190 lines
6.9 KiB
Python
190 lines
6.9 KiB
Python
import numpy as np
|
|
|
|
from sklearn.utils.testing import assert_array_almost_equal
|
|
from sklearn.utils.testing import assert_array_equal
|
|
from sklearn.utils.testing import assert_equal
|
|
from sklearn.utils.testing import SkipTest
|
|
from sklearn.utils.testing import assert_true
|
|
from sklearn.utils.testing import assert_less
|
|
from sklearn.utils.testing import assert_raises
|
|
|
|
from sklearn.decomposition import DictionaryLearning
|
|
from sklearn.decomposition import MiniBatchDictionaryLearning
|
|
from sklearn.decomposition import SparseCoder
|
|
from sklearn.decomposition import dict_learning_online
|
|
from sklearn.decomposition import sparse_encode
|
|
|
|
|
|
rng_global = np.random.RandomState(0)
|
|
n_samples, n_features = 10, 8
|
|
X = rng_global.randn(n_samples, n_features)
|
|
|
|
|
|
def test_dict_learning_shapes():
|
|
n_components = 5
|
|
dico = DictionaryLearning(n_components, random_state=0).fit(X)
|
|
assert_true(dico.components_.shape == (n_components, n_features))
|
|
|
|
|
|
def test_dict_learning_overcomplete():
|
|
n_components = 12
|
|
dico = DictionaryLearning(n_components, random_state=0).fit(X)
|
|
assert_true(dico.components_.shape == (n_components, n_features))
|
|
|
|
|
|
def test_dict_learning_reconstruction():
|
|
n_components = 12
|
|
dico = DictionaryLearning(n_components, transform_algorithm='omp',
|
|
transform_alpha=0.001, random_state=0)
|
|
code = dico.fit(X).transform(X)
|
|
assert_array_almost_equal(np.dot(code, dico.components_), X)
|
|
|
|
dico.set_params(transform_algorithm='lasso_lars')
|
|
code = dico.transform(X)
|
|
assert_array_almost_equal(np.dot(code, dico.components_), X, decimal=2)
|
|
|
|
# used to test lars here too, but there's no guarantee the number of
|
|
# nonzero atoms is right.
|
|
|
|
|
|
def test_dict_learning_nonzero_coefs():
|
|
n_components = 4
|
|
dico = DictionaryLearning(n_components, transform_algorithm='lars',
|
|
transform_n_nonzero_coefs=3, random_state=0)
|
|
code = dico.fit(X).transform(X[1])
|
|
assert_true(len(np.flatnonzero(code)) == 3)
|
|
|
|
dico.set_params(transform_algorithm='omp')
|
|
code = dico.transform(X[1])
|
|
assert_equal(len(np.flatnonzero(code)), 3)
|
|
|
|
|
|
def test_dict_learning_unknown_fit_algorithm():
|
|
n_components = 5
|
|
dico = DictionaryLearning(n_components, fit_algorithm='<unknown>')
|
|
assert_raises(ValueError, dico.fit, X)
|
|
|
|
|
|
def test_dict_learning_split():
|
|
n_components = 5
|
|
dico = DictionaryLearning(n_components, transform_algorithm='threshold',
|
|
random_state=0)
|
|
code = dico.fit(X).transform(X)
|
|
dico.split_sign = True
|
|
split_code = dico.transform(X)
|
|
|
|
assert_array_equal(split_code[:, :n_components] -
|
|
split_code[:, n_components:], code)
|
|
|
|
|
|
def test_dict_learning_online_shapes():
|
|
rng = np.random.RandomState(0)
|
|
n_components = 8
|
|
code, dictionary = dict_learning_online(X, n_components=n_components,
|
|
alpha=1, random_state=rng)
|
|
assert_equal(code.shape, (n_samples, n_components))
|
|
assert_equal(dictionary.shape, (n_components, n_features))
|
|
assert_equal(np.dot(code, dictionary).shape, X.shape)
|
|
|
|
|
|
def test_dict_learning_online_verbosity():
|
|
n_components = 5
|
|
# test verbosity
|
|
from sklearn.externals.six.moves import cStringIO as StringIO
|
|
import sys
|
|
old_stdout = sys.stdout
|
|
sys.stdout = StringIO()
|
|
dico = MiniBatchDictionaryLearning(n_components, n_iter=20, verbose=1,
|
|
random_state=0)
|
|
dico.fit(X)
|
|
dico = MiniBatchDictionaryLearning(n_components, n_iter=20, verbose=2,
|
|
random_state=0)
|
|
dico.fit(X)
|
|
dict_learning_online(X, n_components=n_components, alpha=1, verbose=1,
|
|
random_state=0)
|
|
dict_learning_online(X, n_components=n_components, alpha=1, verbose=2,
|
|
random_state=0)
|
|
sys.stdout = old_stdout
|
|
assert_true(dico.components_.shape == (n_components, n_features))
|
|
|
|
|
|
def test_dict_learning_online_estimator_shapes():
|
|
n_components = 5
|
|
dico = MiniBatchDictionaryLearning(n_components, n_iter=20, random_state=0)
|
|
dico.fit(X)
|
|
assert_true(dico.components_.shape == (n_components, n_features))
|
|
|
|
|
|
def test_dict_learning_online_overcomplete():
|
|
n_components = 12
|
|
dico = MiniBatchDictionaryLearning(n_components, n_iter=20,
|
|
random_state=0).fit(X)
|
|
assert_true(dico.components_.shape == (n_components, n_features))
|
|
|
|
|
|
def test_dict_learning_online_initialization():
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features)
|
|
dico = MiniBatchDictionaryLearning(n_components, n_iter=0,
|
|
dict_init=V, random_state=0).fit(X)
|
|
assert_array_equal(dico.components_, V)
|
|
|
|
|
|
def test_dict_learning_online_partial_fit():
|
|
# this test was not actually passing before!
|
|
raise SkipTest
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features) # random init
|
|
V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
|
|
dico1 = MiniBatchDictionaryLearning(n_components, n_iter=10, batch_size=1,
|
|
shuffle=False, dict_init=V,
|
|
random_state=0).fit(X)
|
|
dico2 = MiniBatchDictionaryLearning(n_components, n_iter=1, dict_init=V,
|
|
random_state=0)
|
|
for ii, sample in enumerate(X):
|
|
dico2.partial_fit(sample, iter_offset=ii * dico2.n_iter)
|
|
# if ii == 1: break
|
|
assert_true(not np.all(sparse_encode(X, dico1.components_, alpha=100) ==
|
|
0))
|
|
assert_array_equal(dico1.components_, dico2.components_)
|
|
|
|
|
|
def test_sparse_encode_shapes():
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features) # random init
|
|
V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
|
|
for algo in ('lasso_lars', 'lasso_cd', 'lars', 'omp', 'threshold'):
|
|
code = sparse_encode(X, V, algorithm=algo)
|
|
assert_equal(code.shape, (n_samples, n_components))
|
|
|
|
|
|
def test_sparse_encode_error():
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features) # random init
|
|
V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
|
|
code = sparse_encode(X, V, alpha=0.001)
|
|
assert_true(not np.all(code == 0))
|
|
assert_less(np.sqrt(np.sum((np.dot(code, V) - X) ** 2)), 0.1)
|
|
|
|
|
|
def test_unknown_method():
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features) # random init
|
|
assert_raises(ValueError, sparse_encode, X, V, algorithm="<unknown>")
|
|
|
|
|
|
def test_sparse_coder_estimator():
|
|
n_components = 12
|
|
rng = np.random.RandomState(0)
|
|
V = rng.randn(n_components, n_features) # random init
|
|
V /= np.sum(V ** 2, axis=1)[:, np.newaxis]
|
|
code = SparseCoder(dictionary=V, transform_algorithm='lasso_lars',
|
|
transform_alpha=0.001).transform(X)
|
|
assert_true(not np.all(code == 0))
|
|
assert_less(np.sqrt(np.sum((np.dot(code, V) - X) ** 2)), 0.1)
|