def test_transform_nan():
# Test that SparsePCA won't return NaN when there is 0 feature in all
# samples.
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng) # wide array
Y[:, 0] = 0
estimator = SparsePCA(n_components=8)
assert not np.any(np.isnan(estimator.fit_transform(Y)))
def test_scaling_fit_transform():
alpha = 1
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=rng)
results_train = spca_lars.fit_transform(Y)
results_test = spca_lars.transform(Y[:10])
assert_allclose(results_train[0], results_test[0])
def test_initialization():
rng = np.random.RandomState(0)
U_init = rng.randn(5, 3)
V_init = rng.randn(3, 4)
model = SparsePCA(n_components=3, U_init=U_init, V_init=V_init, max_iter=0,
random_state=rng)
model.fit(rng.randn(5, 4))
assert_allclose(model.components_,
V_init / np.linalg.norm(V_init, axis=1)[:, None])
def test_pca_vs_spca():
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
Z, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)
spca = SparsePCA(alpha=0, ridge_alpha=0, n_components=2)
pca = PCA(n_components=2)
pca.fit(Y)
spca.fit(Y)
results_test_pca = pca.transform(Z)
results_test_spca = spca.transform(Z)
assert_allclose(np.abs(spca.components_.dot(pca.components_.T)),
np.eye(2), atol=1e-5)
results_test_pca *= np.sign(results_test_pca[0, :])
results_test_spca *= np.sign(results_test_spca[0, :])
assert_allclose(results_test_pca, results_test_spca)
def test_fit_transform():
alpha = 1
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng) # wide array
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=0)
spca_lars.fit(Y)
# Test that CD gives similar results
spca_lasso = SparsePCA(n_components=3, method='cd', random_state=0,
alpha=alpha)
spca_lasso.fit(Y)
assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)
def test_fit_transform_parallel():
alpha = 1
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng) # wide array
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=0)
spca_lars.fit(Y)
U1 = spca_lars.transform(Y)
# Test multiple CPUs
spca = SparsePCA(n_components=3, n_jobs=2, method='lars', alpha=alpha,
random_state=0).fit(Y)
U2 = spca.transform(Y)
assert not np.all(spca_lars.components_ == 0)
assert_array_almost_equal(U1, U2)
def test_fit_transform_tall():
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 65, (8, 8), random_state=rng) # tall array
spca_lars = SparsePCA(n_components=3, method='lars', random_state=rng)
U1 = spca_lars.fit_transform(Y)
spca_lasso = SparsePCA(n_components=3, method='cd', random_state=rng)
U2 = spca_lasso.fit(Y).transform(Y)
assert_array_almost_equal(U1, U2)
def test_correct_shapes():
rng = np.random.RandomState(0)
X = rng.randn(12, 10)
spca = SparsePCA(n_components=8, random_state=rng)
U = spca.fit_transform(X)
assert spca.components_.shape == (8, 10)
assert U.shape == (12, 8)
# test overcomplete decomposition
spca = SparsePCA(n_components=13, random_state=rng)
U = spca.fit_transform(X)
assert spca.components_.shape == (13, 10)
assert U.shape == (12, 13)