +1,4 @@ -from gudhi.barycenter import lagrangian_barycenter +from gudhi.wasserstein.barycenter import lagrangian_barycenter import numpy as np """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -- cgit v1.2.3 From eeeac06a05ee99ae5780b3f37f107680a680985a Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 11:54:06 +0200 Subject: removed unused import --- src/python/gudhi/barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py index 0490fdd1..079bcc57 100644 --- a/src/python/gudhi/barycenter.py +++ b/src/python/gudhi/barycenter.py @@ -12,7 +12,7 @@ import ot import numpy as np import scipy.spatial.distance as sc -from gudhi.wasserstein import wasserstein_distance, _perstot +from gudhi.wasserstein import wasserstein_distance def _mean(x, m): -- cgit v1.2.3 From dae83f0907a5bd94cb483ad0f54755da2d49fb75 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 12:49:22 +0200 Subject: changed into import .barycenter for local import in wasserstein, and modified index to remove barycenter doc --- src/python/doc/index.rst | 4 ---- src/python/gudhi/wasserstein.py | 2 +- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index 96cd3513..0e484483 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -71,10 +71,6 @@ Wasserstein distance .. include:: wasserstein_distance_sum.inc -Barycenter -============ - -.. include:: barycenter_sum.inc Persistence representations =========================== diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 8f03039b..760eea8c 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -9,7 +9,7 @@ import numpy as np import scipy.spatial.distance as sc -import barycenter +import .barycenter try: import ot except ImportError: -- cgit v1.2.3 From a924e71d2f1a649ca389cfeceb678cc45aaf9fa7 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 12:55:51 +0200 Subject: micro modif changed a word to avoid repetition --- src/python/doc/wasserstein_distance_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 6de05afc..a077f9a4 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -112,7 +112,7 @@ to the Lloyd algorithm to estimate a solution to the k-means problem). The local minimum returned depends on the initialization of the barycenter. The combinatorial structure of the algorithm limits its -scaling on large scale problems (thousands of diagrams and of points +performances on large scale problems (thousands of diagrams and of points per diagram). .. figure:: -- cgit v1.2.3 From 1aaffd2e1fab45988d92f5e51a9d294696ff5492 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 13:18:42 +0200 Subject: changed import to import gudhi.barycenter as barycenter --- src/python/gudhi/wasserstein.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py index 760eea8c..51d1d83c 100644 --- a/src/python/gudhi/wasserstein.py +++ b/src/python/gudhi/wasserstein.py @@ -9,7 +9,7 @@ import numpy as np import scipy.spatial.distance as sc -import .barycenter +import gudhi.barycenter as barycenter try: import ot except ImportError: -- cgit v1.2.3 From 842475615841f864b4ce41a2a4b69f1e189a2946 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 15:02:32 +0200 Subject: created wasserstein repo --- src/python/gudhi/barycenter.py | 158 ---------------------------- src/python/gudhi/wasserstein.py | 125 ---------------------- src/python/gudhi/wasserstein/__init__.py | 1 + src/python/gudhi/wasserstein/barycenter.py | 158 ++++++++++++++++++++++++++++ src/python/gudhi/wasserstein/wasserstein.py | 125 ++++++++++++++++++++++ 5 files changed, 284 insertions(+), 283 deletions(-) delete mode 100644 src/python/gudhi/barycenter.py delete mode 100644 src/python/gudhi/wasserstein.py create mode 100644 src/python/gudhi/wasserstein/__init__.py create mode 100644 src/python/gudhi/wasserstein/barycenter.py create mode 100644 src/python/gudhi/wasserstein/wasserstein.py (limited to 'src/python') diff --git a/src/python/gudhi/barycenter.py b/src/python/gudhi/barycenter.py deleted file mode 100644 index 079bcc57..00000000 --- a/src/python/gudhi/barycenter.py +++ /dev/null @@ -1,158 +0,0 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. -# Author(s): Theo Lacombe -# -# Copyright (C) 2019 Inria -# -# Modification(s): -# - YYYY/MM Author: Description of the modification - - -import ot -import numpy as np -import scipy.spatial.distance as sc - -from gudhi.wasserstein import wasserstein_distance - - -def _mean(x, m): - ''' - :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} - :param m: total amount of points taken into account, - that is we have (m-k) copies of diagonal - :returns: the weighted mean of x with (m-k) copies of the diagonal - ''' - k = len(x) - if k > 0: - w = np.mean(x, axis=0) - w_delta = (w[0] + w[1]) / 2 * np.ones(2) - return (k * w + (m-k) * w_delta) / m - else: - return np.array([0, 0]) - - -def lagrangian_barycenter(pdiagset, init=None, verbose=False): - ''' - :param pdiagset: a list of size m containing numpy.array of shape (n x 2) - (n can variate), encoding a set of - persistence diagrams with only finite coordinates. - :param init: The initial value for barycenter estimate. - If None, init is made on a random diagram from the dataset. - Otherwise, it must be an int - (then we init with diagset[init]) - or a (n x 2) numpy.array enconding - a persistence diagram with n points. - :param verbose: if True, returns additional information about the - barycenter. - :returns: If not verbose (default), a numpy.array encoding - the barycenter estimate of pdiagset - (local minima of the energy function). - If pdiagset is empty, returns None. - If verbose, returns a couple (Y, log) - where Y is the barycenter estimate, - and log is a dict that contains additional informations: - - groupings, a list of list of pairs (i,j), - That is, G[k] = [(i, j) ...], where (i,j) indicates - that X[i] is matched to Y[j] - if i = -1 or j = -1, it means they - represent the diagonal. - - energy, a float representing the Frechet - energy value obtained, - that is the mean of squared distances - of observations to the output. - - nb_iter, integer representing the number of iterations - performed before convergence of the algorithm. - ''' - X = pdiagset # to shorten notations, not a copy - m = len(X) # number of diagrams we are averaging - if m == 0: - print("Warning: computing barycenter of empty diag set. Returns None") - return None - - # store the number of off-diagonal point for each of the X_i - nb_off_diag = np.array([len(X_i) for X_i in X]) - # Initialisation of barycenter - if init is None: - i0 = np.random.randint(m) # Index of first state for the barycenter - Y = X[i0].copy() - else: - if type(init)==int: - Y = X[init].copy() - else: - Y = init.copy() - - nb_iter = 0 - - converged = False # stoping criterion - while not converged: - nb_iter += 1 - K = len(Y) # current nb of points in Y (some might be on diagonal) - G = np.full((K, m), -1, dtype=int) # will store for each j, the (index) - # point matched in each other diagram - #(might be the diagonal). - # that is G[j, i] = k <=> y_j is matched to - # x_k in the diagram i-th diagram X[i] - updated_points = np.zeros((K, 2)) # will store the new positions of - # the points of Y. - # If points disappear, there thrown - # on [0,0] by default. - new_created_points = [] # will store potential new points. - - # Step 1 : compute optimal matching (Y, X_i) for each X_i - # and create new points in Y if needed - for i in range(m): - _, indices = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) - for y_j, x_i_j in indices: - if y_j >= 0: # we matched an off diagonal point to x_i_j... - if x_i_j >= 0: # ...which is also an off-diagonal point. - G[y_j, i] = x_i_j - else: # ...which is a diagonal point - G[y_j, i] = -1 # -1 stands for the diagonal (mask) - else: # We matched a diagonal point to x_i_j... - if x_i_j >= 0: # which is a off-diag point ! - # need to create new point in Y - new_y = _mean(np.array([X[i][x_i_j]]), m) - # Average this point with (m-1) copies of Delta - new_created_points.append(new_y) - - # Step 2 : Update current point position thanks to groupings computed - to_delete = [] - for j in range(K): - matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] - new_y_j = _mean(matched_points, m) - if not np.array_equal(new_y_j, np.array([0,0])): - updated_points[j] = new_y_j - else: # this points is no longer of any use. - to_delete.append(j) - # we remove the point to be deleted now. - updated_points = np.delete(updated_points, to_delete, axis=0) - - # we cannot converge if there have been new created points. - if new_created_points: - Y = np.concatenate((updated_points, new_created_points)) - else: - # Step 3 : we check convergence - if np.array_equal(updated_points, Y): - converged = True - Y = updated_points - - - if verbose: - groupings = [] - energy = 0 - log = {} - n_y = len(Y) - for i in range(m): - cost, edges = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) - groupings.append(edges) - energy += cost - log["groupings"] = groupings - energy = energy/m - print(energy) - log["energy"] = energy - log["nb_iter"] = nb_iter - - return Y, log - else: - return Y - diff --git a/src/python/gudhi/wasserstein.py b/src/python/gudhi/wasserstein.py deleted file mode 100644 index 51d1d83c..00000000 --- a/src/python/gudhi/wasserstein.py +++ /dev/null @@ -1,125 +0,0 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. -# Author(s): Theo Lacombe -# -# Copyright (C) 2019 Inria -# -# Modification(s): -# - YYYY/MM Author: Description of the modification - -import numpy as np -import scipy.spatial.distance as sc -import gudhi.barycenter as barycenter -try: - import ot -except ImportError: - print("POT (Python Optimal Transport) package is not installed. Try to run $ conda install -c conda-forge pot ; or $ pip install POT") - -def _proj_on_diag(X): - ''' - :param X: (n x 2) array encoding the points of a persistent diagram. - :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal - ''' - Z = (X[:,0] + X[:,1]) / 2. - return np.array([Z , Z]).T - - -def _build_dist_matrix(X, Y, order=2., internal_p=2.): - ''' - :param X: (n x 2) numpy.array encoding the (points of the) first diagram. - :param Y: (m x 2) numpy.array encoding the second diagram. - :param order: exponent for the Wasserstein metric. - :param internal_p: Ground metric (i.e. norm L^p). - :returns: (n+1) x (m+1) np.array encoding the cost matrix C. - For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], - while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) - and its orthogonal projection onto the diagonal. - note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). - ''' - Xdiag = _proj_on_diag(X) - Ydiag = _proj_on_diag(Y) - if np.isinf(internal_p): - C = sc.cdist(X,Y, metric='chebyshev')**order - Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order - Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order - else: - C = sc.cdist(X,Y, metric='minkowski', p=internal_p)**order - Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order - Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order - Cf = np.hstack((C, Cxd[:,None])) - Cdy = np.append(Cdy, 0) - - Cf = np.vstack((Cf, Cdy[None,:])) - - return Cf - - -def _perstot(X, order, internal_p): - ''' - :param X: (n x 2) numpy.array (points of a given diagram). - :param order: exponent for Wasserstein. Default value is 2. - :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). - :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). - ''' - Xdiag = _proj_on_diag(X) - return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) - - -def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): - ''' - :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points - (i.e. with infinite coordinate). - :param Y: (m x 2) numpy.array encoding the second diagram. - :param matching: if True, computes and returns the optimal matching between X and Y, encoded as - a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to - the j-th point in Y, with the convention (-1) represents the diagonal. - :param order: exponent for Wasserstein; Default value is 2. - :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); - Default value is 2 (Euclidean norm). - :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with - respect to the internal_p-norm as ground metric. - If matching is set to True, also returns the optimal matching between X and Y. - ''' - n = len(X) - m = len(Y) - - # handle empty diagrams - if X.size == 0: - if Y.size == 0: - if not matching: - return 0. - else: - return 0., np.array([]) - else: - if not matching: - return _perstot(Y, order, internal_p) - else: - return _perstot(Y, order, internal_p), np.array([[-1, j] for j in range(m)]) - elif Y.size == 0: - if not matching: - return _perstot(X, order, internal_p) - else: - return _perstot(X, order, internal_p), np.array([[i, -1] for i in range(n)]) - - M = _build_dist_matrix(X, Y, order=order, internal_p=internal_p) - a = np.ones(n+1) # weight vector of the input diagram. Uniform here. - a[-1] = m - b = np.ones(m+1) # weight vector of the input diagram. Uniform here. - b[-1] = n - - if matching: - P = ot.emd(a=a,b=b,M=M, numItermax=2000000) - ot_cost = np.sum(np.multiply(P,M)) - P[-1, -1] = 0 # Remove matching corresponding to the diagonal - match = np.argwhere(P) - # Now we turn to -1 points encoding the diagonal - match[:,0][match[:,0] >= n] = -1 - match[:,1][match[:,1] >= m] = -1 - return ot_cost ** (1./order) , match - - # Comptuation of the otcost using the ot.emd2 library. - # Note: it is the Wasserstein distance to the power q. - # The default numItermax=100000 is not sufficient for some examples with 5000 points, what is a good value? - ot_cost = ot.emd2(a, b, M, numItermax=2000000) - - return ot_cost ** (1./order) diff --git a/src/python/gudhi/wasserstein/__init__.py b/src/python/gudhi/wasserstein/__init__.py new file mode 100644 index 00000000..ed225ba4 --- /dev/null +++ b/src/python/gudhi/wasserstein/__init__.py @@ -0,0 +1 @@ +from .wasserstein import wasserstein_distance diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py new file mode 100644 index 00000000..079bcc57 --- /dev/null +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -0,0 +1,158 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Theo Lacombe +# +# Copyright (C) 2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + + +import ot +import numpy as np +import scipy.spatial.distance as sc + +from gudhi.wasserstein import wasserstein_distance + + +def _mean(x, m): + ''' + :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} + :param m: total amount of points taken into account, + that is we have (m-k) copies of diagonal + :returns: the weighted mean of x with (m-k) copies of the diagonal + ''' + k = len(x) + if k > 0: + w = np.mean(x, axis=0) + w_delta = (w[0] + w[1]) / 2 * np.ones(2) + return (k * w + (m-k) * w_delta) / m + else: + return np.array([0, 0]) + + +def lagrangian_barycenter(pdiagset, init=None, verbose=False): + ''' + :param pdiagset: a list of size m containing numpy.array of shape (n x 2) + (n can variate), encoding a set of + persistence diagrams with only finite coordinates. + :param init: The initial value for barycenter estimate. + If None, init is made on a random diagram from the dataset. + Otherwise, it must be an int + (then we init with diagset[init]) + or a (n x 2) numpy.array enconding + a persistence diagram with n points. + :param verbose: if True, returns additional information about the + barycenter. + :returns: If not verbose (default), a numpy.array encoding + the barycenter estimate of pdiagset + (local minima of the energy function). + If pdiagset is empty, returns None. + If verbose, returns a couple (Y, log) + where Y is the barycenter estimate, + and log is a dict that contains additional informations: + - groupings, a list of list of pairs (i,j), + That is, G[k] = [(i, j) ...], where (i,j) indicates + that X[i] is matched to Y[j] + if i = -1 or j = -1, it means they + represent the diagonal. + - energy, a float representing the Frechet + energy value obtained, + that is the mean of squared distances + of observations to the output. + - nb_iter, integer representing the number of iterations + performed before convergence of the algorithm. + ''' + X = pdiagset # to shorten notations, not a copy + m = len(X) # number of diagrams we are averaging + if m == 0: + print("Warning: computing barycenter of empty diag set. Returns None") + return None + + # store the number of off-diagonal point for each of the X_i + nb_off_diag = np.array([len(X_i) for X_i in X]) + # Initialisation of barycenter + if init is None: + i0 = np.random.randint(m) # Index of first state for the barycenter + Y = X[i0].copy() + else: + if type(init)==int: + Y = X[init].copy() + else: + Y = init.copy() + + nb_iter = 0 + + converged = False # stoping criterion + while not converged: + nb_iter += 1 + K = len(Y) # current nb of points in Y (some might be on diagonal) + G = np.full((K, m), -1, dtype=int) # will store for each j, the (index) + # point matched in each other diagram + #(might be the diagonal). + # that is G[j, i] = k <=> y_j is matched to + # x_k in the diagram i-th diagram X[i] + updated_points = np.zeros((K, 2)) # will store the new positions of + # the points of Y. + # If points disappear, there thrown + # on [0,0] by default. + new_created_points = [] # will store potential new points. + + # Step 1 : compute optimal matching (Y, X_i) for each X_i + # and create new points in Y if needed + for i in range(m): + _, indices = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) + for y_j, x_i_j in indices: + if y_j >= 0: # we matched an off diagonal point to x_i_j... + if x_i_j >= 0: # ...which is also an off-diagonal point. + G[y_j, i] = x_i_j + else: # ...which is a diagonal point + G[y_j, i] = -1 # -1 stands for the diagonal (mask) + else: # We matched a diagonal point to x_i_j... + if x_i_j >= 0: # which is a off-diag point ! + # need to create new point in Y + new_y = _mean(np.array([X[i][x_i_j]]), m) + # Average this point with (m-1) copies of Delta + new_created_points.append(new_y) + + # Step 2 : Update current point position thanks to groupings computed + to_delete = [] + for j in range(K): + matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] + new_y_j = _mean(matched_points, m) + if not np.array_equal(new_y_j, np.array([0,0])): + updated_points[j] = new_y_j + else: # this points is no longer of any use. + to_delete.append(j) + # we remove the point to be deleted now. + updated_points = np.delete(updated_points, to_delete, axis=0) + + # we cannot converge if there have been new created points. + if new_created_points: + Y = np.concatenate((updated_points, new_created_points)) + else: + # Step 3 : we check convergence + if np.array_equal(updated_points, Y): + converged = True + Y = updated_points + + + if verbose: + groupings = [] + energy = 0 + log = {} + n_y = len(Y) + for i in range(m): + cost, edges = wasserstein_distance(Y, X[i], matching=True, order=2., internal_p=2.) + groupings.append(edges) + energy += cost + log["groupings"] = groupings + energy = energy/m + print(energy) + log["energy"] = energy + log["nb_iter"] = nb_iter + + return Y, log + else: + return Y + diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py new file mode 100644 index 00000000..e1233eec --- /dev/null +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -0,0 +1,125 @@ +# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. +# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. +# Author(s): Theo Lacombe +# +# Copyright (C) 2019 Inria +# +# Modification(s): +# - YYYY/MM Author: Description of the modification + +import numpy as np +import scipy.spatial.distance as sc + +try: + import ot +except ImportError: + print("POT (Python Optimal Transport) package is not installed. Try to run $ conda install -c conda-forge pot ; or $ pip install POT") + +def _proj_on_diag(X): + ''' + :param X: (n x 2) array encoding the points of a persistent diagram. + :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal + ''' + Z = (X[:,0] + X[:,1]) / 2. + return np.array([Z , Z]).T + + +def _build_dist_matrix(X, Y, order=2., internal_p=2.): + ''' + :param X: (n x 2) numpy.array encoding the (points of the) first diagram. + :param Y: (m x 2) numpy.array encoding the second diagram. + :param order: exponent for the Wasserstein metric. + :param internal_p: Ground metric (i.e. norm L^p). + :returns: (n+1) x (m+1) np.array encoding the cost matrix C. + For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], + while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) + and its orthogonal projection onto the diagonal. + note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). + ''' + Xdiag = _proj_on_diag(X) + Ydiag = _proj_on_diag(Y) + if np.isinf(internal_p): + C = sc.cdist(X,Y, metric='chebyshev')**order + Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order + Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order + else: + C = sc.cdist(X,Y, metric='minkowski', p=internal_p)**order + Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order + Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order + Cf = np.hstack((C, Cxd[:,None])) + Cdy = np.append(Cdy, 0) + + Cf = np.vstack((Cf, Cdy[None,:])) + + return Cf + + +def _perstot(X, order, internal_p): + ''' + :param X: (n x 2) numpy.array (points of a given diagram). + :param order: exponent for Wasserstein. Default value is 2. + :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). + :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). + ''' + Xdiag = _proj_on_diag(X) + return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) + + +def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): + ''' + :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points + (i.e. with infinite coordinate). + :param Y: (m x 2) numpy.array encoding the second diagram. + :param matching: if True, computes and returns the optimal matching between X and Y, encoded as + a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to + the j-th point in Y, with the convention (-1) represents the diagonal. + :param order: exponent for Wasserstein; Default value is 2. + :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); + Default value is 2 (Euclidean norm). + :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with + respect to the internal_p-norm as ground metric. + If matching is set to True, also returns the optimal matching between X and Y. + ''' + n = len(X) + m = len(Y) + + # handle empty diagrams + if X.size == 0: + if Y.size == 0: + if not matching: + return 0. + else: + return 0., np.array([]) + else: + if not matching: + return _perstot(Y, order, internal_p) + else: + return _perstot(Y, order, internal_p), np.array([[-1, j] for j in range(m)]) + elif Y.size == 0: + if not matching: + return _perstot(X, order, internal_p) + else: + return _perstot(X, order, internal_p), np.array([[i, -1] for i in range(n)]) + + M = _build_dist_matrix(X, Y, order=order, internal_p=internal_p) + a = np.ones(n+1) # weight vector of the input diagram. Uniform here. + a[-1] = m + b = np.ones(m+1) # weight vector of the input diagram. Uniform here. + b[-1] = n + + if matching: + P = ot.emd(a=a,b=b,M=M, numItermax=2000000) + ot_cost = np.sum(np.multiply(P,M)) + P[-1, -1] = 0 # Remove matching corresponding to the diagonal + match = np.argwhere(P) + # Now we turn to -1 points encoding the diagonal + match[:,0][match[:,0] >= n] = -1 + match[:,1][match[:,1] >= m] = -1 + return ot_cost ** (1./order) , match + + # Comptuation of the otcost using the ot.emd2 library. + # Note: it is the Wasserstein distance to the power q. + # The default numItermax=100000 is not sufficient for some examples with 5000 points, what is a good value? + ot_cost = ot.emd2(a, b, M, numItermax=2000000) + + return ot_cost ** (1./order) -- cgit v1.2.3 From 266f1eb706ecf31733acbcdded3b04d8d270fb60 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 17:43:53 +0200 Subject: update CMakeLists to make things compatible with wasserstein/ repo --- src/python/CMakeLists.txt | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index b7d43bea..a91ca30a 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -56,7 +56,6 @@ if(PYTHONINTERP_FOUND) # Modules that should not be auto-imported in __init__.py set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'representations', ") set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'wasserstein', ") - set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'barycenter', ") set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'point_cloud', ") add_gudhi_debug_info("Python version ${PYTHON_VERSION_STRING}") @@ -217,8 +216,7 @@ if(PYTHONINTERP_FOUND) # Other .py files file(COPY "gudhi/persistence_graphical_tools.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") file(COPY "gudhi/representations" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi/") - file(COPY "gudhi/wasserstein.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") - file(COPY "gudhi/barycenter.py" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") + file(COPY "gudhi/wasserstein" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") file(COPY "gudhi/point_cloud" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/gudhi") add_custom_command( -- cgit v1.2.3 From af76331b5b4c709f46a3d705320bfedcf3a60924 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Tue, 31 Mar 2020 18:08:05 +0200 Subject: correction typo user.rst --- src/python/doc/wasserstein_distance_user.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index a077f9a4..c6d49db1 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -128,7 +128,7 @@ per diagram). Basic example ------------- -This example computes the Frechet mean (aka Wasserstein barycenter) between +This example estimates the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. It is initialized on the 4th diagram. As the algorithm is not convex, its output depends on the initialization and @@ -143,7 +143,7 @@ Note that persistence diagrams must be submitted as .. testcode:: - import gudhi.barycenter + from gudhi.wasserstein.barycenter import lagrangian_barycenter import numpy as np dg1 = np.array([[0.2, 0.5]]) @@ -151,7 +151,7 @@ Note that persistence diagrams must be submitted as dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) dg4 = np.array([]) pdiagset = [dg1, dg2, dg3, dg4] - bary = gudhi.wasserstein.barycenter.lagrangian_barycenter(pdiagset=pdiagset,init=3) + bary = lagrangian_barycenter(pdiagset=pdiagset,init=3) message = "Wasserstein barycenter estimated:" print(message) -- cgit v1.2.3 From cfcbe923f132a770363e6a240df8f6911cdd39e9 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Wed, 1 Apr 2020 10:34:48 +0200 Subject: improved doc, turns Basic examples as subsections using * --- src/python/doc/wasserstein_distance_sum.inc | 6 +++--- src/python/doc/wasserstein_distance_user.rst | 10 +++++----- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_sum.inc b/src/python/doc/wasserstein_distance_sum.inc index f10472bc..f9308e5e 100644 --- a/src/python/doc/wasserstein_distance_sum.inc +++ b/src/python/doc/wasserstein_distance_sum.inc @@ -4,10 +4,10 @@ +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | .. figure:: | The q-Wasserstein distance measures the similarity between two | :Author: Theo Lacombe | | ../../doc/Bottleneck_distance/perturb_pd.png | persistence diagrams using the sum of all edges lengths (instead of | | - | :figclass: align-center | the maximum). It allows to define sophisticated objects such as | :Introduced in: GUDHI 3.1.0 | + | :figclass: align-center | the maximum). It allows to define sophisticated objects such as | :Since: GUDHI 3.1.0 | | | barycenters of a family of persistence diagrams. | | - | Wasserstein distance is the q-th root of the sum of the | | :Copyright: MIT | - | edge lengths to the power q. | | | + | | | :License: MIT | + | | | | | | | :Requires: Python Optimal Transport (POT) :math:`\geq` 0.5.1 | +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ | * :doc:`wasserstein_distance_user` | | diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index c6d49db1..c5c250b5 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -9,7 +9,7 @@ Definition .. include:: wasserstein_distance_sum.inc -The q-Wasserstein distance is defined as the minimal value +The q-Wasserstein distance is defined as the minimal value achieved by a perfect matching between the points of the two diagrams (+ all diagonal points), where the value of a matching is defined as the q-th root of the sum of all edge lengths to the power q. Edge lengths @@ -32,7 +32,7 @@ Morozov, and Arnur Nigmetov. .. autofunction:: gudhi.hera.wasserstein_distance Basic example -------------- +************* This example computes the 1-Wasserstein distance from 2 persistence diagrams with Euclidean ground metric. Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. @@ -123,10 +123,10 @@ per diagram). diagrams. -.. autofunction:: gudhi.barycenter.lagrangian_barycenter +.. autofunction:: gudhi.wasserstein.barycenter.lagrangian_barycenter Basic example -------------- +************* This example estimates the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. @@ -135,7 +135,7 @@ As the algorithm is not convex, its output depends on the initialization and is only a local minimum of the objective function. Initialization can be either given as an integer (in which case the i-th diagram of the list is used as initial estimate) or as a diagram. -If None, it will randomly select one of the diagram of the list +If None, it will randomly select one of the diagrams of the list as initial estimate. Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. -- cgit v1.2.3 From c36080ab9e478cd0d44bfd8d5bb8f4726a8aa937 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Wed, 1 Apr 2020 20:24:01 +0200 Subject: improved doc readability --- src/python/gudhi/wasserstein/barycenter.py | 54 ++++++++++++++++-------------- 1 file changed, 28 insertions(+), 26 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index 079bcc57..fae6b68f 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -33,35 +33,37 @@ def _mean(x, m): def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' - :param pdiagset: a list of size m containing numpy.array of shape (n x 2) - (n can variate), encoding a set of + :param pdiagset: a list of ``numpy.array`` of shape `(n x 2)` + (`n` can variate), encoding a set of persistence diagrams with only finite coordinates. :param init: The initial value for barycenter estimate. - If None, init is made on a random diagram from the dataset. - Otherwise, it must be an int - (then we init with diagset[init]) - or a (n x 2) numpy.array enconding - a persistence diagram with n points. - :param verbose: if True, returns additional information about the + If ``None``, init is made on a random diagram from the dataset. + Otherwise, it can be an ``int`` + (then initialization is made on ``pdiagset[init]``) + or a `(n x 2)` ``numpy.array`` enconding + a persistence diagram with `n` points. + :type init: int, (n x 2) np.array + :param verbose: if ``True``, returns additional information about the barycenter. - :returns: If not verbose (default), a numpy.array encoding - the barycenter estimate of pdiagset - (local minima of the energy function). - If pdiagset is empty, returns None. - If verbose, returns a couple (Y, log) - where Y is the barycenter estimate, - and log is a dict that contains additional informations: - - groupings, a list of list of pairs (i,j), - That is, G[k] = [(i, j) ...], where (i,j) indicates - that X[i] is matched to Y[j] - if i = -1 or j = -1, it means they - represent the diagonal. - - energy, a float representing the Frechet - energy value obtained, - that is the mean of squared distances - of observations to the output. - - nb_iter, integer representing the number of iterations - performed before convergence of the algorithm. + :type verbose: boolean + :returns: If not verbose (default), a ``numpy.array`` encoding + the barycenter estimate of pdiagset + (local minimum of the energy function). + If ``pdiagset`` is empty, returns ``None``. + If verbose, returns a couple ``(Y, log)`` + where ``Y`` is the barycenter estimate, + and ``log`` is a ``dict`` that contains additional informations: + + - `"groupings"`, a list of list of pairs ``(i,j)``. + Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates + that ``pdiagset[k][i]`` is matched to ``Y[j]`` + if ``i = -1`` or ``j = -1``, it means they + represent the diagonal. + + - `"energy"`, ``float`` representing the Frechet energy value obtained. + It is the mean of squared distances of observations to the output. + + - `"nb_iter"`, ``int`` number of iterations performed before convergence of the algorithm. ''' X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging -- cgit v1.2.3 From 731358cbfe3880b02a58c70923b5a990ddff7644 Mon Sep 17 00:00:00 2001 From: tlacombe Date: Wed, 1 Apr 2020 20:27:27 +0200 Subject: improved doc, adding double quot for init --- src/python/gudhi/wasserstein/barycenter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index fae6b68f..e879b7dd 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -42,7 +42,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): (then initialization is made on ``pdiagset[init]``) or a `(n x 2)` ``numpy.array`` enconding a persistence diagram with `n` points. - :type init: int, (n x 2) np.array + :type init: ``int``, or (n x 2) ``np.array`` :param verbose: if ``True``, returns additional information about the barycenter. :type verbose: boolean -- cgit v1.2.3 From 4cfe8411f808f52bee0ba37e28fa9f6cc3519abb Mon Sep 17 00:00:00 2001 From: tlacombe Date: Fri, 3 Apr 2020 17:27:47 +0200 Subject: removed the print of energy in verbose mode, added by error --- src/python/gudhi/wasserstein/barycenter.py | 1 - 1 file changed, 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index e879b7dd..99f29a1e 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -150,7 +150,6 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): energy += cost log["groupings"] = groupings energy = energy/m - print(energy) log["energy"] = energy log["nb_iter"] = nb_iter -- cgit v1.2.3 From 6acbc89d185d1c537778fb2d4a8503bab61fca31 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 3 Apr 2020 21:04:52 +0200 Subject: Split compute_persistence from get_persistence. --- src/python/gudhi/cubical_complex.pyx | 6 +++-- src/python/gudhi/periodic_cubical_complex.pyx | 6 +++-- src/python/gudhi/simplex_tree.pxd | 3 ++- src/python/gudhi/simplex_tree.pyx | 6 +++-- .../include/Persistent_cohomology_interface.h | 29 ++++++++++++---------- 5 files changed, 30 insertions(+), 20 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index d5ad1266..ce844558 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -35,7 +35,8 @@ cdef extern from "Cubical_complex_interface.h" namespace "Gudhi": cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Cubical_complex_persistence_interface "Gudhi::Persistent_cohomology_interface>": Cubical_complex_persistence_interface(Bitmap_cubical_complex_base_interface * st, bool persistence_dim_max) - vector[pair[int, pair[double, double]]] get_persistence(int homology_coeff_field, double min_persistence) + void compute_persistence(int homology_coeff_field, double min_persistence) + vector[pair[int, pair[double, double]]] get_persistence() vector[int] betti_numbers() vector[int] persistent_betti_numbers(double from_value, double to_value) vector[pair[double,double]] intervals_in_dimension(int dimension) @@ -149,7 +150,8 @@ cdef class CubicalComplex: self.pcohptr = new Cubical_complex_persistence_interface(self.thisptr, True) cdef vector[pair[int, pair[double, double]]] persistence_result if self.pcohptr != NULL: - persistence_result = self.pcohptr.get_persistence(homology_coeff_field, min_persistence) + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + persistence_result = self.pcohptr.get_persistence() return persistence_result def betti_numbers(self): diff --git a/src/python/gudhi/periodic_cubical_complex.pyx b/src/python/gudhi/periodic_cubical_complex.pyx index fd08b976..ff5ef3bd 100644 --- a/src/python/gudhi/periodic_cubical_complex.pyx +++ b/src/python/gudhi/periodic_cubical_complex.pyx @@ -32,7 +32,8 @@ cdef extern from "Cubical_complex_interface.h" namespace "Gudhi": cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Periodic_cubical_complex_persistence_interface "Gudhi::Persistent_cohomology_interface>>": Periodic_cubical_complex_persistence_interface(Periodic_cubical_complex_base_interface * st, bool persistence_dim_max) - vector[pair[int, pair[double, double]]] get_persistence(int homology_coeff_field, double min_persistence) + void compute_persistence(int homology_coeff_field, double min_persistence) + vector[pair[int, pair[double, double]]] get_persistence() vector[int] betti_numbers() vector[int] persistent_betti_numbers(double from_value, double to_value) vector[pair[double,double]] intervals_in_dimension(int dimension) @@ -154,7 +155,8 @@ cdef class PeriodicCubicalComplex: self.pcohptr = new Periodic_cubical_complex_persistence_interface(self.thisptr, True) cdef vector[pair[int, pair[double, double]]] persistence_result if self.pcohptr != NULL: - persistence_result = self.pcohptr.get_persistence(homology_coeff_field, min_persistence) + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + persistence_result = self.pcohptr.get_persistence() return persistence_result def betti_numbers(self): diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 595f22bb..44040bcb 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -71,7 +71,8 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": Simplex_tree_persistence_interface(Simplex_tree_interface_full_featured * st, bool persistence_dim_max) - vector[pair[int, pair[double, double]]] get_persistence(int homology_coeff_field, double min_persistence) + void compute_persistence(int homology_coeff_field, double min_persistence) + vector[pair[int, pair[double, double]]] get_persistence() vector[int] betti_numbers() vector[int] persistent_betti_numbers(double from_value, double to_value) vector[pair[double,double]] intervals_in_dimension(int dimension) diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index cc3753e1..69e645b4 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -443,7 +443,8 @@ cdef class SimplexTree: if self.pcohptr != NULL: del self.pcohptr self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), False) - persistence_result = self.pcohptr.get_persistence(homology_coeff_field, -1.) + self.pcohptr.compute_persistence(homology_coeff_field, -1.) + persistence_result = self.pcohptr.get_persistence() return self.get_ptr().compute_extended_persistence_subdiagrams(persistence_result, min_persistence) @@ -470,7 +471,8 @@ cdef class SimplexTree: self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) cdef vector[pair[int, pair[double, double]]] persistence_result if self.pcohptr != NULL: - persistence_result = self.pcohptr.get_persistence(homology_coeff_field, min_persistence) + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + persistence_result = self.pcohptr.get_persistence() return persistence_result def betti_numbers(self): diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index 8c79e6f3..a29ebbee 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -23,6 +23,7 @@ template class Persistent_cohomology_interface : public persistent_cohomology::Persistent_cohomology { private: + typedef persistent_cohomology::Persistent_cohomology Base; /* * Compare two intervals by dimension, then by length. */ @@ -43,25 +44,28 @@ persistent_cohomology::Persistent_cohomology(*stptr), + : Base(*stptr), stptr_(stptr) { } Persistent_cohomology_interface(FilteredComplex* stptr, bool persistence_dim_max) - : persistent_cohomology::Persistent_cohomology(*stptr, persistence_dim_max), + : Base(*stptr, persistence_dim_max), stptr_(stptr) { } - std::vector>> get_persistence(int homology_coeff_field, - double min_persistence) { - persistent_cohomology::Persistent_cohomology::init_coefficients(homology_coeff_field); - persistent_cohomology::Persistent_cohomology::compute_persistent_cohomology(min_persistence); + void compute_persistence(int homology_coeff_field, double min_persistence) { + Base::init_coefficients(homology_coeff_field); + Base::compute_persistent_cohomology(min_persistence); + } + + void maybe_compute_persistence(int homology_coeff_field, double min_persistence) { + // Currently get_persistent_pairs safely returns an empty vector before compute_persistent_cohomology + if(Base::get_persistent_pairs().empty()) + compute_persistence(homology_coeff_field, min_persistence); + } + std::vector>> get_persistence() { // Custom sort and output persistence cmp_intervals_by_dim_then_length cmp(stptr_); - auto persistent_pairs = persistent_cohomology::Persistent_cohomology::get_persistent_pairs(); + auto persistent_pairs = Base::get_persistent_pairs(); std::sort(std::begin(persistent_pairs), std::end(persistent_pairs), cmp); std::vector>> persistence; @@ -74,8 +78,7 @@ persistent_cohomology::Persistent_cohomology, std::vector>> persistence_pairs() { - auto pairs = persistent_cohomology::Persistent_cohomology::get_persistent_pairs(); + auto pairs = Base::get_persistent_pairs(); std::vector, std::vector>> persistence_pairs; persistence_pairs.reserve(pairs.size()); -- cgit v1.2.3 From 7830d93607257fd75f09b371e88741a517347579 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 3 Apr 2020 21:11:57 +0200 Subject: Dead code --- src/python/include/Simplex_tree_interface.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'src/python') diff --git a/src/python/include/Simplex_tree_interface.h b/src/python/include/Simplex_tree_interface.h index 1a18aed6..27b123f8 100644 --- a/src/python/include/Simplex_tree_interface.h +++ b/src/python/include/Simplex_tree_interface.h @@ -16,8 +16,6 @@ #include #include -#include "Persistent_cohomology_interface.h" - #include #include #include // std::pair @@ -157,11 +155,6 @@ class Simplex_tree_interface : public Simplex_tree { return new_dgm; } - void create_persistence(Gudhi::Persistent_cohomology_interface* pcoh) { - Base::initialize_filtration(); - pcoh = new Gudhi::Persistent_cohomology_interface(*this); - } - // Iterator over the simplex tree Complex_simplex_iterator get_simplices_iterator_begin() { // this specific case works because the range is just a pair of iterators - won't work if range was a vector -- cgit v1.2.3 From b2cfc0691147ca122861bc423d41495c4b444dde Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 3 Apr 2020 21:27:01 +0200 Subject: Simplify some code --- src/python/gudhi/simplex_tree.pyx | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 69e645b4..d8bd0b79 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -413,7 +413,7 @@ cdef class SimplexTree: Note that this code creates an extra vertex internally, so you should make sure that the Simplex_tree does not contain a vertex with the largest possible value (i.e., 4294967295). """ - return self.get_ptr().compute_extended_filtration() + self.get_ptr().compute_extended_filtration() def extended_persistence(self, homology_coeff_field=11, min_persistence=0): """This function retrieves good values for extended persistence, and separate the diagrams @@ -469,11 +469,8 @@ cdef class SimplexTree: if self.pcohptr != NULL: del self.pcohptr self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) - cdef vector[pair[int, pair[double, double]]] persistence_result - if self.pcohptr != NULL: - self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) - persistence_result = self.pcohptr.get_persistence() - return persistence_result + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + return self.pcohptr.get_persistence() def betti_numbers(self): """This function returns the Betti numbers of the simplicial complex. -- cgit v1.2.3 From f0224ea1c97c7dcb32debeda176139ba10bd21e7 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 4 Apr 2020 05:39:19 +0200 Subject: Local bibliographies in sphinx --- src/python/doc/alpha_complex_user.rst | 2 +- src/python/doc/bottleneck_distance_user.rst | 7 +++++++ src/python/doc/cubical_complex_user.rst | 2 +- src/python/doc/index.rst | 2 +- src/python/doc/nerve_gic_complex_user.rst | 7 +++++++ src/python/doc/persistent_cohomology_user.rst | 2 +- src/python/doc/rips_complex_user.rst | 7 +++++++ src/python/doc/simplex_tree_user.rst | 7 +++++++ src/python/doc/tangential_complex_user.rst | 2 +- src/python/doc/wasserstein_distance_user.rst | 7 +++++++ src/python/doc/witness_complex_user.rst | 2 +- 11 files changed, 41 insertions(+), 6 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 60319e84..6e926fc8 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -207,5 +207,5 @@ CGAL citations ============== .. bibliography:: ../../biblio/how_to_cite_cgal.bib - :filter: docnames + :filter: docname in docnames :style: unsrt diff --git a/src/python/doc/bottleneck_distance_user.rst b/src/python/doc/bottleneck_distance_user.rst index 9435c7f1..95c4e575 100644 --- a/src/python/doc/bottleneck_distance_user.rst +++ b/src/python/doc/bottleneck_distance_user.rst @@ -65,3 +65,10 @@ The output is: Bottleneck distance approximation = 0.81 Bottleneck distance value = 0.75 + +Bibliography +============ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index 93ca6b24..94f59954 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -163,5 +163,5 @@ Bibliography ============ .. bibliography:: ../../biblio/bibliography.bib - :filter: docnames + :filter: docname in docnames :style: unsrt diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index 3387a64f..df1dff68 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -90,5 +90,5 @@ Bibliography ************ .. bibliography:: ../../biblio/bibliography.bib - :filter: docnames + :filter: docname in docnames :style: unsrt diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index 9101f45d..208031fb 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -313,3 +313,10 @@ the program outputs again SC.dot which gives the following visualization after u :alt: Visualization with neato Visualization with neato + +Bibliography +============ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index 5f931b3a..0a5be3a9 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -116,5 +116,5 @@ Bibliography ============ .. bibliography:: ../../biblio/bibliography.bib - :filter: docnames + :filter: docname in docnames :style: unsrt diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index 8efb12e6..325added 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -347,3 +347,10 @@ until dimension 1 - one skeleton graph in other words), the output is: points in the persistence diagram will be under the diagonal, and bottleneck distance and persistence graphical tool will not work properly, this is a known issue. + +Bibliography +============ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index 3df7617f..b0b7153e 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -66,3 +66,10 @@ The output is: ([1, 2], 4.0) ([1], 0.0) ([2], 4.0) + +Bibliography +============ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index 852cf5b6..0bcbc848 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -200,5 +200,5 @@ Bibliography ============ .. bibliography:: ../../biblio/bibliography.bib - :filter: docnames + :filter: docname in docnames :style: unsrt diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index a9b21fa5..9b94573e 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -84,3 +84,10 @@ The output is: point 1 in dgm1 is matched to point 2 in dgm2 point 2 in dgm1 is matched to the diagonal point 1 in dgm2 is matched to the diagonal + +Bibliography +============ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index 7087fa98..b932ed0d 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -131,5 +131,5 @@ Bibliography ============ .. bibliography:: ../../biblio/bibliography.bib - :filter: docnames + :filter: docname in docnames :style: unsrt -- cgit v1.2.3 From d9e6b4f51bc8517453653be2904ab6db9aaab85e Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 4 Apr 2020 06:01:59 +0200 Subject: sphinx label warnings --- src/python/doc/alpha_complex_user.rst | 1 + src/python/doc/bottleneck_distance_user.rst | 1 + src/python/doc/cubical_complex_user.rst | 1 + src/python/doc/index.rst | 1 + src/python/doc/nerve_gic_complex_user.rst | 1 + src/python/doc/persistent_cohomology_user.rst | 1 + src/python/doc/rips_complex_user.rst | 1 + src/python/doc/simplex_tree_user.rst | 1 + src/python/doc/tangential_complex_user.rst | 1 + src/python/doc/wasserstein_distance_user.rst | 1 + src/python/doc/witness_complex_user.rst | 1 + 11 files changed, 11 insertions(+) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 6e926fc8..e1903688 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -209,3 +209,4 @@ CGAL citations .. bibliography:: ../../biblio/how_to_cite_cgal.bib :filter: docname in docnames :style: unsrt + :labelprefix: A diff --git a/src/python/doc/bottleneck_distance_user.rst b/src/python/doc/bottleneck_distance_user.rst index 95c4e575..23a87c19 100644 --- a/src/python/doc/bottleneck_distance_user.rst +++ b/src/python/doc/bottleneck_distance_user.rst @@ -72,3 +72,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: B diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index 94f59954..cdc5b5dc 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -165,3 +165,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: CC diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index df1dff68..089efe23 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -92,3 +92,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: I diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index 208031fb..b022dca7 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -320,3 +320,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: N diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index 0a5be3a9..f97fc759 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -118,3 +118,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: PC diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index 325added..fb6e4b1b 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -354,3 +354,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: R diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index b0b7153e..5a97b3d7 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -73,3 +73,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: ST diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index 0bcbc848..6cdd6125 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -202,3 +202,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: TA diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 9b94573e..817e6981 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -91,3 +91,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: WA diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index b932ed0d..c258ad38 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -133,3 +133,4 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt + :labelprefix: WI -- cgit v1.2.3 From dc80ab48359521dac415292f4d2b1f496f326263 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 4 Apr 2020 06:05:57 +0200 Subject: Revert "sphinx label warnings" This reverts commit d9e6b4f51bc8517453653be2904ab6db9aaab85e. It was able to remove the warnings about duplicate labels, but then it shows [WA1] instead of [1] in the generated doc. And for things cited on multiple pages, it uses the same everywhere, so on a single page, you can have a mix of [I1], [WI2], etc. Not very pretty. --- src/python/doc/alpha_complex_user.rst | 1 - src/python/doc/bottleneck_distance_user.rst | 1 - src/python/doc/cubical_complex_user.rst | 1 - src/python/doc/index.rst | 1 - src/python/doc/nerve_gic_complex_user.rst | 1 - src/python/doc/persistent_cohomology_user.rst | 1 - src/python/doc/rips_complex_user.rst | 1 - src/python/doc/simplex_tree_user.rst | 1 - src/python/doc/tangential_complex_user.rst | 1 - src/python/doc/wasserstein_distance_user.rst | 1 - src/python/doc/witness_complex_user.rst | 1 - 11 files changed, 11 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index e1903688..6e926fc8 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -209,4 +209,3 @@ CGAL citations .. bibliography:: ../../biblio/how_to_cite_cgal.bib :filter: docname in docnames :style: unsrt - :labelprefix: A diff --git a/src/python/doc/bottleneck_distance_user.rst b/src/python/doc/bottleneck_distance_user.rst index 23a87c19..95c4e575 100644 --- a/src/python/doc/bottleneck_distance_user.rst +++ b/src/python/doc/bottleneck_distance_user.rst @@ -72,4 +72,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: B diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index cdc5b5dc..94f59954 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -165,4 +165,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: CC diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index 089efe23..df1dff68 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -92,4 +92,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: I diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index b022dca7..208031fb 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -320,4 +320,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: N diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index f97fc759..0a5be3a9 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -118,4 +118,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: PC diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index fb6e4b1b..325added 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -354,4 +354,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: R diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index 5a97b3d7..b0b7153e 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -73,4 +73,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: ST diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index 6cdd6125..0bcbc848 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -202,4 +202,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: TA diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 817e6981..9b94573e 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -91,4 +91,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: WA diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index c258ad38..b932ed0d 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -133,4 +133,3 @@ Bibliography .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames :style: unsrt - :labelprefix: WI -- cgit v1.2.3 From da3b4a79ca40d08ae5597341f4db2418f20fe3d2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 4 Apr 2020 12:52:52 +0200 Subject: Missing biblio in one file, change title level --- src/python/doc/alpha_complex_user.rst | 2 +- src/python/doc/bottleneck_distance_user.rst | 2 +- src/python/doc/cubical_complex_user.rst | 2 +- src/python/doc/nerve_gic_complex_ref.rst | 7 +++++++ src/python/doc/nerve_gic_complex_user.rst | 2 +- src/python/doc/persistent_cohomology_user.rst | 2 +- src/python/doc/rips_complex_user.rst | 2 +- src/python/doc/simplex_tree_user.rst | 2 +- src/python/doc/tangential_complex_user.rst | 2 +- src/python/doc/wasserstein_distance_user.rst | 2 +- src/python/doc/witness_complex_user.rst | 2 +- 11 files changed, 17 insertions(+), 10 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 6e926fc8..265a82d2 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -204,7 +204,7 @@ the program output is: [3, 6] -> 30.25 CGAL citations -============== +-------------- .. bibliography:: ../../biblio/how_to_cite_cgal.bib :filter: docname in docnames diff --git a/src/python/doc/bottleneck_distance_user.rst b/src/python/doc/bottleneck_distance_user.rst index 95c4e575..206fcb63 100644 --- a/src/python/doc/bottleneck_distance_user.rst +++ b/src/python/doc/bottleneck_distance_user.rst @@ -67,7 +67,7 @@ The output is: Bottleneck distance value = 0.75 Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index 94f59954..e8c94bf6 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -160,7 +160,7 @@ Examples. End user programs are available in python/example/ folder. Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/nerve_gic_complex_ref.rst b/src/python/doc/nerve_gic_complex_ref.rst index abde2e8c..6a81b7af 100644 --- a/src/python/doc/nerve_gic_complex_ref.rst +++ b/src/python/doc/nerve_gic_complex_ref.rst @@ -12,3 +12,10 @@ Cover complexes reference manual :show-inheritance: .. automethod:: gudhi.CoverComplex.__init__ + +Bibliography +------------ + +.. bibliography:: ../../biblio/bibliography.bib + :filter: docname in docnames + :style: unsrt diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index 208031fb..f709ce91 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -315,7 +315,7 @@ the program outputs again SC.dot which gives the following visualization after u Visualization with neato Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index 0a5be3a9..506fa3a7 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -113,7 +113,7 @@ We provide several example files: run these examples with -h for details on thei * :download:`tangential_complex_plain_homology_from_off_file_example.py <../example/tangential_complex_plain_homology_from_off_file_example.py>` Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index 325added..c4bbcfb6 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -349,7 +349,7 @@ until dimension 1 - one skeleton graph in other words), the output is: this is a known issue. Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index b0b7153e..1b272c35 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -68,7 +68,7 @@ The output is: ([2], 4.0) Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index 0bcbc848..cf8199cc 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -197,7 +197,7 @@ The output is: Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 9b94573e..2ae72351 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -86,7 +86,7 @@ The output is: point 1 in dgm2 is matched to the diagonal Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index b932ed0d..799f5444 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -128,7 +128,7 @@ Here is an example of constructing a strong witness complex filtration and compu * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` Bibliography -============ +------------ .. bibliography:: ../../biblio/bibliography.bib :filter: docname in docnames -- cgit v1.2.3 From 3ca13b31e5f48fbaef2ba7db980643716c18725c Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 5 Apr 2020 00:35:23 +0200 Subject: compute_persistence in python Also simplify references, and replace print with assert for errors --- src/python/gudhi/simplex_tree.pyx | 105 ++++++++++----------- .../include/Persistent_cohomology_interface.h | 13 +-- 2 files changed, 52 insertions(+), 66 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index d8bd0b79..c34a64e6 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -139,9 +139,9 @@ cdef class SimplexTree: This function is not constant time because it can recompute dimension if required (can be triggered by - :func:`remove_maximal_simplex()` + :func:`remove_maximal_simplex` or - :func:`prune_above_filtration()` + :func:`prune_above_filtration` methods). """ return self.get_ptr().dimension() @@ -166,9 +166,9 @@ cdef class SimplexTree: This function must be used with caution because it disables dimension recomputation when required (this recomputation can be triggered by - :func:`remove_maximal_simplex()` + :func:`remove_maximal_simplex` or - :func:`prune_above_filtration()` + :func:`prune_above_filtration` ). """ self.get_ptr().set_dimension(dimension) @@ -315,10 +315,10 @@ cdef class SimplexTree: The dimension of the simplicial complex may be lower after calling remove_maximal_simplex than it was before. However, - :func:`upper_bound_dimension()` + :func:`upper_bound_dimension` method will return the old value, which remains a valid upper bound. If you care, you can call - :func:`dimension()` + :func:`dimension` to recompute the exact dimension. """ self.get_ptr().remove_maximal_simplex(simplex) @@ -346,12 +346,12 @@ cdef class SimplexTree: Note that the dimension of the simplicial complex may be lower after calling - :func:`prune_above_filtration()` + :func:`prune_above_filtration` than it was before. However, - :func:`upper_bound_dimension()` + :func:`upper_bound_dimension` will return the old value, which remains a valid upper bound. If you care, you can call - :func:`dimension()` + :func:`dimension` method to recompute the exact dimension. """ return self.get_ptr().prune_above_filtration(filtration) @@ -405,7 +405,7 @@ cdef class SimplexTree: Note that after calling this function, the filtration values are actually modified within the Simplex_tree. - The function :func:`extended_persistence()` + The function :func:`extended_persistence` retrieves the original values. .. note:: @@ -427,11 +427,11 @@ cdef class SimplexTree: 0.0. Sets min_persistence to -1.0 to see all values. :type min_persistence: float. - :returns: A list of four persistence diagrams in the format described in :func:`persistence()`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See https://link.springer.com/article/10.1007/s10208-008-9027-z and/or section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. + :returns: A list of four persistence diagrams in the format described in :func:`persistence`. The first one is Ordinary, the second one is Relative, the third one is Extended+ and the fourth one is Extended-. See https://link.springer.com/article/10.1007/s10208-008-9027-z and/or section 2.2 in https://link.springer.com/article/10.1007/s10208-017-9370-z for a description of these subtypes. .. note:: - This function should be called only if :func:`extend_filtration()` has been called first! + This function should be called only if :func:`extend_filtration` has been called first! .. note:: @@ -466,11 +466,32 @@ cdef class SimplexTree: :returns: The persistence of the simplicial complex. :rtype: list of pairs(dimension, pair(birth, death)) """ + self.compute_persistence(homology_coeff_field, min_persistence, persistence_dim_max) + return self.pcohptr.get_persistence() + + def compute_persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): + """This function computes the persistence of the simplicial complex, so it can be accessed through + :func:`persistent_betti_numbers`, :func:`persistence_pairs`, etc. This function is equivalent to :func:`persistence` + when you do not want the list :func:`persistence` returns. + + :param homology_coeff_field: The homology coefficient field. Must be a + prime number. Default value is 11. + :type homology_coeff_field: int. + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Sets min_persistence to -1.0 to see all values. + :type min_persistence: float. + :param persistence_dim_max: If true, the persistent homology for the + maximal dimension in the complex is computed. If false, it is + ignored. Default is false. + :type persistence_dim_max: bool + :returns: Nothing. + """ if self.pcohptr != NULL: del self.pcohptr self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) - return self.pcohptr.get_persistence() def betti_numbers(self): """This function returns the Betti numbers of the simplicial complex. @@ -479,16 +500,11 @@ cdef class SimplexTree: :rtype: list of int :note: betti_numbers function requires - :func:`persistence()` + :func:`compute_persistence` function to be launched first. """ - cdef vector[int] bn_result - if self.pcohptr != NULL: - bn_result = self.pcohptr.betti_numbers() - else: - print("betti_numbers function requires persistence function" - " to be launched first.") - return bn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before betti_numbers()" + return self.pcohptr.betti_numbers() def persistent_betti_numbers(self, from_value, to_value): """This function returns the persistent Betti numbers of the @@ -505,16 +521,11 @@ cdef class SimplexTree: :rtype: list of int :note: persistent_betti_numbers function requires - :func:`persistence()` + :func:`compute_persistence` function to be launched first. """ - cdef vector[int] pbn_result - if self.pcohptr != NULL: - pbn_result = self.pcohptr.persistent_betti_numbers(from_value, to_value) - else: - print("persistent_betti_numbers function requires persistence function" - " to be launched first.") - return pbn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before persistent_betti_numbers()" + return self.pcohptr.persistent_betti_numbers(from_value, to_value) def persistence_intervals_in_dimension(self, dimension): """This function returns the persistence intervals of the simplicial @@ -526,16 +537,11 @@ cdef class SimplexTree: :rtype: numpy array of dimension 2 :note: intervals_in_dim function requires - :func:`persistence()` + :func:`compute_persistence` function to be launched first. """ - cdef vector[pair[double,double]] intervals_result - if self.pcohptr != NULL: - intervals_result = self.pcohptr.intervals_in_dimension(dimension) - else: - print("intervals_in_dim function requires persistence function" - " to be launched first.") - return np_array(intervals_result) + assert self.pcohptr != NULL, "compute_persistence() must be called before persistence_intervals_in_dimension()" + return np_array(self.pcohptr.intervals_in_dimension(dimension)) def persistence_pairs(self): """This function returns a list of persistence birth and death simplices pairs. @@ -544,18 +550,13 @@ cdef class SimplexTree: :rtype: list of pair of list of int :note: persistence_pairs function requires - :func:`persistence()` + :func:`compute_persistence` function to be launched first. """ - cdef vector[pair[vector[int],vector[int]]] persistence_pairs_result - if self.pcohptr != NULL: - persistence_pairs_result = self.pcohptr.persistence_pairs() - else: - print("persistence_pairs function requires persistence function" - " to be launched first.") - return persistence_pairs_result + assert self.pcohptr != NULL, "compute_persistence() must be called before persistence_pairs()" + return self.pcohptr.persistence_pairs() - def write_persistence_diagram(self, persistence_file=''): + def write_persistence_diagram(self, persistence_file): """This function writes the persistence intervals of the simplicial complex in a user given file name. @@ -563,14 +564,8 @@ cdef class SimplexTree: :type persistence_file: string. :note: intervals_in_dim function requires - :func:`persistence()` + :func:`compute_persistence` function to be launched first. """ - if self.pcohptr != NULL: - if persistence_file != '': - self.pcohptr.write_output_diagram(persistence_file.encode('utf-8')) - else: - print("persistence_file must be specified") - else: - print("intervals_in_dim function requires persistence function" - " to be launched first.") + assert self.pcohptr != NULL, "compute_persistence() must be called before write_persistence_diagram()" + self.pcohptr.write_output_diagram(persistence_file.encode('utf-8')) diff --git a/src/python/include/Persistent_cohomology_interface.h b/src/python/include/Persistent_cohomology_interface.h index a29ebbee..e2b69a52 100644 --- a/src/python/include/Persistent_cohomology_interface.h +++ b/src/python/include/Persistent_cohomology_interface.h @@ -43,25 +43,16 @@ persistent_cohomology::Persistent_cohomology>> get_persistence() { // Custom sort and output persistence cmp_intervals_by_dim_then_length cmp(stptr_); -- cgit v1.2.3 From 73a40006dad55b0a9ce6ca270e566ce91efe6af4 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 5 Apr 2020 12:27:15 +0200 Subject: Proper exception in write_output_diagram --- src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h | 1 + src/python/gudhi/simplex_tree.pxd | 2 +- src/python/gudhi/simplex_tree.pyx | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h index ca4bc10d..5e41edb4 100644 --- a/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h +++ b/src/Persistent_cohomology/include/gudhi/Persistent_cohomology.h @@ -571,6 +571,7 @@ class Persistent_cohomology { void write_output_diagram(std::string diagram_name) { std::ofstream diagram_out(diagram_name.c_str()); + diagram_out.exceptions(diagram_out.failbit); cmp_intervals_by_length cmp(cpx_); std::sort(std::begin(persistent_pairs_), std::end(persistent_pairs_), cmp); bool has_infinity = std::numeric_limits::has_infinity; diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 44040bcb..c46b36ba 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -76,5 +76,5 @@ cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": vector[int] betti_numbers() vector[int] persistent_betti_numbers(double from_value, double to_value) vector[pair[double,double]] intervals_in_dimension(int dimension) - void write_output_diagram(string diagram_file_name) + void write_output_diagram(string diagram_file_name) except + vector[pair[vector[int], vector[int]]] persistence_pairs() diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index c34a64e6..7728ebfc 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -449,7 +449,7 @@ cdef class SimplexTree: def persistence(self, homology_coeff_field=11, min_persistence=0, persistence_dim_max = False): - """This function returns the persistence of the simplicial complex. + """This function computes and returns the persistence of the simplicial complex. :param homology_coeff_field: The homology coefficient field. Must be a prime number. Default value is 11. -- cgit v1.2.3 From 5eaca3ed69c564a6f44e6ff21ac33e2cc576bafa Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 6 Apr 2020 15:58:10 +0200 Subject: compute_persistence for cubical --- src/python/gudhi/cubical_complex.pyx | 63 ++++++++++++++------------ src/python/gudhi/periodic_cubical_complex.pyx | 65 +++++++++++++++------------ 2 files changed, 71 insertions(+), 57 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/cubical_complex.pyx b/src/python/gudhi/cubical_complex.pyx index ce844558..007abcb6 100644 --- a/src/python/gudhi/cubical_complex.pyx +++ b/src/python/gudhi/cubical_complex.pyx @@ -130,8 +130,31 @@ cdef class CubicalComplex: """ return self.thisptr.dimension() + def compute_persistence(self, homology_coeff_field=11, min_persistence=0): + """This function computes the persistence of the complex, so it can be + accessed through :func:`persistent_betti_numbers`, + :func:`persistence_intervals_in_dimension`, etc. This function is + equivalent to :func:`persistence` when you do not want the list + :func:`persistence` returns. + + :param homology_coeff_field: The homology coefficient field. Must be a + prime number + :type homology_coeff_field: int. + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Sets min_persistence to -1.0 to see all values. + :type min_persistence: float. + :returns: Nothing. + """ + if self.pcohptr != NULL: + del self.pcohptr + assert self.__is_defined() + self.pcohptr = new Cubical_complex_persistence_interface(self.thisptr, True) + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + def persistence(self, homology_coeff_field=11, min_persistence=0): - """This function returns the persistence of the complex. + """This function computes and returns the persistence of the complex. :param homology_coeff_field: The homology coefficient field. Must be a prime number @@ -144,31 +167,22 @@ cdef class CubicalComplex: :returns: list of pairs(dimension, pair(birth, death)) -- the persistence of the complex. """ - if self.pcohptr != NULL: - del self.pcohptr - if self.thisptr != NULL: - self.pcohptr = new Cubical_complex_persistence_interface(self.thisptr, True) - cdef vector[pair[int, pair[double, double]]] persistence_result - if self.pcohptr != NULL: - self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) - persistence_result = self.pcohptr.get_persistence() - return persistence_result + self.compute_persistence(homology_coeff_field, min_persistence) + return self.pcohptr.get_persistence() def betti_numbers(self): """This function returns the Betti numbers of the complex. :returns: list of int -- The Betti numbers ([B0, B1, ..., Bn]). - :note: betti_numbers function requires persistence function to be + :note: betti_numbers function requires :func:`compute_persistence` function to be launched first. :note: betti_numbers function always returns [1, 0, 0, ...] as infinity filtration cubes are not removed from the complex. """ - cdef vector[int] bn_result - if self.pcohptr != NULL: - bn_result = self.pcohptr.betti_numbers() - return bn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before betti_numbers()" + return self.pcohptr.betti_numbers() def persistent_betti_numbers(self, from_value, to_value): """This function returns the persistent Betti numbers of the complex. @@ -183,13 +197,11 @@ cdef class CubicalComplex: :returns: list of int -- The persistent Betti numbers ([B0, B1, ..., Bn]). - :note: persistent_betti_numbers function requires persistence + :note: persistent_betti_numbers function requires :func:`compute_persistence` function to be launched first. """ - cdef vector[int] pbn_result - if self.pcohptr != NULL: - pbn_result = self.pcohptr.persistent_betti_numbers(from_value, to_value) - return pbn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before persistent_betti_numbers()" + return self.pcohptr.persistent_betti_numbers(from_value, to_value) def persistence_intervals_in_dimension(self, dimension): """This function returns the persistence intervals of the complex in a @@ -200,13 +212,8 @@ cdef class CubicalComplex: :returns: The persistence intervals. :rtype: numpy array of dimension 2 - :note: intervals_in_dim function requires persistence function to be + :note: intervals_in_dim function requires :func:`compute_persistence` function to be launched first. """ - cdef vector[pair[double,double]] intervals_result - if self.pcohptr != NULL: - intervals_result = self.pcohptr.intervals_in_dimension(dimension) - else: - print("intervals_in_dim function requires persistence function" - " to be launched first.", file=sys.stderr) - return np.array(intervals_result) + assert self.pcohptr != NULL, "compute_persistence() must be called before persistence_intervals_in_dimension()" + return np.array(self.pcohptr.intervals_in_dimension(dimension)) diff --git a/src/python/gudhi/periodic_cubical_complex.pyx b/src/python/gudhi/periodic_cubical_complex.pyx index ff5ef3bd..246a3a02 100644 --- a/src/python/gudhi/periodic_cubical_complex.pyx +++ b/src/python/gudhi/periodic_cubical_complex.pyx @@ -135,8 +135,31 @@ cdef class PeriodicCubicalComplex: """ return self.thisptr.dimension() + def compute_persistence(self, homology_coeff_field=11, min_persistence=0): + """This function computes the persistence of the complex, so it can be + accessed through :func:`persistent_betti_numbers`, + :func:`persistence_intervals_in_dimension`, etc. This function is + equivalent to :func:`persistence` when you do not want the list + :func:`persistence` returns. + + :param homology_coeff_field: The homology coefficient field. Must be a + prime number + :type homology_coeff_field: int. + :param min_persistence: The minimum persistence value to take into + account (strictly greater than min_persistence). Default value is + 0.0. + Sets min_persistence to -1.0 to see all values. + :type min_persistence: float. + :returns: Nothing. + """ + if self.pcohptr != NULL: + del self.pcohptr + assert self.__is_defined() + self.pcohptr = new Periodic_cubical_complex_persistence_interface(self.thisptr, True) + self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + def persistence(self, homology_coeff_field=11, min_persistence=0): - """This function returns the persistence of the complex. + """This function computes and returns the persistence of the complex. :param homology_coeff_field: The homology coefficient field. Must be a prime number @@ -149,31 +172,22 @@ cdef class PeriodicCubicalComplex: :returns: list of pairs(dimension, pair(birth, death)) -- the persistence of the complex. """ - if self.pcohptr != NULL: - del self.pcohptr - if self.thisptr != NULL: - self.pcohptr = new Periodic_cubical_complex_persistence_interface(self.thisptr, True) - cdef vector[pair[int, pair[double, double]]] persistence_result - if self.pcohptr != NULL: - self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) - persistence_result = self.pcohptr.get_persistence() - return persistence_result + self.compute_persistence(homology_coeff_field, min_persistence) + return self.pcohptr.get_persistence() def betti_numbers(self): """This function returns the Betti numbers of the complex. :returns: list of int -- The Betti numbers ([B0, B1, ..., Bn]). - :note: betti_numbers function requires persistence function to be + :note: betti_numbers function requires :func:`compute_persistence` function to be launched first. - :note: betti_numbers function always returns [1, 0, 0, ...] as infinity + :note: This function always returns the Betti numbers of a torus as infinity filtration cubes are not removed from the complex. """ - cdef vector[int] bn_result - if self.pcohptr != NULL: - bn_result = self.pcohptr.betti_numbers() - return bn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before betti_numbers()" + return self.pcohptr.betti_numbers() def persistent_betti_numbers(self, from_value, to_value): """This function returns the persistent Betti numbers of the complex. @@ -188,13 +202,11 @@ cdef class PeriodicCubicalComplex: :returns: list of int -- The persistent Betti numbers ([B0, B1, ..., Bn]). - :note: persistent_betti_numbers function requires persistence + :note: persistent_betti_numbers function requires :func:`compute_persistence` function to be launched first. """ - cdef vector[int] pbn_result - if self.pcohptr != NULL: - pbn_result = self.pcohptr.persistent_betti_numbers(from_value, to_value) - return pbn_result + assert self.pcohptr != NULL, "compute_persistence() must be called before persistent_betti_numbers()" + return self.pcohptr.persistent_betti_numbers(from_value, to_value) def persistence_intervals_in_dimension(self, dimension): """This function returns the persistence intervals of the complex in a @@ -205,13 +217,8 @@ cdef class PeriodicCubicalComplex: :returns: The persistence intervals. :rtype: numpy array of dimension 2 - :note: intervals_in_dim function requires persistence function to be + :note: intervals_in_dim function requires :func:`compute_persistence` function to be launched first. """ - cdef vector[pair[double,double]] intervals_result - if self.pcohptr != NULL: - intervals_result = self.pcohptr.intervals_in_dimension(dimension) - else: - print("intervals_in_dim function requires persistence function" - " to be launched first.", file=sys.stderr) - return np.array(intervals_result) + assert self.pcohptr != NULL, "compute_persistence() must be called before persistence_intervals_in_dimension()" + return np.array(self.pcohptr.intervals_in_dimension(dimension)) -- cgit v1.2.3 From 173506323471cf5175ea2b340abec63968c5cd5f Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 6 Apr 2020 16:51:32 +0200 Subject: Use compute_persistence in an example --- .../example/alpha_rips_persistence_bottleneck_distance.py | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/example/alpha_rips_persistence_bottleneck_distance.py b/src/python/example/alpha_rips_persistence_bottleneck_distance.py index f156826d..3e12b0d5 100755 --- a/src/python/example/alpha_rips_persistence_bottleneck_distance.py +++ b/src/python/example/alpha_rips_persistence_bottleneck_distance.py @@ -5,6 +5,7 @@ import argparse import math import errno import os +import numpy as np """ This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. @@ -56,7 +57,7 @@ with open(args.file, "r") as f: message = "Number of simplices=" + repr(rips_stree.num_simplices()) print(message) - rips_diag = rips_stree.persistence() + rips_stree.compute_persistence() print("##############################################################") print("AlphaComplex creation from points read in a OFF file") @@ -72,18 +73,13 @@ with open(args.file, "r") as f: message = "Number of simplices=" + repr(alpha_stree.num_simplices()) print(message) - alpha_diag = alpha_stree.persistence() + alpha_stree.compute_persistence() max_b_distance = 0.0 for dim in range(args.max_dimension): # Alpha persistence values needs to be transform because filtration # values are alpha square values - funcs = [math.sqrt, math.sqrt] - alpha_intervals = [] - for interval in alpha_stree.persistence_intervals_in_dimension(dim): - alpha_intervals.append( - map(lambda func, value: func(value), funcs, interval) - ) + alpha_intervals = np.sqrt(alpha_stree.persistence_intervals_in_dimension(dim)) rips_intervals = rips_stree.persistence_intervals_in_dimension(dim) bottleneck_distance = gudhi.bottleneck_distance( -- cgit v1.2.3 From dd96965e521313b6210391f511c82cced9b2a950 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 6 Apr 2020 19:37:58 +0200 Subject: Remove trailing whitespace --- src/python/doc/wasserstein_distance_user.rst | 72 +++++++++++++------------- src/python/gudhi/wasserstein/barycenter.py | 42 +++++++-------- src/python/gudhi/wasserstein/wasserstein.py | 14 ++--- src/python/test/test_wasserstein_barycenter.py | 6 +-- src/python/test/test_wasserstein_distance.py | 2 +- 5 files changed, 68 insertions(+), 68 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index b821b6fa..c24da74d 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -10,10 +10,10 @@ Definition .. include:: wasserstein_distance_sum.inc The q-Wasserstein distance is defined as the minimal value achieved -by a perfect matching between the points of the two diagrams (+ all -diagonal points), where the value of a matching is defined as the +by a perfect matching between the points of the two diagrams (+ all +diagonal points), where the value of a matching is defined as the q-th root of the sum of all edge lengths to the power q. Edge lengths -are measured in norm p, for :math:`1 \leq p \leq \infty`. +are measured in norm p, for :math:`1 \leq p \leq \infty`. Distance Functions ------------------ @@ -54,9 +54,9 @@ The output is: Wasserstein distance value = 1.45 -We can also have access to the optimal matching by letting `matching=True`. +We can also have access to the optimal matching by letting `matching=True`. It is encoded as a list of indices (i,j), meaning that the i-th point in X -is mapped to the j-th point in Y. +is mapped to the j-th point in Y. An index of -1 represents the diagonal. .. testcode:: @@ -84,7 +84,7 @@ An index of -1 represents the diagonal. The output is: .. testoutput:: - + Wasserstein distance value = 2.15 point 0 in dgm1 is matched to point 0 in dgm2 point 1 in dgm1 is matched to point 2 in dgm2 @@ -94,32 +94,32 @@ The output is: Barycenters ----------- -A Frechet mean (or barycenter) is a generalization of the arithmetic -mean in a non linear space such as the one of persistence diagrams. -Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is -defined as a minimizer of the variance functional, that is of -:math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. -where :math:`d_2` denotes the Wasserstein-2 distance between -persistence diagrams. -It is known to exist and is generically unique. However, an exact -computation is in general untractable. Current implementation -available is based on (Turner et al., 2014), +A Frechet mean (or barycenter) is a generalization of the arithmetic +mean in a non linear space such as the one of persistence diagrams. +Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is +defined as a minimizer of the variance functional, that is of +:math:`\mu \mapsto \sum_{i=1}^n d_2(\mu,\mu_i)^2`. +where :math:`d_2` denotes the Wasserstein-2 distance between +persistence diagrams. +It is known to exist and is generically unique. However, an exact +computation is in general untractable. Current implementation +available is based on (Turner et al., 2014), :cite:`turner2014frechet` -and uses an EM-scheme to -provide a local minimum of the variance functional (somewhat similar -to the Lloyd algorithm to estimate a solution to the k-means +and uses an EM-scheme to +provide a local minimum of the variance functional (somewhat similar +to the Lloyd algorithm to estimate a solution to the k-means problem). The local minimum returned depends on the initialization of -the barycenter. -The combinatorial structure of the algorithm limits its -performances on large scale problems (thousands of diagrams and of points -per diagram). +the barycenter. +The combinatorial structure of the algorithm limits its +performances on large scale problems (thousands of diagrams and of points +per diagram). + +.. figure:: + ./img/barycenter.png + :figclass: align-center -.. figure:: - ./img/barycenter.png - :figclass: align-center - - Illustration of Frechet mean between persistence - diagrams. + Illustration of Frechet mean between persistence + diagrams. .. autofunction:: gudhi.wasserstein.barycenter.lagrangian_barycenter @@ -127,16 +127,16 @@ per diagram). Basic example ************* -This example estimates the Frechet mean (aka Wasserstein barycenter) between +This example estimates the Frechet mean (aka Wasserstein barycenter) between four persistence diagrams. It is initialized on the 4th diagram. -As the algorithm is not convex, its output depends on the initialization and +As the algorithm is not convex, its output depends on the initialization and is only a local minimum of the objective function. -Initialization can be either given as an integer (in which case the i-th -diagram of the list is used as initial estimate) or as a diagram. -If None, it will randomly select one of the diagrams of the list +Initialization can be either given as an integer (in which case the i-th +diagram of the list is used as initial estimate) or as a diagram. +If None, it will randomly select one of the diagrams of the list as initial estimate. -Note that persistence diagrams must be submitted as +Note that persistence diagrams must be submitted as (n x 2) numpy arrays and must not contain inf values. @@ -152,7 +152,7 @@ Note that persistence diagrams must be submitted as pdiagset = [dg1, dg2, dg3, dg4] bary = lagrangian_barycenter(pdiagset=pdiagset,init=3) - message = "Wasserstein barycenter estimated:" + message = "Wasserstein barycenter estimated:" print(message) print(bary) diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index 99f29a1e..de7aea81 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -18,7 +18,7 @@ from gudhi.wasserstein import wasserstein_distance def _mean(x, m): ''' :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} - :param m: total amount of points taken into account, + :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal :returns: the weighted mean of x with (m-k) copies of the diagonal ''' @@ -33,14 +33,14 @@ def _mean(x, m): def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' - :param pdiagset: a list of ``numpy.array`` of shape `(n x 2)` - (`n` can variate), encoding a set of - persistence diagrams with only finite coordinates. - :param init: The initial value for barycenter estimate. - If ``None``, init is made on a random diagram from the dataset. - Otherwise, it can be an ``int`` + :param pdiagset: a list of ``numpy.array`` of shape `(n x 2)` + (`n` can variate), encoding a set of + persistence diagrams with only finite coordinates. + :param init: The initial value for barycenter estimate. + If ``None``, init is made on a random diagram from the dataset. + Otherwise, it can be an ``int`` (then initialization is made on ``pdiagset[init]``) - or a `(n x 2)` ``numpy.array`` enconding + or a `(n x 2)` ``numpy.array`` enconding a persistence diagram with `n` points. :type init: ``int``, or (n x 2) ``np.array`` :param verbose: if ``True``, returns additional information about the @@ -48,16 +48,16 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): :type verbose: boolean :returns: If not verbose (default), a ``numpy.array`` encoding the barycenter estimate of pdiagset - (local minimum of the energy function). + (local minimum of the energy function). If ``pdiagset`` is empty, returns ``None``. If verbose, returns a couple ``(Y, log)`` where ``Y`` is the barycenter estimate, and ``log`` is a ``dict`` that contains additional informations: - `"groupings"`, a list of list of pairs ``(i,j)``. - Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates + Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates that ``pdiagset[k][i]`` is matched to ``Y[j]`` - if ``i = -1`` or ``j = -1``, it means they + if ``i = -1`` or ``j = -1``, it means they represent the diagonal. - `"energy"`, ``float`` representing the Frechet energy value obtained. @@ -70,13 +70,13 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): if m == 0: print("Warning: computing barycenter of empty diag set. Returns None") return None - + # store the number of off-diagonal point for each of the X_i - nb_off_diag = np.array([len(X_i) for X_i in X]) + nb_off_diag = np.array([len(X_i) for X_i in X]) # Initialisation of barycenter if init is None: i0 = np.random.randint(m) # Index of first state for the barycenter - Y = X[i0].copy() + Y = X[i0].copy() else: if type(init)==int: Y = X[init].copy() @@ -90,8 +90,8 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): nb_iter += 1 K = len(Y) # current nb of points in Y (some might be on diagonal) G = np.full((K, m), -1, dtype=int) # will store for each j, the (index) - # point matched in each other diagram - #(might be the diagonal). + # point matched in each other diagram + #(might be the diagonal). # that is G[j, i] = k <=> y_j is matched to # x_k in the diagram i-th diagram X[i] updated_points = np.zeros((K, 2)) # will store the new positions of @@ -111,7 +111,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): else: # ...which is a diagonal point G[y_j, i] = -1 # -1 stands for the diagonal (mask) else: # We matched a diagonal point to x_i_j... - if x_i_j >= 0: # which is a off-diag point ! + if x_i_j >= 0: # which is a off-diag point ! # need to create new point in Y new_y = _mean(np.array([X[i][x_i_j]]), m) # Average this point with (m-1) copies of Delta @@ -123,19 +123,19 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): matched_points = [X[i][G[j, i]] for i in range(m) if G[j, i] > -1] new_y_j = _mean(matched_points, m) if not np.array_equal(new_y_j, np.array([0,0])): - updated_points[j] = new_y_j + updated_points[j] = new_y_j else: # this points is no longer of any use. to_delete.append(j) # we remove the point to be deleted now. - updated_points = np.delete(updated_points, to_delete, axis=0) + updated_points = np.delete(updated_points, to_delete, axis=0) # we cannot converge if there have been new created points. - if new_created_points: + if new_created_points: Y = np.concatenate((updated_points, new_created_points)) else: # Step 3 : we check convergence if np.array_equal(updated_points, Y): - converged = True + converged = True Y = updated_points diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index e1233eec..35315939 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -30,9 +30,9 @@ def _build_dist_matrix(X, Y, order=2., internal_p=2.): :param Y: (m x 2) numpy.array encoding the second diagram. :param order: exponent for the Wasserstein metric. :param internal_p: Ground metric (i.e. norm L^p). - :returns: (n+1) x (m+1) np.array encoding the cost matrix C. - For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], - while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) + :returns: (n+1) x (m+1) np.array encoding the cost matrix C. + For 0 <= i < n, 0 <= j < m, C[i,j] encodes the distance between X[i] and Y[j], + while C[i, m] (resp. C[n, j]) encodes the distance (to the p) between X[i] (resp Y[j]) and its orthogonal projection onto the diagonal. note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). ''' @@ -59,7 +59,7 @@ def _perstot(X, order, internal_p): :param X: (n x 2) numpy.array (points of a given diagram). :param order: exponent for Wasserstein. Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). - :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). + :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). ''' Xdiag = _proj_on_diag(X) return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) @@ -67,16 +67,16 @@ def _perstot(X, order, internal_p): def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): ''' - :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points + :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). :param Y: (m x 2) numpy.array encoding the second diagram. :param matching: if True, computes and returns the optimal matching between X and Y, encoded as a (n x 2) np.array [...[i,j]...], meaning the i-th point in X is matched to the j-th point in Y, with the convention (-1) represents the diagonal. :param order: exponent for Wasserstein; Default value is 2. - :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); + :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). - :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with + :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with respect to the internal_p-norm as ground metric. If matching is set to True, also returns the optimal matching between X and Y. ''' diff --git a/src/python/test/test_wasserstein_barycenter.py b/src/python/test/test_wasserstein_barycenter.py index f686aef5..f68c748e 100755 --- a/src/python/test/test_wasserstein_barycenter.py +++ b/src/python/test/test_wasserstein_barycenter.py @@ -17,7 +17,7 @@ __license__ = "MIT" def test_lagrangian_barycenter(): - + dg1 = np.array([[0.2, 0.5]]) dg2 = np.array([[0.2, 0.7]]) dg3 = np.array([[0.3, 0.6], [0.7, 0.8], [0.2, 0.3]]) @@ -28,12 +28,12 @@ def test_lagrangian_barycenter(): dg7 = np.array([[0.1, 0.15], [0.1, 0.7], [0.2, 0.22], [0.55, 0.84], [0.11, 0.91], [0.61, 0.75], [0.33, 0.46], [0.12, 0.41], [0.32, 0.48]]) dg8 = np.array([[0., 4.], [4, 8]]) - + # error crit. eps = 1e-7 - assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < eps + assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg1, dg2, dg3, dg4],init=3, verbose=False) - res) < eps assert np.array_equal(lagrangian_barycenter(pdiagset=[dg4, dg5, dg6], verbose=False), np.empty(shape=(0,2))) assert np.linalg.norm(lagrangian_barycenter(pdiagset=[dg7], verbose=False) - dg7) < eps Y, log = lagrangian_barycenter(pdiagset=[dg4, dg8], verbose=True) diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 0d70e11a..7e0d0f5f 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -70,7 +70,7 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat assert np.array_equal(match , [[0, -1], [1, -1]]) match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] assert np.array_equal(match, [[0, 0], [1, 1], [2, -1]]) - + def hera_wrap(delta): -- cgit v1.2.3 From 82dd4481fa0ecb8c1f696ee33e26d9be1e371e88 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 6 Apr 2020 22:46:32 +0200 Subject: Document dependencies for building the doc --- src/python/doc/installation.rst | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/installation.rst b/src/python/doc/installation.rst index d459145b..48425d5e 100644 --- a/src/python/doc/installation.rst +++ b/src/python/doc/installation.rst @@ -175,8 +175,8 @@ Documentation To build the documentation, `sphinx-doc `_ and `sphinxcontrib-bibtex `_ are required. As the documentation is auto-tested, `CGAL`_, `Eigen`_, -`Matplotlib`_, `NumPy`_ and `SciPy`_ are also mandatory to build the -documentation. +`Matplotlib`_, `NumPy`_, `POT`_, `Scikit-learn`_ and `SciPy`_ are +also mandatory to build the documentation. Run the following commands in a terminal: @@ -192,8 +192,8 @@ CGAL ==== Some GUDHI modules (cf. :doc:`modules list `), and few examples -require CGAL, a C++ library that provides easy access to efficient and -reliable geometric algorithms. +require `CGAL `_, a C++ library that provides easy +access to efficient and reliable geometric algorithms. The procedure to install this library -- cgit v1.2.3 From f9a933862050ca95b3a96d7a8572d62f7f2205a9 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 11 Apr 2020 18:18:14 +0200 Subject: Use longer names --- src/python/gudhi/point_cloud/dtm.py | 10 +++-- src/python/gudhi/point_cloud/knn.py | 2 +- src/python/test/test_dtm.py | 18 ++++----- src/python/test/test_knn.py | 76 +++++++++++++++++++++++++++---------- 4 files changed, 71 insertions(+), 35 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 23c36b88..38368f29 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -7,10 +7,10 @@ # Modification(s): # - YYYY/MM Author: Description of the modification -from .knn import KNN +from .knn import KNearestNeighbors -class DTM: +class DistanceToMeasure: """ Class to compute the distance to the empirical measure defined by a point set, as introduced in :cite:`dtm`. """ @@ -20,7 +20,7 @@ class DTM: Args: k (int): number of neighbors (possibly including the point itself). q (float): order used to compute the distance to measure. Defaults to 2. - kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNN`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. + kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNearestNeighbors`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. """ self.k = k self.q = q @@ -35,7 +35,9 @@ class DTM: X (numpy.array): coordinates for mass points. """ if self.params.setdefault("metric", "euclidean") != "neighbors": - self.knn = KNN(self.k, return_index=False, return_distance=True, sort_results=False, **self.params) + self.knn = KNearestNeighbors( + self.k, return_index=False, return_distance=True, sort_results=False, **self.params + ) self.knn.fit(X) return self diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 8369f1f8..6642a3c2 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -10,7 +10,7 @@ import numpy -class KNN: +class KNearestNeighbors: """ Class wrapping several implementations for computing the k nearest neighbors in a point set. """ diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 93b13e1a..37934fdb 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -8,7 +8,7 @@ - YYYY/MM Author: Description of the modification """ -from gudhi.point_cloud.dtm import DTM +from gudhi.point_cloud.dtm import DistanceToMeasure import numpy import pytest @@ -16,35 +16,35 @@ import pytest def test_dtm_compare_euclidean(): pts = numpy.random.rand(1000, 4) k = 3 - dtm = DTM(k, implementation="ckdtree") + dtm = DistanceToMeasure(k, implementation="ckdtree") r0 = dtm.fit_transform(pts) - dtm = DTM(k, implementation="sklearn") + dtm = DistanceToMeasure(k, implementation="sklearn") r1 = dtm.fit_transform(pts) assert r1 == pytest.approx(r0) - dtm = DTM(k, implementation="sklearn", algorithm="brute") + dtm = DistanceToMeasure(k, implementation="sklearn", algorithm="brute") r2 = dtm.fit_transform(pts) assert r2 == pytest.approx(r0) - dtm = DTM(k, implementation="hnsw") + dtm = DistanceToMeasure(k, implementation="hnsw") r3 = dtm.fit_transform(pts) assert r3 == pytest.approx(r0) from scipy.spatial.distance import cdist d = cdist(pts, pts) - dtm = DTM(k, metric="precomputed") + dtm = DistanceToMeasure(k, metric="precomputed") r4 = dtm.fit_transform(d) assert r4 == pytest.approx(r0) - dtm = DTM(k, implementation="keops") + dtm = DistanceToMeasure(k, implementation="keops") r5 = dtm.fit_transform(pts) assert r5 == pytest.approx(r0) def test_dtm_precomputed(): dist = numpy.array([[1.0, 3, 8], [1, 5, 5], [0, 2, 3]]) - dtm = DTM(2, q=1, metric="neighbors") + dtm = DistanceToMeasure(2, q=1, metric="neighbors") r = dtm.fit_transform(dist) assert r == pytest.approx([2.0, 3, 1]) dist = numpy.array([[2.0, 2], [0, 1], [3, 4]]) - dtm = DTM(2, q=2, metric="neighbors") + dtm = DistanceToMeasure(2, q=2, metric="neighbors") r = dtm.fit_transform(dist) assert r == pytest.approx([2.0, 0.707, 3.5355], rel=0.01) diff --git a/src/python/test/test_knn.py b/src/python/test/test_knn.py index e455fb48..6aac2006 100755 --- a/src/python/test/test_knn.py +++ b/src/python/test/test_knn.py @@ -8,7 +8,7 @@ - YYYY/MM Author: Description of the modification """ -from gudhi.point_cloud.knn import KNN +from gudhi.point_cloud.knn import KNearestNeighbors import numpy as np import pytest @@ -16,39 +16,39 @@ import pytest def test_knn_explicit(): base = np.array([[1.0, 1], [1, 2], [4, 2], [4, 3]]) query = np.array([[1.0, 1], [2, 2], [4, 4]]) - knn = KNN(2, metric="manhattan", return_distance=True, return_index=True) + knn = KNearestNeighbors(2, metric="manhattan", return_distance=True, return_index=True) knn.fit(base) r = knn.transform(query) assert r[0] == pytest.approx(np.array([[0, 1], [1, 0], [3, 2]])) assert r[1] == pytest.approx(np.array([[0.0, 1], [1, 2], [1, 2]])) - knn = KNN(2, metric="chebyshev", return_distance=True, return_index=False) + knn = KNearestNeighbors(2, metric="chebyshev", return_distance=True, return_index=False) knn.fit(base) r = knn.transform(query) assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) r = ( - KNN(2, metric="chebyshev", return_distance=True, return_index=False, implementation="keops") + KNearestNeighbors(2, metric="chebyshev", return_distance=True, return_index=False, implementation="keops") .fit(base) .transform(query) ) assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) - knn = KNN(2, metric="minkowski", p=3, return_distance=False, return_index=True) + knn = KNearestNeighbors(2, metric="minkowski", p=3, return_distance=False, return_index=True) knn.fit(base) r = knn.transform(query) assert np.array_equal(r, [[0, 1], [1, 0], [3, 2]]) r = ( - KNN(2, metric="minkowski", p=3, return_distance=False, return_index=True, implementation="keops") + KNearestNeighbors(2, metric="minkowski", p=3, return_distance=False, return_index=True, implementation="keops") .fit(base) .transform(query) ) assert np.array_equal(r, [[0, 1], [1, 0], [3, 2]]) dist = np.array([[0.0, 3, 8], [1, 0, 5], [1, 2, 0]]) - knn = KNN(2, metric="precomputed", return_index=True, return_distance=False) + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=False) r = knn.fit_transform(dist) assert np.array_equal(r, [[0, 1], [1, 0], [2, 0]]) - knn = KNN(2, metric="precomputed", return_index=True, return_distance=True) + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=True) r = knn.fit_transform(dist) assert np.array_equal(r[0], [[0, 1], [1, 0], [2, 0]]) assert np.array_equal(r[1], [[0, 3], [0, 1], [0, 1]]) @@ -57,16 +57,40 @@ def test_knn_explicit(): def test_knn_compare(): base = np.array([[1.0, 1], [1, 2], [4, 2], [4, 3]]) query = np.array([[1.0, 1], [2, 2], [4, 4]]) - r0 = KNN(2, implementation="ckdtree", return_index=True, return_distance=False).fit(base).transform(query) - r1 = KNN(2, implementation="sklearn", return_index=True, return_distance=False).fit(base).transform(query) - r2 = KNN(2, implementation="hnsw", return_index=True, return_distance=False).fit(base).transform(query) - r3 = KNN(2, implementation="keops", return_index=True, return_distance=False).fit(base).transform(query) + r0 = ( + KNearestNeighbors(2, implementation="ckdtree", return_index=True, return_distance=False) + .fit(base) + .transform(query) + ) + r1 = ( + KNearestNeighbors(2, implementation="sklearn", return_index=True, return_distance=False) + .fit(base) + .transform(query) + ) + r2 = ( + KNearestNeighbors(2, implementation="hnsw", return_index=True, return_distance=False).fit(base).transform(query) + ) + r3 = ( + KNearestNeighbors(2, implementation="keops", return_index=True, return_distance=False) + .fit(base) + .transform(query) + ) assert np.array_equal(r0, r1) and np.array_equal(r0, r2) and np.array_equal(r0, r3) - r0 = KNN(2, implementation="ckdtree", return_index=True, return_distance=True).fit(base).transform(query) - r1 = KNN(2, implementation="sklearn", return_index=True, return_distance=True).fit(base).transform(query) - r2 = KNN(2, implementation="hnsw", return_index=True, return_distance=True).fit(base).transform(query) - r3 = KNN(2, implementation="keops", return_index=True, return_distance=True).fit(base).transform(query) + r0 = ( + KNearestNeighbors(2, implementation="ckdtree", return_index=True, return_distance=True) + .fit(base) + .transform(query) + ) + r1 = ( + KNearestNeighbors(2, implementation="sklearn", return_index=True, return_distance=True) + .fit(base) + .transform(query) + ) + r2 = KNearestNeighbors(2, implementation="hnsw", return_index=True, return_distance=True).fit(base).transform(query) + r3 = ( + KNearestNeighbors(2, implementation="keops", return_index=True, return_distance=True).fit(base).transform(query) + ) assert np.array_equal(r0[0], r1[0]) and np.array_equal(r0[0], r2[0]) and np.array_equal(r0[0], r3[0]) d0 = pytest.approx(r0[1]) assert r1[1] == d0 and r2[1] == d0 and r3[1] == d0 @@ -75,8 +99,18 @@ def test_knn_compare(): def test_knn_nop(): # This doesn't look super useful... p = np.array([[0.0]]) - assert None is KNN(k=1, return_index=False, return_distance=False, implementation="sklearn").fit_transform(p) - assert None is KNN(k=1, return_index=False, return_distance=False, implementation="ckdtree").fit_transform(p) - assert None is KNN(k=1, return_index=False, return_distance=False, implementation="hnsw", ef=5).fit_transform(p) - assert None is KNN(k=1, return_index=False, return_distance=False, implementation="keops").fit_transform(p) - assert None is KNN(k=1, return_index=False, return_distance=False, metric="precomputed").fit_transform(p) + assert None is KNearestNeighbors( + k=1, return_index=False, return_distance=False, implementation="sklearn" + ).fit_transform(p) + assert None is KNearestNeighbors( + k=1, return_index=False, return_distance=False, implementation="ckdtree" + ).fit_transform(p) + assert None is KNearestNeighbors( + k=1, return_index=False, return_distance=False, implementation="hnsw", ef=5 + ).fit_transform(p) + assert None is KNearestNeighbors( + k=1, return_index=False, return_distance=False, implementation="keops" + ).fit_transform(p) + assert None is KNearestNeighbors( + k=1, return_index=False, return_distance=False, metric="precomputed" + ).fit_transform(p) -- cgit v1.2.3 From 83a1bc1fb6124a35d515f4836d2e830f3dbdf0e7 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 12 Apr 2020 21:57:51 +0200 Subject: Parallelize the "precomputed" case of knn It is supposed to be possible to compile numpy with openmp, but it looks like it isn't done in any of the usual packages. It may be possible to refactor that code so there is less redundancy. --- src/python/gudhi/point_cloud/knn.py | 78 +++++++++++++++++++++++++++++-------- src/python/test/test_dtm.py | 3 ++ src/python/test/test_knn.py | 8 ++++ 3 files changed, 73 insertions(+), 16 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 6642a3c2..f6870517 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -115,25 +115,71 @@ class KNearestNeighbors: if metric == "precomputed": # scikit-learn could handle that, but they insist on calling fit() with an unused square array, which is too unnatural. - X = numpy.array(X) if self.return_index: - neighbors = numpy.argpartition(X, k - 1)[:, 0:k] - if self.params.get("sort_results", True): - X = numpy.take_along_axis(X, neighbors, axis=-1) - ngb_order = numpy.argsort(X, axis=-1) - neighbors = numpy.take_along_axis(neighbors, ngb_order, axis=-1) + n_jobs = self.params.get("n_jobs", 1) + # Supposedly numpy can be compiled with OpenMP and handle this, but nobody does that?! + if n_jobs == 1: + neighbors = numpy.argpartition(X, k - 1)[:, 0:k] + if self.params.get("sort_results", True): + X = numpy.take_along_axis(X, neighbors, axis=-1) + ngb_order = numpy.argsort(X, axis=-1) + neighbors = numpy.take_along_axis(neighbors, ngb_order, axis=-1) + else: + ngb_order = neighbors + if self.return_distance: + distances = numpy.take_along_axis(X, ngb_order, axis=-1) + return neighbors, distances + else: + return neighbors else: - ngb_order = neighbors - if self.return_distance: - distances = numpy.take_along_axis(X, ngb_order, axis=-1) - return neighbors, distances - else: - return neighbors + from joblib import Parallel, delayed, effective_n_jobs + from sklearn.utils import gen_even_slices + + slices = gen_even_slices(len(X), effective_n_jobs(-1)) + parallel = Parallel(backend="threading", n_jobs=-1) + if self.params.get("sort_results", True): + + def func(M): + neighbors = numpy.argpartition(M, k - 1)[:, 0:k] + Y = numpy.take_along_axis(M, neighbors, axis=-1) + ngb_order = numpy.argsort(Y, axis=-1) + return numpy.take_along_axis(neighbors, ngb_order, axis=-1) + + else: + + def func(M): + return numpy.argpartition(M, k - 1)[:, 0:k] + + neighbors = numpy.concatenate(parallel(delayed(func)(X[s]) for s in slices)) + if self.return_distance: + distances = numpy.take_along_axis(X, neighbors, axis=-1) + return neighbors, distances + else: + return neighbors if self.return_distance: - distances = numpy.partition(X, k - 1)[:, 0:k] - if self.params.get("sort_results"): - # partition is not guaranteed to sort the lower half, although it often does - distances.sort(axis=-1) + n_jobs = self.params.get("n_jobs", 1) + if n_jobs == 1: + distances = numpy.partition(X, k - 1)[:, 0:k] + if self.params.get("sort_results"): + # partition is not guaranteed to sort the lower half, although it often does + distances.sort(axis=-1) + else: + from joblib import Parallel, delayed, effective_n_jobs + from sklearn.utils import gen_even_slices + + if self.params.get("sort_results"): + + def func(M): + # Not partitioning in place, because we should not modify the user's array? + r = numpy.partition(M, k - 1)[:, 0:k] + r.sort(axis=-1) + return r + + else: + func = lambda M: numpy.partition(M, k - 1)[:, 0:k] + slices = gen_even_slices(len(X), effective_n_jobs(-1)) + parallel = Parallel(backend="threading", n_jobs=-1) + distances = numpy.concatenate(parallel(delayed(func)(X[s]) for s in slices)) return distances return None diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 37934fdb..bc0d3698 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -33,6 +33,9 @@ def test_dtm_compare_euclidean(): dtm = DistanceToMeasure(k, metric="precomputed") r4 = dtm.fit_transform(d) assert r4 == pytest.approx(r0) + dtm = DistanceToMeasure(k, metric="precomputed", n_jobs=2) + r4b = dtm.fit_transform(d) + assert r4b == pytest.approx(r0) dtm = DistanceToMeasure(k, implementation="keops") r5 = dtm.fit_transform(pts) assert r5 == pytest.approx(r0) diff --git a/src/python/test/test_knn.py b/src/python/test/test_knn.py index 6aac2006..6269df54 100755 --- a/src/python/test/test_knn.py +++ b/src/python/test/test_knn.py @@ -52,6 +52,14 @@ def test_knn_explicit(): r = knn.fit_transform(dist) assert np.array_equal(r[0], [[0, 1], [1, 0], [2, 0]]) assert np.array_equal(r[1], [[0, 3], [0, 1], [0, 1]]) + # Second time in parallel + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=False, n_jobs=2) + r = knn.fit_transform(dist) + assert np.array_equal(r, [[0, 1], [1, 0], [2, 0]]) + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=True, n_jobs=2) + r = knn.fit_transform(dist) + assert np.array_equal(r[0], [[0, 1], [1, 0], [2, 0]]) + assert np.array_equal(r[1], [[0, 3], [0, 1], [0, 1]]) def test_knn_compare(): -- cgit v1.2.3 From 280eb9d2323837619db1ae013b929adb9b45013b Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 01:09:45 +0200 Subject: enable_autodiff with keops This doesn't seem like the best way to handle it, we may want to handle it like a wrapper that gets the indices from knn (whatever backend) and then computes the distances. --- src/python/gudhi/point_cloud/knn.py | 33 +++++++++++++++++++++++++++++---- src/python/test/test_dtm.py | 8 ++++++++ src/python/test/test_knn.py | 6 ++++++ 3 files changed, 43 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index f6870517..79362c09 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -36,6 +36,9 @@ class KNearestNeighbors: sort_results (bool): if True, then distances and indices of each point are sorted on return, so that the first column contains the closest points. Otherwise, neighbors are returned in an arbitrary order. Defaults to True. + enable_autodiff (bool): if the input is a torch.tensor, jax.numpy.array or similar, this instructs + the function to compute distances in a way that works with automatic differentiation. + This is experimental and not supported for all implementations. kwargs: additional parameters are forwarded to the backends. """ self.k = k @@ -202,13 +205,18 @@ class KNearestNeighbors: if self.params["implementation"] == "keops": import torch from pykeops.torch import LazyTensor + import eagerpy as ep # 'float64' is slow except on super expensive GPUs. Allow it with some param? - XX = torch.tensor(X, dtype=torch.float32) - if X is self.ref_points: + queries = X + X = ep.astensor(X) + XX = torch.as_tensor(X.numpy(), dtype=torch.float32) + if queries is self.ref_points: + Y = X YY = XX else: - YY = torch.tensor(self.ref_points, dtype=torch.float32) + Y = ep.astensor(self.ref_points) + YY = torch.as_tensor(Y.numpy(), dtype=torch.float32) p = self.params["p"] if p == numpy.inf: @@ -219,6 +227,24 @@ class KNearestNeighbors: else: mat = ((LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])).abs() ** p).sum(-1) + # pykeops does not support autodiff for kmin yet :-( + if self.params.get("enable_autodiff", False) and self.return_distance: + # Compute the indices of the neighbors, and recompute the relevant distances autodiff-friendly. + # Another strategy would be to compute the whole distance matrix with torch.cdist + # and use neighbors as indices into it. + neighbors = ep.astensor(mat.argKmin(k, dim=1)).numpy() + neighbor_pts = Y[neighbors] + diff = neighbor_pts - X[:, None, :] + if p == numpy.inf: + distances = diff.abs().max(-1) + elif p == 2: + distances = (diff ** 2).sum(-1) ** 0.5 + else: + distances = (diff.abs() ** p).sum(-1) ** (1.0 / p) + if self.return_index: + return neighbors.raw, distances.raw + else: + return distances.raw if self.return_index: if self.return_distance: distances, neighbors = mat.Kmin_argKmin(k, dim=1) @@ -234,7 +260,6 @@ class KNearestNeighbors: distances = distances ** (1.0 / p) return distances return None - # FIXME: convert everything back to numpy arrays or not? if self.params["implementation"] == "ckdtree": qargs = {key: val for key, val in self.params.items() if key in {"p", "eps", "n_jobs"}} diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index bc0d3698..8709dd07 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -11,6 +11,7 @@ from gudhi.point_cloud.dtm import DistanceToMeasure import numpy import pytest +import torch def test_dtm_compare_euclidean(): @@ -39,6 +40,13 @@ def test_dtm_compare_euclidean(): dtm = DistanceToMeasure(k, implementation="keops") r5 = dtm.fit_transform(pts) assert r5 == pytest.approx(r0) + pts2 = torch.tensor(pts, requires_grad=True) + assert pts2.grad is None + dtm = DistanceToMeasure(k, implementation="keops", enable_autodiff=True) + r6 = dtm.fit_transform(pts2) + assert r6.detach().numpy() == pytest.approx(r0) + r6.sum().backward() + assert pts2.grad is not None def test_dtm_precomputed(): diff --git a/src/python/test/test_knn.py b/src/python/test/test_knn.py index 6269df54..415c9d48 100755 --- a/src/python/test/test_knn.py +++ b/src/python/test/test_knn.py @@ -32,6 +32,12 @@ def test_knn_explicit(): .transform(query) ) assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) + r = ( + KNearestNeighbors(2, metric="chebyshev", return_distance=True, return_index=False, implementation="keops", enable_autodiff=True) + .fit(base) + .transform(query) + ) + assert r == pytest.approx(np.array([[0.0, 1], [1, 1], [1, 2]])) knn = KNearestNeighbors(2, metric="minkowski", p=3, return_distance=False, return_index=True) knn.fit(base) -- cgit v1.2.3 From 2f1576a23cf4ac055565875d384ca604c0ff6844 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 15:01:51 +0200 Subject: Small autodiff tweaks --- src/python/gudhi/point_cloud/knn.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 79362c09..ab3447d4 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -233,16 +233,17 @@ class KNearestNeighbors: # Another strategy would be to compute the whole distance matrix with torch.cdist # and use neighbors as indices into it. neighbors = ep.astensor(mat.argKmin(k, dim=1)).numpy() - neighbor_pts = Y[neighbors] + # Work around https://github.com/pytorch/pytorch/issues/34452 + neighbor_pts = Y[neighbors,] diff = neighbor_pts - X[:, None, :] if p == numpy.inf: distances = diff.abs().max(-1) elif p == 2: - distances = (diff ** 2).sum(-1) ** 0.5 + distances = (diff ** 2).sum(-1).sqrt() else: distances = (diff.abs() ** p).sum(-1) ** (1.0 / p) if self.return_index: - return neighbors.raw, distances.raw + return neighbors, distances.raw else: return distances.raw if self.return_index: -- cgit v1.2.3 From 3a86402b733a48d9c25a4995325e72c7438c06c0 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 15:21:06 +0200 Subject: Fix NaN gradient with pytorch --- src/python/gudhi/point_cloud/knn.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index ab3447d4..185a7764 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -236,12 +236,11 @@ class KNearestNeighbors: # Work around https://github.com/pytorch/pytorch/issues/34452 neighbor_pts = Y[neighbors,] diff = neighbor_pts - X[:, None, :] - if p == numpy.inf: - distances = diff.abs().max(-1) - elif p == 2: - distances = (diff ** 2).sum(-1).sqrt() + if isinstance(diff, ep.PyTorchTensor): + # https://github.com/jonasrauber/eagerpy/issues/6 + distances = ep.astensor(diff.raw.norm(p, -1)) else: - distances = (diff.abs() ** p).sum(-1) ** (1.0 / p) + distances = diff.norms.lp(p, -1) if self.return_index: return neighbors, distances.raw else: -- cgit v1.2.3 From 3afce326428dddd638e22ab37ee4b2afe52eba75 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 20:32:39 +0200 Subject: Generalize enable_autodiff to more implementations Still limited to L^p --- src/python/gudhi/point_cloud/knn.py | 76 +++++++++++++++++++++++++++---------- 1 file changed, 55 insertions(+), 21 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 185a7764..87b2798e 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -9,6 +9,7 @@ import numpy +# TODO: https://github.com/facebookresearch/faiss class KNearestNeighbors: """ @@ -67,6 +68,8 @@ class KNearestNeighbors: self.params["implementation"] = "ckdtree" else: self.params["implementation"] = "sklearn" + if not return_distance: + self.params["enable_autodiff"] = False def fit_transform(self, X, y=None): return self.fit(X).transform(X) @@ -77,6 +80,10 @@ class KNearestNeighbors: X (numpy.array): coordinates for reference points. """ self.ref_points = X + if self.params.get("enable_autodiff", False): + import eagerpy as ep + if self.params["implementation"] != "keops" or not isinstance(X, ep.PyTorchTensor): + X = ep.astensor(X).numpy() if self.params["implementation"] == "ckdtree": # sklearn could handle this, but it is much slower from scipy.spatial import cKDTree @@ -113,6 +120,41 @@ class KNearestNeighbors: Args: X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed". """ + if self.params.get("enable_autodiff", False): + # pykeops does not support autodiff for kmin yet, but when it does in the future, + # we may want a special path. + import eagerpy as ep + save_return_index = self.return_index + self.return_index = True + self.return_distance = False + self.params["enable_autodiff"] = False + try: + # FIXME: how do we test "X is ref_points" then? + newX = ep.astensor(X) + if self.params["implementation"] != "keops" or not isinstance(newX, ep.PyTorchTensor): + newX = newX.numpy() + neighbors = self.transform(newX) + finally: + self.return_index = save_return_index + self.return_distance = True + self.params["enable_autodiff"] = True + # We can implement more later as needed + assert self.metric == "minkowski" + p = self.params["p"] + Y = ep.astensor(self.ref_points) + neighbor_pts = Y[neighbors,] + diff = neighbor_pts - X[:, None, :] + if isinstance(diff, ep.PyTorchTensor): + # https://github.com/jonasrauber/eagerpy/issues/6 + distances = ep.astensor(diff.raw.norm(p, -1)) + else: + distances = diff.norms.lp(p, -1) + if self.return_index: + return neighbors, distances.raw + else: + return distances.raw + + metric = self.metric k = self.k @@ -207,16 +249,26 @@ class KNearestNeighbors: from pykeops.torch import LazyTensor import eagerpy as ep - # 'float64' is slow except on super expensive GPUs. Allow it with some param? queries = X X = ep.astensor(X) - XX = torch.as_tensor(X.numpy(), dtype=torch.float32) + if isinstance(X, ep.PyTorchTensor): + XX = X.raw + else: + # I don't know a clever way to reuse a GPU tensor from tensorflow in pytorch + # without copying to/from the CPU. + XX = X.numpy() + # 'float64' is slow except on super expensive GPUs. Allow it with some param? + XX = torch.as_tensor(XX, dtype=torch.float32) if queries is self.ref_points: Y = X YY = XX else: Y = ep.astensor(self.ref_points) - YY = torch.as_tensor(Y.numpy(), dtype=torch.float32) + if isinstance(Y, ep.PyTorchTensor): + YY = Y.raw + else: + YY = Y.numpy() + YY = torch.as_tensor(YY, dtype=torch.float32) p = self.params["p"] if p == numpy.inf: @@ -227,24 +279,6 @@ class KNearestNeighbors: else: mat = ((LazyTensor(XX[:, None, :]) - LazyTensor(YY[None, :, :])).abs() ** p).sum(-1) - # pykeops does not support autodiff for kmin yet :-( - if self.params.get("enable_autodiff", False) and self.return_distance: - # Compute the indices of the neighbors, and recompute the relevant distances autodiff-friendly. - # Another strategy would be to compute the whole distance matrix with torch.cdist - # and use neighbors as indices into it. - neighbors = ep.astensor(mat.argKmin(k, dim=1)).numpy() - # Work around https://github.com/pytorch/pytorch/issues/34452 - neighbor_pts = Y[neighbors,] - diff = neighbor_pts - X[:, None, :] - if isinstance(diff, ep.PyTorchTensor): - # https://github.com/jonasrauber/eagerpy/issues/6 - distances = ep.astensor(diff.raw.norm(p, -1)) - else: - distances = diff.norms.lp(p, -1) - if self.return_index: - return neighbors, distances.raw - else: - return distances.raw if self.return_index: if self.return_distance: distances, neighbors = mat.Kmin_argKmin(k, dim=1) -- cgit v1.2.3 From 521d8c17c2b7d71c46a51f0490ff2c13c809fc87 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 21:13:19 +0200 Subject: Remove left-over code eagerpy is only used with enable_autodiff --- src/python/gudhi/point_cloud/knn.py | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 87b2798e..f2cddb38 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -82,8 +82,11 @@ class KNearestNeighbors: self.ref_points = X if self.params.get("enable_autodiff", False): import eagerpy as ep + X = ep.astensor(X) if self.params["implementation"] != "keops" or not isinstance(X, ep.PyTorchTensor): - X = ep.astensor(X).numpy() + # I don't know a clever way to reuse a GPU tensor from tensorflow in pytorch + # without copying to/from the CPU. + X = X.numpy() if self.params["implementation"] == "ckdtree": # sklearn could handle this, but it is much slower from scipy.spatial import cKDTree @@ -133,6 +136,8 @@ class KNearestNeighbors: newX = ep.astensor(X) if self.params["implementation"] != "keops" or not isinstance(newX, ep.PyTorchTensor): newX = newX.numpy() + else: + newX = X neighbors = self.transform(newX) finally: self.return_index = save_return_index @@ -247,29 +252,13 @@ class KNearestNeighbors: if self.params["implementation"] == "keops": import torch from pykeops.torch import LazyTensor - import eagerpy as ep - queries = X - X = ep.astensor(X) - if isinstance(X, ep.PyTorchTensor): - XX = X.raw - else: - # I don't know a clever way to reuse a GPU tensor from tensorflow in pytorch - # without copying to/from the CPU. - XX = X.numpy() # 'float64' is slow except on super expensive GPUs. Allow it with some param? - XX = torch.as_tensor(XX, dtype=torch.float32) - if queries is self.ref_points: - Y = X + XX = torch.as_tensor(X, dtype=torch.float32) + if X is self.ref_points: YY = XX else: - Y = ep.astensor(self.ref_points) - if isinstance(Y, ep.PyTorchTensor): - YY = Y.raw - else: - YY = Y.numpy() - YY = torch.as_tensor(YY, dtype=torch.float32) - + YY = torch.as_tensor(self.ref_points, dtype=torch.float32) p = self.params["p"] if p == numpy.inf: # Requires pykeops 1.4 or later -- cgit v1.2.3 From ce75f66da5a2d7ad2c479355112d48817c5ba68b Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 13 Apr 2020 21:38:24 +0200 Subject: Tweak to detect fit_transform --- src/python/gudhi/point_cloud/knn.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index f2cddb38..8b3cdb46 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -11,6 +11,7 @@ import numpy # TODO: https://github.com/facebookresearch/faiss + class KNearestNeighbors: """ Class wrapping several implementations for computing the k nearest neighbors in a point set. @@ -82,6 +83,7 @@ class KNearestNeighbors: self.ref_points = X if self.params.get("enable_autodiff", False): import eagerpy as ep + X = ep.astensor(X) if self.params["implementation"] != "keops" or not isinstance(X, ep.PyTorchTensor): # I don't know a clever way to reuse a GPU tensor from tensorflow in pytorch @@ -127,17 +129,19 @@ class KNearestNeighbors: # pykeops does not support autodiff for kmin yet, but when it does in the future, # we may want a special path. import eagerpy as ep + save_return_index = self.return_index self.return_index = True self.return_distance = False self.params["enable_autodiff"] = False try: - # FIXME: how do we test "X is ref_points" then? newX = ep.astensor(X) - if self.params["implementation"] != "keops" or not isinstance(newX, ep.PyTorchTensor): + if self.params["implementation"] != "keops" or ( + not isinstance(newX, ep.PyTorchTensor) and not isinstance(newX, ep.NumPyTensor) + ): newX = newX.numpy() else: - newX = X + newX = newX.raw neighbors = self.transform(newX) finally: self.return_index = save_return_index @@ -159,7 +163,6 @@ class KNearestNeighbors: else: return distances.raw - metric = self.metric k = self.k -- cgit v1.2.3 From f0c5aab988ee966510503a30b0591105594ac67d Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 14 Apr 2020 15:37:31 +0200 Subject: More testing --- src/python/test/test_dtm.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 8709dd07..db3e5df5 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -47,6 +47,13 @@ def test_dtm_compare_euclidean(): assert r6.detach().numpy() == pytest.approx(r0) r6.sum().backward() assert pts2.grad is not None + pts2 = torch.tensor(pts, requires_grad=True) + assert pts2.grad is None + dtm = DistanceToMeasure(k, implementation="ckdtree", enable_autodiff=True) + r7 = dtm.fit_transform(pts2) + assert r7.detach().numpy() == pytest.approx(r0) + r7.sum().backward() + assert pts2.grad is not None def test_dtm_precomputed(): -- cgit v1.2.3 From b908205e85bbe29c8d18ad1f38e783a1327434d7 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 14 Apr 2020 17:00:27 +0200 Subject: EagerPy in cmake --- src/cmake/modules/GUDHI_third_party_libraries.cmake | 1 + src/python/CMakeLists.txt | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/cmake/modules/GUDHI_third_party_libraries.cmake b/src/cmake/modules/GUDHI_third_party_libraries.cmake index a931b3a1..0abe66b7 100644 --- a/src/cmake/modules/GUDHI_third_party_libraries.cmake +++ b/src/cmake/modules/GUDHI_third_party_libraries.cmake @@ -181,6 +181,7 @@ if( PYTHONINTERP_FOUND ) find_python_module("pybind11") find_python_module("torch") find_python_module("pykeops") + find_python_module("eagerpy") find_python_module_no_version("hnswlib") endif() diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index d7a6a4db..99e8b57c 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -88,6 +88,9 @@ if(PYTHONINTERP_FOUND) if(PYKEOPS_FOUND) add_gudhi_debug_info("PyKeOps version ${PYKEOPS_VERSION}") endif() + if(EAGERPY_FOUND) + add_gudhi_debug_info("EagerPy version ${EAGERPY_VERSION}") + endif() set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_RESULT_OF_USE_DECLTYPE', ") set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DBOOST_ALL_NO_LIB', ") @@ -410,7 +413,7 @@ if(PYTHONINTERP_FOUND) add_gudhi_py_test(test_time_delay) # DTM - if(SCIPY_FOUND AND SKLEARN_FOUND AND TORCH_FOUND AND HNSWLIB_FOUND AND PYKEOPS_FOUND) + if(SCIPY_FOUND AND SKLEARN_FOUND AND TORCH_FOUND AND HNSWLIB_FOUND AND PYKEOPS_FOUND AND EAGERPY_FOUND) add_gudhi_py_test(test_knn) add_gudhi_py_test(test_dtm) endif() -- cgit v1.2.3 From 9518287cfa2a62948ede2e7d17d5c9f29092e0f4 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 14 Apr 2020 18:27:19 +0200 Subject: Doc improvements --- src/python/gudhi/point_cloud/dtm.py | 12 ++++++++++-- src/python/gudhi/point_cloud/knn.py | 11 ++++++++--- 2 files changed, 18 insertions(+), 5 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 38368f29..58dec536 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -20,7 +20,9 @@ class DistanceToMeasure: Args: k (int): number of neighbors (possibly including the point itself). q (float): order used to compute the distance to measure. Defaults to 2. - kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNearestNeighbors`, except that metric="neighbors" means that :func:`transform` expects an array with the distances to the k nearest neighbors. + kwargs: same parameters as :class:`~gudhi.point_cloud.knn.KNearestNeighbors`, except that + metric="neighbors" means that :func:`transform` expects an array with the distances + to the k nearest neighbors. """ self.k = k self.q = q @@ -44,7 +46,13 @@ class DistanceToMeasure: def transform(self, X): """ Args: - X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed", or distances to the k nearest neighbors if metric is "neighbors" (if the array has more than k columns, the remaining ones are ignored). + X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed", + or distances to the k nearest neighbors if metric is "neighbors" (if the array has more + than k columns, the remaining ones are ignored). + + Returns: + numpy.array: a 1-d array with, for each point of X, its distance to the measure defined + by the argument of :func:`fit`. """ if self.params["metric"] == "neighbors": distances = X[:, : self.k] diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 8b3cdb46..d7cf0b2a 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -38,9 +38,9 @@ class KNearestNeighbors: sort_results (bool): if True, then distances and indices of each point are sorted on return, so that the first column contains the closest points. Otherwise, neighbors are returned in an arbitrary order. Defaults to True. - enable_autodiff (bool): if the input is a torch.tensor, jax.numpy.array or similar, this instructs - the function to compute distances in a way that works with automatic differentiation. - This is experimental and not supported for all implementations. + enable_autodiff (bool): if the input is a torch.tensor, jax.numpy.ndarray or tensorflow.Tensor, this + instructs the function to compute distances in a way that works with automatic differentiation. + This is experimental and not supported for all metrics. Defaults to False. kwargs: additional parameters are forwarded to the backends. """ self.k = k @@ -124,6 +124,11 @@ class KNearestNeighbors: """ Args: X (numpy.array): coordinates for query points, or distance matrix if metric is "precomputed". + + Returns: + numpy.array: if return_index, an array of shape (len(X), k) with the indices (in the argument + of :func:`fit`) of the k nearest neighbors to the points of X. If return_distance, an array of the + same shape with the distances to those neighbors. If both, a tuple with the two arrays, in this order. """ if self.params.get("enable_autodiff", False): # pykeops does not support autodiff for kmin yet, but when it does in the future, -- cgit v1.2.3 From acb9d5b9d1317d3d8168bc3ac46860d078abba84 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 14 Apr 2020 20:30:29 +0200 Subject: Check that the gradient is not NaN This can easily happen with pytorch, and there is special code to avoid it. --- src/python/test/test_dtm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index db3e5df5..de74c42b 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -46,14 +46,14 @@ def test_dtm_compare_euclidean(): r6 = dtm.fit_transform(pts2) assert r6.detach().numpy() == pytest.approx(r0) r6.sum().backward() - assert pts2.grad is not None + assert pts2.grad is not None and not torch.isnan(pts2.grad).any() pts2 = torch.tensor(pts, requires_grad=True) assert pts2.grad is None dtm = DistanceToMeasure(k, implementation="ckdtree", enable_autodiff=True) r7 = dtm.fit_transform(pts2) assert r7.detach().numpy() == pytest.approx(r0) r7.sum().backward() - assert pts2.grad is not None + assert pts2.grad is not None and not torch.isnan(pts2.grad).any() def test_dtm_precomputed(): -- cgit v1.2.3 From 17aaa979e4cdfe5faed9b2750d452171de4b67e1 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 17 Apr 2020 22:13:29 +0200 Subject: Simplify distance-to-diagonal in Wasserstein --- src/python/gudhi/wasserstein/wasserstein.py | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 35315939..5df66cf9 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -15,16 +15,19 @@ try: except ImportError: print("POT (Python Optimal Transport) package is not installed. Try to run $ conda install -c conda-forge pot ; or $ pip install POT") -def _proj_on_diag(X): +def _dist_to_diag(X, internal_p): ''' :param X: (n x 2) array encoding the points of a persistent diagram. - :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal + :param internal_p: Ground metric (i.e. norm L^p). + :returns: (n) array encoding the (respective orthogonal) distances of the points to the diagonal + + .. note:: + Assumes that the points are above the diagonal. ''' - Z = (X[:,0] + X[:,1]) / 2. - return np.array([Z , Z]).T + return (X[:, 1] - X[:, 0]) * 2 ** (1.0 / internal_p - 1) -def _build_dist_matrix(X, Y, order=2., internal_p=2.): +def _build_dist_matrix(X, Y, order, internal_p): ''' :param X: (n x 2) numpy.array encoding the (points of the) first diagram. :param Y: (m x 2) numpy.array encoding the second diagram. @@ -36,16 +39,12 @@ def _build_dist_matrix(X, Y, order=2., internal_p=2.): and its orthogonal projection onto the diagonal. note also that C[n, m] = 0 (it costs nothing to move from the diagonal to the diagonal). ''' - Xdiag = _proj_on_diag(X) - Ydiag = _proj_on_diag(Y) + Cxd = _dist_to_diag(X, internal_p)**order + Cdy = _dist_to_diag(Y, internal_p)**order if np.isinf(internal_p): C = sc.cdist(X,Y, metric='chebyshev')**order - Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order - Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order else: C = sc.cdist(X,Y, metric='minkowski', p=internal_p)**order - Cxd = np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order - Cdy = np.linalg.norm(Y - Ydiag, ord=internal_p, axis=1)**order Cf = np.hstack((C, Cxd[:,None])) Cdy = np.append(Cdy, 0) @@ -61,8 +60,7 @@ def _perstot(X, order, internal_p): :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). ''' - Xdiag = _proj_on_diag(X) - return (np.sum(np.linalg.norm(X - Xdiag, ord=internal_p, axis=1)**order))**(1./order) + return np.linalg.norm(_dist_to_diag(X, internal_p), ord=order) def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): -- cgit v1.2.3 From f93c403b81b4ccb98bfad8e4ef30cdf0e7333f6c Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sat, 18 Apr 2020 23:52:12 +0200 Subject: enable_autodiff for POT wasserstein_distance --- src/python/gudhi/wasserstein/wasserstein.py | 64 +++++++++++++++++++++++----- src/python/test/test_wasserstein_distance.py | 14 ++++-- 2 files changed, 63 insertions(+), 15 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 5df66cf9..9660b99b 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -53,17 +53,30 @@ def _build_dist_matrix(X, Y, order, internal_p): return Cf -def _perstot(X, order, internal_p): +def _perstot_autodiff(X, order, internal_p): + ''' + Version of _perstot that works on eagerpy tensors. + ''' + return _dist_to_diag(X, internal_p).norms.lp(order) + +def _perstot(X, order, internal_p, enable_autodiff): ''' :param X: (n x 2) numpy.array (points of a given diagram). :param order: exponent for Wasserstein. Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). + :param enable_autodiff: If X is torch.tensor, tensorflow.Tensor or jax.numpy.ndarray, make the computation + transparent to automatic differentiation. + :type enable_autodiff: bool :returns: float, the total persistence of the diagram (that is, its distance to the empty diagram). ''' - return np.linalg.norm(_dist_to_diag(X, internal_p), ord=order) + if enable_autodiff: + import eagerpy as ep + return _perstot_autodiff(ep.astensor(X), order, internal_p).raw + else: + return np.linalg.norm(_dist_to_diag(X, internal_p), ord=order) -def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): +def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_autodiff=False): ''' :param X: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). @@ -74,6 +87,9 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): :param order: exponent for Wasserstein; Default value is 2. :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). + :param enable_autodiff: If X and Y are torch.tensor, tensorflow.Tensor or jax.numpy.ndarray, make the computation + transparent to automatic differentiation. + :type enable_autodiff: bool :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with respect to the internal_p-norm as ground metric. If matching is set to True, also returns the optimal matching between X and Y. @@ -82,23 +98,30 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): m = len(Y) # handle empty diagrams - if X.size == 0: - if Y.size == 0: + if n == 0: + if m == 0: if not matching: + # What if enable_autodiff? return 0. else: return 0., np.array([]) else: if not matching: - return _perstot(Y, order, internal_p) + return _perstot(Y, order, internal_p, enable_autodiff) else: - return _perstot(Y, order, internal_p), np.array([[-1, j] for j in range(m)]) - elif Y.size == 0: + return _perstot(Y, order, internal_p, enable_autodiff), np.array([[-1, j] for j in range(m)]) + elif m == 0: if not matching: - return _perstot(X, order, internal_p) + return _perstot(X, order, internal_p, enable_autodiff) else: - return _perstot(X, order, internal_p), np.array([[i, -1] for i in range(n)]) - + return _perstot(X, order, internal_p, enable_autodiff), np.array([[i, -1] for i in range(n)]) + + if enable_autodiff: + import eagerpy as ep + X_orig = ep.astensor(X) + Y_orig = ep.astensor(Y) + X = X_orig.numpy() + Y = Y_orig.numpy() M = _build_dist_matrix(X, Y, order=order, internal_p=internal_p) a = np.ones(n+1) # weight vector of the input diagram. Uniform here. a[-1] = m @@ -106,6 +129,7 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): b[-1] = n if matching: + assert not enable_autodiff, "matching and enable_autodiff are currently incompatible" P = ot.emd(a=a,b=b,M=M, numItermax=2000000) ot_cost = np.sum(np.multiply(P,M)) P[-1, -1] = 0 # Remove matching corresponding to the diagonal @@ -115,6 +139,24 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2.): match[:,1][match[:,1] >= m] = -1 return ot_cost ** (1./order) , match + if enable_autodiff: + P = ot.emd(a=a,b=b,M=M, numItermax=2000000) + pairs = np.argwhere(P[:-1, :-1]) + diag2 = np.nonzero(P[-1, :-1]) + diag1 = np.nonzero(P[:-1, -1]) + dists = [] + # empty arrays are not handled properly by the helpers, so we avoid calling them + if len(pairs): + dists.append((Y_orig[pairs[:, 1]] - X_orig[pairs[:, 0]]).norms.lp(internal_p, axis=-1).norms.lp(order)) + if len(diag1): + dists.append(_perstot_autodiff(X_orig[diag1], order, internal_p)) + if len(diag2): + dists.append(_perstot_autodiff(Y_orig[diag2], order, internal_p)) + dists = [ dist.reshape(1) for dist in dists ] + return ep.concatenate(dists).norms.lp(order) + # Should just compute the L^order norm manually? + # We can also concatenate the 3 vectors to compute just one norm. + # Comptuation of the otcost using the ot.emd2 library. # Note: it is the Wasserstein distance to the power q. # The default numItermax=100000 is not sufficient for some examples with 5000 points, what is a good value? diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 7e0d0f5f..5bec5bd3 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -73,14 +73,20 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat -def hera_wrap(delta): +def hera_wrap(**extra): def fun(*kargs,**kwargs): - return hera(*kargs,**kwargs,delta=delta) + return hera(*kargs,**kwargs,**extra) + return fun + +def pot_wrap(**extra): + def fun(*kargs,**kwargs): + return pot(*kargs,**kwargs,**extra) return fun def test_wasserstein_distance_pot(): _basic_wasserstein(pot, 1e-15, test_infinity=False, test_matching=True) + _basic_wasserstein(pot_wrap(enable_autodiff=True), 1e-15, test_infinity=False, test_matching=False) def test_wasserstein_distance_hera(): - _basic_wasserstein(hera_wrap(1e-12), 1e-12, test_matching=False) - _basic_wasserstein(hera_wrap(.1), .1, test_matching=False) + _basic_wasserstein(hera_wrap(delta=1e-12), 1e-12, test_matching=False) + _basic_wasserstein(hera_wrap(delta=.1), .1, test_matching=False) -- cgit v1.2.3 From b2a9ba18ce33778abdd9f5032af4bfff04e8bbd2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 19 Apr 2020 09:06:08 +0200 Subject: Unwrap the result --- src/python/gudhi/wasserstein/wasserstein.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 9660b99b..f0c82962 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -71,6 +71,7 @@ def _perstot(X, order, internal_p, enable_autodiff): ''' if enable_autodiff: import eagerpy as ep + return _perstot_autodiff(ep.astensor(X), order, internal_p).raw else: return np.linalg.norm(_dist_to_diag(X, internal_p), ord=order) @@ -118,6 +119,7 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a if enable_autodiff: import eagerpy as ep + X_orig = ep.astensor(X) Y_orig = ep.astensor(Y) X = X_orig.numpy() @@ -140,10 +142,10 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a return ot_cost ** (1./order) , match if enable_autodiff: - P = ot.emd(a=a,b=b,M=M, numItermax=2000000) + P = ot.emd(a=a, b=b, M=M, numItermax=2000000) pairs = np.argwhere(P[:-1, :-1]) - diag2 = np.nonzero(P[-1, :-1]) diag1 = np.nonzero(P[:-1, -1]) + diag2 = np.nonzero(P[-1, :-1]) dists = [] # empty arrays are not handled properly by the helpers, so we avoid calling them if len(pairs): @@ -152,8 +154,8 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a dists.append(_perstot_autodiff(X_orig[diag1], order, internal_p)) if len(diag2): dists.append(_perstot_autodiff(Y_orig[diag2], order, internal_p)) - dists = [ dist.reshape(1) for dist in dists ] - return ep.concatenate(dists).norms.lp(order) + dists = [dist.reshape(1) for dist in dists] + return ep.concatenate(dists).norms.lp(order).raw # Should just compute the L^order norm manually? # We can also concatenate the 3 vectors to compute just one norm. -- cgit v1.2.3 From 1086b8cad7c1ea2a02742dfc44aef036a674f5d3 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 19 Apr 2020 12:17:42 +0200 Subject: Test gradient --- src/python/test/test_wasserstein_distance.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 5bec5bd3..c6d6b346 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -90,3 +90,16 @@ def test_wasserstein_distance_pot(): def test_wasserstein_distance_hera(): _basic_wasserstein(hera_wrap(delta=1e-12), 1e-12, test_matching=False) _basic_wasserstein(hera_wrap(delta=.1), .1, test_matching=False) + +def test_wasserstein_distance_grad(): + import torch + + diag1 = torch.tensor([[2.7, 3.7], [9.6, 14.0], [34.2, 34.974]], requires_grad=True) + diag2 = torch.tensor([[2.8, 4.45], [9.5, 14.1]], requires_grad=True) + diag3 = torch.tensor([[2.8, 4.45], [9.5, 14.1]], requires_grad=True) + assert diag1.grad is None and diag2.grad is None and diag3.grad is None + dist1 = pot(diag1, diag2, internal_p=2, order=2, enable_autodiff=True) + dist2 = pot(diag3, torch.tensor([]), internal_p=2, order=2, enable_autodiff=True) + dist1.backward() + dist2.backward() + assert not torch.isnan(diag1.grad).any() and not torch.isnan(diag2.grad).any() and not torch.isnan(diag3.grad).any() -- cgit v1.2.3 From 8d9611206603f4f7506fe77a0273c73c9d67716b Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 19 Apr 2020 12:30:35 +0200 Subject: Drop redundant test torch.isnan(None) raises an exception anyway --- src/python/test/test_dtm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index de74c42b..859189fa 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -46,14 +46,14 @@ def test_dtm_compare_euclidean(): r6 = dtm.fit_transform(pts2) assert r6.detach().numpy() == pytest.approx(r0) r6.sum().backward() - assert pts2.grad is not None and not torch.isnan(pts2.grad).any() + assert not torch.isnan(pts2.grad).any() pts2 = torch.tensor(pts, requires_grad=True) assert pts2.grad is None dtm = DistanceToMeasure(k, implementation="ckdtree", enable_autodiff=True) r7 = dtm.fit_transform(pts2) assert r7.detach().numpy() == pytest.approx(r0) r7.sum().backward() - assert pts2.grad is not None and not torch.isnan(pts2.grad).any() + assert not torch.isnan(pts2.grad).any() def test_dtm_precomputed(): -- cgit v1.2.3 From 1fc55e54ed2f24969a691914edee642f97142fa9 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 19 Apr 2020 13:43:23 +0200 Subject: Test comparison with persistence_pairs() --- src/python/test/test_simplex_generators.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'src/python') diff --git a/src/python/test/test_simplex_generators.py b/src/python/test/test_simplex_generators.py index e3bdc094..8a9b4844 100755 --- a/src/python/test/test_simplex_generators.py +++ b/src/python/test/test_simplex_generators.py @@ -24,6 +24,13 @@ def test_flag_generators(): assert np.array_equal(g[2], [0, 4]) assert len(g[3]) == 1 assert np.array_equal(g[3][0], [[7, 6]]) + # Compare trivial cases (where the simplex is the generator) with persistence_pairs. + # This still makes assumptions on the order of vertices in a simplex and could be more robust. + pairs = st.persistence_pairs() + assert {tuple(i) for i in g[0]} == {(i[0][0],) + tuple(i[1]) for i in pairs if len(i[0]) == 1 and len(i[1]) != 0} + assert {(i[0], i[1]) for i in g[1][0]} == {tuple(i[0]) for i in pairs if len(i[0]) == 2 and len(i[1]) != 0} + assert set(g[2]) == {i[0][0] for i in pairs if len(i[0]) == 1 and len(i[1]) == 0} + assert {(i[0], i[1]) for i in g[3][0]} == {tuple(i[0]) for i in pairs if len(i[0]) == 2 and len(i[1]) == 0} def test_lower_star_generators(): -- cgit v1.2.3 From 1c1a99074049e4ff04fa28e7d6e1b6fc2067397a Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 20 Apr 2020 10:38:41 +0200 Subject: Add __license__ --- src/python/gudhi/point_cloud/dtm.py | 4 ++++ src/python/gudhi/point_cloud/knn.py | 8 +++++++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/dtm.py b/src/python/gudhi/point_cloud/dtm.py index 58dec536..13e16d24 100644 --- a/src/python/gudhi/point_cloud/dtm.py +++ b/src/python/gudhi/point_cloud/dtm.py @@ -9,6 +9,10 @@ from .knn import KNearestNeighbors +__author__ = "Marc Glisse" +__copyright__ = "Copyright (C) 2020 Inria" +__license__ = "MIT" + class DistanceToMeasure: """ diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index d7cf0b2a..4017e498 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -11,6 +11,10 @@ import numpy # TODO: https://github.com/facebookresearch/faiss +__author__ = "Marc Glisse" +__copyright__ = "Copyright (C) 2020 Inria" +__license__ = "MIT" + class KNearestNeighbors: """ @@ -156,7 +160,9 @@ class KNearestNeighbors: assert self.metric == "minkowski" p = self.params["p"] Y = ep.astensor(self.ref_points) - neighbor_pts = Y[neighbors,] + neighbor_pts = Y[ + neighbors, + ] diff = neighbor_pts - X[:, None, :] if isinstance(diff, ep.PyTorchTensor): # https://github.com/jonasrauber/eagerpy/issues/6 -- cgit v1.2.3 From 3a9105e0d3bea5cc64610b7c0c3fb15f0e00bb9d Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 20 Apr 2020 11:37:44 +0200 Subject: Reintroduce _proj_on_diag, with a unit test --- src/python/gudhi/wasserstein/wasserstein.py | 11 +++++++++++ src/python/test/test_wasserstein_distance.py | 7 +++++++ 2 files changed, 18 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 5df66cf9..efc851a0 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -15,6 +15,17 @@ try: except ImportError: print("POT (Python Optimal Transport) package is not installed. Try to run $ conda install -c conda-forge pot ; or $ pip install POT") + +# Currently unused, but Théo says it is likely to be used again. +def _proj_on_diag(X): + ''' + :param X: (n x 2) array encoding the points of a persistent diagram. + :returns: (n x 2) array encoding the (respective orthogonal) projections of the points onto the diagonal + ''' + Z = (X[:,0] + X[:,1]) / 2. + return np.array([Z , Z]).T + + def _dist_to_diag(X, internal_p): ''' :param X: (n x 2) array encoding the points of a persistent diagram. diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 7e0d0f5f..1a4acc1d 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -8,6 +8,7 @@ - YYYY/MM Author: Description of the modification """ +from gudhi.wasserstein.wasserstein import _proj_on_diag from gudhi.wasserstein import wasserstein_distance as pot from gudhi.hera import wasserstein_distance as hera import numpy as np @@ -17,6 +18,12 @@ __author__ = "Theo Lacombe" __copyright__ = "Copyright (C) 2019 Inria" __license__ = "MIT" +def test_proj_on_diag(): + dgm = np.array([[1., 1.], [1., 2.], [3., 5.]]) + assert np.array_equal(_proj_on_diag(dgm), [[1., 1.], [1.5, 1.5], [4., 4.]]) + empty = np.empty((0, 2)) + assert np.array_equal(_proj_on_diag(empty), empty) + def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_matching=True): diag1 = np.array([[2.7, 3.7], [9.6, 14.0], [34.2, 34.974]]) diag2 = np.array([[2.8, 4.45], [9.5, 14.1]]) -- cgit v1.2.3 From 9ef7ba65367ab2ff92bf66b1b8166c5990530b76 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 20 Apr 2020 12:16:15 +0200 Subject: Explicitly pass sort_results=True on some tests --- src/python/test/test_knn.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_knn.py b/src/python/test/test_knn.py index 415c9d48..a87ec212 100755 --- a/src/python/test/test_knn.py +++ b/src/python/test/test_knn.py @@ -54,12 +54,12 @@ def test_knn_explicit(): knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=False) r = knn.fit_transform(dist) assert np.array_equal(r, [[0, 1], [1, 0], [2, 0]]) - knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=True) + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=True, sort_results=True) r = knn.fit_transform(dist) assert np.array_equal(r[0], [[0, 1], [1, 0], [2, 0]]) assert np.array_equal(r[1], [[0, 3], [0, 1], [0, 1]]) # Second time in parallel - knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=False, n_jobs=2) + knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=False, n_jobs=2, sort_results=True) r = knn.fit_transform(dist) assert np.array_equal(r, [[0, 1], [1, 0], [2, 0]]) knn = KNearestNeighbors(2, metric="precomputed", return_index=True, return_distance=True, n_jobs=2) -- cgit v1.2.3 From bac284bf7f65c40f03ec8e47316d4f0fd0059c91 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 20 Apr 2020 19:12:35 +0200 Subject: Check that dependencies are present before testing --- src/python/CMakeLists.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index 10dcd161..5ab63e5d 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -401,7 +401,9 @@ if(PYTHONINTERP_FOUND) # Wasserstein if(OT_FOUND AND PYBIND11_FOUND) - add_gudhi_py_test(test_wasserstein_distance) + if(TORCH_FOUND AND EAGERPY_FOUND) + add_gudhi_py_test(test_wasserstein_distance) + endif() add_gudhi_py_test(test_wasserstein_barycenter) endif() -- cgit v1.2.3 From 4ad650bc3184f57e1dda91f6b0a6358830f0562f Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 20 Apr 2020 19:42:34 +0200 Subject: Drop one comment --- src/python/gudhi/wasserstein/wasserstein.py | 1 - 1 file changed, 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 5b61d176..42c8dc2d 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -167,7 +167,6 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a dists.append(_perstot_autodiff(Y_orig[diag2], order, internal_p)) dists = [dist.reshape(1) for dist in dists] return ep.concatenate(dists).norms.lp(order).raw - # Should just compute the L^order norm manually? # We can also concatenate the 3 vectors to compute just one norm. # Comptuation of the otcost using the ot.emd2 library. -- cgit v1.2.3 From 3e713cee177e10536ae8fc231e56fa04769a35ee Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 20 Apr 2020 22:06:38 +0200 Subject: Fix #279 --- src/python/CMakeLists.txt | 129 +++++++++++++++++++++++----------------------- 1 file changed, 65 insertions(+), 64 deletions(-) (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index 10dcd161..055d5b23 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -242,6 +242,71 @@ if(PYTHONINTERP_FOUND) install(CODE "execute_process(COMMAND ${PYTHON_EXECUTABLE} ${CMAKE_CURRENT_BINARY_DIR}/setup.py install)") + # Documentation generation is available through sphinx - requires all modules + # Make it first as sphinx test is by far the longest test which is nice when testing in parallel + if(SPHINX_PATH) + if(MATPLOTLIB_FOUND) + if(NUMPY_FOUND) + if(SCIPY_FOUND) + if(SKLEARN_FOUND) + if(OT_FOUND) + if(PYBIND11_FOUND) + if(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + set (GUDHI_SPHINX_MESSAGE "Generating API documentation with Sphinx in ${CMAKE_CURRENT_BINARY_DIR}/sphinx/") + # User warning - Sphinx is a static pages generator, and configured to work fine with user_version + # Images and biblio warnings because not found on developper version + if (GUDHI_PYTHON_PATH STREQUAL "src/python") + set (GUDHI_SPHINX_MESSAGE "${GUDHI_SPHINX_MESSAGE} \n WARNING : Sphinx is configured for user version, you run it on developper version. Images and biblio will miss") + endif() + # sphinx target requires gudhi.so, because conf.py reads gudhi version from it + add_custom_target(sphinx + WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/doc + COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" + ${SPHINX_PATH} -b html ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/sphinx + DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/gudhi.so" + COMMENT "${GUDHI_SPHINX_MESSAGE}" VERBATIM) + + add_test(NAME sphinx_py_test + WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR} + COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" + ${SPHINX_PATH} -b doctest ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/doctest) + + # Set missing or not modules + set(GUDHI_MODULES ${GUDHI_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MODULES") + else(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + message("++ Python documentation module will not be compiled because it requires a Eigen3 and CGAL version >= 4.11.0") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) + else(PYBIND11_FOUND) + message("++ Python documentation module will not be compiled because pybind11 was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(PYBIND11_FOUND) + else(OT_FOUND) + message("++ Python documentation module will not be compiled because POT was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(OT_FOUND) + else(SKLEARN_FOUND) + message("++ Python documentation module will not be compiled because scikit-learn was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(SKLEARN_FOUND) + else(SCIPY_FOUND) + message("++ Python documentation module will not be compiled because scipy was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(SCIPY_FOUND) + else(NUMPY_FOUND) + message("++ Python documentation module will not be compiled because numpy was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(NUMPY_FOUND) + else(MATPLOTLIB_FOUND) + message("++ Python documentation module will not be compiled because matplotlib was not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(MATPLOTLIB_FOUND) + else(SPHINX_PATH) + message("++ Python documentation module will not be compiled because sphinx and sphinxcontrib-bibtex were not found") + set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") + endif(SPHINX_PATH) + + # Test examples if (NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) # Bottleneck and Alpha @@ -419,70 +484,6 @@ if(PYTHONINTERP_FOUND) add_gudhi_py_test(test_dtm) endif() - # Documentation generation is available through sphinx - requires all modules - if(SPHINX_PATH) - if(MATPLOTLIB_FOUND) - if(NUMPY_FOUND) - if(SCIPY_FOUND) - if(SKLEARN_FOUND) - if(OT_FOUND) - if(PYBIND11_FOUND) - if(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - set (GUDHI_SPHINX_MESSAGE "Generating API documentation with Sphinx in ${CMAKE_CURRENT_BINARY_DIR}/sphinx/") - # User warning - Sphinx is a static pages generator, and configured to work fine with user_version - # Images and biblio warnings because not found on developper version - if (GUDHI_PYTHON_PATH STREQUAL "src/python") - set (GUDHI_SPHINX_MESSAGE "${GUDHI_SPHINX_MESSAGE} \n WARNING : Sphinx is configured for user version, you run it on developper version. Images and biblio will miss") - endif() - # sphinx target requires gudhi.so, because conf.py reads gudhi version from it - add_custom_target(sphinx - WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/doc - COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" - ${SPHINX_PATH} -b html ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/sphinx - DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/gudhi.so" - COMMENT "${GUDHI_SPHINX_MESSAGE}" VERBATIM) - - add_test(NAME sphinx_py_test - WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR} - COMMAND ${CMAKE_COMMAND} -E env "PYTHONPATH=${CMAKE_CURRENT_BINARY_DIR}" - ${SPHINX_PATH} -b doctest ${CMAKE_CURRENT_SOURCE_DIR}/doc ${CMAKE_CURRENT_BINARY_DIR}/doctest) - - # Set missing or not modules - set(GUDHI_MODULES ${GUDHI_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MODULES") - else(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - message("++ Python documentation module will not be compiled because it requires a Eigen3 and CGAL version >= 4.11.0") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - else(PYBIND11_FOUND) - message("++ Python documentation module will not be compiled because pybind11 was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(PYBIND11_FOUND) - else(OT_FOUND) - message("++ Python documentation module will not be compiled because POT was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(OT_FOUND) - else(SKLEARN_FOUND) - message("++ Python documentation module will not be compiled because scikit-learn was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(SKLEARN_FOUND) - else(SCIPY_FOUND) - message("++ Python documentation module will not be compiled because scipy was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(SCIPY_FOUND) - else(NUMPY_FOUND) - message("++ Python documentation module will not be compiled because numpy was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(NUMPY_FOUND) - else(MATPLOTLIB_FOUND) - message("++ Python documentation module will not be compiled because matplotlib was not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(MATPLOTLIB_FOUND) - else(SPHINX_PATH) - message("++ Python documentation module will not be compiled because sphinx and sphinxcontrib-bibtex were not found") - set(GUDHI_MISSING_MODULES ${GUDHI_MISSING_MODULES} "python-documentation" CACHE INTERNAL "GUDHI_MISSING_MODULES") - endif(SPHINX_PATH) - - # Set missing or not modules set(GUDHI_MODULES ${GUDHI_MODULES} "python" CACHE INTERNAL "GUDHI_MODULES") else(CYTHON_FOUND) -- cgit v1.2.3 From aa90b98bee73ab2aaf39ef91f39f5a750168e5d4 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 13:04:15 +0200 Subject: Document several optional dependencies of knn --- src/python/doc/installation.rst | 28 ++++++++++++++++++++++++++++ src/python/gudhi/point_cloud/knn.py | 3 ++- 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/installation.rst b/src/python/doc/installation.rst index 48425d5e..09a843d5 100644 --- a/src/python/doc/installation.rst +++ b/src/python/doc/installation.rst @@ -211,6 +211,14 @@ The following examples requires CGAL version ≥ 4.11.0: * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` +EagerPy +======= + +Some Python functions can handle automatic differentiation (possibly only when +a flag `enable_autodiff=True` is used). In order to reduce code duplication, we +use `EagerPy `_ which wraps arrays from +PyTorch, TensorFlow and JAX in a common interface. + Eigen ===== @@ -229,6 +237,13 @@ The following examples require `Eigen `_ version * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` +Hnswlib +======= + +:class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package +`Hnswlib `_ as a backend if explicitly +requested, to speed-up queries. + Matplotlib ========== @@ -251,6 +266,13 @@ The following examples require the `Matplotlib `_: * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` +PyKeOps +======= + +:class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package +`PyKeOps `_ as a backend if +explicitly requested, to speed-up queries using a GPU. + Python Optimal Transport ======================== @@ -258,6 +280,12 @@ The :doc:`Wasserstein distance ` module requires `POT `_, a library that provides several solvers for optimization problems related to Optimal Transport. +PyTorch +======= + +`PyTorch `_ is currently only used as a dependency of +`PyKeOps`_, and in some tests. + Scikit-learn ============ diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 4017e498..07553d6d 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -44,7 +44,8 @@ class KNearestNeighbors: Otherwise, neighbors are returned in an arbitrary order. Defaults to True. enable_autodiff (bool): if the input is a torch.tensor, jax.numpy.ndarray or tensorflow.Tensor, this instructs the function to compute distances in a way that works with automatic differentiation. - This is experimental and not supported for all metrics. Defaults to False. + This is experimental, not supported for all metrics, and requires the package EagerPy. + Defaults to False. kwargs: additional parameters are forwarded to the backends. """ self.k = k -- cgit v1.2.3 From da2a7a68f8f57495080af37cf981f64228d165a2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 14:06:02 +0200 Subject: Rename local variables --- src/python/gudhi/wasserstein/wasserstein.py | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 42c8dc2d..3d1caeb3 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -154,17 +154,17 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a if enable_autodiff: P = ot.emd(a=a, b=b, M=M, numItermax=2000000) - pairs = np.argwhere(P[:-1, :-1]) - diag1 = np.nonzero(P[:-1, -1]) - diag2 = np.nonzero(P[-1, :-1]) + pairs_X_Y = np.argwhere(P[:-1, :-1]) + pairs_X_diag = np.nonzero(P[:-1, -1]) + pairs_Y_diag = np.nonzero(P[-1, :-1]) dists = [] # empty arrays are not handled properly by the helpers, so we avoid calling them - if len(pairs): - dists.append((Y_orig[pairs[:, 1]] - X_orig[pairs[:, 0]]).norms.lp(internal_p, axis=-1).norms.lp(order)) - if len(diag1): - dists.append(_perstot_autodiff(X_orig[diag1], order, internal_p)) - if len(diag2): - dists.append(_perstot_autodiff(Y_orig[diag2], order, internal_p)) + if len(pairs_X_Y): + dists.append((Y_orig[pairs_X_Y[:, 1]] - X_orig[pairs_X_Y[:, 0]]).norms.lp(internal_p, axis=-1).norms.lp(order)) + if len(pairs_X_diag): + dists.append(_perstot_autodiff(X_orig[pairs_X_diag], order, internal_p)) + if len(pairs_Y_diag): + dists.append(_perstot_autodiff(Y_orig[pairs_Y_diag], order, internal_p)) dists = [dist.reshape(1) for dist in dists] return ep.concatenate(dists).norms.lp(order).raw # We can also concatenate the 3 vectors to compute just one norm. -- cgit v1.2.3 From 51f7b5bb15f351d08af4c26bd1ffdfe979199976 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 16:29:26 +0200 Subject: Test value of computed gradient --- src/python/test/test_wasserstein_distance.py | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index 6bfcb2ee..90d26809 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -105,8 +105,19 @@ def test_wasserstein_distance_grad(): diag2 = torch.tensor([[2.8, 4.45], [9.5, 14.1]], requires_grad=True) diag3 = torch.tensor([[2.8, 4.45], [9.5, 14.1]], requires_grad=True) assert diag1.grad is None and diag2.grad is None and diag3.grad is None - dist1 = pot(diag1, diag2, internal_p=2, order=2, enable_autodiff=True) - dist2 = pot(diag3, torch.tensor([]), internal_p=2, order=2, enable_autodiff=True) - dist1.backward() - dist2.backward() + dist12 = pot(diag1, diag2, internal_p=2, order=2, enable_autodiff=True) + dist30 = pot(diag3, torch.tensor([]), internal_p=2, order=2, enable_autodiff=True) + dist12.backward() + dist30.backward() assert not torch.isnan(diag1.grad).any() and not torch.isnan(diag2.grad).any() and not torch.isnan(diag3.grad).any() + diag4 = torch.tensor([[0., 10.]], requires_grad=True) + diag5 = torch.tensor([[1., 11.], [3., 4.]], requires_grad=True) + dist45 = pot(diag4, diag5, internal_p=1, order=1, enable_autodiff=True) + assert dist45 == 3. + dist45.backward() + assert np.array_equal(diag4.grad, [[-1., -1.]]) + assert np.array_equal(diag5.grad, [[1., 1.], [-1., 1.]]) + diag6 = torch.tensor([[5., 10.]], requires_grad=True) + pot(diag6, diag6, internal_p=2, order=2, enable_autodiff=True).backward() + # https://github.com/jonasrauber/eagerpy/issues/6 + # assert np.array_equal(diag6.grad, [[0., 0.]]) -- cgit v1.2.3 From ba17759cf922d246a0a74ac5cf99f67d48a7d8c3 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 16:52:27 +0200 Subject: Clarify the doc of enable_autodiff --- src/python/gudhi/wasserstein/wasserstein.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 3d1caeb3..0d164eda 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -100,7 +100,10 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). :param enable_autodiff: If X and Y are torch.tensor, tensorflow.Tensor or jax.numpy.ndarray, make the computation - transparent to automatic differentiation. + transparent to automatic differentiation. This requires the package EagerPy. + + .. note:: This considers the function defined on the coordinates of the off-diagonal points of X and Y + and lets the various frameworks compute its gradient. It never pulls new points from the diagonal. :type enable_autodiff: bool :returns: the Wasserstein distance of order q (1 <= q < infinity) between persistence diagrams with respect to the internal_p-norm as ground metric. -- cgit v1.2.3 From a643583a4740fc40cf1e06e6cc1b4d17ca14000f Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 17:39:52 +0200 Subject: Document incompatibility of matching=True and enable_autodiff --- src/python/gudhi/wasserstein/wasserstein.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/wasserstein.py b/src/python/gudhi/wasserstein/wasserstein.py index 0d164eda..89ecab1c 100644 --- a/src/python/gudhi/wasserstein/wasserstein.py +++ b/src/python/gudhi/wasserstein/wasserstein.py @@ -100,7 +100,8 @@ def wasserstein_distance(X, Y, matching=False, order=2., internal_p=2., enable_a :param internal_p: Ground metric on the (upper-half) plane (i.e. norm L^p in R^2); Default value is 2 (Euclidean norm). :param enable_autodiff: If X and Y are torch.tensor, tensorflow.Tensor or jax.numpy.ndarray, make the computation - transparent to automatic differentiation. This requires the package EagerPy. + transparent to automatic differentiation. This requires the package EagerPy and is currently incompatible + with `matching=True`. .. note:: This considers the function defined on the coordinates of the off-diagonal points of X and Y and lets the various frameworks compute its gradient. It never pulls new points from the diagonal. -- cgit v1.2.3 From c5db8c1aec523c0cdf72c75b29e4ba94b51487b8 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 22 Apr 2020 19:46:29 +0200 Subject: Reduce the probability of failure of test_dtm It is expected that hnsw sometimes misses one neighbor, which has an impact on the DTM, especially if the number of neighbors considered is low. --- src/python/test/test_dtm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 859189fa..bff4c267 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -16,7 +16,7 @@ import torch def test_dtm_compare_euclidean(): pts = numpy.random.rand(1000, 4) - k = 3 + k = 6 dtm = DistanceToMeasure(k, implementation="ckdtree") r0 = dtm.fit_transform(pts) dtm = DistanceToMeasure(k, implementation="sklearn") @@ -27,7 +27,7 @@ def test_dtm_compare_euclidean(): assert r2 == pytest.approx(r0) dtm = DistanceToMeasure(k, implementation="hnsw") r3 = dtm.fit_transform(pts) - assert r3 == pytest.approx(r0) + assert r3 == pytest.approx(r0, rel=0.1) from scipy.spatial.distance import cdist d = cdist(pts, pts) -- cgit v1.2.3 From 0f7fe01852dcf827da35460592bd3a17ca0ab08e Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 23 Apr 2020 13:30:32 +0200 Subject: Fix pasto in the doc --- src/python/gudhi/simplex_tree.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 7728ebfc..93f5b332 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -560,7 +560,7 @@ cdef class SimplexTree: """This function writes the persistence intervals of the simplicial complex in a user given file name. - :param persistence_file: The specific dimension. + :param persistence_file: Name of the file. :type persistence_file: string. :note: intervals_in_dim function requires -- cgit v1.2.3 From 658a754397287e8de216ae91d3c9a3c492e4db2d Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Fri, 24 Apr 2020 09:00:39 +0200 Subject: Fix bibliography for sphinx --- src/python/doc/alpha_complex_user.rst | 11 ++--------- src/python/doc/bottleneck_distance_user.rst | 6 ------ src/python/doc/cubical_complex_user.rst | 7 ------- src/python/doc/index.rst | 7 ------- src/python/doc/nerve_gic_complex_ref.rst | 7 ------- src/python/doc/nerve_gic_complex_user.rst | 7 ------- src/python/doc/persistent_cohomology_user.rst | 7 ------- src/python/doc/rips_complex_user.rst | 7 ------- src/python/doc/simplex_tree_user.rst | 7 ------- src/python/doc/tangential_complex_user.rst | 8 -------- src/python/doc/wasserstein_distance_user.rst | 7 ------- src/python/doc/witness_complex_user.rst | 7 ------- src/python/doc/zbibliography.rst | 10 ++++++++++ 13 files changed, 12 insertions(+), 86 deletions(-) create mode 100644 src/python/doc/zbibliography.rst (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 265a82d2..c65e62c8 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -10,9 +10,8 @@ Definition .. include:: alpha_complex_sum.inc `AlphaComplex` is constructing a :doc:`SimplexTree ` using -`Delaunay Triangulation `_ -:cite:`cgal:hdj-t-19b` from `CGAL `_ (the Computational Geometry Algorithms Library -:cite:`cgal:eb-19b`). +`Delaunay Triangulation `_ +from `CGAL `_ (the Computational Geometry Algorithms Library). Remarks ^^^^^^^ @@ -203,9 +202,3 @@ the program output is: [4, 5, 6] -> 22.74 [3, 6] -> 30.25 -CGAL citations --------------- - -.. bibliography:: ../../biblio/how_to_cite_cgal.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/bottleneck_distance_user.rst b/src/python/doc/bottleneck_distance_user.rst index 206fcb63..89da89d3 100644 --- a/src/python/doc/bottleneck_distance_user.rst +++ b/src/python/doc/bottleneck_distance_user.rst @@ -66,9 +66,3 @@ The output is: Bottleneck distance approximation = 0.81 Bottleneck distance value = 0.75 -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index e8c94bf6..e4733653 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -158,10 +158,3 @@ Examples. --------- End user programs are available in python/example/ folder. - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/index.rst b/src/python/doc/index.rst index c153cdfc..13e51047 100644 --- a/src/python/doc/index.rst +++ b/src/python/doc/index.rst @@ -86,10 +86,3 @@ Point cloud utilities ********************* .. include:: point_cloud_sum.inc - -Bibliography -************ - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/nerve_gic_complex_ref.rst b/src/python/doc/nerve_gic_complex_ref.rst index 6a81b7af..abde2e8c 100644 --- a/src/python/doc/nerve_gic_complex_ref.rst +++ b/src/python/doc/nerve_gic_complex_ref.rst @@ -12,10 +12,3 @@ Cover complexes reference manual :show-inheritance: .. automethod:: gudhi.CoverComplex.__init__ - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index f709ce91..9101f45d 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -313,10 +313,3 @@ the program outputs again SC.dot which gives the following visualization after u :alt: Visualization with neato Visualization with neato - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index 506fa3a7..4d743aac 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -111,10 +111,3 @@ We provide several example files: run these examples with -h for details on thei * :download:`rips_complex_diagram_persistence_from_distance_matrix_file_example.py <../example/rips_complex_diagram_persistence_from_distance_matrix_file_example.py>` * :download:`random_cubical_complex_persistence_example.py <../example/random_cubical_complex_persistence_example.py>` * :download:`tangential_complex_plain_homology_from_off_file_example.py <../example/tangential_complex_plain_homology_from_off_file_example.py>` - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/rips_complex_user.rst b/src/python/doc/rips_complex_user.rst index c4bbcfb6..8efb12e6 100644 --- a/src/python/doc/rips_complex_user.rst +++ b/src/python/doc/rips_complex_user.rst @@ -347,10 +347,3 @@ until dimension 1 - one skeleton graph in other words), the output is: points in the persistence diagram will be under the diagonal, and bottleneck distance and persistence graphical tool will not work properly, this is a known issue. - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/simplex_tree_user.rst b/src/python/doc/simplex_tree_user.rst index 1b272c35..3df7617f 100644 --- a/src/python/doc/simplex_tree_user.rst +++ b/src/python/doc/simplex_tree_user.rst @@ -66,10 +66,3 @@ The output is: ([1, 2], 4.0) ([1], 0.0) ([2], 4.0) - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/tangential_complex_user.rst b/src/python/doc/tangential_complex_user.rst index cf8199cc..3d45473b 100644 --- a/src/python/doc/tangential_complex_user.rst +++ b/src/python/doc/tangential_complex_user.rst @@ -194,11 +194,3 @@ The output is: Tangential contains 4 vertices. Inconsistencies has been fixed. - - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index c24da74d..c443bab5 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -164,10 +164,3 @@ The output is: [[0.27916667 0.55416667] [0.7375 0.7625 ] [0.2375 0.2625 ]] - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/witness_complex_user.rst b/src/python/doc/witness_complex_user.rst index 799f5444..08dcd288 100644 --- a/src/python/doc/witness_complex_user.rst +++ b/src/python/doc/witness_complex_user.rst @@ -126,10 +126,3 @@ Example2: Computing persistence using strong relaxed witness complex Here is an example of constructing a strong witness complex filtration and computing persistence on it: * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` - -Bibliography ------------- - -.. bibliography:: ../../biblio/bibliography.bib - :filter: docname in docnames - :style: unsrt diff --git a/src/python/doc/zbibliography.rst b/src/python/doc/zbibliography.rst new file mode 100644 index 00000000..4c377b46 --- /dev/null +++ b/src/python/doc/zbibliography.rst @@ -0,0 +1,10 @@ +:orphan: + +.. To get rid of WARNING: document isn't included in any toctree + +Bibliography +------------ + +.. bibliography:: ../../biblio/bibliography.bib + :style: unsrt + -- cgit v1.2.3 From 66337063d2ee3770275268c264548e99db3ec7f0 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Fri, 24 Apr 2020 19:11:05 +0200 Subject: Code review: plain instead of unsrt for biblio - concatenate biblio files - undo cgal citation removal --- src/cmake/modules/GUDHI_user_version_target.cmake | 6 +++++- src/python/doc/alpha_complex_user.rst | 3 ++- src/python/doc/zbibliography.rst | 2 +- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/cmake/modules/GUDHI_user_version_target.cmake b/src/cmake/modules/GUDHI_user_version_target.cmake index 257d1939..9cf648e3 100644 --- a/src/cmake/modules/GUDHI_user_version_target.cmake +++ b/src/cmake/modules/GUDHI_user_version_target.cmake @@ -26,8 +26,12 @@ add_custom_command(TARGET user_version PRE_BUILD COMMAND ${CMAKE_COMMAND} -E # Generate bib files for Doxygen - cf. root CMakeLists.txt for explanation string(TIMESTAMP GUDHI_VERSION_YEAR "%Y") configure_file(${CMAKE_SOURCE_DIR}/biblio/how_to_cite_gudhi.bib.in "${CMAKE_CURRENT_BINARY_DIR}/biblio/how_to_cite_gudhi.bib" @ONLY) -file(COPY "${CMAKE_SOURCE_DIR}/biblio/how_to_cite_cgal.bib" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/biblio/") file(COPY "${CMAKE_SOURCE_DIR}/biblio/bibliography.bib" DESTINATION "${CMAKE_CURRENT_BINARY_DIR}/biblio/") + +# append cgal citation inside bibliography - sphinx cannot deal with more than one bib file +file(READ "${CMAKE_SOURCE_DIR}/biblio/how_to_cite_cgal.bib" CGAL_CITATION_CONTENT) +file(APPEND "${CMAKE_CURRENT_BINARY_DIR}/biblio/bibliography.bib" "${CGAL_CITATION_CONTENT}") + # Copy biblio directory for user version add_custom_command(TARGET user_version PRE_BUILD COMMAND ${CMAKE_COMMAND} -E copy_directory ${CMAKE_CURRENT_BINARY_DIR}/biblio ${GUDHI_USER_VERSION_DIR}/biblio) diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index c65e62c8..a3b35c10 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -11,7 +11,8 @@ Definition `AlphaComplex` is constructing a :doc:`SimplexTree ` using `Delaunay Triangulation `_ -from `CGAL `_ (the Computational Geometry Algorithms Library). +:cite:`cgal:hdj-t-19b` from `CGAL `_ (the Computational Geometry Algorithms Library +:cite:`cgal:eb-19b`). Remarks ^^^^^^^ diff --git a/src/python/doc/zbibliography.rst b/src/python/doc/zbibliography.rst index 4c377b46..e23fcf25 100644 --- a/src/python/doc/zbibliography.rst +++ b/src/python/doc/zbibliography.rst @@ -6,5 +6,5 @@ Bibliography ------------ .. bibliography:: ../../biblio/bibliography.bib - :style: unsrt + :style: plain -- cgit v1.2.3 From 9e9511152a0495d123091d04af264e187fc6ab21 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Sat, 25 Apr 2020 11:02:14 +0200 Subject: Fix #259 --- src/python/gudhi/persistence_graphical_tools.py | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/persistence_graphical_tools.py b/src/python/gudhi/persistence_graphical_tools.py index cc3db467..03fc9066 100644 --- a/src/python/gudhi/persistence_graphical_tools.py +++ b/src/python/gudhi/persistence_graphical_tools.py @@ -109,9 +109,6 @@ def plot_persistence_barcode( plt.rc('text', usetex=True) plt.rc('font', family='serif') - - persistence = _array_handler(persistence) - if persistence_file != "": if path.isfile(persistence_file): # Reset persistence @@ -126,6 +123,8 @@ def plot_persistence_barcode( print("file " + persistence_file + " not found.") return None + persistence = _array_handler(persistence) + if max_barcodes != 1000: print("Deprecated parameter. It has been replaced by max_intervals") max_intervals = max_barcodes @@ -255,8 +254,6 @@ def plot_persistence_diagram( plt.rc('text', usetex=True) plt.rc('font', family='serif') - persistence = _array_handler(persistence) - if persistence_file != "": if path.isfile(persistence_file): # Reset persistence @@ -271,6 +268,8 @@ def plot_persistence_diagram( print("file " + persistence_file + " not found.") return None + persistence = _array_handler(persistence) + if max_plots != 1000: print("Deprecated parameter. It has been replaced by max_intervals") max_intervals = max_plots @@ -425,8 +424,6 @@ def plot_persistence_density( plt.rc('text', usetex=True) plt.rc('font', family='serif') - persistence = _array_handler(persistence) - if persistence_file != "": if dimension is None: # All dimension case @@ -440,6 +437,7 @@ def plot_persistence_density( return None if len(persistence) > 0: + persistence = _array_handler(persistence) persistence_dim = np.array( [ (dim_interval[1][0], dim_interval[1][1]) -- cgit v1.2.3 From ae80ba10d9bf333a418b255e72c0be2a3c7e73ae Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Sun, 26 Apr 2020 09:16:31 +0200 Subject: Fix alpha complex user sphinx warnings as sphinx was confusing bullet lists and bold font syntax --- src/python/doc/alpha_complex_user.rst | 39 +++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 18 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index a3b35c10..60a2f94e 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -89,25 +89,28 @@ In order to build the alpha complex, first, a Simplex tree is built from the cel Filtration value computation algorithm ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - **for** i : dimension :math:`\rightarrow` 0 **do** - **for all** :math:`\sigma` of dimension i - **if** filtration(:math:`\sigma`) is NaN **then** - filtration(:math:`\sigma`) = :math:`\alpha^2(\sigma)` - **end if** +.. code-block:: bash + + for i : dimension → 0 do + for all σ of dimension i + if filtration(σ) is NaN then + filtration(σ)=α2(σ) + end if + for all τ face of σ do // propagate alpha filtration value + if filtration(τ) is not NaN then + filtration(τ) = min( filtration(τ), filtration(σ) ) + else + if τ is not Gabriel for σ then + filtration(τ) = filtration(σ) + end if + end if + end for + end for + end for + + make_filtration_non_decreasing() + prune_above_filtration() - *//propagate alpha filtration value* - - **for all** :math:`\tau` face of :math:`\sigma` - **if** filtration(:math:`\tau`) is not NaN **then** - filtration(:math:`\tau`) = filtration(:math:`\sigma`) - **end if** - **end for** - **end for** - **end for** - - make_filtration_non_decreasing() - - prune_above_filtration() Dimension 2 ^^^^^^^^^^^ -- cgit v1.2.3 From f47b9607519b5c8c89bbe40341cf5bcc1382f5ef Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Sun, 26 Apr 2020 10:08:29 +0200 Subject: Fix barycenter sphinx warnings --- src/python/doc/alpha_complex_user.rst | 2 +- src/python/gudhi/wasserstein/barycenter.py | 53 +++++++++++++----------------- 2 files changed, 24 insertions(+), 31 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 60a2f94e..02d85389 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -94,7 +94,7 @@ Filtration value computation algorithm for i : dimension → 0 do for all σ of dimension i if filtration(σ) is NaN then - filtration(σ)=α2(σ) + filtration(σ)=α²(σ) end if for all τ face of σ do // propagate alpha filtration value if filtration(τ) is not NaN then diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index de7aea81..1cf8edb3 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -18,8 +18,7 @@ from gudhi.wasserstein import wasserstein_distance def _mean(x, m): ''' :param x: a list of 2D-points, off diagonal, x_0... x_{k-1} - :param m: total amount of points taken into account, - that is we have (m-k) copies of diagonal + :param m: total amount of points taken into account, that is we have (m-k) copies of diagonal :returns: the weighted mean of x with (m-k) copies of the diagonal ''' k = len(x) @@ -33,37 +32,31 @@ def _mean(x, m): def lagrangian_barycenter(pdiagset, init=None, verbose=False): ''' - :param pdiagset: a list of ``numpy.array`` of shape `(n x 2)` - (`n` can variate), encoding a set of - persistence diagrams with only finite coordinates. + :param pdiagset: a list of ``numpy.array`` of shape `(n x 2)` (`n` can variate), encoding a set of persistence + diagrams with only finite coordinates. :param init: The initial value for barycenter estimate. - If ``None``, init is made on a random diagram from the dataset. - Otherwise, it can be an ``int`` - (then initialization is made on ``pdiagset[init]``) - or a `(n x 2)` ``numpy.array`` enconding - a persistence diagram with `n` points. + If ``None``, init is made on a random diagram from the dataset. + Otherwise, it can be an ``int`` (then initialization is made on ``pdiagset[init]``) + or a `(n x 2)` ``numpy.array`` enconding a persistence diagram with `n` points. :type init: ``int``, or (n x 2) ``np.array`` - :param verbose: if ``True``, returns additional information about the - barycenter. + :param verbose: if ``True``, returns additional information about the barycenter. :type verbose: boolean - :returns: If not verbose (default), a ``numpy.array`` encoding - the barycenter estimate of pdiagset - (local minimum of the energy function). - If ``pdiagset`` is empty, returns ``None``. - If verbose, returns a couple ``(Y, log)`` - where ``Y`` is the barycenter estimate, - and ``log`` is a ``dict`` that contains additional informations: - - - `"groupings"`, a list of list of pairs ``(i,j)``. - Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates - that ``pdiagset[k][i]`` is matched to ``Y[j]`` - if ``i = -1`` or ``j = -1``, it means they - represent the diagonal. - - - `"energy"`, ``float`` representing the Frechet energy value obtained. - It is the mean of squared distances of observations to the output. - - - `"nb_iter"`, ``int`` number of iterations performed before convergence of the algorithm. + :returns: If not verbose (default), a ``numpy.array`` encoding the barycenter estimate of pdiagset + (local minimum of the energy function). + If ``pdiagset`` is empty, returns ``None``. + If verbose, returns a couple ``(Y, log)`` where ``Y`` is the barycenter estimate, + and ``log`` is a ``dict`` that contains additional informations: + + - `"groupings"`, a list of list of pairs ``(i,j)``. + + Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates that ``pdiagset[k][i]`` is matched to ``Y[j]`` + if ``i = -1`` or ``j = -1``, it means they represent the diagonal. + + - `"energy"`, ``float`` representing the Frechet energy value obtained. + + It is the mean of squared distances of observations to the output. + + - `"nb_iter"`, ``int`` number of iterations performed before convergence of the algorithm. ''' X = pdiagset # to shorten notations, not a copy m = len(X) # number of diagrams we are averaging -- cgit v1.2.3 From 88043e6b9da458eee7bdb0b9793f94a4e7d0aaa0 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Sun, 26 Apr 2020 10:24:30 +0200 Subject: vim code block has a better highlighting code --- src/python/doc/alpha_complex_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 02d85389..ec218969 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -89,7 +89,7 @@ In order to build the alpha complex, first, a Simplex tree is built from the cel Filtration value computation algorithm ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -.. code-block:: bash +.. code-block:: vim for i : dimension → 0 do for all σ of dimension i -- cgit v1.2.3 From 484732c8ad30721ba4fa596bcb8a3835ad3bc431 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 27 Apr 2020 07:06:16 +0200 Subject: lint pseudo code --- src/python/doc/alpha_complex_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index ec218969..de706de9 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -94,7 +94,7 @@ Filtration value computation algorithm for i : dimension → 0 do for all σ of dimension i if filtration(σ) is NaN then - filtration(σ)=α²(σ) + filtration(σ) = α²(σ) end if for all τ face of σ do // propagate alpha filtration value if filtration(τ) is not NaN then -- cgit v1.2.3 From 87311ec2d59211320e763bc9bc531858b489ff7e Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Tue, 28 Apr 2020 13:28:10 -0400 Subject: added call methods + other fixes --- .../diagram_vectorizations_distances_kernels.py | 98 +++++++--------------- src/python/gudhi/representations/kernel_methods.py | 88 +++++++++++++++---- src/python/gudhi/representations/metrics.py | 97 +++++++++++++++++---- src/python/gudhi/representations/preprocessing.py | 60 +++++++++++++ src/python/gudhi/representations/vector_methods.py | 84 +++++++++++++++++++ 5 files changed, 326 insertions(+), 101 deletions(-) (limited to 'src/python') diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index de22d9e7..ab7d8a16 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -9,26 +9,23 @@ from gudhi.representations import DiagramSelector, Clamping, Landscape, Silhouet TopologicalVector, DiagramScaler, BirthPersistenceTransform,\ PersistenceImage, PersistenceWeightedGaussianKernel, Entropy, \ PersistenceScaleSpaceKernel, SlicedWassersteinDistance,\ - SlicedWassersteinKernel, BottleneckDistance, PersistenceFisherKernel + SlicedWassersteinKernel, BottleneckDistance, PersistenceFisherKernel, WassersteinDistance -D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) -diags = [D] +D1 = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) -diags = DiagramSelector(use=True, point_type="finite").fit_transform(diags) -diags = DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]).fit_transform(diags) -diags = DiagramScaler(use=True, scalers=[([1], Clamping(maximum=.9))]).fit_transform(diags) +proc1, proc2, proc3 = DiagramSelector(use=True, point_type="finite"), DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]), DiagramScaler(use=True, scalers=[([1], Clamping(maximum=.9))]) +D1 = proc3(proc2(proc1(D1))) -D = diags[0] -plt.scatter(D[:,0],D[:,1]) +plt.scatter(D1[:,0], D1[:,1]) plt.plot([0.,1.],[0.,1.]) plt.title("Test Persistence Diagram for vector methods") plt.show() LS = Landscape(resolution=1000) -L = LS.fit_transform(diags) -plt.plot(L[0][:1000]) -plt.plot(L[0][1000:2000]) -plt.plot(L[0][2000:3000]) +L = LS(D1) +plt.plot(L[:1000]) +plt.plot(L[1000:2000]) +plt.plot(L[2000:3000]) plt.title("Landscape") plt.show() @@ -36,50 +33,39 @@ def pow(n): return lambda x: np.power(x[1]-x[0],n) SH = Silhouette(resolution=1000, weight=pow(2)) -sh = SH.fit_transform(diags) -plt.plot(sh[0]) +plt.plot(SH(D1)) plt.title("Silhouette") plt.show() BC = BettiCurve(resolution=1000) -bc = BC.fit_transform(diags) -plt.plot(bc[0]) +plt.plot(BC(D1)) plt.title("Betti Curve") plt.show() CP = ComplexPolynomial(threshold=-1, polynomial_type="T") -cp = CP.fit_transform(diags) -print("Complex polynomial is " + str(cp[0,:])) +print("Complex polynomial is " + str(CP(D1))) TV = TopologicalVector(threshold=-1) -tv = TV.fit_transform(diags) -print("Topological vector is " + str(tv[0,:])) +print("Topological vector is " + str(TV(D1))) PI = PersistenceImage(bandwidth=.1, weight=lambda x: x[1], im_range=[0,1,0,1], resolution=[100,100]) -pi = PI.fit_transform(diags) -plt.imshow(np.flip(np.reshape(pi[0], [100,100]), 0)) +plt.imshow(np.flip(np.reshape(PI(D1), [100,100]), 0)) plt.title("Persistence Image") plt.show() ET = Entropy(mode="scalar") -et = ET.fit_transform(diags) -print("Entropy statistic is " + str(et[0,:])) +print("Entropy statistic is " + str(ET(D1))) ET = Entropy(mode="vector", normalized=False) -et = ET.fit_transform(diags) -plt.plot(et[0]) +plt.plot(ET(D1)) plt.title("Entropy function") plt.show() -D = np.array([[1.,5.],[3.,6.],[2.,7.]]) -diags2 = [D] +D2 = np.array([[1.,5.],[3.,6.],[2.,7.]]) +D2 = proc3(proc2(proc1(D2))) -diags2 = DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]).fit_transform(diags2) - -D = diags[0] -plt.scatter(D[:,0],D[:,1]) -D = diags2[0] -plt.scatter(D[:,0],D[:,1]) +plt.scatter(D1[:,0], D1[:,1]) +plt.scatter(D2[:,0], D2[:,1]) plt.plot([0.,1.],[0.,1.]) plt.title("Test Persistence Diagrams for kernel methods") plt.show() @@ -88,56 +74,34 @@ def arctan(C,p): return lambda x: C*np.arctan(np.power(x[1], p)) PWG = PersistenceWeightedGaussianKernel(bandwidth=1., kernel_approx=None, weight=arctan(1.,1.)) -X = PWG.fit(diags) -Y = PWG.transform(diags2) -print("PWG kernel is " + str(Y[0][0])) +print("PWG kernel is " + str(PWG(D1, D2))) PWG = PersistenceWeightedGaussianKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2])), weight=arctan(1.,1.)) -X = PWG.fit(diags) -Y = PWG.transform(diags2) -print("Approximate PWG kernel is " + str(Y[0][0])) +print("Approximate PWG kernel is " + str(PWG(D1, D2))) PSS = PersistenceScaleSpaceKernel(bandwidth=1.) -X = PSS.fit(diags) -Y = PSS.transform(diags2) -print("PSS kernel is " + str(Y[0][0])) +print("PSS kernel is " + str(PSS(D1, D2))) PSS = PersistenceScaleSpaceKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2]))) -X = PSS.fit(diags) -Y = PSS.transform(diags2) -print("Approximate PSS kernel is " + str(Y[0][0])) +print("Approximate PSS kernel is " + str(PSS(D1, D2))) sW = SlicedWassersteinDistance(num_directions=100) -X = sW.fit(diags) -Y = sW.transform(diags2) -print("SW distance is " + str(Y[0][0])) +print("SW distance is " + str(sW(D1, D2))) SW = SlicedWassersteinKernel(num_directions=100, bandwidth=1.) -X = SW.fit(diags) -Y = SW.transform(diags2) -print("SW kernel is " + str(Y[0][0])) +print("SW kernel is " + str(SW(D1, D2))) W = WassersteinDistance(order=2, internal_p=2, mode="pot") -X = W.fit(diags) -Y = W.transform(diags2) -print("Wasserstein distance (POT) is " + str(Y[0][0])) +print("Wasserstein distance (POT) is " + str(W(D1, D2))) W = WassersteinDistance(order=2, internal_p=2, mode="hera", delta=0.0001) -X = W.fit(diags) -Y = W.transform(diags2) -print("Wasserstein distance (hera) is " + str(Y[0][0])) +print("Wasserstein distance (hera) is " + str(W(D1, D2))) W = BottleneckDistance(epsilon=.001) -X = W.fit(diags) -Y = W.transform(diags2) -print("Bottleneck distance is " + str(Y[0][0])) +print("Bottleneck distance is " + str(W(D1, D2))) PF = PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1.) -X = PF.fit(diags) -Y = PF.transform(diags2) -print("PF kernel is " + str(Y[0][0])) +print("PF kernel is " + str(PF(D1, D2))) PF = PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1., kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2]))) -X = PF.fit(diags) -Y = PF.transform(diags2) -print("Approximate PF kernel is " + str(Y[0][0])) +print("Approximate PF kernel is " + str(PF(D1, D2))) diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py index 50186d63..edd1382a 100644 --- a/src/python/gudhi/representations/kernel_methods.py +++ b/src/python/gudhi/representations/kernel_methods.py @@ -10,14 +10,14 @@ import numpy as np from sklearn.base import BaseEstimator, TransformerMixin from sklearn.metrics import pairwise_distances, pairwise_kernels -from .metrics import SlicedWassersteinDistance, PersistenceFisherDistance, sklearn_wrapper, pairwise_persistence_diagram_distances, sliced_wasserstein_distance, persistence_fisher_distance +from .metrics import SlicedWassersteinDistance, PersistenceFisherDistance, _sklearn_wrapper, pairwise_persistence_diagram_distances, _sliced_wasserstein_distance, _persistence_fisher_distance from .preprocessing import Padding ############################################# # Kernel methods ############################ ############################################# -def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_approx=None, bandwidth=1.): +def _persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence weighted Gaussian kernel value from two persistence diagrams. The persistence weighted Gaussian kernel is computed by convolving the persistence diagram points with weighted Gaussian kernels. See http://proceedings.mlr.press/v48/kusano16.html for more details. @@ -25,7 +25,7 @@ def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_appr D1: (n x 2) numpy.array encoding the (finite points of the) first diagram. Must not contain essential points (i.e. with infinite coordinate). D2: (m x 2) numpy.array encoding the second diagram. bandwidth (double): bandwidth of the Gaussian kernel with which persistence diagrams will be convolved - weight: weight function for the persistence diagram points. This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. + weight: weight function for the persistence diagram points (default constant function, ie lambda x: 1). This function must be defined on 2D points, ie lists or numpy arrays of the form [p_x,p_y]. kernel_approx: kernel approximation class used to speed up computation. Common kernel approximations classes can be found in the scikit-learn library (such as RBFSampler for instance). Returns: @@ -42,7 +42,7 @@ def persistence_weighted_gaussian_kernel(D1, D2, weight=lambda x: 1, kernel_appr E = (1./(np.sqrt(2*np.pi)*bandwidth)) * np.exp(-np.square(pairwise_distances(D1,D2))/(2*bandwidth*bandwidth)) return np.sum(np.multiply(W, E)) -def persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): +def _persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence scale space kernel value from two persistence diagrams. The persistence scale space kernel is computed by adding the symmetric to the diagonal of each point in each persistence diagram, with negative weight, and then convolving the points with a Gaussian kernel. See https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Reininghaus_A_Stable_Multi-Scale_2015_CVPR_paper.pdf for more details. @@ -58,32 +58,32 @@ def persistence_scale_space_kernel(D1, D2, kernel_approx=None, bandwidth=1.): DD1 = np.concatenate([D1, D1[:,[1,0]]], axis=0) DD2 = np.concatenate([D2, D2[:,[1,0]]], axis=0) weight_pss = lambda x: 1 if x[1] >= x[0] else -1 - return 0.5 * persistence_weighted_gaussian_kernel(DD1, DD2, weight=weight_pss, kernel_approx=kernel_approx, bandwidth=bandwidth) + return 0.5 * _persistence_weighted_gaussian_kernel(DD1, DD2, weight=weight_pss, kernel_approx=kernel_approx, bandwidth=bandwidth) -def pairwise_persistence_diagram_kernels(X, Y=None, metric="sliced_wasserstein", **kwargs): +def pairwise_persistence_diagram_kernels(X, Y=None, kernel="sliced_wasserstein", **kwargs): """ This function computes the kernel matrix between two lists of persistence diagrams given as numpy arrays of shape (nx2). Parameters: X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise kernel values are computed from the first list only. - metric: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + kernel: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. Returns: numpy array of shape (nxm): kernel matrix. """ XX = np.reshape(np.arange(len(X)), [-1,1]) YY = None if Y is None else np.reshape(np.arange(len(Y)), [-1,1]) - if metric == "sliced_wasserstein": + if kernel == "sliced_wasserstein": return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="sliced_wasserstein", num_directions=kwargs["num_directions"]) / kwargs["bandwidth"]) - elif metric == "persistence_fisher": + elif kernel == "persistence_fisher": return np.exp(-pairwise_persistence_diagram_distances(X, Y, metric="persistence_fisher", kernel_approx=kwargs["kernel_approx"], bandwidth=kwargs["bandwidth"]) / kwargs["bandwidth_fisher"]) - elif metric == "persistence_scale_space": - return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_scale_space_kernel, X, Y, **kwargs)) - elif metric == "persistence_weighted_gaussian": - return pairwise_kernels(XX, YY, metric=sklearn_wrapper(persistence_weighted_gaussian_kernel, X, Y, **kwargs)) + elif kernel == "persistence_scale_space": + return pairwise_kernels(XX, YY, metric=_sklearn_wrapper(_persistence_scale_space_kernel, X, Y, **kwargs)) + elif kernel == "persistence_weighted_gaussian": + return pairwise_kernels(XX, YY, metric=_sklearn_wrapper(_persistence_weighted_gaussian_kernel, X, Y, **kwargs)) else: - return pairwise_kernels(XX, YY, metric=sklearn_wrapper(metric, **kwargs)) + return pairwise_kernels(XX, YY, metric=_sklearn_wrapper(metric, **kwargs)) class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): """ @@ -121,7 +121,20 @@ class SlicedWassersteinKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise sliced Wasserstein kernel values. """ - return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="sliced_wasserstein", bandwidth=self.bandwidth, num_directions=self.num_directions) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, kernel="sliced_wasserstein", bandwidth=self.bandwidth, num_directions=self.num_directions) + + def __call__(self, diag1, diag2): + """ + Apply SlicedWassersteinKernel on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: sliced Wasserstein kernel value. + """ + return np.exp(-_sliced_wasserstein_distance(diag1, diag2, num_directions=self.num_directions)) / self.bandwidth class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): """ @@ -160,7 +173,20 @@ class PersistenceWeightedGaussianKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence weighted Gaussian kernel values. """ - return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_weighted_gaussian", bandwidth=self.bandwidth, weight=self.weight, kernel_approx=self.kernel_approx) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, kernel="persistence_weighted_gaussian", bandwidth=self.bandwidth, weight=self.weight, kernel_approx=self.kernel_approx) + + def __call__(self, diag1, diag2): + """ + Apply PersistenceWeightedGaussianKernel on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: persistence weighted Gaussian kernel value. + """ + return _persistence_weighted_gaussian_kernel(diag1, diag2, weight=self.weight, kernel_approx=self.kernel_approx, bandwidth=self.bandwidth) class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): """ @@ -197,7 +223,20 @@ class PersistenceScaleSpaceKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence scale space kernel values. """ - return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_scale_space", bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, kernel="persistence_scale_space", bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) + + def __call__(self, diag1, diag2): + """ + Apply PersistenceScaleSpaceKernel on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: persistence scale space kernel value. + """ + return _persistence_scale_space_kernel(diag1, diag2, bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) class PersistenceFisherKernel(BaseEstimator, TransformerMixin): """ @@ -236,5 +275,18 @@ class PersistenceFisherKernel(BaseEstimator, TransformerMixin): Returns: numpy array of shape (number of diagrams in **diagrams**) x (number of diagrams in X): matrix of pairwise persistence Fisher kernel values. """ - return pairwise_persistence_diagram_kernels(X, self.diagrams_, metric="persistence_fisher", bandwidth=self.bandwidth, bandwidth_fisher=self.bandwidth_fisher, kernel_approx=self.kernel_approx) + return pairwise_persistence_diagram_kernels(X, self.diagrams_, kernel="persistence_fisher", bandwidth=self.bandwidth, bandwidth_fisher=self.bandwidth_fisher, kernel_approx=self.kernel_approx) + + def __call__(self, diag1, diag2): + """ + Apply PersistenceFisherKernel on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: persistence Fisher kernel value. + """ + return np.exp(-_persistence_fisher_distance(diag1, diag2, bandwidth=self.bandwidth, kernel_approx=self.kernel_approx)) / self.bandwidth_fisher diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 59440b1a..a4bf19a6 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -17,7 +17,7 @@ from .preprocessing import Padding # Metrics ################################### ############################################# -def sliced_wasserstein_distance(D1, D2, num_directions): +def _sliced_wasserstein_distance(D1, D2, num_directions): """ This is a function for computing the sliced Wasserstein distance from two persistence diagrams. The Sliced Wasserstein distance is computed by projecting the persistence diagrams onto lines, comparing the projections with the 1-norm, and finally averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. @@ -42,7 +42,7 @@ def sliced_wasserstein_distance(D1, D2, num_directions): L1 = np.sum(np.abs(A-B), axis=0) return np.mean(L1) -def compute_persistence_diagram_projections(X, num_directions): +def _compute_persistence_diagram_projections(X, num_directions): """ This is a function for projecting the points of a list of persistence diagrams (as well as their diagonal projections) onto a fixed number of lines sampled uniformly on [-pi/2, pi/2]. This function can be used as a preprocessing step in order to speed up the running time for computing all pairwise sliced Wasserstein distances / kernel values on a list of persistence diagrams. @@ -51,14 +51,14 @@ def compute_persistence_diagram_projections(X, num_directions): num_directions (int): number of lines evenly sampled from [-pi/2,pi/2] in order to approximate and speed up the distance computation. Returns: - XX (list of n numpy arrays of shape (2*numx2)): list of projected persistence diagrams. + list of n numpy arrays of shape (2*numx2): list of projected persistence diagrams. """ thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) XX = [np.vstack([np.matmul(D, lines), np.matmul(np.matmul(D, .5 * np.ones((2,2))), lines)]) for D in X] return XX -def sliced_wasserstein_distance_on_projections(D1, D2): +def _sliced_wasserstein_distance_on_projections(D1, D2): """ This is a function for computing the sliced Wasserstein distance between two persistence diagrams that have already been projected onto some lines. It simply amounts to comparing the sorted projections with the 1-norm, and averaging over the lines. See http://proceedings.mlr.press/v70/carriere17a.html for more details. @@ -76,7 +76,7 @@ def sliced_wasserstein_distance_on_projections(D1, D2): L1 = np.sum(np.abs(A-B), axis=0) return np.mean(L1) -def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): +def _persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): """ This is a function for computing the persistence Fisher distance from two persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. @@ -118,7 +118,7 @@ def persistence_fisher_distance(D1, D2, kernel_approx=None, bandwidth=1.): vectorj = vectorj/vectorj_sum return np.arccos( min(np.dot(np.sqrt(vectori), np.sqrt(vectorj)), 1.) ) -def sklearn_wrapper(metric, X, Y, **kwargs): +def _sklearn_wrapper(metric, X, Y, **kwargs): """ This function is a wrapper for any metric between two persistence diagrams that takes two numpy arrays of shapes (nx2) and (mx2) as arguments. """ @@ -133,7 +133,7 @@ def sklearn_wrapper(metric, X, Y, **kwargs): PAIRWISE_DISTANCE_FUNCTIONS = { "wasserstein": hera_wasserstein_distance, "hera_wasserstein": hera_wasserstein_distance, - "persistence_fisher": persistence_fisher_distance, + "persistence_fisher": _persistence_fisher_distance, } def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwargs): @@ -143,7 +143,7 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa Parameters: X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. - metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a symmetric function taking two numpy arrays of shape (nx2) and (mx2) as inputs. Returns: numpy array of shape (nxm): distance matrix @@ -153,25 +153,25 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa if metric == "bottleneck": try: from .. import bottleneck_distance - return pairwise_distances(XX, YY, metric=sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) + return pairwise_distances(XX, YY, metric=_sklearn_wrapper(bottleneck_distance, X, Y, **kwargs)) except ImportError: print("Gudhi built without CGAL") raise elif metric == "pot_wasserstein": try: from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance - return pairwise_distances(XX, YY, metric=sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) + return pairwise_distances(XX, YY, metric=_sklearn_wrapper(pot_wasserstein_distance, X, Y, **kwargs)) except ImportError: print("POT (Python Optimal Transport) is not installed. Please install POT or use metric='wasserstein' or metric='hera_wasserstein'") raise elif metric == "sliced_wasserstein": - Xproj = compute_persistence_diagram_projections(X, **kwargs) - Yproj = None if Y is None else compute_persistence_diagram_projections(Y, **kwargs) - return pairwise_distances(XX, YY, metric=sklearn_wrapper(sliced_wasserstein_distance_on_projections, Xproj, Yproj)) + Xproj = _compute_persistence_diagram_projections(X, **kwargs) + Yproj = None if Y is None else _compute_persistence_diagram_projections(Y, **kwargs) + return pairwise_distances(XX, YY, metric=_sklearn_wrapper(_sliced_wasserstein_distance_on_projections, Xproj, Yproj)) elif type(metric) == str: - return pairwise_distances(XX, YY, metric=sklearn_wrapper(PAIRWISE_DISTANCE_FUNCTIONS[metric], X, Y, **kwargs)) + return pairwise_distances(XX, YY, metric=_sklearn_wrapper(PAIRWISE_DISTANCE_FUNCTIONS[metric], X, Y, **kwargs)) else: - return pairwise_distances(XX, YY, metric=sklearn_wrapper(metric, X, Y, **kwargs)) + return pairwise_distances(XX, YY, metric=_sklearn_wrapper(metric, X, Y, **kwargs)) class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): """ @@ -209,6 +209,19 @@ class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): """ return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="sliced_wasserstein", num_directions=self.num_directions) + def __call__(self, diag1, diag2): + """ + Apply SlicedWassersteinDistance on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: sliced Wasserstein distance. + """ + return _sliced_wasserstein_distance(diag1, diag2, num_directions=self.num_directions) + class BottleneckDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the bottleneck distance matrix from a list of persistence diagrams. @@ -246,6 +259,24 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric="bottleneck", e=self.epsilon) return Xfit + def __call__(self, diag1, diag2): + """ + Apply BottleneckDistance on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: bottleneck distance. + """ + try: + from .. import bottleneck_distance + return bottleneck_distance(diag1, diag2, e=self.epsilon) + except ImportError: + print("Gudhi built without CGAL") + raise + class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the persistence Fisher distance matrix from a list of persistence diagrams. The persistence Fisher distance is obtained by computing the original Fisher distance between the probability distributions associated to the persistence diagrams given by convolving them with a Gaussian kernel. See http://papers.nips.cc/paper/8205-persistence-fisher-kernel-a-riemannian-manifold-kernel-for-persistence-diagrams for more details. @@ -283,6 +314,19 @@ class PersistenceFisherDistance(BaseEstimator, TransformerMixin): """ return pairwise_persistence_diagram_distances(X, self.diagrams_, metric="persistence_fisher", bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) + def __call__(self, diag1, diag2): + """ + Apply PersistenceFisherDistance on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: persistence Fisher distance. + """ + return _persistence_fisher_distance(diag1, diag2, bandwidth=self.bandwidth, kernel_approx=self.kernel_approx) + class WassersteinDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the Wasserstein distance matrix from a list of persistence diagrams. @@ -325,5 +369,26 @@ class WassersteinDistance(BaseEstimator, TransformerMixin): if self.metric == "hera_wasserstein": Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric=self.metric, order=self.order, internal_p=self.internal_p, delta=self.delta) else: - Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric=self.metric, order=self.order, internal_p=self.internal_p) + Xfit = pairwise_persistence_diagram_distances(X, self.diagrams_, metric=self.metric, order=self.order, internal_p=self.internal_p, matching=False) return Xfit + + def __call__(self, diag1, diag2): + """ + Apply WassersteinDistance on a single pair of persistence diagrams and outputs the result. + + Parameters: + diag1 (n x 2 numpy array): first input persistence diagram. + diag2 (n x 2 numpy array): second input persistence diagram. + + Returns: + float: Wasserstein distance. + """ + if self.metric == "hera_wasserstein": + return hera_wasserstein_distance(diag1, diag2, order=self.order, internal_p=self.internal_p, delta=self.delta) + else: + try: + from gudhi.wasserstein import wasserstein_distance as pot_wasserstein_distance + return pot_wasserstein_distance(diag1, diag2, order=self.order, internal_p=self.internal_p, matching=False) + except ImportError: + print("POT (Python Optimal Transport) is not installed. Please install POT or use metric='wasserstein' or metric='hera_wasserstein'") + raise diff --git a/src/python/gudhi/representations/preprocessing.py b/src/python/gudhi/representations/preprocessing.py index a39b00e4..a8545349 100644 --- a/src/python/gudhi/representations/preprocessing.py +++ b/src/python/gudhi/representations/preprocessing.py @@ -54,6 +54,18 @@ class BirthPersistenceTransform(BaseEstimator, TransformerMixin): Xfit.append(new_diag) return Xfit + def __call__(self, diag): + """ + Apply BirthPersistenceTransform on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + n x 2 numpy array: transformed persistence diagram. + """ + return self.fit_transform([diag])[0] + class Clamping(BaseEstimator, TransformerMixin): """ This is a class for clamping values. It can be used as a parameter for the DiagramScaler class, for instance if you want to clamp abscissae or ordinates of persistence diagrams. @@ -142,6 +154,18 @@ class DiagramScaler(BaseEstimator, TransformerMixin): Xfit[i][:,I] = np.squeeze(scaler.transform(np.reshape(Xfit[i][:,I], [-1,1]))) return Xfit + def __call__(self, diag): + """ + Apply DiagramScaler on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + n x 2 numpy array: transformed persistence diagram. + """ + return self.fit_transform([diag])[0] + class Padding(BaseEstimator, TransformerMixin): """ This is a class for padding a list of persistence diagrams with dummy points, so that all persistence diagrams end up with the same number of points. @@ -186,6 +210,18 @@ class Padding(BaseEstimator, TransformerMixin): Xfit = X return Xfit + def __call__(self, diag): + """ + Apply Padding on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + n x 2 numpy array: padded persistence diagram. + """ + return self.fit_transform([diag])[0] + class ProminentPoints(BaseEstimator, TransformerMixin): """ This is a class for removing points that are close or far from the diagonal in persistence diagrams. If persistence diagrams are n x 2 numpy arrays (i.e. persistence diagrams with ordinary features), points are ordered and thresholded by distance-to-diagonal. If persistence diagrams are n x 1 numpy arrays (i.e. persistence diagrams with essential features), points are not ordered and thresholded by first coordinate. @@ -259,6 +295,18 @@ class ProminentPoints(BaseEstimator, TransformerMixin): Xfit = X return Xfit + def __call__(self, diag): + """ + Apply ProminentPoints on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + n x 2 numpy array: thresholded persistence diagram. + """ + return self.fit_transform([diag])[0] + class DiagramSelector(BaseEstimator, TransformerMixin): """ This is a class for extracting finite or essential points in persistence diagrams. @@ -303,3 +351,15 @@ class DiagramSelector(BaseEstimator, TransformerMixin): else: Xfit = X return Xfit + + def __call__(self, diag): + """ + Apply DiagramSelector on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + n x 2 numpy array: extracted persistence diagram. + """ + return self.fit_transform([diag])[0] diff --git a/src/python/gudhi/representations/vector_methods.py b/src/python/gudhi/representations/vector_methods.py index fe26dbe2..46fee086 100644 --- a/src/python/gudhi/representations/vector_methods.py +++ b/src/python/gudhi/representations/vector_methods.py @@ -81,6 +81,18 @@ class PersistenceImage(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply PersistenceImage on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (number of pixels = **resolution[0]** x **resolution[1]**):: output persistence image. + """ + return self.fit_transform([diag])[0,:] + class Landscape(BaseEstimator, TransformerMixin): """ This is a class for computing persistence landscapes from a list of persistence diagrams. A persistence landscape is a collection of 1D piecewise-linear functions computed from the rank function associated to the persistence diagram. These piecewise-linear functions are then sampled evenly on a given range and the corresponding vectors of samples are concatenated and returned. See http://jmlr.org/papers/v16/bubenik15a.html for more details. @@ -170,6 +182,18 @@ class Landscape(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply Landscape on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (number of samples = **num_landscapes** x **resolution**): output persistence landscape. + """ + return self.fit_transform([diag])[0,:] + class Silhouette(BaseEstimator, TransformerMixin): """ This is a class for computing persistence silhouettes from a list of persistence diagrams. A persistence silhouette is computed by taking a weighted average of the collection of 1D piecewise-linear functions given by the persistence landscapes, and then by evenly sampling this average on a given range. Finally, the corresponding vector of samples is returned. See https://arxiv.org/abs/1312.0308 for more details. @@ -248,6 +272,18 @@ class Silhouette(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply Silhouette on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (**resolution**): output persistence silhouette. + """ + return self.fit_transform([diag])[0,:] + class BettiCurve(BaseEstimator, TransformerMixin): """ This is a class for computing Betti curves from a list of persistence diagrams. A Betti curve is a 1D piecewise-constant function obtained from the rank function. It is sampled evenly on a given range and the vector of samples is returned. See https://www.researchgate.net/publication/316604237_Time_Series_Classification_via_Topological_Data_Analysis for more details. @@ -308,6 +344,18 @@ class BettiCurve(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply BettiCurve on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (**resolution**): output Betti curve. + """ + return self.fit_transform([diag])[0,:] + class Entropy(BaseEstimator, TransformerMixin): """ This is a class for computing persistence entropy. Persistence entropy is a statistic for persistence diagrams inspired from Shannon entropy. This statistic can also be used to compute a feature vector, called the entropy summary function. See https://arxiv.org/pdf/1803.08304.pdf for more details. Note that a previous implementation was contributed by Manuel Soriano-Trigueros. @@ -378,6 +426,18 @@ class Entropy(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply Entropy on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (1 if **mode** = "scalar" else **resolution**): output entropy. + """ + return self.fit_transform([diag])[0,:] + class TopologicalVector(BaseEstimator, TransformerMixin): """ This is a class for computing topological vectors from a list of persistence diagrams. The topological vector associated to a persistence diagram is the sorted vector of a slight modification of the pairwise distances between the persistence diagram points. See https://diglib.eg.org/handle/10.1111/cgf12692 for more details. @@ -431,6 +491,18 @@ class TopologicalVector(BaseEstimator, TransformerMixin): return Xfit + def __call__(self, diag): + """ + Apply TopologicalVector on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (**threshold**): output topological vector. + """ + return self.fit_transform([diag])[0,:] + class ComplexPolynomial(BaseEstimator, TransformerMixin): """ This is a class for computing complex polynomials from a list of persistence diagrams. The persistence diagram points are seen as the roots of some complex polynomial, whose coefficients are returned in a complex vector. See https://link.springer.com/chapter/10.1007%2F978-3-319-23231-7_27 for more details. @@ -490,3 +562,15 @@ class ComplexPolynomial(BaseEstimator, TransformerMixin): coeff = np.array(coeff[::-1])[1:] Xfit[d, :min(thresh, coeff.shape[0])] = coeff[:min(thresh, coeff.shape[0])] return Xfit + + def __call__(self, diag): + """ + Apply ComplexPolynomial on a single persistence diagram and outputs the result. + + Parameters: + diag (n x 2 numpy array): input persistence diagram. + + Returns: + numpy array with shape (**threshold**): output complex vector of coefficients. + """ + return self.fit_transform([diag])[0,:] -- cgit v1.2.3 From b2177e897b575e0c8d17b8ae5ed3259541a06bea Mon Sep 17 00:00:00 2001 From: MathieuCarriere Date: Wed, 29 Apr 2020 19:16:50 -0400 Subject: small modifs --- src/python/doc/representations.rst | 2 +- src/python/example/diagram_vectorizations_distances_kernels.py | 4 +++- src/python/gudhi/representations/kernel_methods.py | 3 ++- src/python/gudhi/representations/metrics.py | 9 ++++----- 4 files changed, 10 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index 11dcbcf9..041e3247 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -10,7 +10,7 @@ Representations manual This module, originally available at https://github.com/MathieuCarriere/sklearn-tda and named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning, by providing implementations of most of the vector representations for persistence diagrams in the literature, in a scikit-learn format. More specifically, it provides tools, using the scikit-learn standard interface, to compute distances and kernels on persistence diagrams, and to convert these diagrams into vectors in Euclidean space. -A diagram is represented as a numpy array of shape (n,2), as can be obtained from :func:`~gudhi.SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. +A diagram is represented as a numpy array of shape (n,2), as can be obtained from :func:`~gudhi.SimplexTree.persistence_intervals_in_dimension` for instance. Points at infinity are represented as a numpy array of shape (n,1), storing only the birth time. The classes in this module can handle several persistence diagrams at once. In that case, the diagrams are provided as a list of numpy arrays. Note that it is not necessary for the diagrams to have the same number of points, i.e., for the corresponding arrays to have the same number of rows: all classes can handle arrays with different shapes. A small example is provided diff --git a/src/python/example/diagram_vectorizations_distances_kernels.py b/src/python/example/diagram_vectorizations_distances_kernels.py index ab7d8a16..c4a71a7a 100755 --- a/src/python/example/diagram_vectorizations_distances_kernels.py +++ b/src/python/example/diagram_vectorizations_distances_kernels.py @@ -13,7 +13,9 @@ from gudhi.representations import DiagramSelector, Clamping, Landscape, Silhouet D1 = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.], [0., np.inf], [5., np.inf]]) -proc1, proc2, proc3 = DiagramSelector(use=True, point_type="finite"), DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]), DiagramScaler(use=True, scalers=[([1], Clamping(maximum=.9))]) +proc1 = DiagramSelector(use=True, point_type="finite") +proc2 = DiagramScaler(use=True, scalers=[([0,1], MinMaxScaler())]) +proc3 = DiagramScaler(use=True, scalers=[([1], Clamping(maximum=.9))]) D1 = proc3(proc2(proc1(D1))) plt.scatter(D1[:,0], D1[:,1]) diff --git a/src/python/gudhi/representations/kernel_methods.py b/src/python/gudhi/representations/kernel_methods.py index edd1382a..596f4f07 100644 --- a/src/python/gudhi/representations/kernel_methods.py +++ b/src/python/gudhi/representations/kernel_methods.py @@ -67,7 +67,8 @@ def pairwise_persistence_diagram_kernels(X, Y=None, kernel="sliced_wasserstein", Parameters: X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise kernel values are computed from the first list only. - kernel: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + kernel: kernel to use. It can be either a string ("sliced_wasserstein", "persistence_scale_space", "persistence_weighted_gaussian", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. If it is a function, make sure that it is symmetric. + **kwargs: optional keyword parameters. Any further parameters are passed directly to the kernel function. See the docs of the various kernel classes in this module. Returns: numpy array of shape (nxm): kernel matrix. diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index a4bf19a6..ce416fb1 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -32,11 +32,9 @@ def _sliced_wasserstein_distance(D1, D2, num_directions): thetas = np.linspace(-np.pi/2, np.pi/2, num=num_directions+1)[np.newaxis,:-1] lines = np.concatenate([np.cos(thetas), np.sin(thetas)], axis=0) approx1 = np.matmul(D1, lines) - diag_proj1 = (1./2) * np.ones((2,2)) - approx_diag1 = np.matmul(np.matmul(D1, diag_proj1), lines) + approx_diag1 = np.matmul(np.broadcast_to(D1.sum(-1,keepdims=True)/2,(len(D1),2)), lines) approx2 = np.matmul(D2, lines) - diag_proj2 = (1./2) * np.ones((2,2)) - approx_diag2 = np.matmul(np.matmul(D2, diag_proj2), lines) + approx_diag2 = np.matmul(np.broadcast_to(D2.sum(-1,keepdims=True)/2,(len(D2),2)), lines) A = np.sort(np.concatenate([approx1, approx_diag2], axis=0), axis=0) B = np.sort(np.concatenate([approx2, approx_diag1], axis=0), axis=0) L1 = np.sum(np.abs(A-B), axis=0) @@ -143,7 +141,8 @@ def pairwise_persistence_diagram_distances(X, Y=None, metric="bottleneck", **kwa Parameters: X (list of n numpy arrays of shape (numx2)): first list of persistence diagrams. Y (list of m numpy arrays of shape (numx2)): second list of persistence diagrams (optional). If None, pairwise distances are computed from the first list only. - metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a symmetric function taking two numpy arrays of shape (nx2) and (mx2) as inputs. + metric: distance to use. It can be either a string ("sliced_wasserstein", "wasserstein", "hera_wasserstein" (Wasserstein distance computed with Hera---note that Hera is also used for the default option "wasserstein"), "pot_wasserstein" (Wasserstein distance computed with POT), "bottleneck", "persistence_fisher") or a function taking two numpy arrays of shape (nx2) and (mx2) as inputs. If it is a function, make sure that it is symmetric and that it outputs 0 if called on the same two arrays. + **kwargs: optional keyword parameters. Any further parameters are passed directly to the distance function. See the docs of the various distance classes in this module. Returns: numpy array of shape (nxm): distance matrix -- cgit v1.2.3 From ac7917ab2cbece048e554e32cc653c14440dbcc0 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Sun, 3 May 2020 20:43:11 +0200 Subject: Fewer copies and no GIL for hera Now the input arrays are not copied as long as they use a float64 data type, even if they are not contiguous. That's not important here, but I wanted an example of how to do it. More importantly, no need to hold the GIL. I was too lazy to benchmark to see if that changed anything... --- src/python/gudhi/hera.cc | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/hera.cc b/src/python/gudhi/hera.cc index 0d562b4c..50d49c77 100644 --- a/src/python/gudhi/hera.cc +++ b/src/python/gudhi/hera.cc @@ -11,14 +11,24 @@ #include #include -#include +#include +#include #include // Hera -#include +#include namespace py = pybind11; -typedef py::array_t Dgm; +typedef py::array_t Dgm; + +// Get m[i,0] and m[i,1] as a pair +auto pairify(void* p, ssize_t h, ssize_t w) { + return [=](ssize_t i){ + char* birth = (char*)p + i * h; + char* death = birth + w; + return std::make_pair(*(double*)birth, *(double*)death); + }; +} double wasserstein_distance( Dgm d1, Dgm d2, @@ -27,16 +37,18 @@ double wasserstein_distance( { py::buffer_info buf1 = d1.request(); py::buffer_info buf2 = d2.request(); + + py::gil_scoped_release release; + // shape (n,2) or (0) for empty if((buf1.ndim!=2 || buf1.shape[1]!=2) && (buf1.ndim!=1 || buf1.shape[0]!=0)) throw std::runtime_error("Diagram 1 must be an array of size n x 2"); if((buf2.ndim!=2 || buf2.shape[1]!=2) && (buf2.ndim!=1 || buf2.shape[0]!=0)) throw std::runtime_error("Diagram 2 must be an array of size n x 2"); - typedef std::array Point; - auto p1 = (Point*)buf1.ptr; - auto p2 = (Point*)buf2.ptr; - auto diag1 = boost::make_iterator_range(p1, p1+buf1.shape[0]); - auto diag2 = boost::make_iterator_range(p2, p2+buf2.shape[0]); + auto cnt1 = boost::counting_range(0, buf1.shape[0]); + auto diag1 = boost::adaptors::transform(cnt1, pairify(buf1.ptr, buf1.strides[0], buf1.strides[1])); + auto cnt2 = boost::counting_range(0, buf2.shape[0]); + auto diag2 = boost::adaptors::transform(cnt2, pairify(buf2.ptr, buf2.strides[0], buf2.strides[1])); hera::AuctionParams params; params.wasserstein_power = wasserstein_power; -- cgit v1.2.3 From 5ad8f41550d94988214fbf128a179d918635c3cf Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 4 May 2020 20:13:05 +0200 Subject: Add some nogil for cython --- src/python/gudhi/alpha_complex.pyx | 17 +++++--- src/python/gudhi/bottleneck.pyx | 20 ++++++--- src/python/gudhi/rips_complex.pyx | 17 ++++---- src/python/gudhi/simplex_tree.pxd | 89 +++++++++++++++++++------------------- src/python/gudhi/simplex_tree.pyx | 14 ++++-- 5 files changed, 88 insertions(+), 69 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/alpha_complex.pyx b/src/python/gudhi/alpha_complex.pyx index e04dc652..d75e374a 100644 --- a/src/python/gudhi/alpha_complex.pyx +++ b/src/python/gudhi/alpha_complex.pyx @@ -27,11 +27,11 @@ __license__ = "GPL v3" cdef extern from "Alpha_complex_interface.h" namespace "Gudhi": cdef cppclass Alpha_complex_interface "Gudhi::alpha_complex::Alpha_complex_interface": - Alpha_complex_interface(vector[vector[double]] points) except + + Alpha_complex_interface(vector[vector[double]] points) nogil except + # bool from_file is a workaround for cython to find the correct signature - Alpha_complex_interface(string off_file, bool from_file) except + - vector[double] get_point(int vertex) except + - void create_simplex_tree(Simplex_tree_interface_full_featured* simplex_tree, double max_alpha_square) except + + Alpha_complex_interface(string off_file, bool from_file) nogil except + + vector[double] get_point(int vertex) nogil except + + void create_simplex_tree(Simplex_tree_interface_full_featured* simplex_tree, double max_alpha_square) nogil except + # AlphaComplex python interface cdef class AlphaComplex: @@ -70,6 +70,7 @@ cdef class AlphaComplex: # The real cython constructor def __cinit__(self, points = None, off_file = ''): + cdef vector[vector[double]] pts if off_file: if os.path.isfile(off_file): self.thisptr = new Alpha_complex_interface( @@ -80,7 +81,9 @@ cdef class AlphaComplex: if points is None: # Empty Alpha construction points=[] - self.thisptr = new Alpha_complex_interface(points) + pts = points + with nogil: + self.thisptr = new Alpha_complex_interface(pts) def __dealloc__(self): @@ -113,6 +116,8 @@ cdef class AlphaComplex: :rtype: SimplexTree """ stree = SimplexTree() + cdef double mas = max_alpha_square cdef intptr_t stree_int_ptr=stree.thisptr - self.thisptr.create_simplex_tree(stree_int_ptr, max_alpha_square) + with nogil: + self.thisptr.create_simplex_tree(stree_int_ptr, mas) return stree diff --git a/src/python/gudhi/bottleneck.pyx b/src/python/gudhi/bottleneck.pyx index af011e88..6a88895e 100644 --- a/src/python/gudhi/bottleneck.pyx +++ b/src/python/gudhi/bottleneck.pyx @@ -17,8 +17,8 @@ __copyright__ = "Copyright (C) 2016 Inria" __license__ = "GPL v3" cdef extern from "Bottleneck_distance_interface.h" namespace "Gudhi::persistence_diagram": - double bottleneck(vector[pair[double, double]], vector[pair[double, double]], double) - double bottleneck(vector[pair[double, double]], vector[pair[double, double]]) + double bottleneck(vector[pair[double, double]], vector[pair[double, double]], double) nogil + double bottleneck(vector[pair[double, double]], vector[pair[double, double]]) nogil def bottleneck_distance(diagram_1, diagram_2, e=None): """This function returns the point corresponding to a given vertex. @@ -40,9 +40,17 @@ def bottleneck_distance(diagram_1, diagram_2, e=None): :rtype: float :returns: the bottleneck distance. """ + cdef vector[pair[double, double]] dgm1 = diagram_1 + cdef vector[pair[double, double]] dgm2 = diagram_2 + cdef double eps + cdef double ret if e is None: - # Default value is the smallest double value (not 0, 0 is for exact version) - return bottleneck(diagram_1, diagram_2) + with nogil: + # Default value is the smallest double value (not 0, 0 is for exact version) + ret = bottleneck(dgm1, dgm2) else: - # Can be 0 for exact version - return bottleneck(diagram_1, diagram_2, e) + eps = e + with nogil: + # Can be 0 for exact version + ret = bottleneck(dgm1, dgm2, eps) + return ret diff --git a/src/python/gudhi/rips_complex.pyx b/src/python/gudhi/rips_complex.pyx index deb8057a..72e82c79 100644 --- a/src/python/gudhi/rips_complex.pyx +++ b/src/python/gudhi/rips_complex.pyx @@ -23,12 +23,12 @@ __license__ = "MIT" cdef extern from "Rips_complex_interface.h" namespace "Gudhi": cdef cppclass Rips_complex_interface "Gudhi::rips_complex::Rips_complex_interface": - Rips_complex_interface() - void init_points(vector[vector[double]] values, double threshold) - void init_matrix(vector[vector[double]] values, double threshold) - void init_points_sparse(vector[vector[double]] values, double threshold, double sparse) - void init_matrix_sparse(vector[vector[double]] values, double threshold, double sparse) - void create_simplex_tree(Simplex_tree_interface_full_featured* simplex_tree, int dim_max) except + + Rips_complex_interface() nogil + void init_points(vector[vector[double]] values, double threshold) nogil + void init_matrix(vector[vector[double]] values, double threshold) nogil + void init_points_sparse(vector[vector[double]] values, double threshold, double sparse) nogil + void init_matrix_sparse(vector[vector[double]] values, double threshold, double sparse) nogil + void create_simplex_tree(Simplex_tree_interface_full_featured* simplex_tree, int dim_max) nogil except + # RipsComplex python interface cdef class RipsComplex: @@ -97,6 +97,7 @@ cdef class RipsComplex: """ stree = SimplexTree() cdef intptr_t stree_int_ptr=stree.thisptr - self.thisref.create_simplex_tree(stree_int_ptr, - max_dimension) + cdef int maxdim = max_dimension + with nogil: + self.thisref.create_simplex_tree(stree_int_ptr, maxdim) return stree diff --git a/src/python/gudhi/simplex_tree.pxd b/src/python/gudhi/simplex_tree.pxd index 1d4ed926..e748ac40 100644 --- a/src/python/gudhi/simplex_tree.pxd +++ b/src/python/gudhi/simplex_tree.pxd @@ -25,57 +25,56 @@ cdef extern from "Simplex_tree_interface.h" namespace "Gudhi": pass cdef cppclass Simplex_tree_simplices_iterator "Gudhi::Simplex_tree_interface::Complex_simplex_iterator": - Simplex_tree_simplices_iterator() - Simplex_tree_simplex_handle& operator*() - Simplex_tree_simplices_iterator operator++() - bint operator!=(Simplex_tree_simplices_iterator) + Simplex_tree_simplices_iterator() nogil + Simplex_tree_simplex_handle& operator*() nogil + Simplex_tree_simplices_iterator operator++() nogil + bint operator!=(Simplex_tree_simplices_iterator) nogil cdef cppclass Simplex_tree_skeleton_iterator "Gudhi::Simplex_tree_interface::Skeleton_simplex_iterator": - Simplex_tree_skeleton_iterator() - Simplex_tree_simplex_handle& operator*() - Simplex_tree_skeleton_iterator operator++() - bint operator!=(Simplex_tree_skeleton_iterator) + Simplex_tree_skeleton_iterator() nogil + Simplex_tree_simplex_handle& operator*() nogil + Simplex_tree_skeleton_iterator operator++() nogil + bint operator!=(Simplex_tree_skeleton_iterator) nogil cdef cppclass Simplex_tree_interface_full_featured "Gudhi::Simplex_tree_interface": - Simplex_tree() - double simplex_filtration(vector[int] simplex) - void assign_simplex_filtration(vector[int] simplex, double filtration) - void initialize_filtration() - int num_vertices() - int num_simplices() - void set_dimension(int dimension) - int dimension() - int upper_bound_dimension() - bool find_simplex(vector[int] simplex) - bool insert(vector[int] simplex, double filtration) - vector[pair[vector[int], double]] get_star(vector[int] simplex) - vector[pair[vector[int], double]] get_cofaces(vector[int] simplex, - int dimension) - void expansion(int max_dim) except + - void remove_maximal_simplex(vector[int] simplex) - bool prune_above_filtration(double filtration) - bool make_filtration_non_decreasing() - void compute_extended_filtration() - vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]] dgm, double min_persistence) + Simplex_tree() nogil + double simplex_filtration(vector[int] simplex) nogil + void assign_simplex_filtration(vector[int] simplex, double filtration) nogil + void initialize_filtration() nogil + int num_vertices() nogil + int num_simplices() nogil + void set_dimension(int dimension) nogil + int dimension() nogil + int upper_bound_dimension() nogil + bool find_simplex(vector[int] simplex) nogil + bool insert(vector[int] simplex, double filtration) nogil + vector[pair[vector[int], double]] get_star(vector[int] simplex) nogil + vector[pair[vector[int], double]] get_cofaces(vector[int] simplex, int dimension) nogil + void expansion(int max_dim) nogil except + + void remove_maximal_simplex(vector[int] simplex) nogil + bool prune_above_filtration(double filtration) nogil + bool make_filtration_non_decreasing() nogil + void compute_extended_filtration() nogil + vector[vector[pair[int, pair[double, double]]]] compute_extended_persistence_subdiagrams(vector[pair[int, pair[double, double]]] dgm, double min_persistence) nogil # Iterators over Simplex tree - pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) - Simplex_tree_simplices_iterator get_simplices_iterator_begin() - Simplex_tree_simplices_iterator get_simplices_iterator_end() - vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() - vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() - Simplex_tree_skeleton_iterator get_skeleton_iterator_begin(int dimension) - Simplex_tree_skeleton_iterator get_skeleton_iterator_end(int dimension) + pair[vector[int], double] get_simplex_and_filtration(Simplex_tree_simplex_handle f_simplex) nogil + Simplex_tree_simplices_iterator get_simplices_iterator_begin() nogil + Simplex_tree_simplices_iterator get_simplices_iterator_end() nogil + vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_begin() nogil + vector[Simplex_tree_simplex_handle].const_iterator get_filtration_iterator_end() nogil + Simplex_tree_skeleton_iterator get_skeleton_iterator_begin(int dimension) nogil + Simplex_tree_skeleton_iterator get_skeleton_iterator_end(int dimension) nogil cdef extern from "Persistent_cohomology_interface.h" namespace "Gudhi": cdef cppclass Simplex_tree_persistence_interface "Gudhi::Persistent_cohomology_interface>": - Simplex_tree_persistence_interface(Simplex_tree_interface_full_featured * st, bool persistence_dim_max) - void compute_persistence(int homology_coeff_field, double min_persistence) - vector[pair[int, pair[double, double]]] get_persistence() - vector[int] betti_numbers() - vector[int] persistent_betti_numbers(double from_value, double to_value) - vector[pair[double,double]] intervals_in_dimension(int dimension) - void write_output_diagram(string diagram_file_name) except + - vector[pair[vector[int], vector[int]]] persistence_pairs() - pair[vector[vector[int]], vector[vector[int]]] lower_star_generators() - pair[vector[vector[int]], vector[vector[int]]] flag_generators() + Simplex_tree_persistence_interface(Simplex_tree_interface_full_featured * st, bool persistence_dim_max) nogil + void compute_persistence(int homology_coeff_field, double min_persistence) nogil + vector[pair[int, pair[double, double]]] get_persistence() nogil + vector[int] betti_numbers() nogil + vector[int] persistent_betti_numbers(double from_value, double to_value) nogil + vector[pair[double,double]] intervals_in_dimension(int dimension) nogil + void write_output_diagram(string diagram_file_name) nogil except + + vector[pair[vector[int], vector[int]]] persistence_pairs() nogil + pair[vector[vector[int]], vector[vector[int]]] lower_star_generators() nogil + pair[vector[vector[int]], vector[vector[int]]] flag_generators() nogil diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 55115cca..e8e4943c 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -33,7 +33,7 @@ cdef class SimplexTree: cdef public intptr_t thisptr # Get the pointer casted as it should be - cdef Simplex_tree_interface_full_featured* get_ptr(self): + cdef Simplex_tree_interface_full_featured* get_ptr(self) nogil: return (self.thisptr) cdef Simplex_tree_persistence_interface * pcohptr @@ -343,7 +343,9 @@ cdef class SimplexTree: :param max_dim: The maximal dimension. :type max_dim: int. """ - self.get_ptr().expansion(max_dim) + cdef int maxdim = max_dim + with nogil: + self.get_ptr().expansion(maxdim) def make_filtration_non_decreasing(self): """This function ensures that each simplex has a higher filtration @@ -449,8 +451,12 @@ cdef class SimplexTree: """ if self.pcohptr != NULL: del self.pcohptr - self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), persistence_dim_max) - self.pcohptr.compute_persistence(homology_coeff_field, min_persistence) + cdef bool pdm = persistence_dim_max + cdef int coef = homology_coeff_field + cdef double minp = min_persistence + with nogil: + self.pcohptr = new Simplex_tree_persistence_interface(self.get_ptr(), pdm) + self.pcohptr.compute_persistence(coef, minp) def betti_numbers(self): """This function returns the Betti numbers of the simplicial complex. -- cgit v1.2.3 From 99549c20e9173b536ac816ab683bc13025f182a2 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Tue, 5 May 2020 11:07:53 +0200 Subject: fix use of threads and n_jobs in Parallel --- src/python/gudhi/point_cloud/knn.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 07553d6d..34e80b5d 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -200,8 +200,8 @@ class KNearestNeighbors: from joblib import Parallel, delayed, effective_n_jobs from sklearn.utils import gen_even_slices - slices = gen_even_slices(len(X), effective_n_jobs(-1)) - parallel = Parallel(backend="threading", n_jobs=-1) + slices = gen_even_slices(len(X), effective_n_jobs(n_jobs)) + parallel = Parallel(prefer="threads", n_jobs=n_jobs) if self.params.get("sort_results", True): def func(M): @@ -242,8 +242,8 @@ class KNearestNeighbors: else: func = lambda M: numpy.partition(M, k - 1)[:, 0:k] - slices = gen_even_slices(len(X), effective_n_jobs(-1)) - parallel = Parallel(backend="threading", n_jobs=-1) + slices = gen_even_slices(len(X), effective_n_jobs(n_jobs)) + parallel = Parallel(prefer="threads", n_jobs=n_jobs) distances = numpy.concatenate(parallel(delayed(func)(X[s]) for s in slices)) return distances return None -- cgit v1.2.3 From dac92c5ae9da6aa21fdcd261737e08d6898dbbdc Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 6 May 2020 12:54:21 +0200 Subject: Avoid reading outside of allocated region The result was unused, but better be safe. --- src/python/gudhi/hera.cc | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/hera.cc b/src/python/gudhi/hera.cc index 50d49c77..63bbb075 100644 --- a/src/python/gudhi/hera.cc +++ b/src/python/gudhi/hera.cc @@ -45,10 +45,12 @@ double wasserstein_distance( throw std::runtime_error("Diagram 1 must be an array of size n x 2"); if((buf2.ndim!=2 || buf2.shape[1]!=2) && (buf2.ndim!=1 || buf2.shape[0]!=0)) throw std::runtime_error("Diagram 2 must be an array of size n x 2"); + ssize_t stride11 = buf1.ndim == 2 ? buf1.strides[1] : 0; + ssize_t stride21 = buf2.ndim == 2 ? buf2.strides[1] : 0; auto cnt1 = boost::counting_range(0, buf1.shape[0]); - auto diag1 = boost::adaptors::transform(cnt1, pairify(buf1.ptr, buf1.strides[0], buf1.strides[1])); + auto diag1 = boost::adaptors::transform(cnt1, pairify(buf1.ptr, buf1.strides[0], stride11)); auto cnt2 = boost::counting_range(0, buf2.shape[0]); - auto diag2 = boost::adaptors::transform(cnt2, pairify(buf2.ptr, buf2.strides[0], buf2.strides[1])); + auto diag2 = boost::adaptors::transform(cnt2, pairify(buf2.ptr, buf2.strides[0], stride21)); hera::AuctionParams params; params.wasserstein_power = wasserstein_power; -- cgit v1.2.3 From 5c5e2c3075235079fda94fc6a159cc5275f85a0c Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 6 May 2020 14:13:14 +0200 Subject: Refactor the numpy -> C++ range conversion If we want to reuse it for bottleneck... --- src/python/gudhi/hera.cc | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/hera.cc b/src/python/gudhi/hera.cc index 63bbb075..5aec1806 100644 --- a/src/python/gudhi/hera.cc +++ b/src/python/gudhi/hera.cc @@ -22,7 +22,7 @@ namespace py = pybind11; typedef py::array_t Dgm; // Get m[i,0] and m[i,1] as a pair -auto pairify(void* p, ssize_t h, ssize_t w) { +static auto pairify(void* p, ssize_t h, ssize_t w) { return [=](ssize_t i){ char* birth = (char*)p + i * h; char* death = birth + w; @@ -30,28 +30,29 @@ auto pairify(void* p, ssize_t h, ssize_t w) { }; } +inline auto numpy_to_range_of_pairs(py::array_t dgm) { + py::buffer_info buf = dgm.request(); + // shape (n,2) or (0) for empty + if((buf.ndim!=2 || buf.shape[1]!=2) && (buf.ndim!=1 || buf.shape[0]!=0)) + throw std::runtime_error("Diagram must be an array of size n x 2"); + // In the case of shape (0), avoid reading non-existing strides[1] even if we won't use it. + ssize_t stride1 = buf.ndim == 2 ? buf.strides[1] : 0; + auto cnt = boost::counting_range(0, buf.shape[0]); + return boost::adaptors::transform(cnt, pairify(buf.ptr, buf.strides[0], stride1)); + // Be careful that the returned range cannot contain references to dead temporaries. +} + double wasserstein_distance( Dgm d1, Dgm d2, double wasserstein_power, double internal_p, double delta) { - py::buffer_info buf1 = d1.request(); - py::buffer_info buf2 = d2.request(); + // I *think* the call to request() has to be before releasing the GIL. + auto diag1 = numpy_to_range_of_pairs(d1); + auto diag2 = numpy_to_range_of_pairs(d2); py::gil_scoped_release release; - // shape (n,2) or (0) for empty - if((buf1.ndim!=2 || buf1.shape[1]!=2) && (buf1.ndim!=1 || buf1.shape[0]!=0)) - throw std::runtime_error("Diagram 1 must be an array of size n x 2"); - if((buf2.ndim!=2 || buf2.shape[1]!=2) && (buf2.ndim!=1 || buf2.shape[0]!=0)) - throw std::runtime_error("Diagram 2 must be an array of size n x 2"); - ssize_t stride11 = buf1.ndim == 2 ? buf1.strides[1] : 0; - ssize_t stride21 = buf2.ndim == 2 ? buf2.strides[1] : 0; - auto cnt1 = boost::counting_range(0, buf1.shape[0]); - auto diag1 = boost::adaptors::transform(cnt1, pairify(buf1.ptr, buf1.strides[0], stride11)); - auto cnt2 = boost::counting_range(0, buf2.shape[0]); - auto diag2 = boost::adaptors::transform(cnt2, pairify(buf2.ptr, buf2.strides[0], stride21)); - hera::AuctionParams params; params.wasserstein_power = wasserstein_power; // hera encodes infinity as -1... -- cgit v1.2.3 From 47e5ac79af3a354358515c0213b28848f878fde6 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Wed, 6 May 2020 22:59:36 +0200 Subject: Reimplement the bottleneck python wrapper with pybind11 --- src/python/CMakeLists.txt | 33 ++++++++++--------- src/python/gudhi/bottleneck.cc | 51 +++++++++++++++++++++++++++++ src/python/gudhi/bottleneck.pyx | 48 --------------------------- src/python/gudhi/hera.cc | 32 +----------------- src/python/include/pybind11_diagram_utils.h | 39 ++++++++++++++++++++++ src/python/setup.py.in | 19 +++++++++-- 6 files changed, 125 insertions(+), 97 deletions(-) create mode 100644 src/python/gudhi/bottleneck.cc delete mode 100644 src/python/gudhi/bottleneck.pyx create mode 100644 src/python/include/pybind11_diagram_utils.h (limited to 'src/python') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index d712e189..976a8b52 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -34,6 +34,7 @@ endfunction( add_gudhi_debug_info ) if(PYTHONINTERP_FOUND) if(PYBIND11_FOUND) add_gudhi_debug_info("Pybind11 version ${PYBIND11_VERSION}") + set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'bottleneck', ") set(GUDHI_PYTHON_MODULES_EXTRA "${GUDHI_PYTHON_MODULES_EXTRA}'hera', ") endif() if(CYTHON_FOUND) @@ -46,7 +47,6 @@ if(PYTHONINTERP_FOUND) set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'reader_utils', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'witness_complex', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'strong_witness_complex', ") - set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'bottleneck', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'nerve_gic', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'subsampling', ") set(GUDHI_PYTHON_MODULES "${GUDHI_PYTHON_MODULES}'tangential_complex', ") @@ -120,24 +120,25 @@ if(PYTHONINTERP_FOUND) set(GUDHI_PYTHON_EXTRA_COMPILE_ARGS "${GUDHI_PYTHON_EXTRA_COMPILE_ARGS}'-DCGAL_EIGEN3_ENABLED', ") endif (EIGEN3_FOUND) - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'off_reader', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'simplex_tree', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'rips_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'cubical_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'periodic_cubical_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'reader_utils', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'witness_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'strong_witness_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'off_reader', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'simplex_tree', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'rips_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'cubical_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'periodic_cubical_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'reader_utils', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'witness_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'strong_witness_complex', ") + set(GUDHI_PYBIND11_MODULES "${GUDHI_PYBIND11_MODULES}'hera', ") if (NOT CGAL_VERSION VERSION_LESS 4.11.0) - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'bottleneck', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'nerve_gic', ") + set(GUDHI_PYBIND11_MODULES "${GUDHI_PYBIND11_MODULES}'bottleneck', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'nerve_gic', ") endif () if (NOT CGAL_WITH_EIGEN3_VERSION VERSION_LESS 4.11.0) - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'alpha_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'subsampling', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'tangential_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'euclidean_witness_complex', ") - set(GUDHI_PYTHON_MODULES_TO_COMPILE "${GUDHI_PYTHON_MODULES_TO_COMPILE}'euclidean_strong_witness_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'alpha_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'subsampling', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'tangential_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'euclidean_witness_complex', ") + set(GUDHI_CYTHON_MODULES "${GUDHI_CYTHON_MODULES}'euclidean_strong_witness_complex', ") endif () if(CGAL_FOUND) diff --git a/src/python/gudhi/bottleneck.cc b/src/python/gudhi/bottleneck.cc new file mode 100644 index 00000000..577e5e0b --- /dev/null +++ b/src/python/gudhi/bottleneck.cc @@ -0,0 +1,51 @@ +/* This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + * See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + * Author(s): Marc Glisse + * + * Copyright (C) 2020 Inria + * + * Modification(s): + * - YYYY/MM Author: Description of the modification + */ + +#include + +#include + +double bottleneck(Dgm d1, Dgm d2, double epsilon) +{ + // I *think* the call to request() has to be before releasing the GIL. + auto diag1 = numpy_to_range_of_pairs(d1); + auto diag2 = numpy_to_range_of_pairs(d2); + + py::gil_scoped_release release; + + return Gudhi::persistence_diagram::bottleneck_distance(diag1, diag2, epsilon); +} + +PYBIND11_MODULE(bottleneck, m) { + m.attr("__license__") = "GPL v3"; + m.def("bottleneck_distance", &bottleneck, + py::arg("diagram_1"), py::arg("diagram_2"), + py::arg("e") = (std::numeric_limits::min)(), + R"pbdoc( + This function returns the point corresponding to a given vertex. + + :param diagram_1: The first diagram. + :type diagram_1: vector[pair[double, double]] + :param diagram_2: The second diagram. + :type diagram_2: vector[pair[double, double]] + :param e: If `e` is 0, this uses an expensive algorithm to compute the + exact distance. + If `e` is not 0, it asks for an additive `e`-approximation, and + currently also allows a small multiplicative error (the last 2 or 3 + bits of the mantissa may be wrong). This version of the algorithm takes + advantage of the limited precision of `double` and is usually a lot + faster to compute, whatever the value of `e`. + + Thus, by default, `e` is the smallest positive double. + :type e: float + :rtype: float + :returns: the bottleneck distance. + )pbdoc"); +} diff --git a/src/python/gudhi/bottleneck.pyx b/src/python/gudhi/bottleneck.pyx deleted file mode 100644 index af011e88..00000000 --- a/src/python/gudhi/bottleneck.pyx +++ /dev/null @@ -1,48 +0,0 @@ -# This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. -# See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. -# Author(s): Vincent Rouvreau -# -# Copyright (C) 2016 Inria -# -# Modification(s): -# - YYYY/MM Author: Description of the modification - -from cython cimport numeric -from libcpp.vector cimport vector -from libcpp.utility cimport pair -import os - -__author__ = "Vincent Rouvreau" -__copyright__ = "Copyright (C) 2016 Inria" -__license__ = "GPL v3" - -cdef extern from "Bottleneck_distance_interface.h" namespace "Gudhi::persistence_diagram": - double bottleneck(vector[pair[double, double]], vector[pair[double, double]], double) - double bottleneck(vector[pair[double, double]], vector[pair[double, double]]) - -def bottleneck_distance(diagram_1, diagram_2, e=None): - """This function returns the point corresponding to a given vertex. - - :param diagram_1: The first diagram. - :type diagram_1: vector[pair[double, double]] - :param diagram_2: The second diagram. - :type diagram_2: vector[pair[double, double]] - :param e: If `e` is 0, this uses an expensive algorithm to compute the - exact distance. - If `e` is not 0, it asks for an additive `e`-approximation, and - currently also allows a small multiplicative error (the last 2 or 3 - bits of the mantissa may be wrong). This version of the algorithm takes - advantage of the limited precision of `double` and is usually a lot - faster to compute, whatever the value of `e`. - - Thus, by default, `e` is the smallest positive double. - :type e: float - :rtype: float - :returns: the bottleneck distance. - """ - if e is None: - # Default value is the smallest double value (not 0, 0 is for exact version) - return bottleneck(diagram_1, diagram_2) - else: - # Can be 0 for exact version - return bottleneck(diagram_1, diagram_2, e) diff --git a/src/python/gudhi/hera.cc b/src/python/gudhi/hera.cc index 5aec1806..ea80a9a8 100644 --- a/src/python/gudhi/hera.cc +++ b/src/python/gudhi/hera.cc @@ -8,39 +8,9 @@ * - YYYY/MM Author: Description of the modification */ -#include -#include - -#include -#include - #include // Hera -#include - -namespace py = pybind11; -typedef py::array_t Dgm; - -// Get m[i,0] and m[i,1] as a pair -static auto pairify(void* p, ssize_t h, ssize_t w) { - return [=](ssize_t i){ - char* birth = (char*)p + i * h; - char* death = birth + w; - return std::make_pair(*(double*)birth, *(double*)death); - }; -} - -inline auto numpy_to_range_of_pairs(py::array_t dgm) { - py::buffer_info buf = dgm.request(); - // shape (n,2) or (0) for empty - if((buf.ndim!=2 || buf.shape[1]!=2) && (buf.ndim!=1 || buf.shape[0]!=0)) - throw std::runtime_error("Diagram must be an array of size n x 2"); - // In the case of shape (0), avoid reading non-existing strides[1] even if we won't use it. - ssize_t stride1 = buf.ndim == 2 ? buf.strides[1] : 0; - auto cnt = boost::counting_range(0, buf.shape[0]); - return boost::adaptors::transform(cnt, pairify(buf.ptr, buf.strides[0], stride1)); - // Be careful that the returned range cannot contain references to dead temporaries. -} +#include double wasserstein_distance( Dgm d1, Dgm d2, diff --git a/src/python/include/pybind11_diagram_utils.h b/src/python/include/pybind11_diagram_utils.h new file mode 100644 index 00000000..d9627258 --- /dev/null +++ b/src/python/include/pybind11_diagram_utils.h @@ -0,0 +1,39 @@ +/* This file is part of the Gudhi Library - https://gudhi.inria.fr/ - which is released under MIT. + * See file LICENSE or go to https://gudhi.inria.fr/licensing/ for full license details. + * Author(s): Marc Glisse + * + * Copyright (C) 2020 Inria + * + * Modification(s): + * - YYYY/MM Author: Description of the modification + */ + +#include +#include + +#include +#include + +namespace py = pybind11; +typedef py::array_t Dgm; + +// Get m[i,0] and m[i,1] as a pair +static auto pairify(void* p, ssize_t h, ssize_t w) { + return [=](ssize_t i){ + char* birth = (char*)p + i * h; + char* death = birth + w; + return std::make_pair(*(double*)birth, *(double*)death); + }; +} + +inline auto numpy_to_range_of_pairs(py::array_t dgm) { + py::buffer_info buf = dgm.request(); + // shape (n,2) or (0) for empty + if((buf.ndim!=2 || buf.shape[1]!=2) && (buf.ndim!=1 || buf.shape[0]!=0)) + throw std::runtime_error("Diagram must be an array of size n x 2"); + // In the case of shape (0), avoid reading non-existing strides[1] even if we won't use it. + ssize_t stride1 = buf.ndim == 2 ? buf.strides[1] : 0; + auto cnt = boost::counting_range(0, buf.shape[0]); + return boost::adaptors::transform(cnt, pairify(buf.ptr, buf.strides[0], stride1)); + // Be careful that the returned range cannot contain references to dead temporaries. +} diff --git a/src/python/setup.py.in b/src/python/setup.py.in index f968bd59..852da910 100644 --- a/src/python/setup.py.in +++ b/src/python/setup.py.in @@ -18,7 +18,8 @@ __author__ = "Vincent Rouvreau" __copyright__ = "Copyright (C) 2016 Inria" __license__ = "MIT" -modules = [@GUDHI_PYTHON_MODULES_TO_COMPILE@] +cython_modules = [@GUDHI_CYTHON_MODULES@] +pybind11_modules = [@GUDHI_PYBIND11_MODULES@] source_dir='@CMAKE_CURRENT_SOURCE_DIR@/gudhi/' extra_compile_args=[@GUDHI_PYTHON_EXTRA_COMPILE_ARGS@] @@ -30,7 +31,7 @@ runtime_library_dirs=[@GUDHI_PYTHON_RUNTIME_LIBRARY_DIRS@] # Create ext_modules list from module list ext_modules = [] -for module in modules: +for module in cython_modules: ext_modules.append(Extension( 'gudhi.' + module, sources = [source_dir + module + '.pyx',], @@ -55,6 +56,20 @@ ext_modules.append(Extension( extra_compile_args=extra_compile_args + [@GUDHI_PYBIND11_EXTRA_COMPILE_ARGS@], )) +if "bottleneck" in pybind11_modules: + ext_modules.append(Extension( + 'gudhi.bottleneck', + sources = [source_dir + 'bottleneck.cc'], + language = 'c++', + include_dirs = include_dirs + + [pybind11.get_include(False), pybind11.get_include(True)], + extra_compile_args=extra_compile_args + [@GUDHI_PYBIND11_EXTRA_COMPILE_ARGS@], + extra_link_args=extra_link_args, + libraries=libraries, + library_dirs=library_dirs, + runtime_library_dirs=runtime_library_dirs, + )) + setup( name = 'gudhi', packages=find_packages(), # find_namespace_packages(include=["gudhi*"]) -- cgit v1.2.3 From d61bfd349274456f8d7e0ccd64839a2d84eea0a0 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 7 May 2020 08:40:55 +0200 Subject: doc --- src/python/gudhi/bottleneck.cc | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/bottleneck.cc b/src/python/gudhi/bottleneck.cc index 577e5e0b..732cb9a8 100644 --- a/src/python/gudhi/bottleneck.cc +++ b/src/python/gudhi/bottleneck.cc @@ -32,9 +32,9 @@ PYBIND11_MODULE(bottleneck, m) { This function returns the point corresponding to a given vertex. :param diagram_1: The first diagram. - :type diagram_1: vector[pair[double, double]] + :type diagram_1: numpy array of shape (m,2) :param diagram_2: The second diagram. - :type diagram_2: vector[pair[double, double]] + :type diagram_2: numpy array of shape (n,2) :param e: If `e` is 0, this uses an expensive algorithm to compute the exact distance. If `e` is not 0, it asks for an additive `e`-approximation, and @@ -42,7 +42,6 @@ PYBIND11_MODULE(bottleneck, m) { bits of the mantissa may be wrong). This version of the algorithm takes advantage of the limited precision of `double` and is usually a lot faster to compute, whatever the value of `e`. - Thus, by default, `e` is the smallest positive double. :type e: float :rtype: float -- cgit v1.2.3 From acc76eb90b8cfe3f8cbb8d30f101c7f879ab61c4 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Thu, 7 May 2020 20:10:46 +0200 Subject: Warn for initialize_filtration --- src/python/gudhi/simplex_tree.pyx | 2 ++ 1 file changed, 2 insertions(+) (limited to 'src/python') diff --git a/src/python/gudhi/simplex_tree.pyx b/src/python/gudhi/simplex_tree.pyx index 55115cca..b23885b4 100644 --- a/src/python/gudhi/simplex_tree.pyx +++ b/src/python/gudhi/simplex_tree.pyx @@ -101,6 +101,8 @@ cdef class SimplexTree: .. deprecated:: 3.2.0 """ + import warnings + warnings.warn("Since Gudhi 3.2, calling SimplexTree.initialize_filtration is unnecessary.", DeprecationWarning) self.get_ptr().initialize_filtration() def num_vertices(self): -- cgit v1.2.3 From 778c0af7dea0c103db85986fe2e2eb5fddd7588f Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Fri, 8 May 2020 10:14:50 +0200 Subject: Loop on pybind11 modules --- src/python/setup.py.in | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) (limited to 'src/python') diff --git a/src/python/setup.py.in b/src/python/setup.py.in index 852da910..b9f4e3f0 100644 --- a/src/python/setup.py.in +++ b/src/python/setup.py.in @@ -46,23 +46,15 @@ for module in cython_modules: ext_modules = cythonize(ext_modules) -ext_modules.append(Extension( - 'gudhi.hera', - sources = [source_dir + 'hera.cc'], - language = 'c++', - include_dirs = include_dirs + - ['@HERA_WASSERSTEIN_INCLUDE_DIR@', - pybind11.get_include(False), pybind11.get_include(True)], - extra_compile_args=extra_compile_args + [@GUDHI_PYBIND11_EXTRA_COMPILE_ARGS@], - )) - -if "bottleneck" in pybind11_modules: +for module in pybind11_modules: + my_include_dirs = include_dirs + [pybind11.get_include(False), pybind11.get_include(True)] + if module == 'hera': + my_include_dirs = ['@HERA_WASSERSTEIN_INCLUDE_DIR@'] + my_include_dirs ext_modules.append(Extension( - 'gudhi.bottleneck', - sources = [source_dir + 'bottleneck.cc'], + 'gudhi.' + module, + sources = [source_dir + module + '.cc'], language = 'c++', - include_dirs = include_dirs + - [pybind11.get_include(False), pybind11.get_include(True)], + include_dirs = my_include_dirs, extra_compile_args=extra_compile_args + [@GUDHI_PYBIND11_EXTRA_COMPILE_ARGS@], extra_link_args=extra_link_args, libraries=libraries, -- cgit v1.2.3 From 0ed4c3bba47d1375acb49596db2c863c38e9a090 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 11 May 2020 08:39:11 +0200 Subject: Fix #299 --- src/python/doc/alpha_complex_sum.inc | 28 ++++---- src/python/doc/cubical_complex_user.rst | 4 +- src/python/doc/fileformats.rst | 2 - src/python/doc/installation.rst | 84 +++++++++++++--------- src/python/doc/nerve_gic_complex_user.rst | 2 +- src/python/doc/persistence_graphical_tools_sum.inc | 22 +++--- .../doc/persistence_graphical_tools_user.rst | 9 +-- src/python/doc/point_cloud.rst | 2 + src/python/doc/point_cloud_sum.inc | 21 +++--- src/python/doc/representations_sum.inc | 22 +++--- src/python/doc/wasserstein_distance_user.rst | 15 +++- src/python/gudhi/persistence_graphical_tools.py | 18 ++--- src/python/gudhi/point_cloud/knn.py | 4 ++ src/python/gudhi/point_cloud/timedelay.py | 5 +- src/python/gudhi/representations/metrics.py | 4 +- 15 files changed, 135 insertions(+), 107 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_sum.inc b/src/python/doc/alpha_complex_sum.inc index 9e6414d0..74331333 100644 --- a/src/python/doc/alpha_complex_sum.inc +++ b/src/python/doc/alpha_complex_sum.inc @@ -1,17 +1,17 @@ .. table:: :widths: 30 40 30 - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | - | ../../doc/Alpha_complex/alpha_complex_representation.png | cells of a Delaunay Triangulation. | | - | :alt: Alpha complex representation | | :Since: GUDHI 2.0.0 | - | :figclass: align-center | The filtration value of each simplex is computed as the **square** of | | - | | the circumradius of the simplex if the circumsphere is empty (the | :License: MIT (`GPL v3 `_) | - | | simplex is then said to be Gabriel), and as the minimum of the | | - | | filtration values of the codimension 1 cofaces that make it not | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | - | | Gabriel otherwise. | | - | | | | - | | For performances reasons, it is advised to use CGAL ≥ 5.0.0. | | - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | * :doc:`alpha_complex_user` | * :doc:`alpha_complex_ref` | - +----------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ + +----------------------------------------------------------------+-------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ + | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | + | ../../doc/Alpha_complex/alpha_complex_representation.png | cells of a Delaunay Triangulation. | | + | :alt: Alpha complex representation | | :Since: GUDHI 2.0.0 | + | :figclass: align-center | The filtration value of each simplex is computed as the **square** of | | + | | the circumradius of the simplex if the circumsphere is empty (the | :License: MIT (`GPL v3 `_) | + | | simplex is then said to be Gabriel), and as the minimum of the | | + | | filtration values of the codimension 1 cofaces that make it not | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | + | | Gabriel otherwise. | | + | | | | + | | For performances reasons, it is advised to use CGAL :math:`\geq` 5.0.0. | | + +----------------------------------------------------------------+-------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ + | * :doc:`alpha_complex_user` | * :doc:`alpha_complex_ref` | + +----------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index e4733653..e6e61d75 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -91,7 +91,7 @@ Currently one input from a text file is used. It uses a format inspired from the we allow any filtration values. As a consequence one cannot use ``-1``'s to indicate missing cubes. If you have missing cubes in your complex, please set their filtration to :math:`+\infty` (aka. ``inf`` in the file). -The file format is described in details in :ref:`Perseus file format` file format section. +The file format is described in details in `Perseus file format `__ section. .. testcode:: @@ -120,7 +120,7 @@ conditions are imposed in all directions, then complex :math:`\mathcal{K}` becam various constructors from the file Bitmap_cubical_complex_periodic_boundary_conditions_base.h to construct cubical complex with periodic boundary conditions. -One can also use Perseus style input files (see :doc:`Perseus `) for the specific periodic case: +One can also use Perseus style input files (see `Perseus file format `__) for the specific periodic case: .. testcode:: diff --git a/src/python/doc/fileformats.rst b/src/python/doc/fileformats.rst index 345dfdba..ae1b00f3 100644 --- a/src/python/doc/fileformats.rst +++ b/src/python/doc/fileformats.rst @@ -80,8 +80,6 @@ Here is a simple sample file in the 3D case:: 1. 1. 1. -.. _Perseus file format: - Perseus ******* diff --git a/src/python/doc/installation.rst b/src/python/doc/installation.rst index 09a843d5..d72e91b5 100644 --- a/src/python/doc/installation.rst +++ b/src/python/doc/installation.rst @@ -12,8 +12,8 @@ The easiest way to install the Python version of GUDHI is using Compiling ********* -The library uses c++14 and requires `Boost `_ ≥ 1.56.0, -`CMake `_ ≥ 3.1 to generate makefiles, +The library uses c++14 and requires `Boost `_ :math:`\geq` 1.56.0, +`CMake `_ :math:`\geq` 3.1 to generate makefiles, `NumPy `_, `Cython `_ and `pybind11 `_ to compile the GUDHI Python module. @@ -21,7 +21,7 @@ It is a multi-platform library and compiles on Linux, Mac OSX and Visual Studio 2017. On `Windows `_ , only Python -≥ 3.5 are available because of the required Visual Studio version. +:math:`\geq` 3.5 are available because of the required Visual Studio version. On other systems, if you have several Python/python installed, the version 2.X will be used by default, but you can force it by adding @@ -30,7 +30,8 @@ will be used by default, but you can force it by adding GUDHI Python module compilation =============================== -To build the GUDHI Python module, run the following commands in a terminal: +After making sure that the `Compilation dependencies`_ are properly installed, +one can build the GUDHI Python module, by running the following commands in a terminal: .. code-block:: bash @@ -188,8 +189,14 @@ Run the following commands in a terminal: Optional third-party library **************************** +Compilation dependencies +======================== + +These third party dependencies are detected by `CMake `_. +They have to be installed before performing the `GUDHI Python module compilation`_. + CGAL -==== +---- Some GUDHI modules (cf. :doc:`modules list `), and few examples require `CGAL `_, a C++ library that provides easy @@ -200,7 +207,7 @@ The procedure to install this library according to your operating system is detailed `here `_. -The following examples requires CGAL version ≥ 4.11.0: +The following examples requires CGAL version :math:`\geq` 4.11.0: .. only:: builder_html @@ -211,23 +218,15 @@ The following examples requires CGAL version ≥ 4.11.0: * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` -EagerPy -======= - -Some Python functions can handle automatic differentiation (possibly only when -a flag `enable_autodiff=True` is used). In order to reduce code duplication, we -use `EagerPy `_ which wraps arrays from -PyTorch, TensorFlow and JAX in a common interface. - Eigen -===== +----- Some GUDHI modules (cf. :doc:`modules list `), and few examples require `Eigen `_, a C++ template library for linear algebra: matrices, vectors, numerical solvers, and related algorithms. -The following examples require `Eigen `_ version ≥ 3.1.0: +The following examples require `Eigen `_ version :math:`\geq` 3.1.0: .. only:: builder_html @@ -237,15 +236,39 @@ The following examples require `Eigen `_ version * :download:`euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_strong_witness_complex_diagram_persistence_from_off_file_example.py>` * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` +Threading Building Blocks +------------------------- + +`Intel® TBB `_ lets you easily write +parallel C++ programs that take full advantage of multicore performance, that +are portable and composable, and that have future-proof scalability. + +Having Intel® TBB installed is recommended to parallelize and accelerate some +GUDHI computations. + +Run time dependencies +===================== + +These third party dependencies are detected by Python `import` mechanism at run time. +They can be installed when required. + +EagerPy +------- + +Some Python functions can handle automatic differentiation (possibly only when +a flag `enable_autodiff=True` is used). In order to reduce code duplication, we +use `EagerPy `_ which wraps arrays from +PyTorch, TensorFlow and JAX in a common interface. + Hnswlib -======= +------- :class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package `Hnswlib `_ as a backend if explicitly requested, to speed-up queries. Matplotlib -========== +---------- The :doc:`persistence graphical tools ` module requires `Matplotlib `_, a Python 2D plotting @@ -267,49 +290,46 @@ The following examples require the `Matplotlib `_: * :download:`euclidean_witness_complex_diagram_persistence_from_off_file_example.py <../example/euclidean_witness_complex_diagram_persistence_from_off_file_example.py>` PyKeOps -======= +------- :class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package `PyKeOps `_ as a backend if explicitly requested, to speed-up queries using a GPU. Python Optimal Transport -======================== +------------------------ The :doc:`Wasserstein distance ` module requires `POT `_, a library that provides several solvers for optimization problems related to Optimal Transport. PyTorch -======= +------- `PyTorch `_ is currently only used as a dependency of `PyKeOps`_, and in some tests. Scikit-learn -============ +------------ The :doc:`persistence representations ` module require `scikit-learn `_, a Python-based ecosystem of open-source software for machine learning. +:class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package +`scikit-learn `_ as a backend if explicitly +requested. + SciPy -===== +----- The :doc:`persistence graphical tools ` and :doc:`Wasserstein distance ` modules require `SciPy `_, a Python-based ecosystem of open-source software for mathematics, science, and engineering. -Threading Building Blocks -========================= - -`Intel® TBB `_ lets you easily write -parallel C++ programs that take full advantage of multicore performance, that -are portable and composable, and that have future-proof scalability. - -Having Intel® TBB installed is recommended to parallelize and accelerate some -GUDHI computations. +:class:`~gudhi.point_cloud.knn.KNearestNeighbors` can use the Python package +`SciPy `_ as a backend if explicitly requested. Bug reports and contributions ***************************** diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index 9101f45d..d5c5438d 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -13,7 +13,7 @@ Visualizations of the simplicial complexes can be done with either neato (from `graphviz `_), `geomview `_, `KeplerMapper `_. -Input point clouds are assumed to be OFF files (cf. :doc:`fileformats`). +Input point clouds are assumed to be OFF files (cf. `OFF file format `__). Covers ------ diff --git a/src/python/doc/persistence_graphical_tools_sum.inc b/src/python/doc/persistence_graphical_tools_sum.inc index b68d3d7e..0f41b420 100644 --- a/src/python/doc/persistence_graphical_tools_sum.inc +++ b/src/python/doc/persistence_graphical_tools_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ - | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | - | img/graphical_tools_representation.png | the user to display easily persistence barcode, diagram or density. | | - | | | :Since: GUDHI 2.0.0 | - | | Note that these functions return the matplotlib axis, allowing | | - | | for further modifications (title, aspect, etc.) | :License: MIT | - | | | | - | | | :Requires: matplotlib, numpy and scipy | - +-----------------------------------------------------------------+-----------------------------------------------------------------------+-----------------------------------------------+ - | * :doc:`persistence_graphical_tools_user` | * :doc:`persistence_graphical_tools_ref` | - +-----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------+ + +-----------------------------------------------------------------+-----------------------------------------------------------------------+----------------------------------------------------------+ + | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | + | img/graphical_tools_representation.png | the user to display easily persistence barcode, diagram or density. | | + | | | :Since: GUDHI 2.0.0 | + | | Note that these functions return the matplotlib axis, allowing | | + | | for further modifications (title, aspect, etc.) | :License: MIT | + | | | | + | | | :Requires: `Matplotlib `__ | + +-----------------------------------------------------------------+-----------------------------------------------------------------------+----------------------------------------------------------+ + | * :doc:`persistence_graphical_tools_user` | * :doc:`persistence_graphical_tools_ref` | + +-----------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/persistence_graphical_tools_user.rst b/src/python/doc/persistence_graphical_tools_user.rst index 91e52703..fce628b1 100644 --- a/src/python/doc/persistence_graphical_tools_user.rst +++ b/src/python/doc/persistence_graphical_tools_user.rst @@ -12,9 +12,6 @@ Definition Show persistence as a barcode ----------------------------- -.. note:: - this function requires matplotlib and numpy to be available - This function can display the persistence result as a barcode: .. plot:: @@ -36,9 +33,6 @@ This function can display the persistence result as a barcode: Show persistence as a diagram ----------------------------- -.. note:: - this function requires matplotlib and numpy to be available - This function can display the persistence result as a diagram: .. plot:: @@ -73,8 +67,7 @@ of shape (N x 2) encoding a persistence diagram (in a given dimension). Persistence density ------------------- -.. note:: - this function requires matplotlib, numpy and scipy to be available +:Requires: `SciPy `__ If you want more information on a specific dimension, for instance: diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index 192f70db..523a9dfa 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -16,6 +16,8 @@ File Readers Subsampling ----------- +:Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 + .. automodule:: gudhi.subsampling :members: :special-members: diff --git a/src/python/doc/point_cloud_sum.inc b/src/python/doc/point_cloud_sum.inc index d4761aba..4315cea6 100644 --- a/src/python/doc/point_cloud_sum.inc +++ b/src/python/doc/point_cloud_sum.inc @@ -1,15 +1,12 @@ .. table:: :widths: 30 40 30 - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, | :Authors: Vincent Rouvreau, Marc Glisse, Masatoshi Takenouchi | - | | :math:`(y_1, y_2, \ldots, y_d)` | find neighbors, embed time series in higher dimension, etc. | | - | | | :Since: GUDHI 2.0.0 | - | | | | - | | | :License: MIT (`GPL v3 `_, BSD-3-Clause, Apache-2.0) | - | | Parts of this package require CGAL. | | - | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | - | | | | - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | * :doc:`point_cloud` | - +----------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ + +-----------------------------------+---------------------------------------------------------------+-------------------------------------------------------------------+ + | | :math:`(x_1, x_2, \ldots, x_d)` | Utilities to process point clouds: read from file, subsample, | :Authors: Vincent Rouvreau, Marc Glisse, Masatoshi Takenouchi | + | | :math:`(y_1, y_2, \ldots, y_d)` | find neighbors, embed time series in higher dimension, etc. | | + | | | :Since: GUDHI 2.0.0 | + | | | | + | | | :License: MIT (`GPL v3 `_, BSD-3-Clause, Apache-2.0) | + +-----------------------------------+---------------------------------------------------------------+-------------------------------------------------------------------+ + | * :doc:`point_cloud` | + +-----------------------------------+-----------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/representations_sum.inc b/src/python/doc/representations_sum.inc index eac89b9d..cdad4716 100644 --- a/src/python/doc/representations_sum.inc +++ b/src/python/doc/representations_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ - | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | - | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | - | | | :Since: GUDHI 3.1.0 | - | | | | - | | | :License: MIT | - | | | | - | | | :Requires: scikit-learn | - +------------------------------------------------------------------+----------------------------------------------------------------+-----------------------------------------------+ - | * :doc:`representations` | - +------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------+ + +------------------------------------------------------------------+----------------------------------------------------------------+--------------------------------------------------------------+ + | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | + | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | + | | | :Since: GUDHI 3.1.0 | + | | | | + | | | :License: MIT | + | | | | + | | | :Requires: `Scikit-learn `__ | + +------------------------------------------------------------------+----------------------------------------------------------------+--------------------------------------------------------------+ + | * :doc:`representations` | + +------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index c443bab5..2d2e2ae7 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -17,12 +17,21 @@ are measured in norm p, for :math:`1 \leq p \leq \infty`. Distance Functions ------------------ -This first implementation uses the Python Optimal Transport library and is based -on ideas from "Large Scale Computation of Means and Cluster for Persistence + +Optimal Transport +***************** + +:Requires: `Python Optimal Transport `__ (POT) :math:`\geq` 0.5.1 + +This first implementation uses the `Python Optimal Transport `__ +library and is based on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport" :cite:`10.5555/3327546.3327645`. .. autofunction:: gudhi.wasserstein.wasserstein_distance +Hera +**** + This other implementation comes from `Hera `_ (BSD-3-Clause) which is based on "Geometry Helps to Compare Persistence Diagrams" @@ -94,6 +103,8 @@ The output is: Barycenters ----------- +:Requires: `Python Optimal Transport `__ (POT) :math:`\geq` 0.5.1 + A Frechet mean (or barycenter) is a generalization of the arithmetic mean in a non linear space such as the one of persistence diagrams. Given a set of persistence diagrams :math:`\mu_1 \dots \mu_n`, it is diff --git a/src/python/gudhi/persistence_graphical_tools.py b/src/python/gudhi/persistence_graphical_tools.py index cc3db467..e36af304 100644 --- a/src/python/gudhi/persistence_graphical_tools.py +++ b/src/python/gudhi/persistence_graphical_tools.py @@ -72,11 +72,11 @@ def plot_persistence_barcode( """This function plots the persistence bar code from persistence values list , a np.array of shape (N x 2) (representing a diagram in a single homology dimension), - or from a :doc:`persistence file `. + or from a `persistence diagram `__ file. :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A :doc:`persistence file ` style name + :param persistence_file: A `persistence diagram `__ file style name (reset persistence if both are set). :type persistence_file: string :param alpha: barcode transparency value (0.0 transparent through 1.0 @@ -214,11 +214,11 @@ def plot_persistence_diagram( ): """This function plots the persistence diagram from persistence values list, a np.array of shape (N x 2) representing a diagram in a single - homology dimension, or from a :doc:`persistence file `. + homology dimension, or from a `persistence diagram `__ file`. :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A :doc:`persistence file ` style name + :param persistence_file: A `persistence diagram `__ file style name (reset persistence if both are set). :type persistence_file: string :param alpha: plot transparency value (0.0 transparent through 1.0 @@ -369,17 +369,19 @@ def plot_persistence_density( """This function plots the persistence density from persistence values list, np.array of shape (N x 2) representing a diagram in a single homology dimension, - or from a :doc:`persistence file `. Be - aware that this function does not distinguish the dimension, it is + or from a `persistence diagram `__ file. + Be aware that this function does not distinguish the dimension, it is up to you to select the required one. This function also does not handle degenerate data set (scipy correlation matrix inversion can fail). + :Requires: `SciPy `__ + :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A :doc:`persistence file ` - style name (reset persistence if both are set). + :param persistence_file: A `persistence diagram `__ + file style name (reset persistence if both are set). :type persistence_file: string :param nbins: Evaluate a gaussian kde on a regular grid of nbins x nbins over data extents (default is 300) diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 34e80b5d..19363097 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -19,6 +19,10 @@ __license__ = "MIT" class KNearestNeighbors: """ Class wrapping several implementations for computing the k nearest neighbors in a point set. + + :Requires: `PyKeOps `__, `SciPy `__, + `Scikit-learn `__, and/or `Hnswlib `__ + in function of the selected `implementation`. """ def __init__(self, k, return_index=True, return_distance=False, metric="euclidean", **kwargs): diff --git a/src/python/gudhi/point_cloud/timedelay.py b/src/python/gudhi/point_cloud/timedelay.py index f01df442..5292e752 100644 --- a/src/python/gudhi/point_cloud/timedelay.py +++ b/src/python/gudhi/point_cloud/timedelay.py @@ -10,9 +10,8 @@ import numpy as np class TimeDelayEmbedding: - """Point cloud transformation class. - Embeds time-series data in the R^d according to [Takens' Embedding Theorem] - (https://en.wikipedia.org/wiki/Takens%27s_theorem) and obtains the + """Point cloud transformation class. Embeds time-series data in the R^d according to + `Takens' Embedding Theorem `_ and obtains the coordinates of each point. Parameters diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index ce416fb1..0a6dd680 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -223,7 +223,9 @@ class SlicedWassersteinDistance(BaseEstimator, TransformerMixin): class BottleneckDistance(BaseEstimator, TransformerMixin): """ - This is a class for computing the bottleneck distance matrix from a list of persistence diagrams. + This is a class for computing the bottleneck distance matrix from a list of persistence diagrams. + + :Requires: `CGAL `__ :math:`\geq` 4.11.0 """ def __init__(self, epsilon=None): """ -- cgit v1.2.3 From 627772e4c5bc7038b0814182dbb918b08356c892 Mon Sep 17 00:00:00 2001 From: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> Date: Mon, 11 May 2020 08:42:40 +0200 Subject: Fixed by @tlacombe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: Théo Lacombe --- src/python/gudhi/wasserstein/barycenter.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index 1cf8edb3..7eeeae7a 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -52,9 +52,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates that ``pdiagset[k][i]`` is matched to ``Y[j]`` if ``i = -1`` or ``j = -1``, it means they represent the diagonal. - - `"energy"`, ``float`` representing the Frechet energy value obtained. - - It is the mean of squared distances of observations to the output. + - `"energy"`, ``float`` representing the Frechet energy value obtained. It is the mean of squared distances of observations to the output. - `"nb_iter"`, ``int`` number of iterations performed before convergence of the algorithm. ''' @@ -149,4 +147,3 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): return Y, log else: return Y - -- cgit v1.2.3 From 779e4c4e8225e279ef8322988d4d06a6c2e06529 Mon Sep 17 00:00:00 2001 From: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> Date: Mon, 11 May 2020 08:43:06 +0200 Subject: Fixed by @tlacombe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: Théo Lacombe --- src/python/gudhi/wasserstein/barycenter.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'src/python') diff --git a/src/python/gudhi/wasserstein/barycenter.py b/src/python/gudhi/wasserstein/barycenter.py index 7eeeae7a..d67bcde7 100644 --- a/src/python/gudhi/wasserstein/barycenter.py +++ b/src/python/gudhi/wasserstein/barycenter.py @@ -47,10 +47,7 @@ def lagrangian_barycenter(pdiagset, init=None, verbose=False): If verbose, returns a couple ``(Y, log)`` where ``Y`` is the barycenter estimate, and ``log`` is a ``dict`` that contains additional informations: - - `"groupings"`, a list of list of pairs ``(i,j)``. - - Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates that ``pdiagset[k][i]`` is matched to ``Y[j]`` - if ``i = -1`` or ``j = -1``, it means they represent the diagonal. + - `"groupings"`, a list of list of pairs ``(i,j)``. Namely, ``G[k] = [...(i, j)...]``, where ``(i,j)`` indicates that `pdiagset[k][i]`` is matched to ``Y[j]`` if ``i = -1`` or ``j = -1``, it means they represent the diagonal. - `"energy"`, ``float`` representing the Frechet energy value obtained. It is the mean of squared distances of observations to the output. -- cgit v1.2.3 From 7e85b0451c686f043b61cde2e5f78674cf8de248 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 11 May 2020 09:31:49 +0200 Subject: Double underscore is not the correct syntax --- src/python/doc/alpha_complex_sum.inc | 28 +++++++++++----------- src/python/doc/bottleneck_distance_sum.inc | 22 ++++++++--------- src/python/doc/cubical_complex_user.rst | 4 ++-- src/python/doc/nerve_gic_complex_sum.inc | 26 ++++++++++---------- src/python/doc/nerve_gic_complex_user.rst | 2 +- src/python/doc/persistence_graphical_tools_sum.inc | 22 ++++++++--------- .../doc/persistence_graphical_tools_user.rst | 2 +- src/python/doc/point_cloud.rst | 2 +- src/python/doc/representations_sum.inc | 22 ++++++++--------- src/python/doc/tangential_complex_sum.inc | 22 ++++++++--------- src/python/doc/wasserstein_distance_user.rst | 6 ++--- src/python/doc/witness_complex_sum.inc | 28 +++++++++++----------- src/python/gudhi/persistence_graphical_tools.py | 14 +++++------ src/python/gudhi/point_cloud/knn.py | 4 ++-- src/python/gudhi/representations/metrics.py | 2 +- 15 files changed, 103 insertions(+), 103 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_sum.inc b/src/python/doc/alpha_complex_sum.inc index 74331333..3aba0d71 100644 --- a/src/python/doc/alpha_complex_sum.inc +++ b/src/python/doc/alpha_complex_sum.inc @@ -1,17 +1,17 @@ .. table:: :widths: 30 40 30 - +----------------------------------------------------------------+-------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | - | ../../doc/Alpha_complex/alpha_complex_representation.png | cells of a Delaunay Triangulation. | | - | :alt: Alpha complex representation | | :Since: GUDHI 2.0.0 | - | :figclass: align-center | The filtration value of each simplex is computed as the **square** of | | - | | the circumradius of the simplex if the circumsphere is empty (the | :License: MIT (`GPL v3 `_) | - | | simplex is then said to be Gabriel), and as the minimum of the | | - | | filtration values of the codimension 1 cofaces that make it not | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | - | | Gabriel otherwise. | | - | | | | - | | For performances reasons, it is advised to use CGAL :math:`\geq` 5.0.0. | | - +----------------------------------------------------------------+-------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | * :doc:`alpha_complex_user` | * :doc:`alpha_complex_ref` | - +----------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ + +----------------------------------------------------------------+-------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------+ + | .. figure:: | Alpha complex is a simplicial complex constructed from the finite | :Author: Vincent Rouvreau | + | ../../doc/Alpha_complex/alpha_complex_representation.png | cells of a Delaunay Triangulation. | | + | :alt: Alpha complex representation | | :Since: GUDHI 2.0.0 | + | :figclass: align-center | The filtration value of each simplex is computed as the **square** of | | + | | the circumradius of the simplex if the circumsphere is empty (the | :License: MIT (`GPL v3 `_) | + | | simplex is then said to be Gabriel), and as the minimum of the | | + | | filtration values of the codimension 1 cofaces that make it not | :Requires: `Eigen `_ :math:`\geq` 3.1.0 and `CGAL `_ :math:`\geq` 4.11.0 | + | | Gabriel otherwise. | | + | | | | + | | For performances reasons, it is advised to use CGAL :math:`\geq` 5.0.0. | | + +----------------------------------------------------------------+-------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------+ + | * :doc:`alpha_complex_user` | * :doc:`alpha_complex_ref` | + +----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/bottleneck_distance_sum.inc b/src/python/doc/bottleneck_distance_sum.inc index 0de4625c..77dc368d 100644 --- a/src/python/doc/bottleneck_distance_sum.inc +++ b/src/python/doc/bottleneck_distance_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ - | .. figure:: | Bottleneck distance measures the similarity between two persistence | :Author: François Godi | - | ../../doc/Bottleneck_distance/perturb_pd.png | diagrams. It's the shortest distance b for which there exists a | | - | :figclass: align-center | perfect matching between the points of the two diagrams (+ all the | :Since: GUDHI 2.0.0 | - | | diagonal points) such that any couple of matched points are at | | - | Bottleneck distance is the length of | distance at most b, where the distance between points is the sup | :License: MIT (`GPL v3 `_) | - | the longest edge | norm in :math:`\mathbb{R}^2`. | | - | | | :Requires: `CGAL `__ :math:`\geq` 4.11.0 | - +-----------------------------------------------------------------+----------------------------------------------------------------------+------------------------------------------------------------------+ - | * :doc:`bottleneck_distance_user` | | - +-----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------+ + +-----------------------------------------------------------------+----------------------------------------------------------------------+-----------------------------------------------------------------+ + | .. figure:: | Bottleneck distance measures the similarity between two persistence | :Author: François Godi | + | ../../doc/Bottleneck_distance/perturb_pd.png | diagrams. It's the shortest distance b for which there exists a | | + | :figclass: align-center | perfect matching between the points of the two diagrams (+ all the | :Since: GUDHI 2.0.0 | + | | diagonal points) such that any couple of matched points are at | | + | Bottleneck distance is the length of | distance at most b, where the distance between points is the sup | :License: MIT (`GPL v3 `_) | + | the longest edge | norm in :math:`\mathbb{R}^2`. | | + | | | :Requires: `CGAL `_ :math:`\geq` 4.11.0 | + +-----------------------------------------------------------------+----------------------------------------------------------------------+-----------------------------------------------------------------+ + | * :doc:`bottleneck_distance_user` | | + +-----------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index e6e61d75..3fd4e27a 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -91,7 +91,7 @@ Currently one input from a text file is used. It uses a format inspired from the we allow any filtration values. As a consequence one cannot use ``-1``'s to indicate missing cubes. If you have missing cubes in your complex, please set their filtration to :math:`+\infty` (aka. ``inf`` in the file). -The file format is described in details in `Perseus file format `__ section. +The file format is described in details in `Perseus file format `_ section. .. testcode:: @@ -120,7 +120,7 @@ conditions are imposed in all directions, then complex :math:`\mathcal{K}` becam various constructors from the file Bitmap_cubical_complex_periodic_boundary_conditions_base.h to construct cubical complex with periodic boundary conditions. -One can also use Perseus style input files (see `Perseus file format `__) for the specific periodic case: +One can also use Perseus style input files (see `Perseus file format `_) for the specific periodic case: .. testcode:: diff --git a/src/python/doc/nerve_gic_complex_sum.inc b/src/python/doc/nerve_gic_complex_sum.inc index 7fe55aff..7db6c124 100644 --- a/src/python/doc/nerve_gic_complex_sum.inc +++ b/src/python/doc/nerve_gic_complex_sum.inc @@ -1,16 +1,16 @@ .. table:: :widths: 30 40 30 - +----------------------------------------------------------------+------------------------------------------------------------------------+------------------------------------------------------------------+ - | .. figure:: | Nerves and Graph Induced Complexes are cover complexes, i.e. | :Author: Mathieu Carrière | - | ../../doc/Nerve_GIC/gicvisu.jpg | simplicial complexes that provably contain topological information | | - | :alt: Graph Induced Complex of a point cloud. | about the input data. They can be computed with a cover of the data, | :Since: GUDHI 2.3.0 | - | :figclass: align-center | that comes i.e. from the preimage of a family of intervals covering | | - | | the image of a scalar-valued function defined on the data. | :License: MIT (`GPL v3 `_) | - | | | | - | | | :Requires: `CGAL `__ :math:`\geq` 4.11.0 | - | | | | - | | | | - +----------------------------------------------------------------+------------------------------------------------------------------------+------------------------------------------------------------------+ - | * :doc:`nerve_gic_complex_user` | * :doc:`nerve_gic_complex_ref` | - +----------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------+ + +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------+ + | .. figure:: | Nerves and Graph Induced Complexes are cover complexes, i.e. | :Author: Mathieu Carrière | + | ../../doc/Nerve_GIC/gicvisu.jpg | simplicial complexes that provably contain topological information | | + | :alt: Graph Induced Complex of a point cloud. | about the input data. They can be computed with a cover of the data, | :Since: GUDHI 2.3.0 | + | :figclass: align-center | that comes i.e. from the preimage of a family of intervals covering | | + | | the image of a scalar-valued function defined on the data. | :License: MIT (`GPL v3 `_) | + | | | | + | | | :Requires: `CGAL `_ :math:`\geq` 4.11.0 | + | | | | + | | | | + +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------+ + | * :doc:`nerve_gic_complex_user` | * :doc:`nerve_gic_complex_ref` | + +----------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/nerve_gic_complex_user.rst b/src/python/doc/nerve_gic_complex_user.rst index d5c5438d..0e67fc78 100644 --- a/src/python/doc/nerve_gic_complex_user.rst +++ b/src/python/doc/nerve_gic_complex_user.rst @@ -13,7 +13,7 @@ Visualizations of the simplicial complexes can be done with either neato (from `graphviz `_), `geomview `_, `KeplerMapper `_. -Input point clouds are assumed to be OFF files (cf. `OFF file format `__). +Input point clouds are assumed to be OFF files (cf. `OFF file format `_). Covers ------ diff --git a/src/python/doc/persistence_graphical_tools_sum.inc b/src/python/doc/persistence_graphical_tools_sum.inc index 0f41b420..7ff63ae2 100644 --- a/src/python/doc/persistence_graphical_tools_sum.inc +++ b/src/python/doc/persistence_graphical_tools_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +-----------------------------------------------------------------+-----------------------------------------------------------------------+----------------------------------------------------------+ - | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | - | img/graphical_tools_representation.png | the user to display easily persistence barcode, diagram or density. | | - | | | :Since: GUDHI 2.0.0 | - | | Note that these functions return the matplotlib axis, allowing | | - | | for further modifications (title, aspect, etc.) | :License: MIT | - | | | | - | | | :Requires: `Matplotlib `__ | - +-----------------------------------------------------------------+-----------------------------------------------------------------------+----------------------------------------------------------+ - | * :doc:`persistence_graphical_tools_user` | * :doc:`persistence_graphical_tools_ref` | - +-----------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------+ + +-----------------------------------------------------------------+-----------------------------------------------------------------------+---------------------------------------------------------+ + | .. figure:: | These graphical tools comes on top of persistence results and allows | :Author: Vincent Rouvreau, Theo Lacombe | + | img/graphical_tools_representation.png | the user to display easily persistence barcode, diagram or density. | | + | | | :Since: GUDHI 2.0.0 | + | | Note that these functions return the matplotlib axis, allowing | | + | | for further modifications (title, aspect, etc.) | :License: MIT | + | | | | + | | | :Requires: `Matplotlib `_ | + +-----------------------------------------------------------------+-----------------------------------------------------------------------+---------------------------------------------------------+ + | * :doc:`persistence_graphical_tools_user` | * :doc:`persistence_graphical_tools_ref` | + +-----------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/persistence_graphical_tools_user.rst b/src/python/doc/persistence_graphical_tools_user.rst index fce628b1..b5a38eb1 100644 --- a/src/python/doc/persistence_graphical_tools_user.rst +++ b/src/python/doc/persistence_graphical_tools_user.rst @@ -67,7 +67,7 @@ of shape (N x 2) encoding a persistence diagram (in a given dimension). Persistence density ------------------- -:Requires: `SciPy `__ +:Requires: `SciPy `_ If you want more information on a specific dimension, for instance: diff --git a/src/python/doc/point_cloud.rst b/src/python/doc/point_cloud.rst index 523a9dfa..ffd8f85b 100644 --- a/src/python/doc/point_cloud.rst +++ b/src/python/doc/point_cloud.rst @@ -16,7 +16,7 @@ File Readers Subsampling ----------- -:Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 +:Requires: `Eigen `_ :math:`\geq` 3.1.0 and `CGAL `_ :math:`\geq` 4.11.0 .. automodule:: gudhi.subsampling :members: diff --git a/src/python/doc/representations_sum.inc b/src/python/doc/representations_sum.inc index cdad4716..323a0920 100644 --- a/src/python/doc/representations_sum.inc +++ b/src/python/doc/representations_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +------------------------------------------------------------------+----------------------------------------------------------------+--------------------------------------------------------------+ - | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | - | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | - | | | :Since: GUDHI 3.1.0 | - | | | | - | | | :License: MIT | - | | | | - | | | :Requires: `Scikit-learn `__ | - +------------------------------------------------------------------+----------------------------------------------------------------+--------------------------------------------------------------+ - | * :doc:`representations` | - +------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------+ + +------------------------------------------------------------------+----------------------------------------------------------------+-------------------------------------------------------------+ + | .. figure:: | Vectorizations, distances and kernels that work on persistence | :Author: Mathieu Carrière | + | img/sklearn-tda.png | diagrams, compatible with scikit-learn. | | + | | | :Since: GUDHI 3.1.0 | + | | | | + | | | :License: MIT | + | | | | + | | | :Requires: `Scikit-learn `_ | + +------------------------------------------------------------------+----------------------------------------------------------------+-------------------------------------------------------------+ + | * :doc:`representations` | + +------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/tangential_complex_sum.inc b/src/python/doc/tangential_complex_sum.inc index 45ce2a66..22314a2d 100644 --- a/src/python/doc/tangential_complex_sum.inc +++ b/src/python/doc/tangential_complex_sum.inc @@ -1,14 +1,14 @@ .. table:: :widths: 30 40 30 - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | .. figure:: | A Tangential Delaunay complex is a simplicial complex designed to | :Author: Clément Jamin | - | ../../doc/Tangential_complex/tc_examples.png | reconstruct a :math:`k`-dimensional manifold embedded in :math:`d`- | | - | :figclass: align-center | dimensional Euclidean space. The input is a point sample coming from | :Since: GUDHI 2.0.0 | - | | an unknown manifold. The running time depends only linearly on the | | - | | extrinsic dimension :math:`d` and exponentially on the intrinsic | :License: MIT (`GPL v3 `_) | - | | dimension :math:`k`. | | - | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 | - +----------------------------------------------------------------+------------------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------+ - | * :doc:`tangential_complex_user` | * :doc:`tangential_complex_ref` | - +----------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ + +----------------------------------------------------------------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------+ + | .. figure:: | A Tangential Delaunay complex is a simplicial complex designed to | :Author: Clément Jamin | + | ../../doc/Tangential_complex/tc_examples.png | reconstruct a :math:`k`-dimensional manifold embedded in :math:`d`- | | + | :figclass: align-center | dimensional Euclidean space. The input is a point sample coming from | :Since: GUDHI 2.0.0 | + | | an unknown manifold. The running time depends only linearly on the | | + | | extrinsic dimension :math:`d` and exponentially on the intrinsic | :License: MIT (`GPL v3 `_) | + | | dimension :math:`k`. | | + | | | :Requires: `Eigen `_ :math:`\geq` 3.1.0 and `CGAL `_ :math:`\geq` 4.11.0 | + +----------------------------------------------------------------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------+ + | * :doc:`tangential_complex_user` | * :doc:`tangential_complex_ref` | + +----------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/doc/wasserstein_distance_user.rst b/src/python/doc/wasserstein_distance_user.rst index 2d2e2ae7..96ec7872 100644 --- a/src/python/doc/wasserstein_distance_user.rst +++ b/src/python/doc/wasserstein_distance_user.rst @@ -21,9 +21,9 @@ Distance Functions Optimal Transport ***************** -:Requires: `Python Optimal Transport `__ (POT) :math:`\geq` 0.5.1 +:Requires: `Python Optimal Transport `_ (POT) :math:`\geq` 0.5.1 -This first implementation uses the `Python Optimal Transport `__ +This first implementation uses the `Python Optimal Transport `_ library and is based on ideas from "Large Scale Computation of Means and Cluster for Persistence Diagrams via Optimal Transport" :cite:`10.5555/3327546.3327645`. @@ -103,7 +103,7 @@ The output is: Barycenters ----------- -:Requires: `Python Optimal Transport `__ (POT) :math:`\geq` 0.5.1 +:Requires: `Python Optimal Transport `_ (POT) :math:`\geq` 0.5.1 A Frechet mean (or barycenter) is a generalization of the arithmetic mean in a non linear space such as the one of persistence diagrams. diff --git a/src/python/doc/witness_complex_sum.inc b/src/python/doc/witness_complex_sum.inc index 34d4df4a..4416fec0 100644 --- a/src/python/doc/witness_complex_sum.inc +++ b/src/python/doc/witness_complex_sum.inc @@ -1,18 +1,18 @@ .. table:: :widths: 30 40 30 - +-------------------------------------------------------------------+----------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------+ - | .. figure:: | Witness complex :math:`Wit(W,L)` is a simplicial complex defined on | :Author: Siargey Kachanovich | - | ../../doc/Witness_complex/Witness_complex_representation.png | two sets of points in :math:`\mathbb{R}^D`. | | - | :alt: Witness complex representation | | :Since: GUDHI 2.0.0 | - | :figclass: align-center | The data structure is described in | | - | | :cite:`boissonnatmariasimplextreealgorithmica`. | :License: MIT (`GPL v3 `_ for Euclidean versions only) | - | | | | - | | | :Requires: `Eigen `__ :math:`\geq` 3.1.0 and `CGAL `__ :math:`\geq` 4.11.0 for Euclidean versions only | - +-------------------------------------------------------------------+----------------------------------------------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------+ - | * :doc:`witness_complex_user` | * :doc:`witness_complex_ref` | - | | * :doc:`strong_witness_complex_ref` | - | | * :doc:`euclidean_witness_complex_ref` | - | | * :doc:`euclidean_strong_witness_complex_ref` | - +-------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ + +-------------------------------------------------------------------+----------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+ + | .. figure:: | Witness complex :math:`Wit(W,L)` is a simplicial complex defined on | :Author: Siargey Kachanovich | + | ../../doc/Witness_complex/Witness_complex_representation.png | two sets of points in :math:`\mathbb{R}^D`. | | + | :alt: Witness complex representation | | :Since: GUDHI 2.0.0 | + | :figclass: align-center | The data structure is described in | | + | | :cite:`boissonnatmariasimplextreealgorithmica`. | :License: MIT (`GPL v3 `_ for Euclidean versions only) | + | | | | + | | | :Requires: `Eigen `_ :math:`\geq` 3.1.0 and `CGAL `_ :math:`\geq` 4.11.0 for Euclidean versions only | + +-------------------------------------------------------------------+----------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+ + | * :doc:`witness_complex_user` | * :doc:`witness_complex_ref` | + | | * :doc:`strong_witness_complex_ref` | + | | * :doc:`euclidean_witness_complex_ref` | + | | * :doc:`euclidean_strong_witness_complex_ref` | + +-------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/src/python/gudhi/persistence_graphical_tools.py b/src/python/gudhi/persistence_graphical_tools.py index e36af304..d59e51a0 100644 --- a/src/python/gudhi/persistence_graphical_tools.py +++ b/src/python/gudhi/persistence_graphical_tools.py @@ -72,11 +72,11 @@ def plot_persistence_barcode( """This function plots the persistence bar code from persistence values list , a np.array of shape (N x 2) (representing a diagram in a single homology dimension), - or from a `persistence diagram `__ file. + or from a `persistence diagram `_ file. :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A `persistence diagram `__ file style name + :param persistence_file: A `persistence diagram `_ file style name (reset persistence if both are set). :type persistence_file: string :param alpha: barcode transparency value (0.0 transparent through 1.0 @@ -214,11 +214,11 @@ def plot_persistence_diagram( ): """This function plots the persistence diagram from persistence values list, a np.array of shape (N x 2) representing a diagram in a single - homology dimension, or from a `persistence diagram `__ file`. + homology dimension, or from a `persistence diagram `_ file`. :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A `persistence diagram `__ file style name + :param persistence_file: A `persistence diagram `_ file style name (reset persistence if both are set). :type persistence_file: string :param alpha: plot transparency value (0.0 transparent through 1.0 @@ -369,18 +369,18 @@ def plot_persistence_density( """This function plots the persistence density from persistence values list, np.array of shape (N x 2) representing a diagram in a single homology dimension, - or from a `persistence diagram `__ file. + or from a `persistence diagram `_ file. Be aware that this function does not distinguish the dimension, it is up to you to select the required one. This function also does not handle degenerate data set (scipy correlation matrix inversion can fail). - :Requires: `SciPy `__ + :Requires: `SciPy `_ :param persistence: Persistence intervals values list. Can be grouped by dimension or not. :type persistence: an array of (dimension, array of (birth, death)) or an array of (birth, death). - :param persistence_file: A `persistence diagram `__ + :param persistence_file: A `persistence diagram `_ file style name (reset persistence if both are set). :type persistence_file: string :param nbins: Evaluate a gaussian kde on a regular grid of nbins x diff --git a/src/python/gudhi/point_cloud/knn.py b/src/python/gudhi/point_cloud/knn.py index 19363097..86008bc3 100644 --- a/src/python/gudhi/point_cloud/knn.py +++ b/src/python/gudhi/point_cloud/knn.py @@ -20,8 +20,8 @@ class KNearestNeighbors: """ Class wrapping several implementations for computing the k nearest neighbors in a point set. - :Requires: `PyKeOps `__, `SciPy `__, - `Scikit-learn `__, and/or `Hnswlib `__ + :Requires: `PyKeOps `_, `SciPy `_, + `Scikit-learn `_, and/or `Hnswlib `_ in function of the selected `implementation`. """ diff --git a/src/python/gudhi/representations/metrics.py b/src/python/gudhi/representations/metrics.py index 0a6dd680..8a32f7e9 100644 --- a/src/python/gudhi/representations/metrics.py +++ b/src/python/gudhi/representations/metrics.py @@ -225,7 +225,7 @@ class BottleneckDistance(BaseEstimator, TransformerMixin): """ This is a class for computing the bottleneck distance matrix from a list of persistence diagrams. - :Requires: `CGAL `__ :math:`\geq` 4.11.0 + :Requires: `CGAL `_ :math:`\geq` 4.11.0 """ def __init__(self, epsilon=None): """ -- cgit v1.2.3 From 9bfee982ae6fa6d4ca64b16d4c37e6eadf27c27a Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 11 May 2020 11:10:12 +0200 Subject: Fix duplicate link --- src/python/doc/alpha_complex_user.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index de706de9..373853c8 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -11,8 +11,8 @@ Definition `AlphaComplex` is constructing a :doc:`SimplexTree ` using `Delaunay Triangulation `_ -:cite:`cgal:hdj-t-19b` from `CGAL `_ (the Computational Geometry Algorithms Library -:cite:`cgal:eb-19b`). +:cite:`cgal:hdj-t-19b` from the `Computational Geometry Algorithms Library `_ +(CGAL Library :cite:`cgal:eb-19b`). Remarks ^^^^^^^ -- cgit v1.2.3 From a9fa1ba093b13f847dd3921d0c3d2d44342a4dcd Mon Sep 17 00:00:00 2001 From: Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> Date: Mon, 11 May 2020 17:06:50 +0200 Subject: Update src/python/doc/installation.rst Co-authored-by: Marc Glisse --- src/python/doc/installation.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/installation.rst b/src/python/doc/installation.rst index d72e91b5..de09c5b3 100644 --- a/src/python/doc/installation.rst +++ b/src/python/doc/installation.rst @@ -207,7 +207,7 @@ The procedure to install this library according to your operating system is detailed `here `_. -The following examples requires CGAL version :math:`\geq` 4.11.0: +The following examples require CGAL version :math:`\geq` 4.11.0: .. only:: builder_html -- cgit v1.2.3 From 0c64c706fa2c298cac079c00f71ef95061f9e6f8 Mon Sep 17 00:00:00 2001 From: ROUVREAU Vincent Date: Mon, 11 May 2020 17:14:22 +0200 Subject: doc review --- src/python/doc/alpha_complex_user.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/python') diff --git a/src/python/doc/alpha_complex_user.rst b/src/python/doc/alpha_complex_user.rst index 373853c8..d49f45b4 100644 --- a/src/python/doc/alpha_complex_user.rst +++ b/src/python/doc/alpha_complex_user.rst @@ -12,7 +12,7 @@ Definition `AlphaComplex` is constructing a :doc:`SimplexTree ` using `Delaunay Triangulation `_ :cite:`cgal:hdj-t-19b` from the `Computational Geometry Algorithms Library `_ -(CGAL Library :cite:`cgal:eb-19b`). +:cite:`cgal:eb-19b`. Remarks ^^^^^^^ -- cgit v1.2.3 From f94c2e1b7ba982fda62239f5c6b378bda867cd40 Mon Sep 17 00:00:00 2001 From: Marc Glisse Date: Mon, 11 May 2020 19:56:06 +0200 Subject: More DOI in the biblio and update references from a preprint to the published version --- biblio/bibliography.bib | 8 +++++++- src/Persistent_cohomology/doc/Intro_persistent_cohomology.h | 2 +- src/common/doc/main_page.md | 2 +- src/python/doc/persistent_cohomology_sum.inc | 2 +- src/python/doc/persistent_cohomology_user.rst | 2 +- 5 files changed, 11 insertions(+), 5 deletions(-) (limited to 'src/python') diff --git a/biblio/bibliography.bib b/biblio/bibliography.bib index 99a15c5e..3ea2f59f 100644 --- a/biblio/bibliography.bib +++ b/biblio/bibliography.bib @@ -13,7 +13,9 @@ pages = {1--39}, publisher = {JMLR.org}, title = {{Statistical analysis and parameter selection for Mapper}}, volume = {19}, -year = {2018} +year = {2018}, +url = {http://jmlr.org/papers/v19/17-291.html}, +doi = {10.5555/3291125.3291137} } @inproceedings{Dey13, @@ -22,6 +24,7 @@ year = {2018} booktitle = {Proceedings of the Twenty-ninth Annual Symposium on Computational Geometry}, year = {2013}, pages = {107--116}, + doi = {10.1145/2462356.2462387} } @article{Carriere16, @@ -832,6 +835,7 @@ book{hatcher2002algebraic, number = {4}, year = {2010}, pages = {367-405}, + doi = {10.1007/s10208-010-9066-0}, ee = {http://dx.doi.org/10.1007/s10208-010-9066-0}, bibsource = {DBLP, http://dblp.uni-trier.de} } @@ -927,6 +931,7 @@ language={English} booktitle = {Symposium on Computational Geometry}, year = {2014}, pages = {345}, + doi = {10.1145/2582112.2582165}, ee = {http://doi.acm.org/10.1145/2582112.2582165}, bibsource = {DBLP, http://dblp.uni-trier.de} } @@ -1241,6 +1246,7 @@ year = "2011" title={Fr{\'e}chet means for distributions of persistence diagrams}, author={Turner, Katharine and Mileyko, Yuriy and Mukherjee, Sayan and Harer, John}, journal={Discrete \& Computational Geometry}, + doi={10.1007/s00454-014-9604-7}, volume={52}, number={1}, pages={44--70}, diff --git a/src/Persistent_cohomology/doc/Intro_persistent_cohomology.h b/src/Persistent_cohomology/doc/Intro_persistent_cohomology.h index 46b784d8..b4f9fd2c 100644 --- a/src/Persistent_cohomology/doc/Intro_persistent_cohomology.h +++ b/src/Persistent_cohomology/doc/Intro_persistent_cohomology.h @@ -21,7 +21,7 @@ namespace persistent_cohomology { \author Clément Maria Computation of persistent cohomology using the algorithm of - \cite DBLP:journals/dcg/SilvaMV11 and \cite DBLP:journals/corr/abs-1208-5018 + \cite DBLP:journals/dcg/SilvaMV11 and \cite DBLP:conf/compgeom/DeyFW14 and the Compressed Annotation Matrix implementation of \cite DBLP:conf/esa/BoissonnatDM13 diff --git a/src/common/doc/main_page.md b/src/common/doc/main_page.md index 6ea10b88..a33d98cd 100644 --- a/src/common/doc/main_page.md +++ b/src/common/doc/main_page.md @@ -312,7 +312,7 @@ theory is essentially composed of three elements: topological spaces, their homology groups and an evolution scheme. Computation of persistent cohomology using the algorithm of \cite DBLP:journals/dcg/SilvaMV11 and - \cite DBLP:journals/corr/abs-1208-5018 and the Compressed Annotation Matrix implementation of + \cite DBLP:conf/compgeom/DeyFW14 and the Compressed Annotation Matrix implementation of \cite DBLP:conf/esa/BoissonnatDM13 . diff --git a/src/python/doc/persistent_cohomology_sum.inc b/src/python/doc/persistent_cohomology_sum.inc index 0effb50f..a1ff2eee 100644 --- a/src/python/doc/persistent_cohomology_sum.inc +++ b/src/python/doc/persistent_cohomology_sum.inc @@ -12,7 +12,7 @@ | | | | | | Computation of persistent cohomology using the algorithm of | | | | :cite:`DBLP:journals/dcg/SilvaMV11` and | | - | | :cite:`DBLP:journals/corr/abs-1208-5018` and the Compressed | | + | | :cite:`DBLP:conf/compgeom/DeyFW14` and the Compressed | | | | Annotation Matrix implementation of | | | | :cite:`DBLP:conf/esa/BoissonnatDM13`. | | | | | | diff --git a/src/python/doc/persistent_cohomology_user.rst b/src/python/doc/persistent_cohomology_user.rst index 4d743aac..a3f294b2 100644 --- a/src/python/doc/persistent_cohomology_user.rst +++ b/src/python/doc/persistent_cohomology_user.rst @@ -21,7 +21,7 @@ Definition Computation of persistent cohomology using the algorithm of :cite:`DBLP:journals/dcg/SilvaMV11` and -:cite:`DBLP:journals/corr/abs-1208-5018` and the Compressed Annotation Matrix implementation of +:cite:`DBLP:conf/compgeom/DeyFW14` and the Compressed Annotation Matrix implementation of :cite:`DBLP:conf/esa/BoissonnatDM13`. The theory of homology consists in attaching to a topological space a sequence of (homology) groups, capturing global -- cgit v1.2.3