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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
""" test the label propagation module """
import numpy as np
import pytest
from scipy.sparse import issparse
from sklearn.utils._testing import assert_warns
from sklearn.utils._testing import assert_no_warnings
from sklearn.semi_supervised import _label_propagation as label_propagation
from sklearn.metrics.pairwise import rbf_kernel
from sklearn.model_selection import train_test_split
from sklearn.neighbors import NearestNeighbors
from sklearn.datasets import make_classification
from sklearn.exceptions import ConvergenceWarning
from numpy.testing import assert_array_almost_equal
from numpy.testing import assert_array_equal
ESTIMATORS = [
(label_propagation.LabelPropagation, {'kernel': 'rbf'}),
(label_propagation.LabelPropagation, {'kernel': 'knn', 'n_neighbors': 2}),
(label_propagation.LabelPropagation, {
'kernel': lambda x, y: rbf_kernel(x, y, gamma=20)
}),
(label_propagation.LabelSpreading, {'kernel': 'rbf'}),
(label_propagation.LabelSpreading, {'kernel': 'knn', 'n_neighbors': 2}),
(label_propagation.LabelSpreading, {
'kernel': lambda x, y: rbf_kernel(x, y, gamma=20)
}),
]
def test_fit_transduction():
samples = [[1., 0.], [0., 2.], [1., 3.]]
labels = [0, 1, -1]
for estimator, parameters in ESTIMATORS:
clf = estimator(**parameters).fit(samples, labels)
assert clf.transduction_[2] == 1
def test_distribution():
samples = [[1., 0.], [0., 1.], [1., 1.]]
labels = [0, 1, -1]
for estimator, parameters in ESTIMATORS:
clf = estimator(**parameters).fit(samples, labels)
if parameters['kernel'] == 'knn':
continue # unstable test; changes in k-NN ordering break it
assert_array_almost_equal(clf.predict_proba([[1., 0.0]]),
np.array([[1., 0.]]), 2)
else:
assert_array_almost_equal(np.asarray(clf.label_distributions_[2]),
np.array([.5, .5]), 2)
def test_predict():
samples = [[1., 0.], [0., 2.], [1., 3.]]
labels = [0, 1, -1]
for estimator, parameters in ESTIMATORS:
clf = estimator(**parameters).fit(samples, labels)
assert_array_equal(clf.predict([[0.5, 2.5]]), np.array([1]))
def test_predict_proba():
samples = [[1., 0.], [0., 1.], [1., 2.5]]
labels = [0, 1, -1]
for estimator, parameters in ESTIMATORS:
clf = estimator(**parameters).fit(samples, labels)
assert_array_almost_equal(clf.predict_proba([[1., 1.]]),
np.array([[0.5, 0.5]]))
def test_label_spreading_closed_form():
n_classes = 2
X, y = make_classification(n_classes=n_classes, n_samples=200,
random_state=0)
y[::3] = -1
clf = label_propagation.LabelSpreading().fit(X, y)
# adopting notation from Zhou et al (2004):
S = clf._build_graph()
Y = np.zeros((len(y), n_classes + 1))
Y[np.arange(len(y)), y] = 1
Y = Y[:, :-1]
for alpha in [0.1, 0.3, 0.5, 0.7, 0.9]:
expected = np.dot(np.linalg.inv(np.eye(len(S)) - alpha * S), Y)
expected /= expected.sum(axis=1)[:, np.newaxis]
clf = label_propagation.LabelSpreading(max_iter=10000, alpha=alpha)
clf.fit(X, y)
assert_array_almost_equal(expected, clf.label_distributions_, 4)
def test_label_propagation_closed_form():
n_classes = 2
X, y = make_classification(n_classes=n_classes, n_samples=200,
random_state=0)
y[::3] = -1
Y = np.zeros((len(y), n_classes + 1))
Y[np.arange(len(y)), y] = 1
unlabelled_idx = Y[:, (-1,)].nonzero()[0]
labelled_idx = (Y[:, (-1,)] == 0).nonzero()[0]
clf = label_propagation.LabelPropagation(max_iter=10000,
gamma=0.1)
clf.fit(X, y)
# adopting notation from Zhu et al 2002
T_bar = clf._build_graph()
Tuu = T_bar[tuple(np.meshgrid(unlabelled_idx, unlabelled_idx,
indexing='ij'))]
Tul = T_bar[tuple(np.meshgrid(unlabelled_idx, labelled_idx,
indexing='ij'))]
Y = Y[:, :-1]
Y_l = Y[labelled_idx, :]
Y_u = np.dot(np.dot(np.linalg.inv(np.eye(Tuu.shape[0]) - Tuu), Tul), Y_l)
expected = Y.copy()
expected[unlabelled_idx, :] = Y_u
expected /= expected.sum(axis=1)[:, np.newaxis]
assert_array_almost_equal(expected, clf.label_distributions_, 4)
def test_valid_alpha():
n_classes = 2
X, y = make_classification(n_classes=n_classes, n_samples=200,
random_state=0)
for alpha in [-0.1, 0, 1, 1.1, None]:
with pytest.raises(ValueError):
label_propagation.LabelSpreading(alpha=alpha).fit(X, y)
def test_convergence_speed():
# This is a non-regression test for #5774
X = np.array([[1., 0.], [0., 1.], [1., 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=5000)
mdl.fit(X, y)
# this should converge quickly:
assert mdl.n_iter_ < 10
assert_array_equal(mdl.predict(X), [0, 1, 1])
def test_convergence_warning():
# This is a non-regression test for #5774
X = np.array([[1., 0.], [0., 1.], [1., 2.5]])
y = np.array([0, 1, -1])
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=1)
assert_warns(ConvergenceWarning, mdl.fit, X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=1)
assert_warns(ConvergenceWarning, mdl.fit, X, y)
assert mdl.n_iter_ == mdl.max_iter
mdl = label_propagation.LabelSpreading(kernel='rbf', max_iter=500)
assert_no_warnings(mdl.fit, X, y)
mdl = label_propagation.LabelPropagation(kernel='rbf', max_iter=500)
assert_no_warnings(mdl.fit, X, y)
def test_label_propagation_non_zero_normalizer():
# check that we don't divide by zero in case of null normalizer
# non-regression test for
# https://github.com/scikit-learn/scikit-learn/pull/15946
X = np.array([[100., 100.], [100., 100.], [0., 0.], [0., 0.]])
y = np.array([0, 1, -1, -1])
mdl = label_propagation.LabelSpreading(kernel='knn',
max_iter=100,
n_neighbors=1)
assert_no_warnings(mdl.fit, X, y)
def test_predict_sparse_callable_kernel():
# This is a non-regression test for #15866
# Custom sparse kernel (top-K RBF)
def topk_rbf(X, Y=None, n_neighbors=10, gamma=1e-5):
nn = NearestNeighbors(n_neighbors=10, metric='euclidean', n_jobs=-1)
nn.fit(X)
W = -1 * nn.kneighbors_graph(Y, mode='distance').power(2) * gamma
np.exp(W.data, out=W.data)
assert issparse(W)
return W.T
n_classes = 4
n_samples = 500
n_test = 10
X, y = make_classification(n_classes=n_classes,
n_samples=n_samples,
n_features=20,
n_informative=20,
n_redundant=0,
n_repeated=0,
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=n_test,
random_state=0)
model = label_propagation.LabelSpreading(kernel=topk_rbf)
model.fit(X_train, y_train)
assert model.score(X_test, y_test) >= 0.9
model = label_propagation.LabelPropagation(kernel=topk_rbf)
model.fit(X_train, y_train)
assert model.score(X_test, y_test) >= 0.9
|
