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
|
import numpy as np
from scipy import sparse as sp
import pytest
from sklearn.svm.bounds import l1_min_c
from sklearn.svm import LinearSVC
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.utils.testing import assert_true, assert_raises
from sklearn.utils.testing import assert_raise_message
dense_X = [[-1, 0], [0, 1], [1, 1], [1, 1]]
sparse_X = sp.csr_matrix(dense_X)
Y1 = [0, 1, 1, 1]
Y2 = [2, 1, 0, 0]
@pytest.mark.parametrize('loss', ['squared_hinge', 'log'])
@pytest.mark.parametrize('X_label', ['sparse', 'dense'])
@pytest.mark.parametrize('Y_label', ['two-classes', 'multi-class'])
@pytest.mark.parametrize('intercept_label', ['no-intercept', 'fit-intercept'])
def test_l1_min_c(loss, X_label, Y_label, intercept_label):
Xs = {'sparse': sparse_X, 'dense': dense_X}
Ys = {'two-classes': Y1, 'multi-class': Y2}
intercepts = {'no-intercept': {'fit_intercept': False},
'fit-intercept': {'fit_intercept': True,
'intercept_scaling': 10}}
X = Xs[X_label]
Y = Ys[Y_label]
intercept_params = intercepts[intercept_label]
check_l1_min_c(X, Y, loss, **intercept_params)
def test_l1_min_c_l2_loss():
# loss='l2' should raise ValueError
assert_raise_message(ValueError, "loss type not in",
l1_min_c, dense_X, Y1, "l2")
def check_l1_min_c(X, y, loss, fit_intercept=True, intercept_scaling=None):
min_c = l1_min_c(X, y, loss, fit_intercept, intercept_scaling)
clf = {
'log': LogisticRegression(penalty='l1', solver='liblinear',
multi_class='ovr'),
'squared_hinge': LinearSVC(loss='squared_hinge',
penalty='l1', dual=False),
}[loss]
clf.fit_intercept = fit_intercept
clf.intercept_scaling = intercept_scaling
clf.C = min_c
clf.fit(X, y)
assert (np.asarray(clf.coef_) == 0).all()
assert (np.asarray(clf.intercept_) == 0).all()
clf.C = min_c * 1.01
clf.fit(X, y)
assert_true((np.asarray(clf.coef_) != 0).any() or
(np.asarray(clf.intercept_) != 0).any())
def test_ill_posed_min_c():
X = [[0, 0], [0, 0]]
y = [0, 1]
assert_raises(ValueError, l1_min_c, X, y)
def test_unsupported_loss():
assert_raises(ValueError, l1_min_c, dense_X, Y1, 'l1')
|
