247 lines
8.7 KiB
Python
247 lines
8.7 KiB
Python
|
"""Truncated SVD for sparse matrices, aka latent semantic analysis (LSA).
|
||
|
|
"""
|
||
|
|
|
||
|
|
# Author: Lars Buitinck
|
||
|
|
# Olivier Grisel <olivier.grisel@ensta.org>
|
||
|
|
# Michael Becker <mike@beckerfuffle.com>
|
||
|
|
# License: 3-clause BSD.
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
import scipy.sparse as sp
|
||
|
|
from scipy.sparse.linalg import svds
|
||
|
|
|
||
|
|
from ..base import BaseEstimator, TransformerMixin
|
||
|
|
from ..utils import check_array, check_random_state
|
||
|
|
from ..utils._arpack import _init_arpack_v0
|
||
|
|
from ..utils.extmath import randomized_svd, safe_sparse_dot, svd_flip
|
||
|
|
from ..utils.sparsefuncs import mean_variance_axis
|
||
|
|
from ..utils.validation import _deprecate_positional_args
|
||
|
|
from ..utils.validation import check_is_fitted
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["TruncatedSVD"]
|
||
|
|
|
||
|
|
|
||
|
|
class TruncatedSVD(TransformerMixin, BaseEstimator):
|
||
|
|
"""Dimensionality reduction using truncated SVD (aka LSA).
|
||
|
|
|
||
|
|
This transformer performs linear dimensionality reduction by means of
|
||
|
|
truncated singular value decomposition (SVD). Contrary to PCA, this
|
||
|
|
estimator does not center the data before computing the singular value
|
||
|
|
decomposition. This means it can work with sparse matrices
|
||
|
|
efficiently.
|
||
|
|
|
||
|
|
In particular, truncated SVD works on term count/tf-idf matrices as
|
||
|
|
returned by the vectorizers in :mod:`sklearn.feature_extraction.text`. In
|
||
|
|
that context, it is known as latent semantic analysis (LSA).
|
||
|
|
|
||
|
|
This estimator supports two algorithms: a fast randomized SVD solver, and
|
||
|
|
a "naive" algorithm that uses ARPACK as an eigensolver on `X * X.T` or
|
||
|
|
`X.T * X`, whichever is more efficient.
|
||
|
|
|
||
|
|
Read more in the :ref:`User Guide <LSA>`.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
n_components : int, default=2
|
||
|
|
Desired dimensionality of output data.
|
||
|
|
Must be strictly less than the number of features.
|
||
|
|
The default value is useful for visualisation. For LSA, a value of
|
||
|
|
100 is recommended.
|
||
|
|
|
||
|
|
algorithm : {'arpack', 'randomized'}, default='randomized'
|
||
|
|
SVD solver to use. Either "arpack" for the ARPACK wrapper in SciPy
|
||
|
|
(scipy.sparse.linalg.svds), or "randomized" for the randomized
|
||
|
|
algorithm due to Halko (2009).
|
||
|
|
|
||
|
|
n_iter : int, default=5
|
||
|
|
Number of iterations for randomized SVD solver. Not used by ARPACK. The
|
||
|
|
default is larger than the default in
|
||
|
|
:func:`~sklearn.utils.extmath.randomized_svd` to handle sparse
|
||
|
|
matrices that may have large slowly decaying spectrum.
|
||
|
|
|
||
|
|
random_state : int, RandomState instance or None, default=None
|
||
|
|
Used during randomized svd. Pass an int for reproducible results across
|
||
|
|
multiple function calls.
|
||
|
|
See :term:`Glossary <random_state>`.
|
||
|
|
|
||
|
|
tol : float, default=0.
|
||
|
|
Tolerance for ARPACK. 0 means machine precision. Ignored by randomized
|
||
|
|
SVD solver.
|
||
|
|
|
||
|
|
Attributes
|
||
|
|
----------
|
||
|
|
components_ : ndarray of shape (n_components, n_features)
|
||
|
|
|
||
|
|
explained_variance_ : ndarray of shape (n_components,)
|
||
|
|
The variance of the training samples transformed by a projection to
|
||
|
|
each component.
|
||
|
|
|
||
|
|
explained_variance_ratio_ : ndarray of shape (n_components,)
|
||
|
|
Percentage of variance explained by each of the selected components.
|
||
|
|
|
||
|
|
singular_values_ : ndarray od shape (n_components,)
|
||
|
|
The singular values corresponding to each of the selected components.
|
||
|
|
The singular values are equal to the 2-norms of the ``n_components``
|
||
|
|
variables in the lower-dimensional space.
|
||
|
|
|
||
|
|
Examples
|
||
|
|
--------
|
||
|
|
>>> from sklearn.decomposition import TruncatedSVD
|
||
|
|
>>> from scipy.sparse import random as sparse_random
|
||
|
|
>>> X = sparse_random(100, 100, density=0.01, format='csr',
|
||
|
|
... random_state=42)
|
||
|
|
>>> svd = TruncatedSVD(n_components=5, n_iter=7, random_state=42)
|
||
|
|
>>> svd.fit(X)
|
||
|
|
TruncatedSVD(n_components=5, n_iter=7, random_state=42)
|
||
|
|
>>> print(svd.explained_variance_ratio_)
|
||
|
|
[0.0646... 0.0633... 0.0639... 0.0535... 0.0406...]
|
||
|
|
>>> print(svd.explained_variance_ratio_.sum())
|
||
|
|
0.286...
|
||
|
|
>>> print(svd.singular_values_)
|
||
|
|
[1.553... 1.512... 1.510... 1.370... 1.199...]
|
||
|
|
|
||
|
|
See Also
|
||
|
|
--------
|
||
|
|
PCA
|
||
|
|
|
||
|
|
References
|
||
|
|
----------
|
||
|
|
Finding structure with randomness: Stochastic algorithms for constructing
|
||
|
|
approximate matrix decompositions
|
||
|
|
Halko, et al., 2009 (arXiv:909) https://arxiv.org/pdf/0909.4061.pdf
|
||
|
|
|
||
|
|
Notes
|
||
|
|
-----
|
||
|
|
SVD suffers from a problem called "sign indeterminacy", which means the
|
||
|
|
sign of the ``components_`` and the output from transform depend on the
|
||
|
|
algorithm and random state. To work around this, fit instances of this
|
||
|
|
class to data once, then keep the instance around to do transformations.
|
||
|
|
|
||
|
|
"""
|
||
|
|
@_deprecate_positional_args
|
||
|
|
def __init__(self, n_components=2, *, algorithm="randomized", n_iter=5,
|
||
|
|
random_state=None, tol=0.):
|
||
|
|
self.algorithm = algorithm
|
||
|
|
self.n_components = n_components
|
||
|
|
self.n_iter = n_iter
|
||
|
|
self.random_state = random_state
|
||
|
|
self.tol = tol
|
||
|
|
|
||
|
|
def fit(self, X, y=None):
|
||
|
|
"""Fit model on training data X.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
X : {array-like, sparse matrix} of shape (n_samples, n_features)
|
||
|
|
Training data.
|
||
|
|
|
||
|
|
y : Ignored
|
||
|
|
|
||
|
|
Returns
|
||
|
|
-------
|
||
|
|
self : object
|
||
|
|
Returns the transformer object.
|
||
|
|
"""
|
||
|
|
self.fit_transform(X)
|
||
|
|
return self
|
||
|
|
|
||
|
|
def fit_transform(self, X, y=None):
|
||
|
|
"""Fit model to X and perform dimensionality reduction on X.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
X : {array-like, sparse matrix} of shape (n_samples, n_features)
|
||
|
|
Training data.
|
||
|
|
|
||
|
|
y : Ignored
|
||
|
|
|
||
|
|
Returns
|
||
|
|
-------
|
||
|
|
X_new : ndarray of shape (n_samples, n_components)
|
||
|
|
Reduced version of X. This will always be a dense array.
|
||
|
|
"""
|
||
|
|
X = self._validate_data(X, accept_sparse=['csr', 'csc'],
|
||
|
|
ensure_min_features=2)
|
||
|
|
random_state = check_random_state(self.random_state)
|
||
|
|
|
||
|
|
if self.algorithm == "arpack":
|
||
|
|
v0 = _init_arpack_v0(min(X.shape), random_state)
|
||
|
|
U, Sigma, VT = svds(X, k=self.n_components, tol=self.tol, v0=v0)
|
||
|
|
# svds doesn't abide by scipy.linalg.svd/randomized_svd
|
||
|
|
# conventions, so reverse its outputs.
|
||
|
|
Sigma = Sigma[::-1]
|
||
|
|
U, VT = svd_flip(U[:, ::-1], VT[::-1])
|
||
|
|
|
||
|
|
elif self.algorithm == "randomized":
|
||
|
|
k = self.n_components
|
||
|
|
n_features = X.shape[1]
|
||
|
|
if k >= n_features:
|
||
|
|
raise ValueError("n_components must be < n_features;"
|
||
|
|
" got %d >= %d" % (k, n_features))
|
||
|
|
U, Sigma, VT = randomized_svd(X, self.n_components,
|
||
|
|
n_iter=self.n_iter,
|
||
|
|
random_state=random_state)
|
||
|
|
else:
|
||
|
|
raise ValueError("unknown algorithm %r" % self.algorithm)
|
||
|
|
|
||
|
|
self.components_ = VT
|
||
|
|
|
||
|
|
# As a result of the SVD approximation error on X ~ U @ Sigma @ V.T,
|
||
|
|
# X @ V is not the same as U @ Sigma
|
||
|
|
if self.algorithm == "randomized" or \
|
||
|
|
(self.algorithm == "arpack" and self.tol > 0):
|
||
|
|
X_transformed = safe_sparse_dot(X, self.components_.T)
|
||
|
|
else:
|
||
|
|
X_transformed = U * Sigma
|
||
|
|
|
||
|
|
# Calculate explained variance & explained variance ratio
|
||
|
|
self.explained_variance_ = exp_var = np.var(X_transformed, axis=0)
|
||
|
|
if sp.issparse(X):
|
||
|
|
_, full_var = mean_variance_axis(X, axis=0)
|
||
|
|
full_var = full_var.sum()
|
||
|
|
else:
|
||
|
|
full_var = np.var(X, axis=0).sum()
|
||
|
|
self.explained_variance_ratio_ = exp_var / full_var
|
||
|
|
self.singular_values_ = Sigma # Store the singular values.
|
||
|
|
|
||
|
|
return X_transformed
|
||
|
|
|
||
|
|
def transform(self, X):
|
||
|
|
"""Perform dimensionality reduction on X.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
X : {array-like, sparse matrix} of shape (n_samples, n_features)
|
||
|
|
New data.
|
||
|
|
|
||
|
|
Returns
|
||
|
|
-------
|
||
|
|
X_new : ndarray of shape (n_samples, n_components)
|
||
|
|
Reduced version of X. This will always be a dense array.
|
||
|
|
"""
|
||
|
|
check_is_fitted(self)
|
||
|
|
X = self._validate_data(X, accept_sparse=['csr', 'csc'], reset=False)
|
||
|
|
return safe_sparse_dot(X, self.components_.T)
|
||
|
|
|
||
|
|
def inverse_transform(self, X):
|
||
|
|
"""Transform X back to its original space.
|
||
|
|
|
||
|
|
Returns an array X_original whose transform would be X.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
X : array-like of shape (n_samples, n_components)
|
||
|
|
New data.
|
||
|
|
|
||
|
|
Returns
|
||
|
|
-------
|
||
|
|
X_original : ndarray of shape (n_samples, n_features)
|
||
|
|
Note that this is always a dense array.
|
||
|
|
"""
|
||
|
|
X = check_array(X)
|
||
|
|
return np.dot(X, self.components_)
|
||
|
|
|
||
|
|
def _more_tags(self):
|
||
|
|
return {'preserves_dtype': [np.float64, np.float32]}
|