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
|
import nose
from nose.tools import assert_true
import numpy as np
from scipy import sparse as sp
from sklearn.svm.bounds import l1_min_c
from sklearn.svm import LinearSVC
from sklearn.linear_model.logistic import LogisticRegression
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]
def test_l1_min_c():
losses = ['l2', 'log']
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}}
for loss in losses:
for X_label, X in Xs.items():
for Y_label, Y in Ys.items():
for intercept_label, intercept_params in intercepts.items():
check = lambda: check_l1_min_c(X, Y, loss,
**intercept_params)
check.description = 'Test l1_min_c loss=%r %s %s %s' % \
(loss, X_label, Y_label, intercept_label)
yield check
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'),
'l2': LinearSVC(loss='l2', penalty='l1', dual=False),
}[loss]
clf.fit_intercept = fit_intercept
clf.intercept_scaling = intercept_scaling
clf.C = min_c
clf.fit(X, y)
assert_true((np.asarray(clf.coef_) == 0).all())
assert_true((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())
@nose.tools.raises(ValueError)
def test_ill_posed_min_c():
X = [[0, 0], [0, 0]]
y = [0, 1]
l1_min_c(X, y)
@nose.tools.raises(ValueError)
def test_unsupported_loss():
l1_min_c(dense_X, Y1, 'l1')
|
