def test_incremental_pca_num_features_change():
# Test that changing n_components will raise an error.
rng = np.random.RandomState(1999)
n_samples = 100
X = rng.randn(n_samples, 20)
X2 = rng.randn(n_samples, 50)
X = da.from_array(X, chunks=[4, -1])
X2 = da.from_array(X2, chunks=[4, -1])
ipca = IncrementalPCA(n_components=None)
ipca.fit(X)
with pytest.raises(ValueError):
ipca.partial_fit(X2)
def test_n_components_none():
# Ensures that n_components == None is handled correctly
rng = np.random.RandomState(1999)
for n_samples, n_features in [(50, 10), (10, 50)]:
X = rng.rand(n_samples, n_features)
X = da.from_array(X, chunks=[4, -1])
ipca = IncrementalPCA(n_components=None)
# First partial_fit call, ipca.n_components_ is inferred from
# min(X.shape)
ipca.partial_fit(X)
assert ipca.n_components_ == min(X.shape)
# Second partial_fit call, ipca.n_components_ is inferred from
# ipca.components_ computed from the first partial_fit call
ipca.partial_fit(X)
assert ipca.n_components_ == ipca.components_.shape[0]
def test_incremental_pca_partial_fit():
# Test that fit and partial_fit get equivalent results.
rng = np.random.RandomState(1999)
n, p = 50, 3
X = rng.randn(n, p) # spherical data
X[:, 1] *= 0.00001 # make middle component relatively small
X += [5, 4, 3] # make a large mean
X = da.from_array(X, chunks=[4, -1])
# same check that we can find the original data from the transformed
# signal (since the data is almost of rank n_components)
batch_size = 10
ipca = IncrementalPCA(n_components=2, batch_size=batch_size).fit(X)
pipca = IncrementalPCA(n_components=2, batch_size=batch_size)
# Add one to make sure endpoint is included
batch_itr = np.arange(0, n + 1, batch_size)
for i, j in zip(batch_itr[:-1], batch_itr[1:]):
pipca.partial_fit(X[i:j, :])
assert_almost_equal(ipca.components_, pipca.components_, decimal=3)
def test_incremental_pca_partial_fit_float_division():
# Test to ensure float division is used in all versions of Python
# (non-regression test for issue #9489)
rng = np.random.RandomState(0)
A = rng.randn(5, 3) + 2
B = rng.randn(7, 3) + 5
A = da.from_array(A, chunks=[3, -1])
B = da.from_array(B, chunks=[3, -1])
pca = IncrementalPCA(n_components=2)
pca.partial_fit(A)
# Set n_samples_seen_ to be a floating point number instead of an int
pca.n_samples_seen_ = float(pca.n_samples_seen_)
pca.partial_fit(B)
singular_vals_float_samples_seen = pca.singular_values_
pca2 = IncrementalPCA(n_components=2)
pca2.partial_fit(A)
pca2.partial_fit(B)
singular_vals_int_samples_seen = pca2.singular_values_
np.testing.assert_allclose(
singular_vals_float_samples_seen, singular_vals_int_samples_seen
)
def test_incremental_pca_set_params():
# Test that components_ sign is stable over batch sizes.
rng = np.random.RandomState(1999)
n_samples = 100
n_features = 20
X = rng.randn(n_samples, n_features)
X2 = rng.randn(n_samples, n_features)
X3 = rng.randn(n_samples, n_features)
X = da.from_array(X, chunks=[4, -1])
X2 = da.from_array(X2, chunks=[4, -1])
X3 = da.from_array(X3, chunks=[4, -1])
ipca = IncrementalPCA(n_components=20)
ipca.fit(X)
# Decreasing number of components
ipca.set_params(n_components=10)
with pytest.raises(ValueError):
ipca.partial_fit(X2)
# Increasing number of components
ipca.set_params(n_components=15)
with pytest.raises(ValueError):
ipca.partial_fit(X3)
# Returning to original setting
ipca.set_params(n_components=20)
ipca.partial_fit(X)