From f55ae9257a7006fd0906a21bd3033f47b2958c6b Mon Sep 17 00:00:00 2001 From: VincentRouvreau Date: Mon, 4 Oct 2021 16:46:01 +0200 Subject: review: modification proposed from EB + HM comments fix --- src/python/CMakeLists.txt | 7 ++- src/python/doc/cubical_complex_user.rst | 5 +- src/python/gudhi/representations/preprocessing.py | 51 ++++++++++++++++++- src/python/gudhi/sklearn/cubical_persistence.py | 40 ++++++++------- src/python/gudhi/sklearn/post_processing.py | 57 ---------------------- .../test/test_representations_preprocessing.py | 39 +++++++++++++++ .../test/test_sklearn_cubical_persistence.py | 16 +++--- src/python/test/test_sklearn_post_processing.py | 43 ---------------- 8 files changed, 123 insertions(+), 135 deletions(-) delete mode 100644 src/python/gudhi/sklearn/post_processing.py create mode 100644 src/python/test/test_representations_preprocessing.py delete mode 100644 src/python/test/test_sklearn_post_processing.py (limited to 'src') diff --git a/src/python/CMakeLists.txt b/src/python/CMakeLists.txt index b38bb9aa..2ff05384 100644 --- a/src/python/CMakeLists.txt +++ b/src/python/CMakeLists.txt @@ -519,6 +519,11 @@ if(PYTHONINTERP_FOUND) add_gudhi_py_test(test_representations) endif() + # Representations preprocessing + if(SKLEARN_FOUND) + add_gudhi_py_test(test_representations_preprocessing) + endif() + # Time Delay add_gudhi_py_test(test_time_delay) @@ -546,10 +551,8 @@ if(PYTHONINTERP_FOUND) # sklearn if(SKLEARN_FOUND) add_gudhi_py_test(test_sklearn_cubical_persistence) - add_gudhi_py_test(test_sklearn_post_processing) endif() - # Set missing or not modules set(GUDHI_MODULES ${GUDHI_MODULES} "python" CACHE INTERNAL "GUDHI_MODULES") else(CYTHON_FOUND) diff --git a/src/python/doc/cubical_complex_user.rst b/src/python/doc/cubical_complex_user.rst index a140a279..e62a4395 100644 --- a/src/python/doc/cubical_complex_user.rst +++ b/src/python/doc/cubical_complex_user.rst @@ -211,7 +211,10 @@ two holes in :math:`\mathbf{H}_1`, or, like in this example, three connected com X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0) pipe = Pipeline( [ - ("cub_pers", CubicalPersistence(only_this_dim=0, dimensions=[28, 28], n_jobs=-2)), + ("cub_pers", CubicalPersistence(persistence_dimension=0, dimensions=[28, 28], n_jobs=-2)), + # Or for multiple persistence dimension computation + # ("cub_pers", CubicalPersistence(persistence_dimension=[0, 1], dimensions=[28, 28], n_jobs=-2)), + # ("H0_diags", DimensionSelector(index=0), # where index is the index in persistence_dimension array ("finite_diags", DiagramSelector(use=True, point_type="finite")), ( "pers_img", diff --git a/src/python/gudhi/representations/preprocessing.py b/src/python/gudhi/representations/preprocessing.py index a8545349..823e3954 100644 --- a/src/python/gudhi/representations/preprocessing.py +++ b/src/python/gudhi/representations/preprocessing.py @@ -1,10 +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): Mathieu Carrière +# Author(s): Mathieu Carrière, Vincent Rouvreau # # Copyright (C) 2018-2019 Inria # # Modification(s): +# - 2021/10 Vincent Rouvreau: Add DimensionSelector # - YYYY/MM Author: Description of the modification import numpy as np @@ -363,3 +364,51 @@ class DiagramSelector(BaseEstimator, TransformerMixin): n x 2 numpy array: extracted persistence diagram. """ return self.fit_transform([diag])[0] + + +# Mermaid sequence diagram - https://mermaid-js.github.io/mermaid-live-editor/ +# sequenceDiagram +# USER->>DimensionSelector: fit_transform(
[[array( Hi(X0) ), array( Hj(X0) ), ...],
[array( Hi(X1) ), array( Hj(X1) ), ...],
...]) +# DimensionSelector->>thread1: _transform([array( Hi(X0) ), array( Hj(X0) )], ...) +# DimensionSelector->>thread2: _transform([array( Hi(X1) ), array( Hj(X1) )], ...) +# Note right of DimensionSelector: ... +# thread1->>DimensionSelector: array( Hn(X0) ) +# thread2->>DimensionSelector: array( Hn(X1) ) +# Note right of DimensionSelector: ... +# DimensionSelector->>USER: [array( Hn(X0) ),
array( Hn(X1) ),
...] + +class DimensionSelector(BaseEstimator, TransformerMixin): + """ + This is a class to select persistence diagrams in a specific dimension from its index. + """ + + def __init__(self, index=0): + """ + Constructor for the DimensionSelector class. + + Parameters: + index (int): The returned persistence diagrams dimension index. Default value is `0`. + """ + self.index = index + + def fit(self, X, Y=None): + """ + Nothing to be done, but useful when included in a scikit-learn Pipeline. + """ + return self + + def transform(self, X, Y=None): + """ + Select persistence diagrams from its dimension. + + Parameters: + X (list of list of pairs): List of list of persistence pairs, i.e. + `[[array( Hi(X0) ), array( Hj(X0) ), ...], [array( Hi(X1) ), array( Hj(X1) ), ...], ...]` + + Returns: + list of pairs: + Persistence diagrams in a specific dimension. i.e. if `index` was set to `m` and `Hn` is at index `n` of + the input, it returns `[array( Hn(X0) ), array( Hn(X1), ...]` + """ + + return [persistence[self.index] for persistence in X] diff --git a/src/python/gudhi/sklearn/cubical_persistence.py b/src/python/gudhi/sklearn/cubical_persistence.py index 329c9435..454cdd07 100644 --- a/src/python/gudhi/sklearn/cubical_persistence.py +++ b/src/python/gudhi/sklearn/cubical_persistence.py @@ -33,8 +33,7 @@ class CubicalPersistence(BaseEstimator, TransformerMixin): def __init__( self, dimensions=None, - max_persistence_dimension=0, - only_this_dim=-1, + persistence_dimension=-1, homology_coeff_field=11, min_persistence=0.0, n_jobs=None, @@ -45,20 +44,16 @@ class CubicalPersistence(BaseEstimator, TransformerMixin): Parameters: dimensions (list of int): A list of number of top dimensional cells if cells filtration values will require to be reshaped (cf. :func:`~gudhi.sklearn.cubical_persistence.CubicalPersistence.transform`) - max_persistence_dimension (int): The returned persistence diagrams maximal dimension. Default value is `0`. - Ignored if `only_this_dim` is set. - only_this_dim (int): The returned persistence diagrams dimension. If `only_this_dim` is set, - `max_persistence_dimension` will be ignored. - Short circuit the use of :class:`~gudhi.sklearn.post_processing.DimensionSelector` when only one - dimension matters. + persistence_dimension (int or list of int): The returned persistence diagrams dimension(s). + Short circuit the use of :class:`~gudhi.representations.preprocessing.DimensionSelector` when only one + dimension matters (in other words, when `persistence_dimension` is an int). homology_coeff_field (int): The homology coefficient field. Must be a prime number. Default value is 11. min_persistence (float): 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. + `min_persistence`). Default value is `0.0`. Set `min_persistence` to `-1.0` to see all values. n_jobs (int): cf. https://joblib.readthedocs.io/en/latest/generated/joblib.Parallel.html """ self.dimensions = dimensions - self.max_persistence_dimension = max_persistence_dimension - self.only_this_dim = only_this_dim + self.persistence_dimension = persistence_dimension self.homology_coeff_field = homology_coeff_field self.min_persistence = min_persistence self.n_jobs = n_jobs @@ -75,7 +70,7 @@ class CubicalPersistence(BaseEstimator, TransformerMixin): homology_coeff_field=self.homology_coeff_field, min_persistence=self.min_persistence ) return [ - cubical_complex.persistence_intervals_in_dimension(dim) for dim in range(self.max_persistence_dimension + 1) + cubical_complex.persistence_intervals_in_dimension(dim) for dim in self.persistence_dimension ] def __transform_only_this_dim(self, cells): @@ -83,28 +78,31 @@ class CubicalPersistence(BaseEstimator, TransformerMixin): cubical_complex.compute_persistence( homology_coeff_field=self.homology_coeff_field, min_persistence=self.min_persistence ) - return cubical_complex.persistence_intervals_in_dimension(self.only_this_dim) + return cubical_complex.persistence_intervals_in_dimension(self.persistence_dimension) def transform(self, X, Y=None): """ Compute all the cubical complexes and their associated persistence diagrams. Parameters: - X (list of list of double OR list of numpy.ndarray): List of cells filtration values that can be flatten if - `dimensions` is set in the constructor, or already with the correct shape in a numpy.ndarray (and + X (list of list of double OR list of numpy.ndarray): List of cells filtration values that should be flatten + if `dimensions` is set in the constructor, or already with the correct shape in a numpy.ndarray (and `dimensions` must not be set). Returns: + list of pairs or list of list of pairs: Persistence diagrams in the format: - - If `only_this_dim` was set to `n`: `[array( Hn(X[0]) ), array( Hn(X[1]) ), ...]` - - else: `[[array( H0(X[0]) ), array( H1(X[0]) ), ...], [array( H0(X[1]) ), array( H1(X[1]) ), ...], ...]` + - If `persistence_dimension` was set to `n`: `[array( Hn(X[0]) ), array( Hn(X[1]) ), ...]` + - If `persistence_dimension` was set to `[i, j]`: `[[array( Hi(X[0]) ), array( Hj(X[0]) )], [array( Hi(X[1]) ), array( Hj(X[1]) )], ...]` """ - if self.only_this_dim == -1: - # threads is preferred as cubical construction and persistence computation releases the GIL - return Parallel(n_jobs=self.n_jobs, prefer="threads")(delayed(self.__transform)(cells) for cells in X) - else: + # Depends on persistence_dimension is an integer or a list of integer (else case) + if isinstance(self.persistence_dimension, int): # threads is preferred as cubical construction and persistence computation releases the GIL return Parallel(n_jobs=self.n_jobs, prefer="threads")( delayed(self.__transform_only_this_dim)(cells) for cells in X ) + else: + # threads is preferred as cubical construction and persistence computation releases the GIL + return Parallel(n_jobs=self.n_jobs, prefer="threads")(delayed(self.__transform)(cells) for cells in X) + diff --git a/src/python/gudhi/sklearn/post_processing.py b/src/python/gudhi/sklearn/post_processing.py deleted file mode 100644 index 3b12466b..00000000 --- a/src/python/gudhi/sklearn/post_processing.py +++ /dev/null @@ -1,57 +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) 2021 Inria -# -# Modification(s): -# - YYYY/MM Author: Description of the modification - -from sklearn.base import BaseEstimator, TransformerMixin - -# Mermaid sequence diagram - https://mermaid-js.github.io/mermaid-live-editor/ -# sequenceDiagram -# USER->>DimensionSelector: fit_transform(
[[array( H0(X0) ), array( H1(X0) ), ...],
[array( H0(X1) ), array( H1(X1) ), ...],
...]) -# DimensionSelector->>thread1: _transform([array( H0(X0) ), array( H1(X0) )], ...) -# DimensionSelector->>thread2: _transform([array( H0(X1) ), array( H1(X1) )], ...) -# Note right of DimensionSelector: ... -# thread1->>DimensionSelector: array( Hn(X0) ) -# thread2->>DimensionSelector: array( Hn(X1) ) -# Note right of DimensionSelector: ... -# DimensionSelector->>USER: [array( Hn(X0) ),
array( Hn(X1) ),
...] - - -class DimensionSelector(BaseEstimator, TransformerMixin): - """ - This is a class to select persistence diagrams in a specific dimension. - """ - - def __init__(self, persistence_dimension=0): - """ - Constructor for the DimensionSelector class. - - Parameters: - persistence_dimension (int): The returned persistence diagrams dimension. Default value is `0`. - """ - self.persistence_dimension = persistence_dimension - - def fit(self, X, Y=None): - """ - Nothing to be done, but useful when included in a scikit-learn Pipeline. - """ - return self - - def transform(self, X, Y=None): - """ - Select persistence diagrams from its dimension. - - Parameters: - X (list of list of pairs): List of list of persistence pairs, i.e. - `[[array( H0(X0) ), array( H1(X0) ), ...], [array( H0(X1) ), array( H1(X1) ), ...], ...]` - - Returns: - Persistence diagrams in a specific dimension, i.e. - `[array( Hn(X0) ), array( Hn(X1), ...]` - """ - - return [persistence[self.persistence_dimension] for persistence in X] diff --git a/src/python/test/test_representations_preprocessing.py b/src/python/test/test_representations_preprocessing.py new file mode 100644 index 00000000..838cf30c --- /dev/null +++ b/src/python/test/test_representations_preprocessing.py @@ -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): Vincent Rouvreau + + Copyright (C) 2021 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +from gudhi.representations.preprocessing import DimensionSelector +import numpy as np +import pytest + +H0_0 = np.array([0.0, 0.0]) +H1_0 = np.array([1.0, 0.0]) +H0_1 = np.array([0.0, 1.0]) +H1_1 = np.array([1.0, 1.0]) +H0_2 = np.array([0.0, 2.0]) +H1_2 = np.array([1.0, 2.0]) + + +def test_dimension_selector(): + X = [[H0_0, H1_0], [H0_1, H1_1], [H0_2, H1_2]] + ds = DimensionSelector(index=0) + h0 = ds.fit_transform(X) + np.testing.assert_array_equal(h0[0], H0_0) + np.testing.assert_array_equal(h0[1], H0_1) + np.testing.assert_array_equal(h0[2], H0_2) + + ds = DimensionSelector(index=1) + h1 = ds.fit_transform(X) + np.testing.assert_array_equal(h1[0], H1_0) + np.testing.assert_array_equal(h1[1], H1_1) + np.testing.assert_array_equal(h1[2], H1_2) + + ds = DimensionSelector(index=2) + with pytest.raises(IndexError): + h2 = ds.fit_transform([[H0_0, H1_0], [H0_1, H1_1], [H0_2, H1_2]]) diff --git a/src/python/test/test_sklearn_cubical_persistence.py b/src/python/test/test_sklearn_cubical_persistence.py index 488495d1..bd728a29 100644 --- a/src/python/test/test_sklearn_cubical_persistence.py +++ b/src/python/test/test_sklearn_cubical_persistence.py @@ -12,32 +12,28 @@ from gudhi.sklearn.cubical_persistence import CubicalPersistence import numpy as np from sklearn import datasets -__author__ = "Vincent Rouvreau" -__copyright__ = "Copyright (C) 2021 Inria" -__license__ = "MIT" - CUBICAL_PERSISTENCE_H0_IMG0 = np.array([[0.0, 6.0], [0.0, 8.0], [0.0, np.inf]]) def test_simple_constructor_from_top_cells(): cells = datasets.load_digits().images[0] - cp = CubicalPersistence(only_this_dim=0) - np.testing.assert_array_equal(cp._CubicalPersistence__transform(cells), [CUBICAL_PERSISTENCE_H0_IMG0]) - cp = CubicalPersistence(max_persistence_dimension=2) + cp = CubicalPersistence(persistence_dimension=0) + np.testing.assert_array_equal(cp._CubicalPersistence__transform_only_this_dim(cells), CUBICAL_PERSISTENCE_H0_IMG0) + cp = CubicalPersistence(persistence_dimension=[0, 2]) diags = cp._CubicalPersistence__transform(cells) - assert len(diags) == 3 + assert len(diags) == 2 np.testing.assert_array_equal(diags[0], CUBICAL_PERSISTENCE_H0_IMG0) def test_simple_constructor_from_top_cells_list(): digits = datasets.load_digits().images[:10] - cp = CubicalPersistence(only_this_dim=0, n_jobs=-2) + cp = CubicalPersistence(persistence_dimension=0, n_jobs=-2) diags = cp.fit_transform(digits) assert len(diags) == 10 np.testing.assert_array_equal(diags[0], CUBICAL_PERSISTENCE_H0_IMG0) - cp = CubicalPersistence(max_persistence_dimension=1, n_jobs=-1) + cp = CubicalPersistence(persistence_dimension=[0, 1], n_jobs=-1) diagsH0H1 = cp.fit_transform(digits) assert len(diagsH0H1) == 10 for idx in range(10): diff --git a/src/python/test/test_sklearn_post_processing.py b/src/python/test/test_sklearn_post_processing.py deleted file mode 100644 index e60eadc6..00000000 --- a/src/python/test/test_sklearn_post_processing.py +++ /dev/null @@ -1,43 +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) 2021 Inria - - Modification(s): - - YYYY/MM Author: Description of the modification -""" - -from gudhi.sklearn.post_processing import DimensionSelector -import numpy as np -import pytest - -__author__ = "Vincent Rouvreau" -__copyright__ = "Copyright (C) 2021 Inria" -__license__ = "MIT" - -H0_0 = np.array([0.0, 0.0]) -H1_0 = np.array([1.0, 0.0]) -H0_1 = np.array([0.0, 1.0]) -H1_1 = np.array([1.0, 1.0]) -H0_2 = np.array([0.0, 2.0]) -H1_2 = np.array([1.0, 2.0]) - - -def test_dimension_selector(): - X = [[H0_0, H1_0], [H0_1, H1_1], [H0_2, H1_2]] - ds = DimensionSelector(persistence_dimension=0) - h0 = ds.fit_transform(X) - np.testing.assert_array_equal(h0[0], H0_0) - np.testing.assert_array_equal(h0[1], H0_1) - np.testing.assert_array_equal(h0[2], H0_2) - - ds = DimensionSelector(persistence_dimension=1) - h1 = ds.fit_transform(X) - np.testing.assert_array_equal(h1[0], H1_0) - np.testing.assert_array_equal(h1[1], H1_1) - np.testing.assert_array_equal(h1[2], H1_2) - - ds = DimensionSelector(persistence_dimension=2) - with pytest.raises(IndexError): - h2 = ds.fit_transform([[H0_0, H1_0], [H0_1, H1_1], [H0_2, H1_2]]) -- cgit v1.2.3