Merge remote-tracking branch 'origin/master' into wass-autodiff

3 files changed, 205 insertions, 0 deletions

diff --git a/src/python/test/test_dtm.py b/src/python/test/test_dtm.py
new file mode 100755
index 00000000..859189fa
--- /dev/null
+++ b/src/python/test/test_dtm.py
@@ -0,0 +1,68 @@
+""" 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 DistanceToMeasure
+import numpy
+import pytest
+import torch
+
+
+def test_dtm_compare_euclidean():
+    pts = numpy.random.rand(1000, 4)
+    k = 3
+    dtm = DistanceToMeasure(k, implementation="ckdtree")
+    r0 = dtm.fit_transform(pts)
+    dtm = DistanceToMeasure(k, implementation="sklearn")
+    r1 = dtm.fit_transform(pts)
+    assert r1 == pytest.approx(r0)
+    dtm = DistanceToMeasure(k, implementation="sklearn", algorithm="brute")
+    r2 = dtm.fit_transform(pts)
+    assert r2 == pytest.approx(r0)
+    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 = 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)
+    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 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 not torch.isnan(pts2.grad).any()
+
+
+def test_dtm_precomputed():
+    dist = numpy.array([[1.0, 3, 8], [1, 5, 5], [0, 2, 3]])
+    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 = 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
new file mode 100755
index 00000000..a87ec212
--- /dev/null
+++ b/src/python/test/test_knn.py
@@ -0,0 +1,130 @@
+""" 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 KNearestNeighbors
+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 = 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 = 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 = (
+        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]]))
+    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)
+    r = knn.transform(query)
+    assert np.array_equal(r, [[0, 1], [1, 0], [3, 2]])
+    r = (
+        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 = 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, 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, 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)
+    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 = (
+        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 = (
+        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
+
+
+def test_knn_nop():
+    # This doesn't look super useful...
+    p = np.array([[0.0]])
+    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)
diff --git a/src/python/test/test_wasserstein_distance.py b/src/python/test/test_wasserstein_distance.py
index c6d6b346..6bfcb2ee 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]])