forked from pingfansong/mdla
/
test_mdla.py
391 lines (327 loc) · 15.6 KB
/
test_mdla.py
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
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
from __future__ import print_function
import numpy as np
from sklearn.utils.testing import assert_almost_equal
from sklearn.utils.testing import assert_array_almost_equal
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_raises
from mdla import MultivariateDictLearning
from mdla import MiniBatchMultivariateDictLearning
from mdla import SparseMultivariateCoder
from mdla import reconstruct_from_code
from mdla import multivariate_sparse_encode
rng_global = np.random.RandomState(0)
def test_mdla_shapes():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=10, verbose=5).fit(X)
for i in range(n_kernels):
assert_true(dico.kernels_[i].shape == (n_features, n_dims))
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, verbose=5, n_iter=10).fit(X)
for i in range(n_kernels):
assert_true(dico.kernels_[i].shape == (n_features, n_dims))
def test_multivariate_input_shape():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 7
n_dims_w = 6
Xw = [rng_global.randn(n_features, n_dims_w) for i in range(n_samples)]
dico = MultivariateDictLearning(n_kernels=n_kernels).fit(X)
for i in range(n_kernels):
assert_true(dico.kernels_[i].shape == (n_features, n_dims))
dico = MultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.fit, Xw)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels).fit(X)
for i in range(n_kernels):
assert_true(dico.kernels_[i].shape == (n_features, n_dims))
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.fit, Xw)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels).partial_fit(X)
for i in range(n_kernels):
assert_true(dico.kernels_[i].shape == (n_features, n_dims))
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.partial_fit, Xw)
def test_mdla_normalization():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, verbose=1).fit(X)
for k in dico.kernels_:
assert_almost_equal(np.linalg.norm(k, 'fro'), 1.)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=2, verbose=1).fit(X)
for k in dico.kernels_:
assert_almost_equal(np.linalg.norm(k, 'fro'), 1.)
def test_callback():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
def my_callback(loc):
d = loc['dict_obj']
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, n_nonzero_coefs=1,
callback=my_callback)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=2, n_nonzero_coefs=1,
callback=my_callback)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
def test_mdla_nonzero_coefs():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
def test_X_array():
n_samples, n_features, n_dims = 10, 5, 3
n_kernels = 8
X = rng_global.randn(n_samples, n_features, n_dims)
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
def test_mdla_shuffle():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=1,
verbose=5, shuffle=False)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
def test_n_kernels():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dico = MultivariateDictLearning(random_state=0, max_iter=2,
n_nonzero_coefs=1, verbose=5).fit(X)
assert_true(len(dico.kernels_) == 2*n_features)
dico = MiniBatchMultivariateDictLearning(random_state=0,
n_iter=2, n_nonzero_coefs=1, verbose=5).fit(X)
assert_true(len(dico.kernels_) == 2*n_features)
dico = MiniBatchMultivariateDictLearning(random_state=0,
n_iter=2, n_nonzero_coefs=1, verbose=5).partial_fit(X)
assert_true(len(dico.kernels_) == 2*n_features)
def test_mdla_nonzero_coef_errors():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, n_nonzero_coefs=0)
assert_raises(ValueError, dico.fit, X)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels, random_state=0,
n_iter=2, n_nonzero_coefs=n_kernels+1)
assert_raises(ValueError, dico.fit, X)
def test_sparse_encode():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, n_nonzero_coefs=1)
dico = dico.fit(X)
_, code = multivariate_sparse_encode(X, dico, n_nonzero_coefs=1,
n_jobs=-1, verbose=3)
assert_true(len(code[0]) <= 1)
def test_dict_init():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
d = [rng_global.randn(n_features, n_dims) for i in range(n_kernels)]
for i in range(len(d)):
d[i] /= np.linalg.norm(d[i], 'fro')
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=1, n_nonzero_coefs=1, learning_rate=0.,
dict_init=d, verbose=5).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
# code = dico.fit(X).transform(X[0])
# assert_true(len(code[0]) > 1)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=1, n_nonzero_coefs=1,
dict_init=d, verbose=1, learning_rate=0.).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
# code = dico.fit(X).transform(X[0])
# assert_true(len(code[0]) <= 1)
def test_mdla_dict_init():
n_kernels = 10
n_samples, n_features, n_dims = 20, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dict_init = [np.random.randn(n_features, n_dims) for i in range(n_kernels)]
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=10, dict_init=dict_init).fit(X)
diff = 0.
for i in range(n_kernels):
diff = diff + (dico.kernels_[i]-dict_init[i]).sum()
assert_true(diff !=0)
def test_mdla_dict_update():
n_kernels = 10
# n_samples, n_features, n_dims = 100, 5, 3
n_samples, n_features, n_dims = 80, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=10, n_jobs=-1).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=10, n_jobs=-1).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=10, n_jobs=-1).partial_fit(X)
first_epoch = list(dico.kernels_)
dico = dico.partial_fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
def test_sparse_multivariate_coder():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
d = [np.random.randn(n_features, n_dims) for i in range(n_kernels)]
coder = SparseMultivariateCoder(dictionary=d, n_nonzero_coefs=1, n_jobs=-1)
coder.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(d[i], coder.kernels_[i])
def TODO_test_shift_invariant_input():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = list()
dico.append(np.array([1, 2, 3, 2, 1]))
def _generate_testbed(kernel_init_len, n_nonzero_coefs, n_kernels,
n_samples=10, n_features=5, n_dims=3):
dico = [np.random.randn(kernel_init_len, n_dims) for i in range(n_kernels)]
for i in range(len(dico)):
dico[i] /= np.linalg.norm(dico[i], 'fro')
signals = list()
decomposition = list()
for i in range(n_samples):
s = np.zeros(shape=(n_features, n_dims))
d = np.zeros(shape=(n_nonzero_coefs, 3))
rk = np.random.permutation(range(n_kernels))
for j in range(n_nonzero_coefs):
k_idx = rk[j]
k_amplitude = 3. * np.random.rand() + 1.
k_offset = np.random.randint(n_features - kernel_init_len + 1)
s[k_offset:k_offset+kernel_init_len, :] += (k_amplitude *
dico[k_idx])
d[j, :] = np.array([k_amplitude, k_offset, k_idx])
decomposition.append(d)
signals.append(s)
signals = np.array(signals)
return dico, signals, decomposition
def test_mdla_reconstruction():
n_samples, n_features, n_dims = 10, 5, 3
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels)
assert_array_almost_equal(reconstruct_from_code(decomposition,
dico, n_features),
signals)
def test_multivariate_OMP():
n_samples = 10
n_features = 100
n_dims = 90
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
verbose = False
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels,
n_samples, n_features,
n_dims)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1)
if verbose == True:
for i in range(n_samples):
# original signal decomposition, sorted by amplitude
sorted_decomposition = np.zeros_like(decomposition[i]).view('float, int, int')
for j in range(decomposition[i].shape[0]):
sorted_decomposition[j] = tuple(decomposition[i][j,:].tolist())
sorted_decomposition.sort(order=['f0'], axis=0)
for j in reversed(sorted_decomposition): print (j)
# decomposition found by OMP, also sorted
sorted_d = np.zeros_like(d[i]).view('float, int, int')
for j in range(d[i].shape[0]):
sorted_d[j] = tuple(d[i][j,:].tolist())
sorted_d.sort(order=['f0'], axis=0)
for j in reversed(sorted_d): print (j)
assert_array_almost_equal(reconstruct_from_code(d, dico, n_features),
signals, decimal=3)
def _test_with_pydico():
import pickle, shutil
n_samples, n_features, n_dims = 10, 5, 3
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs, n_kernels)
o = {'signals':signals, 'dico':dico, 'decomposition':decomposition}
with open('skmdla.pck', 'w') as f:
pickle.dump(o, f)
f.close()
shutil.copy('skmdla.pck', '../RC/skmdla.pck')
print (signals)
print (dico)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1, verbose=4)
def _test_with_pydico_reload():
import pickle
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
with open('skmdla.pck', 'w') as f:
o = pickle.load(f)
f.close()
dico = o['dico']
signals = o['signals']
decomposition = o['decomposition']
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1, verbose=4)
def _verif_OMP():
n_samples = 1000
n_nonzero_coefs = 3
for n_features in range (5, 50, 5):
kernel_init_len = n_features - n_features/2
n_dims = n_features/2
n_kernels = n_features*5
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels,
n_samples, n_features,
n_dims)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1)
reconstructed = reconstruct_from_code(d, dico, n_features)
residual_energy = 0.
for sig, rec in zip(signals, reconstructed):
residual_energy += ((sig-rec)**2).sum(1).mean()
print ('Mean energy of the', n_samples, 'residuals for', (n_features, n_dims), 'features and', n_kernels, 'kernels of', (kernel_init_len, n_dims),' is', residual_energy/n_samples)