merge upstream/master into essential parts

6 files changed, 206 insertions, 11 deletions

diff --git a/src/python/test/test_alpha_complex.py b/src/python/test/test_alpha_complex.py
index a4ee260b..814f8289 100755
--- a/src/python/test/test_alpha_complex.py
+++ b/src/python/test/test_alpha_complex.py
@@ -198,8 +198,7 @@ def test_delaunay_complex():
         _delaunay_complex(precision)
 
 def _3d_points_on_a_plane(precision, default_filtration_value):
-    alpha = gd.AlphaComplex(off_file=gd.__root_source_dir__ + '/data/points/alphacomplexdoc.off',
-                         precision = precision)
+    alpha = gd.AlphaComplex(off_file='alphacomplexdoc.off', precision = precision)
 
     simplex_tree = alpha.create_simplex_tree(default_filtration_value = default_filtration_value)
     assert simplex_tree.dimension() == 2
@@ -207,6 +206,18 @@ def _3d_points_on_a_plane(precision, default_filtration_value):
     assert simplex_tree.num_simplices() == 25
 
 def test_3d_points_on_a_plane():
+    off_file = open("alphacomplexdoc.off", "w")
+    off_file.write("OFF         \n" \
+                   "7 0 0       \n" \
+                   "1.0 1.0  0.0\n" \
+                   "7.0 0.0  0.0\n" \
+                   "4.0 6.0  0.0\n" \
+                   "9.0 6.0  0.0\n" \
+                   "0.0 14.0 0.0\n" \
+                   "2.0 19.0 0.0\n" \
+                   "9.0 17.0 0.0\n"  )
+    off_file.close()
+
     for default_filtration_value in [True, False]:
         for precision in ['fast', 'safe', 'exact']:
             _3d_points_on_a_plane(precision, default_filtration_value)
diff --git a/src/python/test/test_bottleneck_distance.py b/src/python/test/test_bottleneck_distance.py
index 6915bea8..07fcc9cc 100755
--- a/src/python/test/test_bottleneck_distance.py
+++ b/src/python/test/test_bottleneck_distance.py
@@ -25,3 +25,15 @@ def test_basic_bottleneck():
     assert gudhi.bottleneck_distance(diag1, diag2, 0.1) == pytest.approx(0.75, abs=0.1)
     assert gudhi.hera.bottleneck_distance(diag1, diag2, 0) == 0.75
     assert gudhi.hera.bottleneck_distance(diag1, diag2, 0.1) == pytest.approx(0.75, rel=0.1)
+
+    import numpy as np
+
+    # Translating both diagrams along the diagonal should not affect the distance,
+    # checks that negative numbers are not an issue
+    diag1 = np.array(diag1) - 100
+    diag2 = np.array(diag2) - 100
+
+    assert gudhi.bottleneck_distance(diag1, diag2) == 0.75
+    assert gudhi.bottleneck_distance(diag1, diag2, 0.1) == pytest.approx(0.75, abs=0.1)
+    assert gudhi.hera.bottleneck_distance(diag1, diag2, 0) == 0.75
+    assert gudhi.hera.bottleneck_distance(diag1, diag2, 0.1) == pytest.approx(0.75, rel=0.1)
diff --git a/src/python/test/test_representations.py b/src/python/test/test_representations.py
index 589cee00..cda1a15b 100755
--- a/src/python/test/test_representations.py
+++ b/src/python/test/test_representations.py
@@ -4,6 +4,8 @@ import matplotlib.pyplot as plt
 import numpy as np
 import pytest
 
+from sklearn.cluster import KMeans
+
 
 def test_representations_examples():
     # Disable graphics for testing purposes
@@ -15,6 +17,7 @@ def test_representations_examples():
     return None
 
 
+from gudhi.representations.vector_methods import Atol
 from gudhi.representations.metrics import *
 from gudhi.representations.kernel_methods import *
 
@@ -36,8 +39,62 @@ def test_multiple():
     d2 = BottleneckDistance(epsilon=0.00001).fit_transform(l1)
     d3 = pairwise_persistence_diagram_distances(l1, l1b, e=0.00001, n_jobs=4)
     assert d1 == pytest.approx(d2)
-    assert d3 == pytest.approx(d2, abs=1e-5) # Because of 0 entries (on the diagonal)
+    assert d3 == pytest.approx(d2, abs=1e-5)  # Because of 0 entries (on the diagonal)
     d1 = pairwise_persistence_diagram_distances(l1, l2, metric="wasserstein", order=2, internal_p=2)
     d2 = WassersteinDistance(order=2, internal_p=2, n_jobs=4).fit(l2).transform(l1)
     print(d1.shape, d2.shape)
-    assert d1 == pytest.approx(d2, rel=.02)
+    assert d1 == pytest.approx(d2, rel=0.02)
+
+
+# Test sorted values as points order can be inverted, and sorted test is not documentation-friendly
+# Note the test below must be up to date with the Atol class documentation
+def test_atol_doc():
+    a = np.array([[1, 2, 4], [1, 4, 0], [1, 0, 4]])
+    b = np.array([[4, 2, 0], [4, 4, 0], [4, 0, 2]])
+    c = np.array([[3, 2, -1], [1, 2, -1]])
+
+    atol_vectoriser = Atol(quantiser=KMeans(n_clusters=2, random_state=202006))
+    # Atol will do
+    # X = np.concatenate([a,b,c])
+    # kmeans = KMeans(n_clusters=2, random_state=202006).fit(X) 
+    # kmeans.labels_ will be : array([1, 0, 1, 0, 0, 1, 0, 0])
+    first_cluster = np.asarray([a[0], a[2], b[2]])
+    second_cluster = np.asarray([a[1], b[0], b[2], c[0], c[1]])
+
+    # Check the center of the first_cluster and second_cluster are in Atol centers
+    centers = atol_vectoriser.fit(X=[a, b, c]).centers
+    np.isclose(centers, first_cluster.mean(axis=0)).all(1).any() 
+    np.isclose(centers, second_cluster.mean(axis=0)).all(1).any() 
+
+    vectorization = atol_vectoriser.transform(X=[a, b, c])
+    assert np.allclose(vectorization[0], atol_vectoriser(a))
+    assert np.allclose(vectorization[1], atol_vectoriser(b))
+    assert np.allclose(vectorization[2], atol_vectoriser(c))
+
+
+def test_dummy_atol():
+    a = np.array([[1, 2, 4], [1, 4, 0], [1, 0, 4]])
+    b = np.array([[4, 2, 0], [4, 4, 0], [4, 0, 2]])
+    c = np.array([[3, 2, -1], [1, 2, -1]])
+
+    for weighting_method in ["cloud", "iidproba"]:
+        for contrast in ["gaussian", "laplacian", "indicator"]:
+            atol_vectoriser = Atol(
+                quantiser=KMeans(n_clusters=1, random_state=202006),
+                weighting_method=weighting_method,
+                contrast=contrast,
+            )
+            atol_vectoriser.fit([a, b, c])
+            atol_vectoriser(a)
+            atol_vectoriser.transform(X=[a, b, c])
+
+
+from gudhi.representations.vector_methods import BettiCurve
+
+
+def test_infinity():
+    a = np.array([[1.0, 8.0], [2.0, np.inf], [3.0, 4.0]])
+    c = BettiCurve(20, [0.0, 10.0])(a)
+    assert c[1] == 0
+    assert c[7] == 3
+    assert c[9] == 2
diff --git a/src/python/test/test_simplex_tree.py b/src/python/test/test_simplex_tree.py
index 2137d822..a3eacaa9 100755
--- a/src/python/test/test_simplex_tree.py
+++ b/src/python/test/test_simplex_tree.py
@@ -8,7 +8,7 @@
       - YYYY/MM Author: Description of the modification
 """
 
-from gudhi import SimplexTree
+from gudhi import SimplexTree, __GUDHI_USE_EIGEN3
 import pytest
 
 __author__ = "Vincent Rouvreau"
@@ -340,3 +340,67 @@ def test_simplices_iterator():
         assert st.find(simplex[0]) == True
         print("filtration is: ", simplex[1])
         assert st.filtration(simplex[0]) == simplex[1]
+
+def test_collapse_edges():
+    st = SimplexTree()
+    
+    assert st.insert([0, 1], filtration=1.0) == True
+    assert st.insert([1, 2], filtration=1.0) == True
+    assert st.insert([2, 3], filtration=1.0) == True
+    assert st.insert([0, 3], filtration=1.0) == True
+    assert st.insert([0, 2], filtration=2.0) == True
+    assert st.insert([1, 3], filtration=2.0) == True
+
+    assert st.num_simplices() == 10
+
+    if __GUDHI_USE_EIGEN3:
+        st.collapse_edges()
+        assert st.num_simplices() == 9
+        assert st.find([1, 3]) == False
+        for simplex in st.get_skeleton(0):
+            assert simplex[1] == 1.
+    else:
+        # If no Eigen3, collapse_edges throws an exception
+        with pytest.raises(RuntimeError):
+            st.collapse_edges()
+
+def test_reset_filtration():
+    st = SimplexTree()
+    
+    assert st.insert([0, 1, 2], 3.) == True
+    assert st.insert([0, 3], 2.) == True
+    assert st.insert([3, 4, 5], 3.) == True
+    assert st.insert([0, 1, 6, 7], 4.) == True
+
+    # Guaranteed by construction
+    for simplex in st.get_simplices():
+        assert st.filtration(simplex[0]) >= 2.
+    
+    # dimension until 5 even if simplex tree is of dimension 3 to test the limits
+    for dimension in range(5, -1, -1):
+        st.reset_filtration(0., dimension)
+        for simplex in st.get_skeleton(3):
+            print(simplex)
+            if len(simplex[0]) < (dimension) + 1:
+                assert st.filtration(simplex[0]) >= 2.
+            else:
+                assert st.filtration(simplex[0]) == 0.
+
+def test_boundaries_iterator():
+    st = SimplexTree()
+
+    assert st.insert([0, 1, 2, 3], filtration=1.0) == True
+    assert st.insert([1, 2, 3, 4], filtration=2.0) == True
+
+    assert list(st.get_boundaries([1, 2, 3])) == [([1, 2], 1.0), ([1, 3], 1.0), ([2, 3], 1.0)]
+    assert list(st.get_boundaries([2, 3, 4])) == [([2, 3], 1.0), ([2, 4], 2.0), ([3, 4], 2.0)]
+    assert list(st.get_boundaries([2])) == []
+
+    with pytest.raises(RuntimeError):
+        list(st.get_boundaries([]))
+
+    with pytest.raises(RuntimeError):
+        list(st.get_boundaries([0, 4])) # (0, 4) does not exist
+
+    with pytest.raises(RuntimeError):
+        list(st.get_boundaries([6])) # (6) does not exist
diff --git a/src/python/test/test_subsampling.py b/src/python/test/test_subsampling.py
index 31f64e32..4019852e 100755
--- a/src/python/test/test_subsampling.py
+++ b/src/python/test/test_subsampling.py
@@ -141,12 +141,16 @@ def test_simple_sparsify_points():
     # assert gudhi.sparsify_point_set(points = [], min_squared_dist = 0.0) == []
     # assert gudhi.sparsify_point_set(points = [], min_squared_dist = 10.0) == []
     assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=0.0) == point_set
-    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=1.0) == point_set
-    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=2.0) == [
+    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=0.999) == point_set
+    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=1.001) == [
         [0, 1],
         [1, 0],
     ]
-    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=2.01) == [[0, 1]]
+    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=1.999) == [
+        [0, 1],
+        [1, 0],
+    ]
+    assert gudhi.sparsify_point_set(points=point_set, min_squared_dist=2.001) == [[0, 1]]
 
     assert (
         len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=0.0))
@@ -157,11 +161,11 @@ def test_simple_sparsify_points():
         == 5
     )
     assert (
-        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=40.0))
+        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=40.1))
         == 4
     )
     assert (
-        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=90.0))
+        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=89.9))
         == 3
     )
     assert (
@@ -169,7 +173,7 @@ def test_simple_sparsify_points():
         == 2
     )
     assert (
-        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=325.0))
+        len(gudhi.sparsify_point_set(off_file="subsample.off", min_squared_dist=324.9))
         == 2
     )
     assert (
diff --git a/src/python/test/test_wasserstein_with_tensors.py b/src/python/test/test_wasserstein_with_tensors.py
new file mode 100755
index 00000000..e3f1411a
--- /dev/null
+++ b/src/python/test/test_wasserstein_with_tensors.py
@@ -0,0 +1,47 @@
+""" 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 Carriere
+
+    Copyright (C) 2020 Inria
+
+    Modification(s):
+      - YYYY/MM Author: Description of the modification
+"""
+
+from gudhi.wasserstein import wasserstein_distance as pot
+import numpy as np
+import torch
+import tensorflow as tf
+
+def test_wasserstein_distance_grad():
+    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
+    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.]])
+
+def test_wasserstein_distance_grad_tensorflow():
+    with tf.GradientTape() as tape:
+        diag4 = tf.convert_to_tensor(tf.Variable(initial_value=np.array([[0., 10.]]),           trainable=True))
+        diag5 = tf.convert_to_tensor(tf.Variable(initial_value=np.array([[1., 11.], [3., 4.]]), trainable=True))
+        dist45 = pot(diag4, diag5, internal_p=1, order=1, enable_autodiff=True)
+        assert dist45 == 3.
+
+    grads = tape.gradient(dist45, [diag4, diag5])
+    assert np.array_equal(grads[0].values, [[-1., -1.]])
+    assert np.array_equal(grads[1].values, [[1., 1.], [-1., 1.]])
\ No newline at end of file