diff options
Diffstat (limited to 'src/python/test')
-rwxr-xr-x | src/python/test/test_cubical_complex.py | 25 | ||||
-rwxr-xr-x | src/python/test/test_datasets_generators.py | 39 | ||||
-rwxr-xr-x | src/python/test/test_dtm.py | 12 | ||||
-rwxr-xr-x | src/python/test/test_reader_utils.py | 2 | ||||
-rwxr-xr-x | src/python/test/test_representations.py | 71 | ||||
-rwxr-xr-x | src/python/test/test_rips_complex.py | 21 | ||||
-rwxr-xr-x | src/python/test/test_simplex_tree.py | 44 | ||||
-rwxr-xr-x | src/python/test/test_tomato.py | 2 | ||||
-rwxr-xr-x | src/python/test/test_wasserstein_distance.py | 109 |
9 files changed, 319 insertions, 6 deletions
diff --git a/src/python/test/test_cubical_complex.py b/src/python/test/test_cubical_complex.py index d0e4e9e8..29d559b3 100755 --- a/src/python/test/test_cubical_complex.py +++ b/src/python/test/test_cubical_complex.py @@ -174,3 +174,28 @@ def test_periodic_cofaces_of_persistence_pairs_when_pd_has_no_paired_birth_and_d assert np.array_equal(pairs[1][0], np.array([0])) assert np.array_equal(pairs[1][1], np.array([0, 1])) assert np.array_equal(pairs[1][2], np.array([1])) + +def test_cubical_persistence_intervals_in_dimension(): + cub = CubicalComplex( + dimensions=[3, 3], + top_dimensional_cells=[1, 2, 3, 4, 5, 6, 7, 8, 9], + ) + cub.compute_persistence() + H0 = cub.persistence_intervals_in_dimension(0) + assert np.array_equal(H0, np.array([[ 1., float("inf")]])) + assert cub.persistence_intervals_in_dimension(1).shape == (0, 2) + +def test_periodic_cubical_persistence_intervals_in_dimension(): + cub = PeriodicCubicalComplex( + dimensions=[3, 3], + top_dimensional_cells=[1, 2, 3, 4, 5, 6, 7, 8, 9], + periodic_dimensions = [True, True] + ) + cub.compute_persistence() + H0 = cub.persistence_intervals_in_dimension(0) + assert np.array_equal(H0, np.array([[ 1., float("inf")]])) + H1 = cub.persistence_intervals_in_dimension(1) + assert np.array_equal(H1, np.array([[ 3., float("inf")], [ 7., float("inf")]])) + H2 = cub.persistence_intervals_in_dimension(2) + assert np.array_equal(H2, np.array([[ 9., float("inf")]])) + assert cub.persistence_intervals_in_dimension(3).shape == (0, 2) diff --git a/src/python/test/test_datasets_generators.py b/src/python/test/test_datasets_generators.py new file mode 100755 index 00000000..91ec4a65 --- /dev/null +++ b/src/python/test/test_datasets_generators.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): Hind Montassif + + Copyright (C) 2021 Inria + + Modification(s): + - YYYY/MM Author: Description of the modification +""" + +from gudhi.datasets.generators import points + +import pytest + +def test_sphere(): + assert points.sphere(n_samples = 10, ambient_dim = 2, radius = 1., sample = 'random').shape == (10, 2) + + with pytest.raises(ValueError): + points.sphere(n_samples = 10, ambient_dim = 2, radius = 1., sample = 'other') + +def _basic_torus(impl): + assert impl(n_samples = 64, dim = 3, sample = 'random').shape == (64, 6) + assert impl(n_samples = 64, dim = 3, sample = 'grid').shape == (64, 6) + + assert impl(n_samples = 10, dim = 4, sample = 'random').shape == (10, 8) + + # Here 1**dim < n_samples < 2**dim, the output shape is therefore (1, 2*dim) = (1, 8), where shape[0] is rounded down to the closest perfect 'dim'th power + assert impl(n_samples = 10, dim = 4, sample = 'grid').shape == (1, 8) + + with pytest.raises(ValueError): + impl(n_samples = 10, dim = 4, sample = 'other') + +def test_torus(): + for torus_impl in [points.torus, points.ctorus]: + _basic_torus(torus_impl) + # Check that the two versions (torus and ctorus) generate the same output + assert points.ctorus(n_samples = 64, dim = 3, sample = 'random').all() == points.torus(n_samples = 64, dim = 3, sample = 'random').all() + assert points.ctorus(n_samples = 64, dim = 3, sample = 'grid').all() == points.torus(n_samples = 64, dim = 3, sample = 'grid').all() + assert points.ctorus(n_samples = 10, dim = 3, sample = 'grid').all() == points.torus(n_samples = 10, dim = 3, sample = 'grid').all() diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py index 0a52279e..e46d616c 100755 --- a/src/python/test/test_dtm.py +++ b/src/python/test/test_dtm.py @@ -13,6 +13,7 @@ import numpy import pytest import torch import math +import warnings def test_dtm_compare_euclidean(): @@ -87,3 +88,14 @@ def test_density(): assert density == pytest.approx(expected) density = DTMDensity(weights=[0.5, 0.5], metric="neighbors", dim=1).fit_transform(distances) assert density == pytest.approx(expected) + +def test_dtm_overflow_warnings(): + pts = numpy.array([[10., 100000000000000000000000000000.], [1000., 100000000000000000000000000.]]) + + with warnings.catch_warnings(record=True) as w: + # TODO Test "keops" implementation as well when next version of pykeops (current is 1.5) is released (should fix the problem (cf. issue #543)) + dtm = DistanceToMeasure(2, implementation="hnsw") + r = dtm.fit_transform(pts) + assert len(w) == 1 + assert issubclass(w[0].category, RuntimeWarning) + assert "Overflow" in str(w[0].message) diff --git a/src/python/test/test_reader_utils.py b/src/python/test/test_reader_utils.py index 90da6651..e96e0569 100755 --- a/src/python/test/test_reader_utils.py +++ b/src/python/test/test_reader_utils.py @@ -30,7 +30,7 @@ def test_full_square_distance_matrix_csv_file(): test_file.write("0;1;2;3;\n1;0;4;5;\n2;4;0;6;\n3;5;6;0;") test_file.close() matrix = gudhi.read_lower_triangular_matrix_from_csv_file( - csv_file="full_square_distance_matrix.csv" + csv_file="full_square_distance_matrix.csv", separator=";" ) assert matrix == [[], [1.0], [2.0, 4.0], [3.0, 5.0, 6.0]] diff --git a/src/python/test/test_representations.py b/src/python/test/test_representations.py index cda1a15b..93461f1e 100755 --- a/src/python/test/test_representations.py +++ b/src/python/test/test_representations.py @@ -3,9 +3,23 @@ import sys import matplotlib.pyplot as plt import numpy as np import pytest +import random from sklearn.cluster import KMeans +# Vectorization +from gudhi.representations import (Landscape, Silhouette, BettiCurve, ComplexPolynomial,\ + TopologicalVector, PersistenceImage, Entropy) + +# Preprocessing +from gudhi.representations import (BirthPersistenceTransform, Clamping, DiagramScaler, Padding, ProminentPoints, \ + DiagramSelector) + +# Kernel +from gudhi.representations import (PersistenceWeightedGaussianKernel, \ + PersistenceScaleSpaceKernel, SlicedWassersteinDistance,\ + SlicedWassersteinKernel, PersistenceFisherKernel, WassersteinDistance) + def test_representations_examples(): # Disable graphics for testing purposes @@ -98,3 +112,60 @@ def test_infinity(): assert c[1] == 0 assert c[7] == 3 assert c[9] == 2 + + +def test_preprocessing_empty_diagrams(): + empty_diag = np.empty(shape = [0, 2]) + assert not np.any(BirthPersistenceTransform()(empty_diag)) + assert not np.any(Clamping().fit_transform(empty_diag)) + assert not np.any(DiagramScaler()(empty_diag)) + assert not np.any(Padding()(empty_diag)) + assert not np.any(ProminentPoints()(empty_diag)) + assert not np.any(DiagramSelector()(empty_diag)) + +def pow(n): + return lambda x: np.power(x[1]-x[0],n) + +def test_vectorization_empty_diagrams(): + empty_diag = np.empty(shape = [0, 2]) + random_resolution = random.randint(50,100)*10 # between 500 and 1000 + print("resolution = ", random_resolution) + lsc = Landscape(resolution=random_resolution)(empty_diag) + assert not np.any(lsc) + assert lsc.shape[0]%random_resolution == 0 + slt = Silhouette(resolution=random_resolution, weight=pow(2))(empty_diag) + assert not np.any(slt) + assert slt.shape[0] == random_resolution + btc = BettiCurve(resolution=random_resolution)(empty_diag) + assert not np.any(btc) + assert btc.shape[0] == random_resolution + cpp = ComplexPolynomial(threshold=random_resolution, polynomial_type="T")(empty_diag) + assert not np.any(cpp) + assert cpp.shape[0] == random_resolution + tpv = TopologicalVector(threshold=random_resolution)(empty_diag) + assert tpv.shape[0] == random_resolution + assert not np.any(tpv) + prmg = PersistenceImage(resolution=[random_resolution,random_resolution])(empty_diag) + assert not np.any(prmg) + assert prmg.shape[0] == random_resolution * random_resolution + sce = Entropy(mode="scalar", resolution=random_resolution)(empty_diag) + assert not np.any(sce) + assert sce.shape[0] == 1 + scv = Entropy(mode="vector", normalized=False, resolution=random_resolution)(empty_diag) + assert not np.any(scv) + assert scv.shape[0] == random_resolution + +def test_kernel_empty_diagrams(): + empty_diag = np.empty(shape = [0, 2]) + assert SlicedWassersteinDistance(num_directions=100)(empty_diag, empty_diag) == 0. + assert SlicedWassersteinKernel(num_directions=100, bandwidth=1.)(empty_diag, empty_diag) == 1. + assert WassersteinDistance(mode="hera", delta=0.0001)(empty_diag, empty_diag) == 0. + assert WassersteinDistance(mode="pot")(empty_diag, empty_diag) == 0. + assert BottleneckDistance(epsilon=.001)(empty_diag, empty_diag) == 0. + assert BottleneckDistance()(empty_diag, empty_diag) == 0. +# PersistenceWeightedGaussianKernel(bandwidth=1., kernel_approx=None, weight=arctan(1.,1.))(empty_diag, empty_diag) +# PersistenceWeightedGaussianKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2])), weight=arctan(1.,1.))(empty_diag, empty_diag) +# PersistenceScaleSpaceKernel(bandwidth=1.)(empty_diag, empty_diag) +# PersistenceScaleSpaceKernel(kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2])))(empty_diag, empty_diag) +# PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1.)(empty_diag, empty_diag) +# PersistenceFisherKernel(bandwidth_fisher=1., bandwidth=1., kernel_approx=RBFSampler(gamma=1./2, n_components=100000).fit(np.ones([1,2])))(empty_diag, empty_diag) diff --git a/src/python/test/test_rips_complex.py b/src/python/test/test_rips_complex.py index b86e7498..a2f43a1b 100755 --- a/src/python/test/test_rips_complex.py +++ b/src/python/test/test_rips_complex.py @@ -133,3 +133,24 @@ def test_filtered_rips_from_distance_matrix(): assert simplex_tree.num_simplices() == 8 assert simplex_tree.num_vertices() == 4 + + +def test_sparse_with_multiplicity(): + points = [ + [3, 4], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [0.1, 2], + [3, 4.1], + ] + rips = RipsComplex(points=points, sparse=0.01) + simplex_tree = rips.create_simplex_tree(max_dimension=2) + assert simplex_tree.num_simplices() == 7 + diag = simplex_tree.persistence() diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py index a3eacaa9..31c46213 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, __GUDHI_USE_EIGEN3 +import numpy as np import pytest __author__ = "Vincent Rouvreau" @@ -404,3 +405,46 @@ def test_boundaries_iterator(): with pytest.raises(RuntimeError): list(st.get_boundaries([6])) # (6) does not exist + +def test_persistence_intervals_in_dimension(): + # Here is our triangulation of a 2-torus - taken from https://dioscuri-tda.org/Paris_TDA_Tutorial_2021.html + # 0-----3-----4-----0 + # | \ | \ | \ | \ | + # | \ | \ | \| \ | + # 1-----8-----7-----1 + # | \ | \ | \ | \ | + # | \ | \ | \ | \ | + # 2-----5-----6-----2 + # | \ | \ | \ | \ | + # | \ | \ | \ | \ | + # 0-----3-----4-----0 + st = SimplexTree() + st.insert([0,1,8]) + st.insert([0,3,8]) + st.insert([3,7,8]) + st.insert([3,4,7]) + st.insert([1,4,7]) + st.insert([0,1,4]) + st.insert([1,2,5]) + st.insert([1,5,8]) + st.insert([5,6,8]) + st.insert([6,7,8]) + st.insert([2,6,7]) + st.insert([1,2,7]) + st.insert([0,2,3]) + st.insert([2,3,5]) + st.insert([3,4,5]) + st.insert([4,5,6]) + st.insert([0,4,6]) + st.insert([0,2,6]) + st.compute_persistence(persistence_dim_max=True) + + H0 = st.persistence_intervals_in_dimension(0) + assert np.array_equal(H0, np.array([[ 0., float("inf")]])) + H1 = st.persistence_intervals_in_dimension(1) + assert np.array_equal(H1, np.array([[ 0., float("inf")], [ 0., float("inf")]])) + H2 = st.persistence_intervals_in_dimension(2) + assert np.array_equal(H2, np.array([[ 0., float("inf")]])) + # Test empty case + assert st.persistence_intervals_in_dimension(3).shape == (0, 2) +
\ No newline at end of file diff --git a/src/python/test/test_tomato.py b/src/python/test/test_tomato.py index ecab03c4..c571f799 100755 --- a/src/python/test/test_tomato.py +++ b/src/python/test/test_tomato.py @@ -37,7 +37,7 @@ def test_tomato_1(): t = Tomato(metric="euclidean", graph_type="radius", r=4.7, k=4) t.fit(a) assert t.max_weight_per_cc_.size == 2 - assert np.array_equal(t.neighbors_, [[0, 1, 2], [0, 1, 2], [0, 1, 2], [3, 4, 5, 6], [3, 4, 5], [3, 4, 5], [3, 6]]) + assert t.neighbors_ == [[0, 1, 2], [0, 1, 2], [0, 1, 2], [3, 4, 5, 6], [3, 4, 5], [3, 4, 5], [3, 6]] t.plot_diagram() t = Tomato(graph_type="radius", r=4.7, k=4, symmetrize_graph=True) diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py index e3b521d6..3a004d77 100755 --- a/src/python/test/test_wasserstein_distance.py +++ b/src/python/test/test_wasserstein_distance.py @@ -5,25 +5,97 @@ Copyright (C) 2019 Inria Modification(s): + - 2020/07 Théo Lacombe: Added tests about handling essential parts in diagrams. - YYYY/MM Author: Description of the modification """ -from gudhi.wasserstein.wasserstein import _proj_on_diag +from gudhi.wasserstein.wasserstein import _proj_on_diag, _finite_part, _handle_essential_parts, _get_essential_parts +from gudhi.wasserstein.wasserstein import _warn_infty from gudhi.wasserstein import wasserstein_distance as pot from gudhi.hera import wasserstein_distance as hera import numpy as np import pytest + __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 test_finite_part(): + diag = np.array([[0, 1], [3, 5], [2, np.inf], [3, np.inf], [-np.inf, 8], [-np.inf, 12], [-np.inf, -np.inf], + [np.inf, np.inf], [-np.inf, np.inf], [-np.inf, np.inf]]) + assert np.array_equal(_finite_part(diag), [[0, 1], [3, 5]]) + + +def test_handle_essential_parts(): + diag1 = np.array([[0, 1], [3, 5], + [2, np.inf], [3, np.inf], + [-np.inf, 8], [-np.inf, 12], + [-np.inf, -np.inf], + [np.inf, np.inf], + [-np.inf, np.inf], [-np.inf, np.inf]]) + + diag2 = np.array([[0, 2], [3, 5], + [2, np.inf], [4, np.inf], + [-np.inf, 8], [-np.inf, 11], + [-np.inf, -np.inf], + [np.inf, np.inf], + [-np.inf, np.inf], [-np.inf, np.inf]]) + + diag3 = np.array([[0, 2], [3, 5], + [2, np.inf], [4, np.inf], [6, np.inf], + [-np.inf, 8], [-np.inf, 11], + [-np.inf, -np.inf], + [np.inf, np.inf], + [-np.inf, np.inf], [-np.inf, np.inf]]) + + c, m = _handle_essential_parts(diag1, diag2, order=1) + assert c == pytest.approx(2, 0.0001) # Note: here c is only the cost due to essential part (thus 2, not 3) + # Similarly, the matching only corresponds to essential parts. + # Note that (-inf,-inf) and (+inf,+inf) coordinates are matched to the diagonal. + assert np.array_equal(m, [[4, 4], [5, 5], [2, 2], [3, 3], [8, 8], [9, 9], [6, -1], [7, -1], [-1, 6], [-1, 7]]) + + c, m = _handle_essential_parts(diag1, diag3, order=1) + assert c == np.inf + assert (m is None) + + +def test_get_essential_parts(): + diag1 = np.array([[0, 1], [3, 5], [2, np.inf], [3, np.inf], [-np.inf, 8], [-np.inf, 12], [-np.inf, -np.inf], + [np.inf, np.inf], [-np.inf, np.inf], [-np.inf, np.inf]]) + + diag2 = np.array([[0, 1], [3, 5], [2, np.inf], [3, np.inf]]) + + res = _get_essential_parts(diag1) + res2 = _get_essential_parts(diag2) + assert np.array_equal(res[0], [4, 5]) + assert np.array_equal(res[1], [2, 3]) + assert np.array_equal(res[2], [8, 9]) + assert np.array_equal(res[3], [6] ) + assert np.array_equal(res[4], [7] ) + + assert np.array_equal(res2[0], [] ) + assert np.array_equal(res2[1], [2, 3]) + assert np.array_equal(res2[2], [] ) + assert np.array_equal(res2[3], [] ) + assert np.array_equal(res2[4], [] ) + + +def test_warn_infty(): + assert _warn_infty(matching=False)==np.inf + c, m = _warn_infty(matching=True) + assert (c == np.inf) + assert (m is None) + + 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]]) @@ -64,7 +136,7 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat assert wasserstein_distance(diag4, diag5) == np.inf assert wasserstein_distance(diag5, diag6, order=1, internal_p=np.inf) == approx(4.) - + assert wasserstein_distance(diag5, emptydiag) == np.inf if test_matching: match = wasserstein_distance(emptydiag, emptydiag, matching=True, internal_p=1., order=2)[1] @@ -78,6 +150,31 @@ def _basic_wasserstein(wasserstein_distance, delta, test_infinity=True, test_mat match = wasserstein_distance(diag1, diag2, matching=True, internal_p=2., order=2.)[1] assert np.array_equal(match, [[0, 0], [1, 1], [2, -1]]) + if test_matching and test_infinity: + diag7 = np.array([[0, 3], [4, np.inf], [5, np.inf]]) + diag8 = np.array([[0,1], [0, np.inf], [-np.inf, -np.inf], [np.inf, np.inf]]) + diag9 = np.array([[-np.inf, -np.inf], [np.inf, np.inf]]) + diag10 = np.array([[0,1], [-np.inf, -np.inf], [np.inf, np.inf]]) + + match = wasserstein_distance(diag5, diag6, matching=True, internal_p=2., order=2.)[1] + assert np.array_equal(match, [[0, -1], [-1,0], [-1, 1], [1, 2]]) + match = wasserstein_distance(diag5, diag7, matching=True, internal_p=2., order=2.)[1] + assert (match is None) + cost, match = wasserstein_distance(diag7, emptydiag, matching=True, internal_p=2., order=2.3) + assert (cost == np.inf) + assert (match is None) + cost, match = wasserstein_distance(emptydiag, diag7, matching=True, internal_p=2.42, order=2.) + assert (cost == np.inf) + assert (match is None) + cost, match = wasserstein_distance(diag8, diag9, matching=True, internal_p=2., order=2.) + assert (cost == np.inf) + assert (match is None) + cost, match = wasserstein_distance(diag9, diag10, matching=True, internal_p=1., order=1.) + assert (cost == 1) + assert (match == [[0, -1],[1, -1],[-1, 0], [-1, 1], [-1, 2]]) # type 4 and 5 are match to the diag anyway. + cost, match = wasserstein_distance(diag9, emptydiag, matching=True, internal_p=2., order=2.) + assert (cost == 0.) + assert (match == [[0, -1], [1, -1]]) def hera_wrap(**extra): @@ -85,15 +182,19 @@ def hera_wrap(**extra): 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) + _basic_wasserstein(pot, 1e-15, test_infinity=False, test_matching=True) # pot with its standard args + _basic_wasserstein(pot_wrap(enable_autodiff=True, keep_essential_parts=False), 1e-15, test_infinity=False, test_matching=False) + 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) + |