def test_var_with_ddof(self):
x = np.random.uniform(0, 10, (20, 100))
for axis in [None, 0, 1]:
np.testing.assert_almost_equal(
np.var(x, axis=axis, ddof=10),
var(csr_matrix(x), axis=axis, ddof=10),
)
def test_var_with_ddof(self):
x = np.random.uniform(0, 10, (20, 100))
for axis in [None, 0, 1]:
np.testing.assert_almost_equal(
np.var(x, axis=axis, ddof=10),
var(csr_matrix(x), axis=axis, ddof=10),
)
def test_var(self):
for data in self.data:
for axis in chain((None,), range(len(data.shape))):
# Can't use array_equal here due to differences on 1e-16 level
np.testing.assert_array_almost_equal(
var(csr_matrix(data), axis=axis),
np.var(data, axis=axis)
)
def test_var(self):
for data in self.data:
for axis in chain((None,), range(len(data.shape))):
# Can't use array_equal here due to differences on 1e-16 level
np.testing.assert_array_almost_equal(
var(csr_matrix(data), axis=axis),
np.var(data, axis=axis)
)
def _fit_truncated(self, X, n_components, svd_solver):
"""Fit the model by computing truncated SVD (by ARPACK or randomized) on X"""
n_samples, n_features = X.shape
if isinstance(n_components, six.string_types):
raise ValueError(
"n_components=%r cannot be a string with svd_solver='%s'" %
(n_components, svd_solver)
)
elif not 1 <= n_components <= min(n_samples, n_features):
raise ValueError(
"n_components=%r must be between 1 and min(n_samples, "
"n_features)=%r with svd_solver='%s'" % (
n_components, min(n_samples, n_features), svd_solver
)
)
elif not isinstance(n_components, (numbers.Integral, np.integer)):
raise ValueError(
"n_components=%r must be of type int when greater than or "
"equal to 1, was of type=%r" % (n_components, type(n_components))
)
elif svd_solver == "arpack" and n_components == min(n_samples, n_features):
raise ValueError(
"n_components=%r must be strictly less than min(n_samples, "
"n_features)=%r with svd_solver='%s'" % (
n_components, min(n_samples, n_features), svd_solver
)
)
random_state = check_random_state(self.random_state)
self.mean_ = X.mean(axis=0)
total_var = ut.var(X, axis=0, ddof=1)
if svd_solver == "arpack":
# Center data
X -= self.mean_
# random init solution, as ARPACK does it internally
v0 = random_state.uniform(-1, 1, size=min(X.shape))
U, S, V = sp.linalg.svds(X, k=n_components, tol=self.tol, v0=v0)
# svds doesn't abide by scipy.linalg.svd/randomized_svd
# conventions, so reverse its outputs.
S = S[::-1]
# flip eigenvectors' sign to enforce deterministic output
U, V = svd_flip(U[:, ::-1], V[::-1])
elif svd_solver == "randomized":
# sign flipping is done inside
U, S, V = randomized_pca(
X,
n_components=n_components,
n_iter=self.iterated_power,
flip_sign=True,
random_state=random_state,
)
self.n_samples_, self.n_features_ = n_samples, n_features
self.components_ = V
self.n_components_ = n_components
# Get variance explained by singular values
self.explained_variance_ = (S ** 2) / (n_samples - 1)
self.explained_variance_ratio_ = self.explained_variance_ / total_var.sum()
self.singular_values_ = S.copy() # Store the singular values.
if self.n_components_ < min(n_features, n_samples):
self.noise_variance_ = (total_var.sum() - self.explained_variance_.sum())
self.noise_variance_ /= min(n_features, n_samples) - n_components
else:
self.noise_variance_ = 0
return U, S, V
