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
|
"""
Tests for sklearn.cluster._feature_agglomeration
"""
import numpy as np
from numpy.testing import assert_array_equal
from sklearn.cluster import FeatureAgglomeration
from sklearn.datasets import make_blobs
from sklearn.utils._testing import assert_array_almost_equal
def test_feature_agglomeration():
n_clusters = 1
X = np.array([0, 0, 1]).reshape(1, 3) # (n_samples, n_features)
agglo_mean = FeatureAgglomeration(n_clusters=n_clusters, pooling_func=np.mean)
agglo_median = FeatureAgglomeration(n_clusters=n_clusters, pooling_func=np.median)
agglo_mean.fit(X)
agglo_median.fit(X)
assert np.size(np.unique(agglo_mean.labels_)) == n_clusters
assert np.size(np.unique(agglo_median.labels_)) == n_clusters
assert np.size(agglo_mean.labels_) == X.shape[1]
assert np.size(agglo_median.labels_) == X.shape[1]
# Test transform
Xt_mean = agglo_mean.transform(X)
Xt_median = agglo_median.transform(X)
assert Xt_mean.shape[1] == n_clusters
assert Xt_median.shape[1] == n_clusters
assert Xt_mean == np.array([1 / 3.0])
assert Xt_median == np.array([0.0])
# Test inverse transform
X_full_mean = agglo_mean.inverse_transform(Xt_mean)
X_full_median = agglo_median.inverse_transform(Xt_median)
assert np.unique(X_full_mean[0]).size == n_clusters
assert np.unique(X_full_median[0]).size == n_clusters
assert_array_almost_equal(agglo_mean.transform(X_full_mean), Xt_mean)
assert_array_almost_equal(agglo_median.transform(X_full_median), Xt_median)
def test_feature_agglomeration_feature_names_out():
"""Check `get_feature_names_out` for `FeatureAgglomeration`."""
X, _ = make_blobs(n_features=6, random_state=0)
agglo = FeatureAgglomeration(n_clusters=3)
agglo.fit(X)
n_clusters = agglo.n_clusters_
names_out = agglo.get_feature_names_out()
assert_array_equal(
[f"featureagglomeration{i}" for i in range(n_clusters)], names_out
)
|
