def _fit_full_daal4py(self, X, n_components):
n_samples, n_features = X.shape
# due to need to flip components, need to do full decomposition
self._fit_daal4py(X, min(n_samples, n_features))
U = self._transform_daal4py(X, whiten=True, check_X=False, scale_eigenvalues=True)
V = self.components_
U, V = svd_flip(U, V)
U = U.copy()
V = V.copy()
S = self.singular_values_.copy()
if n_components == 'mle':
n_components = \
_infer_dimension_(self.explained_variance_, n_samples, n_features)
elif 0 < n_components < 1.0:
n_components = _n_components_from_fraction(
self.explained_variance_ratio_, n_components)
# Compute noise covariance using Probabilistic PCA model
# The sigma2 maximum likelihood (cf. eq. 12.46)
if n_components < min(n_features, n_samples):
self.noise_variance_ = self.explained_variance_[n_components:].mean()
else:
self.noise_variance_ = 0.
self.n_samples_, self.n_features_ = n_samples, n_features
self.components_ = self.components_[:n_components]
self.n_components_ = n_components
self.explained_variance_ = self.explained_variance_[:n_components]
self.explained_variance_ratio_ = \
self.explained_variance_ratio_[:n_components]
self.singular_values_ = self.singular_values_[:n_components]
return U, S, V
def _fit_full(self, X, n_components):
"""Fit the model by computing full SVD on X"""
n_samples, n_features = X.shape
_validate_n_components(n_components, n_samples, n_features)
# Center data
self.mean_ = np.mean(X, axis=0)
X -= self.mean_
if X.shape[0] > X.shape[1] and (X.dtype == np.float64
or X.dtype == np.float32):
U, S, V = _daal4py_svd(X)
else:
U, S, V = np.linalg.svd(X, full_matrices=False)
# flip eigenvectors' sign to enforce deterministic output
U, V = svd_flip(U, V)
components_ = V
# Get variance explained by singular values
explained_variance_ = (S**2) / (n_samples - 1)
total_var = explained_variance_.sum()
explained_variance_ratio_ = explained_variance_ / total_var
# Postprocess the number of components required
if n_components == 'mle':
n_components = \
_infer_dimension_(explained_variance_, n_samples, n_features)
elif 0 < n_components < 1.0:
# number of components for which the cumulated explained
# variance percentage is superior to the desired threshold
ratio_cumsum = explained_variance_ratio_.cumsum()
n_components = np.searchsorted(ratio_cumsum, n_components) + 1
# Compute noise covariance using Probabilistic PCA model
# The sigma2 maximum likelihood (cf. eq. 12.46)
if n_components < min(n_features, n_samples):
self.noise_variance_ = explained_variance_[n_components:].mean()
else:
self.noise_variance_ = 0.
self.n_samples_, self.n_features_ = n_samples, n_features
self.components_ = components_[:n_components]
self.n_components_ = n_components
self.explained_variance_ = explained_variance_[:n_components]
self.explained_variance_ratio_ = \
explained_variance_ratio_[:n_components]
self.singular_values_ = S[:n_components]
return U, S, V
def _fit_full_vanilla(self, X, n_components):
"""Fit the model by computing full SVD on X"""
n_samples, n_features = X.shape
# Center data
self.mean_ = np.mean(X, axis=0)
X -= self.mean_
U, S, V = np.linalg.svd(X, full_matrices=False)
# flip eigenvectors' sign to enforce deterministic output
U, V = svd_flip(U, V)
components_ = V
# Get variance explained by singular values
explained_variance_ = (S**2) / (n_samples - 1)
total_var = explained_variance_.sum()
explained_variance_ratio_ = explained_variance_ / total_var
# Postprocess the number of components required
if n_components == 'mle':
n_components = \
_infer_dimension(explained_variance_, n_samples)
elif 0 < n_components < 1.0:
n_components = _n_components_from_fraction(
explained_variance_ratio_, n_components)
# Compute noise covariance using Probabilistic PCA model
# The sigma2 maximum likelihood (cf. eq. 12.46)
if n_components < min(n_features, n_samples):
self.noise_variance_ = explained_variance_[n_components:].mean()
else:
self.noise_variance_ = 0.
self.n_samples_, self.n_features_ = n_samples, n_features
self.components_ = components_[:n_components]
self.n_components_ = n_components
self.explained_variance_ = explained_variance_[:n_components]
self.explained_variance_ratio_ = \
explained_variance_ratio_[:n_components]
self.singular_values_ = S[:n_components]
return U, S, V
def _fit_full_daal4py(self, X, n_components):
n_samples, n_features = X.shape
# due to need to flip components, need to do full decomposition
self._fit_daal4py(X, min(n_samples, n_features))
U = self._transform_daal4py(X,
whiten=True,
check_X=False,
scale_eigenvalues=True)
V = self.components_
U, V = svd_flip(U, V)
U = U.copy()
V = V.copy()
S = self.singular_values_.copy()
if n_components == 'mle':
n_components = \
_infer_dimension_(self.explained_variance_, n_samples, n_features)
elif 0 < n_components < 1.0:
# number of components for which the cumulated explained
# variance percentage is superior to the desired threshold
ratio_cumsum = stable_cumsum(self.explained_variance_ratio_)
n_components = np.searchsorted(ratio_cumsum, n_components) + 1
# Compute noise covariance using Probabilistic PCA model
# The sigma2 maximum likelihood (cf. eq. 12.46)
if n_components < min(n_features, n_samples):
self.noise_variance_ = self.explained_variance_[
n_components:].mean()
else:
self.noise_variance_ = 0.
self.n_samples_, self.n_features_ = n_samples, n_features
self.components_ = self.components_[:n_components]
self.n_components_ = n_components
self.explained_variance_ = self.explained_variance_[:n_components]
self.explained_variance_ratio_ = \
self.explained_variance_ratio_[:n_components]
self.singular_values_ = self.singular_values_[:n_components]
return U, S, V
