428 lines
14 KiB
Python
428 lines
14 KiB
Python
"""
|
|
Generalized Linear models.
|
|
"""
|
|
|
|
# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
|
|
# Fabian Pedregosa <fabian.pedregosa@inria.fr>
|
|
# Olivier Grisel <olivier.grisel@ensta.org>
|
|
# Vincent Michel <vincent.michel@inria.fr>
|
|
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
|
|
# Mathieu Blondel <mathieu@mblondel.org>
|
|
# Lars Buitinck <L.J.Buitinck@uva.nl>
|
|
#
|
|
# License: BSD 3 clause
|
|
|
|
from __future__ import division
|
|
from abc import ABCMeta, abstractmethod
|
|
import numbers
|
|
import warnings
|
|
|
|
import numpy as np
|
|
import scipy.sparse as sp
|
|
from scipy import linalg
|
|
from scipy import sparse
|
|
|
|
from ..externals import six
|
|
from ..externals.joblib import Parallel, delayed
|
|
from ..base import BaseEstimator, ClassifierMixin, RegressorMixin
|
|
from ..utils import as_float_array, check_array
|
|
from ..utils.extmath import safe_sparse_dot
|
|
from ..utils.sparsefuncs import mean_variance_axis, inplace_column_scale
|
|
from ..utils.fixes import sparse_lsqr
|
|
|
|
|
|
###
|
|
### TODO: intercept for all models
|
|
### We should define a common function to center data instead of
|
|
### repeating the same code inside each fit method.
|
|
|
|
### TODO: bayesian_ridge_regression and bayesian_regression_ard
|
|
### should be squashed into its respective objects.
|
|
|
|
|
|
def sparse_center_data(X, y, fit_intercept, normalize=False):
|
|
"""
|
|
Compute information needed to center data to have mean zero along
|
|
axis 0. Be aware that X will not be centered since it would break
|
|
the sparsity, but will be normalized if asked so.
|
|
"""
|
|
if fit_intercept:
|
|
# we might require not to change the csr matrix sometimes
|
|
# store a copy if normalize is True.
|
|
# Change dtype to float64 since mean_variance_axis accepts
|
|
# it that way.
|
|
if sp.isspmatrix(X) and X.getformat() == 'csr':
|
|
X = sp.csr_matrix(X, copy=normalize, dtype=np.float64)
|
|
else:
|
|
X = sp.csc_matrix(X, copy=normalize, dtype=np.float64)
|
|
|
|
X_mean, X_var = mean_variance_axis(X, axis=0)
|
|
if normalize:
|
|
# transform variance to std in-place
|
|
# XXX: currently scaled to variance=n_samples to match center_data
|
|
X_var *= X.shape[0]
|
|
X_std = np.sqrt(X_var, X_var)
|
|
del X_var
|
|
X_std[X_std == 0] = 1
|
|
inplace_column_scale(X, 1. / X_std)
|
|
else:
|
|
X_std = np.ones(X.shape[1])
|
|
y_mean = y.mean(axis=0)
|
|
y = y - y_mean
|
|
else:
|
|
X_mean = np.zeros(X.shape[1])
|
|
X_std = np.ones(X.shape[1])
|
|
y_mean = 0. if y.ndim == 1 else np.zeros(y.shape[1], dtype=X.dtype)
|
|
|
|
return X, y, X_mean, y_mean, X_std
|
|
|
|
|
|
def center_data(X, y, fit_intercept, normalize=False, copy=True,
|
|
sample_weight=None):
|
|
"""
|
|
Centers data to have mean zero along axis 0. This is here because
|
|
nearly all linear models will want their data to be centered.
|
|
|
|
If sample_weight is not None, then the weighted mean of X and y
|
|
is zero, and not the mean itself
|
|
"""
|
|
X = as_float_array(X, copy)
|
|
if fit_intercept:
|
|
if isinstance(sample_weight, numbers.Number):
|
|
sample_weight = None
|
|
if sp.issparse(X):
|
|
X_mean = np.zeros(X.shape[1])
|
|
X_std = np.ones(X.shape[1])
|
|
else:
|
|
X_mean = np.average(X, axis=0, weights=sample_weight)
|
|
X -= X_mean
|
|
if normalize:
|
|
# XXX: currently scaled to variance=n_samples
|
|
X_std = np.sqrt(np.sum(X ** 2, axis=0))
|
|
X_std[X_std == 0] = 1
|
|
X /= X_std
|
|
else:
|
|
X_std = np.ones(X.shape[1])
|
|
y_mean = np.average(y, axis=0, weights=sample_weight)
|
|
y = y - y_mean
|
|
else:
|
|
X_mean = np.zeros(X.shape[1])
|
|
X_std = np.ones(X.shape[1])
|
|
y_mean = 0. if y.ndim == 1 else np.zeros(y.shape[1], dtype=X.dtype)
|
|
return X, y, X_mean, y_mean, X_std
|
|
|
|
|
|
class LinearModel(six.with_metaclass(ABCMeta, BaseEstimator)):
|
|
"""Base class for Linear Models"""
|
|
|
|
@abstractmethod
|
|
def fit(self, X, y):
|
|
"""Fit model."""
|
|
|
|
def decision_function(self, X):
|
|
"""Decision function of the linear model.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix}, shape = (n_samples, n_features)
|
|
Samples.
|
|
|
|
Returns
|
|
-------
|
|
C : array, shape = (n_samples,)
|
|
Returns predicted values.
|
|
"""
|
|
X = check_array(X, accept_sparse=['csr', 'csc', 'coo'])
|
|
return safe_sparse_dot(X, self.coef_.T,
|
|
dense_output=True) + self.intercept_
|
|
|
|
def predict(self, X):
|
|
"""Predict using the linear model
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix}, shape = (n_samples, n_features)
|
|
Samples.
|
|
|
|
Returns
|
|
-------
|
|
C : array, shape = (n_samples,)
|
|
Returns predicted values.
|
|
"""
|
|
return self.decision_function(X)
|
|
|
|
_center_data = staticmethod(center_data)
|
|
|
|
def _set_intercept(self, X_mean, y_mean, X_std):
|
|
"""Set the intercept_
|
|
"""
|
|
if self.fit_intercept:
|
|
self.coef_ = self.coef_ / X_std
|
|
self.intercept_ = y_mean - np.dot(X_mean, self.coef_.T)
|
|
else:
|
|
self.intercept_ = 0.
|
|
|
|
|
|
# XXX Should this derive from LinearModel? It should be a mixin, not an ABC.
|
|
# Maybe the n_features checking can be moved to LinearModel.
|
|
class LinearClassifierMixin(ClassifierMixin):
|
|
"""Mixin for linear classifiers.
|
|
|
|
Handles prediction for sparse and dense X.
|
|
"""
|
|
|
|
def decision_function(self, X):
|
|
"""Predict confidence scores for samples.
|
|
|
|
The confidence score for a sample is the signed distance of that
|
|
sample to the hyperplane.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix}, shape = (n_samples, n_features)
|
|
Samples.
|
|
|
|
Returns
|
|
-------
|
|
array, shape=(n_samples,) if n_classes == 2 else (n_samples, n_classes)
|
|
Confidence scores per (sample, class) combination. In the binary
|
|
case, confidence score for self.classes_[1] where >0 means this
|
|
class would be predicted.
|
|
"""
|
|
X = check_array(X, accept_sparse='csr')
|
|
|
|
n_features = self.coef_.shape[1]
|
|
if X.shape[1] != n_features:
|
|
raise ValueError("X has %d features per sample; expecting %d"
|
|
% (X.shape[1], n_features))
|
|
|
|
scores = safe_sparse_dot(X, self.coef_.T,
|
|
dense_output=True) + self.intercept_
|
|
return scores.ravel() if scores.shape[1] == 1 else scores
|
|
|
|
def predict(self, X):
|
|
"""Predict class labels for samples in X.
|
|
|
|
Parameters
|
|
----------
|
|
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
|
|
Samples.
|
|
|
|
Returns
|
|
-------
|
|
C : array, shape = [n_samples]
|
|
Predicted class label per sample.
|
|
"""
|
|
scores = self.decision_function(X)
|
|
if len(scores.shape) == 1:
|
|
indices = (scores > 0).astype(np.int)
|
|
else:
|
|
indices = scores.argmax(axis=1)
|
|
return self.classes_[indices]
|
|
|
|
def _predict_proba_lr(self, X):
|
|
"""Probability estimation for OvR logistic regression.
|
|
|
|
Positive class probabilities are computed as
|
|
1. / (1. + np.exp(-self.decision_function(X)));
|
|
multiclass is handled by normalizing that over all classes.
|
|
"""
|
|
prob = self.decision_function(X)
|
|
prob *= -1
|
|
np.exp(prob, prob)
|
|
prob += 1
|
|
np.reciprocal(prob, prob)
|
|
if len(prob.shape) == 1:
|
|
return np.vstack([1 - prob, prob]).T
|
|
else:
|
|
# OvR normalization, like LibLinear's predict_probability
|
|
prob /= prob.sum(axis=1).reshape((prob.shape[0], -1))
|
|
return prob
|
|
|
|
|
|
class SparseCoefMixin(object):
|
|
"""Mixin for converting coef_ to and from CSR format.
|
|
|
|
L1-regularizing estimators should inherit this.
|
|
"""
|
|
|
|
def densify(self):
|
|
"""Convert coefficient matrix to dense array format.
|
|
|
|
Converts the ``coef_`` member (back) to a numpy.ndarray. This is the
|
|
default format of ``coef_`` and is required for fitting, so calling
|
|
this method is only required on models that have previously been
|
|
sparsified; otherwise, it is a no-op.
|
|
|
|
Returns
|
|
-------
|
|
self: estimator
|
|
"""
|
|
if not hasattr(self, "coef_"):
|
|
raise ValueError("Estimator must be fitted before densifying.")
|
|
if sp.issparse(self.coef_):
|
|
self.coef_ = self.coef_.toarray()
|
|
return self
|
|
|
|
def sparsify(self):
|
|
"""Convert coefficient matrix to sparse format.
|
|
|
|
Converts the ``coef_`` member to a scipy.sparse matrix, which for
|
|
L1-regularized models can be much more memory- and storage-efficient
|
|
than the usual numpy.ndarray representation.
|
|
|
|
The ``intercept_`` member is not converted.
|
|
|
|
Notes
|
|
-----
|
|
For non-sparse models, i.e. when there are not many zeros in ``coef_``,
|
|
this may actually *increase* memory usage, so use this method with
|
|
care. A rule of thumb is that the number of zero elements, which can
|
|
be computed with ``(coef_ == 0).sum()``, must be more than 50% for this
|
|
to provide significant benefits.
|
|
|
|
After calling this method, further fitting with the partial_fit
|
|
method (if any) will not work until you call densify.
|
|
|
|
Returns
|
|
-------
|
|
self: estimator
|
|
"""
|
|
if not hasattr(self, "coef_"):
|
|
raise ValueError("Estimator must be fitted before sparsifying.")
|
|
self.coef_ = sp.csr_matrix(self.coef_)
|
|
return self
|
|
|
|
|
|
class LinearRegression(LinearModel, RegressorMixin):
|
|
"""
|
|
Ordinary least squares Linear Regression.
|
|
|
|
Parameters
|
|
----------
|
|
fit_intercept : boolean, optional
|
|
whether to calculate the intercept for this model. If set
|
|
to false, no intercept will be used in calculations
|
|
(e.g. data is expected to be already centered).
|
|
|
|
normalize : boolean, optional, default False
|
|
If True, the regressors X will be normalized before regression.
|
|
|
|
copy_X : boolean, optional, default True
|
|
If True, X will be copied; else, it may be overwritten.
|
|
|
|
n_jobs : The number of jobs to use for the computation.
|
|
If -1 all CPUs are used. This will only provide speedup for
|
|
n_targets > 1 and sufficient large problems.
|
|
|
|
Attributes
|
|
----------
|
|
coef_ : array, shape (n_features, ) or (n_targets, n_features)
|
|
Estimated coefficients for the linear regression problem.
|
|
If multiple targets are passed during the fit (y 2D), this
|
|
is a 2D array of shape (n_targets, n_features), while if only
|
|
one target is passed, this is a 1D array of length n_features.
|
|
|
|
intercept_ : array
|
|
Independent term in the linear model.
|
|
|
|
Notes
|
|
-----
|
|
From the implementation point of view, this is just plain Ordinary
|
|
Least Squares (scipy.linalg.lstsq) wrapped as a predictor object.
|
|
|
|
"""
|
|
|
|
def __init__(self, fit_intercept=True, normalize=False, copy_X=True,
|
|
n_jobs=1):
|
|
self.fit_intercept = fit_intercept
|
|
self.normalize = normalize
|
|
self.copy_X = copy_X
|
|
self.n_jobs = n_jobs
|
|
|
|
def fit(self, X, y, n_jobs=1):
|
|
"""
|
|
Fit linear model.
|
|
|
|
Parameters
|
|
----------
|
|
X : numpy array or sparse matrix of shape [n_samples,n_features]
|
|
Training data
|
|
y : numpy array of shape [n_samples, n_targets]
|
|
Target values
|
|
|
|
Returns
|
|
-------
|
|
self : returns an instance of self.
|
|
"""
|
|
if n_jobs != 1:
|
|
warnings.warn("The n_jobs parameter in fit is deprecated and will "
|
|
"be removed in 0.17. It has been moved from the fit "
|
|
"method to the LinearRegression class constructor.",
|
|
DeprecationWarning, stacklevel=2)
|
|
n_jobs_ = n_jobs
|
|
else:
|
|
n_jobs_ = self.n_jobs
|
|
X = check_array(X, accept_sparse=['csr', 'csc', 'coo'])
|
|
y = np.asarray(y)
|
|
|
|
X, y, X_mean, y_mean, X_std = self._center_data(
|
|
X, y, self.fit_intercept, self.normalize, self.copy_X)
|
|
|
|
if sp.issparse(X):
|
|
if y.ndim < 2:
|
|
out = sparse_lsqr(X, y)
|
|
self.coef_ = out[0]
|
|
self.residues_ = out[3]
|
|
else:
|
|
# sparse_lstsq cannot handle y with shape (M, K)
|
|
outs = Parallel(n_jobs=n_jobs_)(
|
|
delayed(sparse_lsqr)(X, y[:, j].ravel())
|
|
for j in range(y.shape[1]))
|
|
self.coef_ = np.vstack(out[0] for out in outs)
|
|
self.residues_ = np.vstack(out[3] for out in outs)
|
|
else:
|
|
self.coef_, self.residues_, self.rank_, self.singular_ = \
|
|
linalg.lstsq(X, y)
|
|
self.coef_ = self.coef_.T
|
|
|
|
if y.ndim == 1:
|
|
self.coef_ = np.ravel(self.coef_)
|
|
self._set_intercept(X_mean, y_mean, X_std)
|
|
return self
|
|
|
|
|
|
def _pre_fit(X, y, Xy, precompute, normalize, fit_intercept, copy):
|
|
"""Aux function used at beginning of fit in linear models"""
|
|
n_samples, n_features = X.shape
|
|
if sparse.isspmatrix(X):
|
|
precompute = False
|
|
X, y, X_mean, y_mean, X_std = sparse_center_data(
|
|
X, y, fit_intercept, normalize)
|
|
else:
|
|
# copy was done in fit if necessary
|
|
X, y, X_mean, y_mean, X_std = center_data(
|
|
X, y, fit_intercept, normalize, copy=copy)
|
|
|
|
if hasattr(precompute, '__array__') \
|
|
and not np.allclose(X_mean, np.zeros(n_features)) \
|
|
and not np.allclose(X_std, np.ones(n_features)):
|
|
# recompute Gram
|
|
precompute = 'auto'
|
|
Xy = None
|
|
|
|
# precompute if n_samples > n_features
|
|
if precompute == 'auto':
|
|
precompute = (n_samples > n_features)
|
|
|
|
if precompute is True:
|
|
precompute = np.dot(X.T, X)
|
|
|
|
if not hasattr(precompute, '__array__'):
|
|
Xy = None # cannot use Xy if precompute is not Gram
|
|
|
|
if hasattr(precompute, '__array__') and Xy is None:
|
|
Xy = np.dot(X.T, y)
|
|
|
|
return X, y, X_mean, y_mean, X_std, precompute, Xy
|