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
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
|
"""
Todo: cross-check the F-value with stats model
"""
from sklearn.feature_selection import (chi2, f_classif, f_oneway, f_regression,
SelectPercentile, SelectKBest,
SelectFpr, SelectFdr, SelectFwe,
GenericUnivariateSelect)
from nose.tools import assert_equal, assert_true
import numpy as np
from numpy.testing import assert_array_equal, assert_array_almost_equal
from scipy import stats
from sklearn.datasets.samples_generator import make_classification, \
make_regression
##############################################################################
# Test the score functions
def test_f_oneway_vs_scipy_stats():
"""Test that our f_oneway gives the same result as scipy.stats"""
rng = np.random.RandomState(0)
X1 = rng.randn(10, 3)
X2 = 1 + rng.randn(10, 3)
f, pv = stats.f_oneway(X1, X2)
f2, pv2 = f_oneway(X1, X2)
assert_true(np.allclose(f, f2))
assert_true(np.allclose(pv, pv2))
def test_f_classif():
"""
Test whether the F test yields meaningful results
on a simple simulated classification problem
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
F, pv = f_classif(X, Y)
assert(F > 0).all()
assert(pv > 0).all()
assert(pv < 1).all()
assert(pv[:5] < 0.05).all()
assert(pv[5:] > 1.e-4).all()
def test_f_regression():
"""
Test whether the F test yields meaningful results
on a simple simulated regression problem
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
F, pv = f_regression(X, Y)
assert(F > 0).all()
assert(pv > 0).all()
assert(pv < 1).all()
assert(pv[:5] < 0.05).all()
assert(pv[5:] > 1.e-4).all()
def test_f_regression_input_dtype():
"""
Test whether f_regression returns the same value
for any numeric data_type
"""
rng = np.random.RandomState(0)
X = rng.rand(10, 20)
y = np.arange(10).astype(np.int)
F1, pv1 = f_regression(X, y)
F2, pv2 = f_regression(X, y.astype(np.float))
assert_array_almost_equal(F1, F2, 5)
assert_array_almost_equal(pv1, pv2, 5)
def test_f_classif_multi_class():
"""
Test whether the F test yields meaningful results
on a simple simulated classification problem
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
F, pv = f_classif(X, Y)
assert(F > 0).all()
assert(pv > 0).all()
assert(pv < 1).all()
assert(pv[:5] < 0.05).all()
assert(pv[5:] > 1.e-5).all()
def test_select_percentile_classif():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple classification problem
with the percentile heuristic
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
univariate_filter = SelectPercentile(f_classif, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='percentile',
param=25).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
##############################################################################
# Test univariate selection in classification settings
def test_select_kbest_classif():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple classification problem
with the k best heuristic
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
univariate_filter = SelectKBest(f_classif, k=5)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='k_best',
param=5).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_select_fpr_classif():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple classification problem
with the fpr heuristic
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
univariate_filter = SelectFpr(f_classif, alpha=0.0001)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='fpr',
param=0.0001).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_select_fdr_classif():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple classification problem
with the fpr heuristic
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
univariate_filter = SelectFdr(f_classif, alpha=0.0001)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='fdr',
param=0.0001).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_select_fwe_classif():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple classification problem
with the fpr heuristic
"""
X, Y = make_classification(n_samples=200, n_features=20,
n_informative=3, n_redundant=2,
n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
univariate_filter = SelectFwe(f_classif, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='fwe',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert(np.sum(np.abs(support - gtruth)) < 2)
##############################################################################
# Test univariate selection in regression settings
def test_select_percentile_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the percentile heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=25).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
X_2 = X.copy()
X_2[:, np.logical_not(support)] = 0
assert_array_equal(X_2, univariate_filter.inverse_transform(X_r))
def test_select_percentile_regression_full():
"""
Test whether the relative univariate feature selection
selects all features when '100%' is asked.
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=100)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=100).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.ones(20)
assert_array_equal(support, gtruth)
def test_select_kbest_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the k best heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectKBest(f_regression, k=5)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='k_best',
param=5).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_select_fpr_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the fpr heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFpr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fpr',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert(support[:5] == 1).all()
assert(np.sum(support[5:] == 1) < 3)
def test_select_fdr_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the fdr heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFdr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fdr',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_select_fwe_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the fwe heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFwe(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fwe',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert(support[:5] == 1).all()
assert(np.sum(support[5:] == 1) < 2)
def test_selectkbest_tiebreaking():
"""Test whether SelectKBest actually selects k features in case of ties.
Prior to 0.11, SelectKBest would return more features than requested.
"""
X = [[1, 0, 0], [0, 1, 1]]
y = [0, 1]
X1 = SelectKBest(chi2, k=1).fit_transform(X, y)
assert_equal(X1.shape[1], 1)
X2 = SelectKBest(chi2, k=2).fit_transform(X, y)
assert_equal(X2.shape[1], 2)
|
