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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
|
import numpy as np
import pytest
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_blobs
from sklearn.utils.class_weight import compute_class_weight
from sklearn.utils.class_weight import compute_sample_weight
from sklearn.utils.testing import assert_array_almost_equal
from sklearn.utils.testing import assert_almost_equal
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_raise_message
from sklearn.utils.testing import assert_equal
def test_compute_class_weight():
# Test (and demo) compute_class_weight.
y = np.asarray([2, 2, 2, 3, 3, 4])
classes = np.unique(y)
cw = compute_class_weight("balanced", classes, y)
# total effect of samples is preserved
class_counts = np.bincount(y)[2:]
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert cw[0] < cw[1] < cw[2]
def test_compute_class_weight_not_present():
# Raise error when y does not contain all class labels
classes = np.arange(4)
y = np.asarray([0, 0, 0, 1, 1, 2])
assert_raises(ValueError, compute_class_weight, "balanced", classes, y)
# Fix exception in error message formatting when missing label is a string
# https://github.com/scikit-learn/scikit-learn/issues/8312
assert_raise_message(ValueError,
'Class label label_not_present not present',
compute_class_weight,
{'label_not_present': 1.}, classes, y)
# Raise error when y has items not in classes
classes = np.arange(2)
assert_raises(ValueError, compute_class_weight, "balanced", classes, y)
assert_raises(ValueError, compute_class_weight, {0: 1., 1: 2.}, classes, y)
def test_compute_class_weight_dict():
classes = np.arange(3)
class_weights = {0: 1.0, 1: 2.0, 2: 3.0}
y = np.asarray([0, 0, 1, 2])
cw = compute_class_weight(class_weights, classes, y)
# When the user specifies class weights, compute_class_weights should just
# return them.
assert_array_almost_equal(np.asarray([1.0, 2.0, 3.0]), cw)
# When a class weight is specified that isn't in classes, a ValueError
# should get raised
msg = 'Class label 4 not present.'
class_weights = {0: 1.0, 1: 2.0, 2: 3.0, 4: 1.5}
assert_raise_message(ValueError, msg, compute_class_weight, class_weights,
classes, y)
msg = 'Class label -1 not present.'
class_weights = {-1: 5.0, 0: 1.0, 1: 2.0, 2: 3.0}
assert_raise_message(ValueError, msg, compute_class_weight, class_weights,
classes, y)
@pytest.mark.filterwarnings('ignore: Default solver will be changed') # 0.22
@pytest.mark.filterwarnings('ignore: Default multi_class will') # 0.22
def test_compute_class_weight_invariance():
# Test that results with class_weight="balanced" is invariant wrt
# class imbalance if the number of samples is identical.
# The test uses a balanced two class dataset with 100 datapoints.
# It creates three versions, one where class 1 is duplicated
# resulting in 150 points of class 1 and 50 of class 0,
# one where there are 50 points in class 1 and 150 in class 0,
# and one where there are 100 points of each class (this one is balanced
# again).
# With balancing class weights, all three should give the same model.
X, y = make_blobs(centers=2, random_state=0)
# create dataset where class 1 is duplicated twice
X_1 = np.vstack([X] + [X[y == 1]] * 2)
y_1 = np.hstack([y] + [y[y == 1]] * 2)
# create dataset where class 0 is duplicated twice
X_0 = np.vstack([X] + [X[y == 0]] * 2)
y_0 = np.hstack([y] + [y[y == 0]] * 2)
# duplicate everything
X_ = np.vstack([X] * 2)
y_ = np.hstack([y] * 2)
# results should be identical
logreg1 = LogisticRegression(class_weight="balanced").fit(X_1, y_1)
logreg0 = LogisticRegression(class_weight="balanced").fit(X_0, y_0)
logreg = LogisticRegression(class_weight="balanced").fit(X_, y_)
assert_array_almost_equal(logreg1.coef_, logreg0.coef_)
assert_array_almost_equal(logreg.coef_, logreg0.coef_)
def test_compute_class_weight_balanced_negative():
# Test compute_class_weight when labels are negative
# Test with balanced class labels.
classes = np.array([-2, -1, 0])
y = np.asarray([-1, -1, 0, 0, -2, -2])
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
# Test with unbalanced class labels.
y = np.asarray([-1, 0, 0, -2, -2, -2])
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
class_counts = np.bincount(y + 2)
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2. / 3, 2., 1.])
def test_compute_class_weight_balanced_unordered():
# Test compute_class_weight when classes are unordered
classes = np.array([1, 0, 3])
y = np.asarray([1, 0, 0, 3, 3, 3])
cw = compute_class_weight("balanced", classes, y)
class_counts = np.bincount(y)[classes]
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2., 1., 2. / 3])
def test_compute_class_weight_default():
# Test for the case where no weight is given for a present class.
# Current behaviour is to assign the unweighted classes a weight of 1.
y = np.asarray([2, 2, 2, 3, 3, 4])
classes = np.unique(y)
classes_len = len(classes)
# Test for non specified weights
cw = compute_class_weight(None, classes, y)
assert_equal(len(cw), classes_len)
assert_array_almost_equal(cw, np.ones(3))
# Tests for partly specified weights
cw = compute_class_weight({2: 1.5}, classes, y)
assert_equal(len(cw), classes_len)
assert_array_almost_equal(cw, [1.5, 1., 1.])
cw = compute_class_weight({2: 1.5, 4: 0.5}, classes, y)
assert_equal(len(cw), classes_len)
assert_array_almost_equal(cw, [1.5, 1., 0.5])
def test_compute_sample_weight():
# Test (and demo) compute_sample_weight.
# Test with balanced classes
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with user-defined weights
sample_weight = compute_sample_weight({1: 2, 2: 1}, y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 1., 1., 1.])
# Test with column vector of balanced classes
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with unbalanced classes
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("balanced", y)
expected_balanced = np.array([0.7777, 0.7777, 0.7777, 0.7777, 0.7777,
0.7777, 2.3333])
assert_array_almost_equal(sample_weight, expected_balanced, decimal=4)
# Test with `None` weights
sample_weight = compute_sample_weight(None, y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 1.])
# Test with multi-output of balanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with multi-output with user-defined weights
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight([{1: 2, 2: 1}, {0: 1, 1: 2}], y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 2., 2., 2.])
# Test with multi-output of unbalanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [3, -1]])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, expected_balanced ** 2, decimal=3)
def test_compute_sample_weight_with_subsample():
# Test compute_sample_weight with subsamples specified.
# Test with balanced classes and all samples present
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with column vector of balanced classes and all samples present
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with a subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("balanced", y, range(4))
assert_array_almost_equal(sample_weight, [2. / 3, 2. / 3,
2. / 3, 2., 2., 2.])
# Test with a bootstrap subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
expected_balanced = np.asarray([0.6, 0.6, 0.6, 3., 3., 3.])
assert_array_almost_equal(sample_weight, expected_balanced)
# Test with a bootstrap subsample for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected_balanced ** 2)
# Test with a missing class
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
# Test with a missing class for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [2, 2]])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
def test_compute_sample_weight_errors():
# Test compute_sample_weight raises errors expected.
# Invalid preset string
y = np.asarray([1, 1, 1, 2, 2, 2])
y_ = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
assert_raises(ValueError, compute_sample_weight, "ni", y)
assert_raises(ValueError, compute_sample_weight, "ni", y, range(4))
assert_raises(ValueError, compute_sample_weight, "ni", y_)
assert_raises(ValueError, compute_sample_weight, "ni", y_, range(4))
# Not "balanced" for subsample
assert_raises(ValueError,
compute_sample_weight, {1: 2, 2: 1}, y, range(4))
# Not a list or preset for multi-output
assert_raises(ValueError, compute_sample_weight, {1: 2, 2: 1}, y_)
# Incorrect length list for multi-output
assert_raises(ValueError, compute_sample_weight, [{1: 2, 2: 1}], y_)
def test_compute_sample_weight_more_than_32():
# Non-regression smoke test for #12146
y = np.arange(50) # more than 32 distinct classes
indices = np.arange(50) # use subsampling
weight = compute_sample_weight('balanced', y, indices=indices)
assert_array_almost_equal(weight, np.ones(y.shape[0]))
|
