diff options
author | Vincent Rouvreau <10407034+VincentRouvreau@users.noreply.github.com> | 2019-12-12 10:17:24 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2019-12-12 10:17:24 +0100 |
commit | 5a5a534b840216719fb3f9cb819d1306ca7ed196 (patch) | |
tree | db5e90a48b287e237cdf5c4aeb069c294e13436d | |
parent | 3e829fd6f4a3a122da9df35a88e5c51122860bf6 (diff) | |
parent | 7bd6907e577e22803fec179f652ecf0ec64dcb4a (diff) |
Merge pull request #173 from MathieuCarriere/master
Example in doc + fix on Landscape
Fix #166
-rw-r--r-- | src/python/doc/representations.rst | 26 | ||||
-rw-r--r-- | src/python/gudhi/representations/vector_methods.py | 29 |
2 files changed, 43 insertions, 12 deletions
diff --git a/src/python/doc/representations.rst b/src/python/doc/representations.rst index b3131a25..11dcbcf9 100644 --- a/src/python/doc/representations.rst +++ b/src/python/doc/representations.rst @@ -8,7 +8,7 @@ Representations manual .. include:: representations_sum.inc -This module, originally named sklearn_tda, aims at bridging the gap between persistence diagrams and machine learning tools, in particular scikit-learn. It provides tools, using the scikit-learn standard interface, to compute distances and kernels on diagrams, and to convert diagrams into vectors. +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. @@ -46,3 +46,27 @@ Metrics :members: :special-members: :show-inheritance: + +Basic example +------------- + +This example computes the first two Landscapes associated to a persistence diagram with four points. The landscapes are evaluated on ten samples, leading to two vectors with ten coordinates each, that are eventually concatenated in order to produce a single vector representation. + +.. testcode:: + + import numpy as np + from gudhi.representations import Landscape + # A single diagram with 4 points + D = np.array([[0.,4.],[1.,2.],[3.,8.],[6.,8.]]) + diags = [D] + l=Landscape(num_landscapes=2,resolution=10).fit_transform(diags) + print(l) + +The output is: + +.. testoutput:: + + [[1.02851895 2.05703791 2.57129739 1.54277843 0.89995409 1.92847304 + 2.95699199 3.08555686 2.05703791 1.02851895 0. 0.64282435 + 0. 0. 0.51425948 0. 0. 0. + 0.77138922 1.02851895]] diff --git a/src/python/gudhi/representations/vector_methods.py b/src/python/gudhi/representations/vector_methods.py index 61c4fb84..fe26dbe2 100644 --- a/src/python/gudhi/representations/vector_methods.py +++ b/src/python/gudhi/representations/vector_methods.py @@ -95,6 +95,8 @@ class Landscape(BaseEstimator, TransformerMixin): sample_range ([double, double]): minimum and maximum of all piecewise-linear function domains, of the form [x_min, x_max] (default [numpy.nan, numpy.nan]). It is the interval on which samples will be drawn evenly. If one of the values is numpy.nan, it can be computed from the persistence diagrams with the fit() method. """ self.num_landscapes, self.resolution, self.sample_range = num_landscapes, resolution, sample_range + self.nan_in_range = np.isnan(np.array(self.sample_range)) + self.new_resolution = self.resolution + self.nan_in_range.sum() def fit(self, X, y=None): """ @@ -104,10 +106,10 @@ class Landscape(BaseEstimator, TransformerMixin): X (list of n x 2 numpy arrays): input persistence diagrams. y (n x 1 array): persistence diagram labels (unused). """ - if np.isnan(np.array(self.sample_range)).any(): + if self.nan_in_range.any(): pre = DiagramScaler(use=True, scalers=[([0], MinMaxScaler()), ([1], MinMaxScaler())]).fit(X,y) [mx,my],[Mx,My] = [pre.scalers[0][1].data_min_[0], pre.scalers[1][1].data_min_[0]], [pre.scalers[0][1].data_max_[0], pre.scalers[1][1].data_max_[0]] - self.sample_range = np.where(np.isnan(np.array(self.sample_range)), np.array([mx, My]), np.array(self.sample_range)) + self.sample_range = np.where(self.nan_in_range, np.array([mx, My]), np.array(self.sample_range)) return self def transform(self, X): @@ -121,26 +123,26 @@ class Landscape(BaseEstimator, TransformerMixin): numpy array with shape (number of diagrams) x (number of samples = **num_landscapes** x **resolution**): output persistence landscapes. """ num_diag, Xfit = len(X), [] - x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.resolution) + x_values = np.linspace(self.sample_range[0], self.sample_range[1], self.new_resolution) step_x = x_values[1] - x_values[0] for i in range(num_diag): diagram, num_pts_in_diag = X[i], X[i].shape[0] - ls = np.zeros([self.num_landscapes, self.resolution]) + ls = np.zeros([self.num_landscapes, self.new_resolution]) events = [] - for j in range(self.resolution): + for j in range(self.new_resolution): events.append([]) for j in range(num_pts_in_diag): [px,py] = diagram[j,:2] - min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) - mid_idx = np.clip(np.ceil((0.5*(py+px) - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) - max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.resolution) + min_idx = np.clip(np.ceil((px - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) + mid_idx = np.clip(np.ceil((0.5*(py+px) - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) + max_idx = np.clip(np.ceil((py - self.sample_range[0]) / step_x).astype(int), 0, self.new_resolution) - if min_idx < self.resolution and max_idx > 0: + if min_idx < self.new_resolution and max_idx > 0: landscape_value = self.sample_range[0] + min_idx * step_x - px for k in range(min_idx, mid_idx): @@ -152,12 +154,17 @@ class Landscape(BaseEstimator, TransformerMixin): events[k].append(landscape_value) landscape_value -= step_x - for j in range(self.resolution): + for j in range(self.new_resolution): events[j].sort(reverse=True) for k in range( min(self.num_landscapes, len(events[j])) ): ls[k,j] = events[j][k] - Xfit.append(np.sqrt(2)*np.reshape(ls,[1,-1])) + if self.nan_in_range[0]: + ls = ls[:,1:] + if self.nan_in_range[1]: + ls = ls[:,:-1] + ls = np.sqrt(2)*np.reshape(ls,[1,-1]) + Xfit.append(ls) Xfit = np.concatenate(Xfit,0) |