summaryrefslogtreecommitdiff
path: root/src/python/test/test_representations.py
blob: cda1a15b37318c1e8c5d5f864101e632e507f722 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
import os
import sys
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
    plt.show = lambda: None
    here = os.path.dirname(os.path.realpath(__file__))
    sys.path.append(here + "/../example")
    import diagram_vectorizations_distances_kernels

    return None


from gudhi.representations.vector_methods import Atol
from gudhi.representations.metrics import *
from gudhi.representations.kernel_methods import *


def _n_diags(n):
    l = []
    for _ in range(n):
        a = np.random.rand(50, 2)
        a[:, 1] += a[:, 0]  # So that y >= x
        l.append(a)
    return l


def test_multiple():
    l1 = _n_diags(9)
    l2 = _n_diags(11)
    l1b = l1.copy()
    d1 = pairwise_persistence_diagram_distances(l1, e=0.00001, n_jobs=4)
    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)
    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=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