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
|
# Author: Vlad Niculae
# License: BSD 3 clause
import numpy as np
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_array_equal
from sklearn.utils.testing import assert_array_almost_equal
from sklearn.utils.testing import assert_warns
from sklearn.utils.testing import ignore_warnings
from sklearn.linear_model import (orthogonal_mp, orthogonal_mp_gram,
OrthogonalMatchingPursuit,
OrthogonalMatchingPursuitCV,
LinearRegression)
from sklearn.utils import check_random_state
from sklearn.datasets import make_sparse_coded_signal
n_samples, n_features, n_nonzero_coefs, n_targets = 20, 30, 5, 3
y, X, gamma = make_sparse_coded_signal(n_targets, n_features, n_samples,
n_nonzero_coefs, random_state=0)
# Make X not of norm 1 for testing
X *= 10
y *= 10
G, Xy = np.dot(X.T, X), np.dot(X.T, y)
# this makes X (n_samples, n_features)
# and y (n_samples, 3)
def test_correct_shapes():
assert_equal(orthogonal_mp(X, y[:, 0], n_nonzero_coefs=5).shape,
(n_features,))
assert_equal(orthogonal_mp(X, y, n_nonzero_coefs=5).shape,
(n_features, 3))
def test_correct_shapes_gram():
assert_equal(orthogonal_mp_gram(G, Xy[:, 0], n_nonzero_coefs=5).shape,
(n_features,))
assert_equal(orthogonal_mp_gram(G, Xy, n_nonzero_coefs=5).shape,
(n_features, 3))
def test_n_nonzero_coefs():
assert_true(np.count_nonzero(orthogonal_mp(X, y[:, 0],
n_nonzero_coefs=5)) <= 5)
assert_true(np.count_nonzero(orthogonal_mp(X, y[:, 0], n_nonzero_coefs=5,
precompute=True)) <= 5)
def test_tol():
tol = 0.5
gamma = orthogonal_mp(X, y[:, 0], tol=tol)
gamma_gram = orthogonal_mp(X, y[:, 0], tol=tol, precompute=True)
assert np.sum((y[:, 0] - np.dot(X, gamma)) ** 2) <= tol
assert np.sum((y[:, 0] - np.dot(X, gamma_gram)) ** 2) <= tol
def test_with_without_gram():
assert_array_almost_equal(
orthogonal_mp(X, y, n_nonzero_coefs=5),
orthogonal_mp(X, y, n_nonzero_coefs=5, precompute=True))
def test_with_without_gram_tol():
assert_array_almost_equal(
orthogonal_mp(X, y, tol=1.),
orthogonal_mp(X, y, tol=1., precompute=True))
def test_unreachable_accuracy():
assert_array_almost_equal(
orthogonal_mp(X, y, tol=0),
orthogonal_mp(X, y, n_nonzero_coefs=n_features))
assert_array_almost_equal(
assert_warns(RuntimeWarning, orthogonal_mp, X, y, tol=0,
precompute=True),
orthogonal_mp(X, y, precompute=True,
n_nonzero_coefs=n_features))
def test_bad_input():
assert_raises(ValueError, orthogonal_mp, X, y, tol=-1)
assert_raises(ValueError, orthogonal_mp, X, y, n_nonzero_coefs=-1)
assert_raises(ValueError, orthogonal_mp, X, y,
n_nonzero_coefs=n_features + 1)
assert_raises(ValueError, orthogonal_mp_gram, G, Xy, tol=-1)
assert_raises(ValueError, orthogonal_mp_gram, G, Xy, n_nonzero_coefs=-1)
assert_raises(ValueError, orthogonal_mp_gram, G, Xy,
n_nonzero_coefs=n_features + 1)
def test_perfect_signal_recovery():
idx, = gamma[:, 0].nonzero()
gamma_rec = orthogonal_mp(X, y[:, 0], 5)
gamma_gram = orthogonal_mp_gram(G, Xy[:, 0], 5)
assert_array_equal(idx, np.flatnonzero(gamma_rec))
assert_array_equal(idx, np.flatnonzero(gamma_gram))
assert_array_almost_equal(gamma[:, 0], gamma_rec, decimal=2)
assert_array_almost_equal(gamma[:, 0], gamma_gram, decimal=2)
def test_orthogonal_mp_gram_readonly():
# Non-regression test for:
# https://github.com/scikit-learn/scikit-learn/issues/5956
idx, = gamma[:, 0].nonzero()
G_readonly = G.copy()
G_readonly.setflags(write=False)
Xy_readonly = Xy.copy()
Xy_readonly.setflags(write=False)
gamma_gram = orthogonal_mp_gram(G_readonly, Xy_readonly[:, 0], 5,
copy_Gram=False, copy_Xy=False)
assert_array_equal(idx, np.flatnonzero(gamma_gram))
assert_array_almost_equal(gamma[:, 0], gamma_gram, decimal=2)
def test_estimator():
omp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_nonzero_coefs)
omp.fit(X, y[:, 0])
assert_equal(omp.coef_.shape, (n_features,))
assert_equal(omp.intercept_.shape, ())
assert np.count_nonzero(omp.coef_) <= n_nonzero_coefs
omp.fit(X, y)
assert_equal(omp.coef_.shape, (n_targets, n_features))
assert_equal(omp.intercept_.shape, (n_targets,))
assert np.count_nonzero(omp.coef_) <= n_targets * n_nonzero_coefs
coef_normalized = omp.coef_[0].copy()
omp.set_params(fit_intercept=True, normalize=False)
omp.fit(X, y[:, 0])
assert_array_almost_equal(coef_normalized, omp.coef_)
omp.set_params(fit_intercept=False, normalize=False)
omp.fit(X, y[:, 0])
assert np.count_nonzero(omp.coef_) <= n_nonzero_coefs
assert_equal(omp.coef_.shape, (n_features,))
assert_equal(omp.intercept_, 0)
omp.fit(X, y)
assert_equal(omp.coef_.shape, (n_targets, n_features))
assert_equal(omp.intercept_, 0)
assert np.count_nonzero(omp.coef_) <= n_targets * n_nonzero_coefs
def test_identical_regressors():
newX = X.copy()
newX[:, 1] = newX[:, 0]
gamma = np.zeros(n_features)
gamma[0] = gamma[1] = 1.
newy = np.dot(newX, gamma)
assert_warns(RuntimeWarning, orthogonal_mp, newX, newy, 2)
def test_swapped_regressors():
gamma = np.zeros(n_features)
# X[:, 21] should be selected first, then X[:, 0] selected second,
# which will take X[:, 21]'s place in case the algorithm does
# column swapping for optimization (which is the case at the moment)
gamma[21] = 1.0
gamma[0] = 0.5
new_y = np.dot(X, gamma)
new_Xy = np.dot(X.T, new_y)
gamma_hat = orthogonal_mp(X, new_y, 2)
gamma_hat_gram = orthogonal_mp_gram(G, new_Xy, 2)
assert_array_equal(np.flatnonzero(gamma_hat), [0, 21])
assert_array_equal(np.flatnonzero(gamma_hat_gram), [0, 21])
def test_no_atoms():
y_empty = np.zeros_like(y)
Xy_empty = np.dot(X.T, y_empty)
gamma_empty = ignore_warnings(orthogonal_mp)(X, y_empty, 1)
gamma_empty_gram = ignore_warnings(orthogonal_mp)(G, Xy_empty, 1)
assert_equal(np.all(gamma_empty == 0), True)
assert_equal(np.all(gamma_empty_gram == 0), True)
def test_omp_path():
path = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=True)
last = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=False)
assert_equal(path.shape, (n_features, n_targets, 5))
assert_array_almost_equal(path[:, :, -1], last)
path = orthogonal_mp_gram(G, Xy, n_nonzero_coefs=5, return_path=True)
last = orthogonal_mp_gram(G, Xy, n_nonzero_coefs=5, return_path=False)
assert_equal(path.shape, (n_features, n_targets, 5))
assert_array_almost_equal(path[:, :, -1], last)
def test_omp_return_path_prop_with_gram():
path = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=True,
precompute=True)
last = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=False,
precompute=True)
assert_equal(path.shape, (n_features, n_targets, 5))
assert_array_almost_equal(path[:, :, -1], last)
def test_omp_cv():
y_ = y[:, 0]
gamma_ = gamma[:, 0]
ompcv = OrthogonalMatchingPursuitCV(normalize=True, fit_intercept=False,
max_iter=10, cv=5)
ompcv.fit(X, y_)
assert_equal(ompcv.n_nonzero_coefs_, n_nonzero_coefs)
assert_array_almost_equal(ompcv.coef_, gamma_)
omp = OrthogonalMatchingPursuit(normalize=True, fit_intercept=False,
n_nonzero_coefs=ompcv.n_nonzero_coefs_)
omp.fit(X, y_)
assert_array_almost_equal(ompcv.coef_, omp.coef_)
def test_omp_reaches_least_squares():
# Use small simple data; it's a sanity check but OMP can stop early
rng = check_random_state(0)
n_samples, n_features = (10, 8)
n_targets = 3
X = rng.randn(n_samples, n_features)
Y = rng.randn(n_samples, n_targets)
omp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_features)
lstsq = LinearRegression()
omp.fit(X, Y)
lstsq.fit(X, Y)
assert_array_almost_equal(omp.coef_, lstsq.coef_)
|
