batuhan-basoglu/Vehicle-Anti-Theft-Face-Recognition-System
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Uploaded Test files

Browse source
This commit is contained in:
Batuhan Berk Başoğlu 2020-11-12 11:05:57 -05:00
parent f584ad9d97
commit 2e81cb7d99
16627 changed files with 2065359 additions and 102444 deletions
Download patch file Download diff file Expand all files Collapse all files

4
venv/Lib/site-packages/sklearn/cross_decomposition/__init__.py Normal file
View file

@ -0,0 +1,4 @@
from ._pls import PLSCanonical, PLSRegression, PLSSVD
from ._cca import CCA
__all__ = ['PLSCanonical', 'PLSRegression', 'PLSSVD', 'CCA']

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/__pycache__/__init__.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/__pycache__/_cca.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/__pycache__/_pls.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/__pycache__/cca_.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/__pycache__/pls_.cpython-36.pyc Normal file
View file

Binary file not shown.

112
venv/Lib/site-packages/sklearn/cross_decomposition/_cca.py Normal file
View file

@ -0,0 +1,112 @@
from ._pls import _PLS
from ..base import _UnstableArchMixin
from ..utils.validation import _deprecate_positional_args
__all__ = ['CCA']
class CCA(_UnstableArchMixin, _PLS):
"""CCA Canonical Correlation Analysis.
CCA inherits from PLS with mode="B" and deflation_mode="canonical".
Read more in the :ref:`User Guide <cross_decomposition>`.
Parameters
----------
n_components : int, (default 2).
number of components to keep.
scale : boolean, (default True)
whether to scale the data?
max_iter : an integer, (default 500)
the maximum number of iterations of the NIPALS inner loop
tol : non-negative real, default 1e-06.
the tolerance used in the iterative algorithm
copy : boolean
Whether the deflation be done on a copy. Let the default value
to True unless you don't care about side effects
Attributes
----------
x_weights_ : array, [p, n_components]
X block weights vectors.
y_weights_ : array, [q, n_components]
Y block weights vectors.
x_loadings_ : array, [p, n_components]
X block loadings vectors.
y_loadings_ : array, [q, n_components]
Y block loadings vectors.
x_scores_ : array, [n_samples, n_components]
X scores.
y_scores_ : array, [n_samples, n_components]
Y scores.
x_rotations_ : array, [p, n_components]
X block to latents rotations.
y_rotations_ : array, [q, n_components]
Y block to latents rotations.
coef_ : array of shape (p, q)
The coefficients of the linear model: ``Y = X coef_ + Err``
n_iter_ : array-like
Number of iterations of the NIPALS inner loop for each
component.
Notes
-----
For each component k, find the weights u, v that maximizes
max corr(Xk u, Yk v), such that ``|u| = |v| = 1``
Note that it maximizes only the correlations between the scores.
The residual matrix of X (Xk+1) block is obtained by the deflation on the
current X score: x_score.
The residual matrix of Y (Yk+1) block is obtained by deflation on the
current Y score.
Examples
--------
>>> from sklearn.cross_decomposition import CCA
>>> X = [[0., 0., 1.], [1.,0.,0.], [2.,2.,2.], [3.,5.,4.]]
>>> Y = [[0.1, -0.2], [0.9, 1.1], [6.2, 5.9], [11.9, 12.3]]
>>> cca = CCA(n_components=1)
>>> cca.fit(X, Y)
CCA(n_components=1)
>>> X_c, Y_c = cca.transform(X, Y)
References
----------
Jacob A. Wegelin. A survey of Partial Least Squares (PLS) methods, with
emphasis on the two-block case. Technical Report 371, Department of
Statistics, University of Washington, Seattle, 2000.
In french but still a reference:
Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
See also
--------
PLSCanonical
PLSSVD
"""
@_deprecate_positional_args
def __init__(self, n_components=2, *, scale=True,
max_iter=500, tol=1e-06, copy=True):
super().__init__(n_components=n_components, scale=scale,
deflation_mode="canonical", mode="B",
norm_y_weights=True, algorithm="nipals",
max_iter=max_iter, tol=tol, copy=copy)

973
venv/Lib/site-packages/sklearn/cross_decomposition/_pls.py Normal file
View file

@ -0,0 +1,973 @@
"""
The :mod:`sklearn.pls` module implements Partial Least Squares (PLS).
"""
# Author: Edouard Duchesnay <edouard.duchesnay@cea.fr>
# License: BSD 3 clause
import warnings
from abc import ABCMeta, abstractmethod
import numpy as np
from scipy.linalg import pinv2, svd
from scipy.sparse.linalg import svds
from ..base import BaseEstimator, RegressorMixin, TransformerMixin
from ..base import MultiOutputMixin
from ..utils import check_array, check_consistent_length
from ..utils.extmath import svd_flip
from ..utils.validation import check_is_fitted, FLOAT_DTYPES
from ..utils.validation import _deprecate_positional_args
from ..exceptions import ConvergenceWarning
__all__ = ['PLSCanonical', 'PLSRegression', 'PLSSVD']
def _nipals_twoblocks_inner_loop(X, Y, mode="A", max_iter=500, tol=1e-06,
norm_y_weights=False):
"""Inner loop of the iterative NIPALS algorithm.
Provides an alternative to the svd(X'Y); returns the first left and right
singular vectors of X'Y. See PLS for the meaning of the parameters. It is
similar to the Power method for determining the eigenvectors and
eigenvalues of a X'Y.
"""
for col in Y.T:
if np.any(np.abs(col) > np.finfo(np.double).eps):
y_score = col.reshape(len(col), 1)
break
x_weights_old = 0
ite = 1
X_pinv = Y_pinv = None
eps = np.finfo(X.dtype).eps
if mode == "B":
# Uses condition from scipy<1.3 in pinv2 which was changed in
# https://github.com/scipy/scipy/pull/10067. In scipy 1.3, the
# condition was changed to depend on the largest singular value
X_t = X.dtype.char.lower()
Y_t = Y.dtype.char.lower()
factor = {'f': 1E3, 'd': 1E6}
cond_X = factor[X_t] * eps
cond_Y = factor[Y_t] * eps
# Inner loop of the Wold algo.
while True:
# 1.1 Update u: the X weights
if mode == "B":
if X_pinv is None:
# We use slower pinv2 (same as np.linalg.pinv) for stability
# reasons
X_pinv = pinv2(X, check_finite=False, cond=cond_X)
x_weights = np.dot(X_pinv, y_score)
else: # mode A
# Mode A regress each X column on y_score
x_weights = np.dot(X.T, y_score) / np.dot(y_score.T, y_score)
# If y_score only has zeros x_weights will only have zeros. In
# this case add an epsilon to converge to a more acceptable
# solution
if np.dot(x_weights.T, x_weights) < eps:
x_weights += eps
# 1.2 Normalize u
x_weights /= np.sqrt(np.dot(x_weights.T, x_weights)) + eps
# 1.3 Update x_score: the X latent scores
x_score = np.dot(X, x_weights)
# 2.1 Update y_weights
if mode == "B":
if Y_pinv is None:
# compute once pinv(Y)
Y_pinv = pinv2(Y, check_finite=False, cond=cond_Y)
y_weights = np.dot(Y_pinv, x_score)
else:
# Mode A regress each Y column on x_score
y_weights = np.dot(Y.T, x_score) / np.dot(x_score.T, x_score)
# 2.2 Normalize y_weights
if norm_y_weights:
y_weights /= np.sqrt(np.dot(y_weights.T, y_weights)) + eps
# 2.3 Update y_score: the Y latent scores
y_score = np.dot(Y, y_weights) / (np.dot(y_weights.T, y_weights) + eps)
# y_score = np.dot(Y, y_weights) / np.dot(y_score.T, y_score) ## BUG
x_weights_diff = x_weights - x_weights_old
if np.dot(x_weights_diff.T, x_weights_diff) < tol or Y.shape[1] == 1:
break
if ite == max_iter:
warnings.warn('Maximum number of iterations reached',
ConvergenceWarning)
break
x_weights_old = x_weights
ite += 1
return x_weights, y_weights, ite
def _svd_cross_product(X, Y):
C = np.dot(X.T, Y)
U, s, Vh = svd(C, full_matrices=False)
u = U[:, [0]]
v = Vh.T[:, [0]]
return u, v
def _center_scale_xy(X, Y, scale=True):
""" Center X, Y and scale if the scale parameter==True
Returns
-------
X, Y, x_mean, y_mean, x_std, y_std
"""
# center
x_mean = X.mean(axis=0)
X -= x_mean
y_mean = Y.mean(axis=0)
Y -= y_mean
# scale
if scale:
x_std = X.std(axis=0, ddof=1)
x_std[x_std == 0.0] = 1.0
X /= x_std
y_std = Y.std(axis=0, ddof=1)
y_std[y_std == 0.0] = 1.0
Y /= y_std
else:
x_std = np.ones(X.shape[1])
y_std = np.ones(Y.shape[1])
return X, Y, x_mean, y_mean, x_std, y_std
class _PLS(TransformerMixin, RegressorMixin, MultiOutputMixin, BaseEstimator,
metaclass=ABCMeta):
"""Partial Least Squares (PLS)
This class implements the generic PLS algorithm, constructors' parameters
allow to obtain a specific implementation such as:
- PLS2 regression, i.e., PLS 2 blocks, mode A, with asymmetric deflation
and unnormalized y weights such as defined by [Tenenhaus 1998] p. 132.
With univariate response it implements PLS1.
- PLS canonical, i.e., PLS 2 blocks, mode A, with symmetric deflation and
normalized y weights such as defined by [Tenenhaus 1998] (p. 132) and
[Wegelin et al. 2000]. This parametrization implements the original Wold
algorithm.
We use the terminology defined by [Wegelin et al. 2000].
This implementation uses the PLS Wold 2 blocks algorithm based on two
nested loops:
(i) The outer loop iterate over components.
(ii) The inner loop estimates the weights vectors. This can be done
with two algo. (a) the inner loop of the original NIPALS algo. or (b) a
SVD on residuals cross-covariance matrices.
n_components : int, number of components to keep. (default 2).
scale : boolean, scale data? (default True)
deflation_mode : str, "canonical" or "regression". See notes.
mode : "A" classical PLS and "B" CCA. See notes.
norm_y_weights : boolean, normalize Y weights to one? (default False)
algorithm : string, "nipals" or "svd"
The algorithm used to estimate the weights. It will be called
n_components times, i.e. once for each iteration of the outer loop.
max_iter : int (default 500)
The maximum number of iterations
of the NIPALS inner loop (used only if algorithm="nipals")
tol : non-negative real, default 1e-06
The tolerance used in the iterative algorithm.
copy : boolean, default True
Whether the deflation should be done on a copy. Let the default
value to True unless you don't care about side effects.
Attributes
----------
x_weights_ : array, [p, n_components]
X block weights vectors.
y_weights_ : array, [q, n_components]
Y block weights vectors.
x_loadings_ : array, [p, n_components]
X block loadings vectors.
y_loadings_ : array, [q, n_components]
Y block loadings vectors.
x_scores_ : array, [n_samples, n_components]
X scores.
y_scores_ : array, [n_samples, n_components]
Y scores.
x_rotations_ : array, [p, n_components]
X block to latents rotations.
y_rotations_ : array, [q, n_components]
Y block to latents rotations.
x_mean_ : array, [p]
X mean for each predictor.
y_mean_ : array, [q]
Y mean for each response variable.
x_std_ : array, [p]
X standard deviation for each predictor.
y_std_ : array, [q]
Y standard deviation for each response variable.
coef_ : array, [p, q]
The coefficients of the linear model: ``Y = X coef_ + Err``
n_iter_ : array-like
Number of iterations of the NIPALS inner loop for each
component. Not useful if the algorithm given is "svd".
References
----------
Jacob A. Wegelin. A survey of Partial Least Squares (PLS) methods, with
emphasis on the two-block case. Technical Report 371, Department of
Statistics, University of Washington, Seattle, 2000.
In French but still a reference:
Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
See also
--------
PLSCanonical
PLSRegression
CCA
PLS_SVD
"""
@abstractmethod
def __init__(self, n_components=2, *, scale=True,
deflation_mode="regression",
mode="A", algorithm="nipals", norm_y_weights=False,
max_iter=500, tol=1e-06, copy=True):
self.n_components = n_components
self.deflation_mode = deflation_mode
self.mode = mode
self.norm_y_weights = norm_y_weights
self.scale = scale
self.algorithm = algorithm
self.max_iter = max_iter
self.tol = tol
self.copy = copy
def fit(self, X, Y):
"""Fit model to data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
Y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
"""
# copy since this will contains the residuals (deflated) matrices
check_consistent_length(X, Y)
X = self._validate_data(X, dtype=np.float64, copy=self.copy,
ensure_min_samples=2)
Y = check_array(Y, dtype=np.float64, copy=self.copy, ensure_2d=False)
if Y.ndim == 1:
Y = Y.reshape(-1, 1)
n = X.shape[0]
p = X.shape[1]
q = Y.shape[1]
if self.n_components < 1 or self.n_components > p:
raise ValueError('Invalid number of components: %d' %
self.n_components)
if self.algorithm not in ("svd", "nipals"):
raise ValueError("Got algorithm %s when only 'svd' "
"and 'nipals' are known" % self.algorithm)
if self.algorithm == "svd" and self.mode == "B":
raise ValueError('Incompatible configuration: mode B is not '
'implemented with svd algorithm')
if self.deflation_mode not in ["canonical", "regression"]:
raise ValueError('The deflation mode is unknown')
# Scale (in place)
X, Y, self.x_mean_, self.y_mean_, self.x_std_, self.y_std_ = (
_center_scale_xy(X, Y, self.scale))
# Residuals (deflated) matrices
Xk = X
Yk = Y
# Results matrices
self.x_scores_ = np.zeros((n, self.n_components))
self.y_scores_ = np.zeros((n, self.n_components))
self.x_weights_ = np.zeros((p, self.n_components))
self.y_weights_ = np.zeros((q, self.n_components))
self.x_loadings_ = np.zeros((p, self.n_components))
self.y_loadings_ = np.zeros((q, self.n_components))
self.n_iter_ = []
# NIPALS algo: outer loop, over components
Y_eps = np.finfo(Yk.dtype).eps
for k in range(self.n_components):
if np.all(np.dot(Yk.T, Yk) < np.finfo(np.double).eps):
# Yk constant
warnings.warn('Y residual constant at iteration %s' % k)
break
# 1) weights estimation (inner loop)
# -----------------------------------
if self.algorithm == "nipals":
# Replace columns that are all close to zero with zeros
Yk_mask = np.all(np.abs(Yk) < 10 * Y_eps, axis=0)
Yk[:, Yk_mask] = 0.0
x_weights, y_weights, n_iter_ = \
_nipals_twoblocks_inner_loop(
X=Xk, Y=Yk, mode=self.mode, max_iter=self.max_iter,
tol=self.tol, norm_y_weights=self.norm_y_weights)
self.n_iter_.append(n_iter_)
elif self.algorithm == "svd":
x_weights, y_weights = _svd_cross_product(X=Xk, Y=Yk)
# Forces sign stability of x_weights and y_weights
# Sign undeterminacy issue from svd if algorithm == "svd"
# and from platform dependent computation if algorithm == 'nipals'
x_weights, y_weights = svd_flip(x_weights, y_weights.T)
y_weights = y_weights.T
# compute scores
x_scores = np.dot(Xk, x_weights)
if self.norm_y_weights:
y_ss = 1
else:
y_ss = np.dot(y_weights.T, y_weights)
y_scores = np.dot(Yk, y_weights) / y_ss
# test for null variance
if np.dot(x_scores.T, x_scores) < np.finfo(np.double).eps:
warnings.warn('X scores are null at iteration %s' % k)
break
# 2) Deflation (in place)
# ----------------------
# Possible memory footprint reduction may done here: in order to
# avoid the allocation of a data chunk for the rank-one
# approximations matrix which is then subtracted to Xk, we suggest
# to perform a column-wise deflation.
#
# - regress Xk's on x_score
x_loadings = np.dot(Xk.T, x_scores) / np.dot(x_scores.T, x_scores)
# - subtract rank-one approximations to obtain remainder matrix
Xk -= np.dot(x_scores, x_loadings.T)
if self.deflation_mode == "canonical":
# - regress Yk's on y_score, then subtract rank-one approx.
y_loadings = (np.dot(Yk.T, y_scores)
/ np.dot(y_scores.T, y_scores))
Yk -= np.dot(y_scores, y_loadings.T)
if self.deflation_mode == "regression":
# - regress Yk's on x_score, then subtract rank-one approx.
y_loadings = (np.dot(Yk.T, x_scores)
/ np.dot(x_scores.T, x_scores))
Yk -= np.dot(x_scores, y_loadings.T)
# 3) Store weights, scores and loadings # Notation:
self.x_scores_[:, k] = x_scores.ravel() # T
self.y_scores_[:, k] = y_scores.ravel() # U
self.x_weights_[:, k] = x_weights.ravel() # W
self.y_weights_[:, k] = y_weights.ravel() # C
self.x_loadings_[:, k] = x_loadings.ravel() # P
self.y_loadings_[:, k] = y_loadings.ravel() # Q
# Such that: X = TP' + Err and Y = UQ' + Err
# 4) rotations from input space to transformed space (scores)
# T = X W(P'W)^-1 = XW* (W* : p x k matrix)
# U = Y C(Q'C)^-1 = YC* (W* : q x k matrix)
self.x_rotations_ = np.dot(
self.x_weights_,
pinv2(np.dot(self.x_loadings_.T, self.x_weights_),
check_finite=False))
if Y.shape[1] > 1:
self.y_rotations_ = np.dot(
self.y_weights_,
pinv2(np.dot(self.y_loadings_.T, self.y_weights_),
check_finite=False))
else:
self.y_rotations_ = np.ones(1)
if True or self.deflation_mode == "regression":
# FIXME what's with the if?
# Estimate regression coefficient
# Regress Y on T
# Y = TQ' + Err,
# Then express in function of X
# Y = X W(P'W)^-1Q' + Err = XB + Err
# => B = W*Q' (p x q)
self.coef_ = np.dot(self.x_rotations_, self.y_loadings_.T)
self.coef_ = self.coef_ * self.y_std_
return self
def transform(self, X, Y=None, copy=True):
"""Apply the dimension reduction learned on the train data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
Y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
copy : boolean, default True
Whether to copy X and Y, or perform in-place normalization.
Returns
-------
x_scores if Y is not given, (x_scores, y_scores) otherwise.
"""
check_is_fitted(self)
X = check_array(X, copy=copy, dtype=FLOAT_DTYPES)
# Normalize
X -= self.x_mean_
X /= self.x_std_
# Apply rotation
x_scores = np.dot(X, self.x_rotations_)
if Y is not None:
Y = check_array(Y, ensure_2d=False, copy=copy, dtype=FLOAT_DTYPES)
if Y.ndim == 1:
Y = Y.reshape(-1, 1)
Y -= self.y_mean_
Y /= self.y_std_
y_scores = np.dot(Y, self.y_rotations_)
return x_scores, y_scores
return x_scores
def inverse_transform(self, X):
"""Transform data back to its original space.
Parameters
----------
X : array-like of shape (n_samples, n_components)
New data, where n_samples is the number of samples
and n_components is the number of pls components.
Returns
-------
x_reconstructed : array-like of shape (n_samples, n_features)
Notes
-----
This transformation will only be exact if n_components=n_features
"""
check_is_fitted(self)
X = check_array(X, dtype=FLOAT_DTYPES)
# From pls space to original space
X_reconstructed = np.matmul(X, self.x_loadings_.T)
# Denormalize
X_reconstructed *= self.x_std_
X_reconstructed += self.x_mean_
return X_reconstructed
def predict(self, X, copy=True):
"""Apply the dimension reduction learned on the train data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
copy : boolean, default True
Whether to copy X and Y, or perform in-place normalization.
Notes
-----
This call requires the estimation of a p x q matrix, which may
be an issue in high dimensional space.
"""
check_is_fitted(self)
X = check_array(X, copy=copy, dtype=FLOAT_DTYPES)
# Normalize
X -= self.x_mean_
X /= self.x_std_
Ypred = np.dot(X, self.coef_)
return Ypred + self.y_mean_
def fit_transform(self, X, y=None):
"""Learn and apply the dimension reduction on the train data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
Returns
-------
x_scores if Y is not given, (x_scores, y_scores) otherwise.
"""
return self.fit(X, y).transform(X, y)
def _more_tags(self):
return {'poor_score': True,
'requires_y': False}
class PLSRegression(_PLS):
"""PLS regression
PLSRegression implements the PLS 2 blocks regression known as PLS2 or PLS1
in case of one dimensional response.
This class inherits from _PLS with mode="A", deflation_mode="regression",
norm_y_weights=False and algorithm="nipals".
Read more in the :ref:`User Guide <cross_decomposition>`.
.. versionadded:: 0.8
Parameters
----------
n_components : int, (default 2)
Number of components to keep.
scale : boolean, (default True)
whether to scale the data
max_iter : an integer, (default 500)
the maximum number of iterations of the NIPALS inner loop (used
only if algorithm="nipals")
tol : non-negative real
Tolerance used in the iterative algorithm default 1e-06.
copy : boolean, default True
Whether the deflation should be done on a copy. Let the default
value to True unless you don't care about side effect
Attributes
----------
x_weights_ : array, [p, n_components]
X block weights vectors.
y_weights_ : array, [q, n_components]
Y block weights vectors.
x_loadings_ : array, [p, n_components]
X block loadings vectors.
y_loadings_ : array, [q, n_components]
Y block loadings vectors.
x_scores_ : array, [n_samples, n_components]
X scores.
y_scores_ : array, [n_samples, n_components]
Y scores.
x_rotations_ : array, [p, n_components]
X block to latents rotations.
y_rotations_ : array, [q, n_components]
Y block to latents rotations.
coef_ : array, [p, q]
The coefficients of the linear model: ``Y = X coef_ + Err``
n_iter_ : array-like
Number of iterations of the NIPALS inner loop for each
component.
Notes
-----
Matrices::
T: x_scores_
U: y_scores_
W: x_weights_
C: y_weights_
P: x_loadings_
Q: y_loadings_
Are computed such that::
X = T P.T + Err and Y = U Q.T + Err
T[:, k] = Xk W[:, k] for k in range(n_components)
U[:, k] = Yk C[:, k] for k in range(n_components)
x_rotations_ = W (P.T W)^(-1)
y_rotations_ = C (Q.T C)^(-1)
where Xk and Yk are residual matrices at iteration k.
`Slides explaining
PLS <http://www.eigenvector.com/Docs/Wise_pls_properties.pdf>`_
For each component k, find weights u, v that optimizes:
``max corr(Xk u, Yk v) * std(Xk u) std(Yk u)``, such that ``|u| = 1``
Note that it maximizes both the correlations between the scores and the
intra-block variances.
The residual matrix of X (Xk+1) block is obtained by the deflation on
the current X score: x_score.
The residual matrix of Y (Yk+1) block is obtained by deflation on the
current X score. This performs the PLS regression known as PLS2. This
mode is prediction oriented.
This implementation provides the same results that 3 PLS packages
provided in the R language (R-project):
- "mixOmics" with function pls(X, Y, mode = "regression")
- "plspm " with function plsreg2(X, Y)
- "pls" with function oscorespls.fit(X, Y)
Examples
--------
>>> from sklearn.cross_decomposition import PLSRegression
>>> X = [[0., 0., 1.], [1.,0.,0.], [2.,2.,2.], [2.,5.,4.]]
>>> Y = [[0.1, -0.2], [0.9, 1.1], [6.2, 5.9], [11.9, 12.3]]
>>> pls2 = PLSRegression(n_components=2)
>>> pls2.fit(X, Y)
PLSRegression()
>>> Y_pred = pls2.predict(X)
References
----------
Jacob A. Wegelin. A survey of Partial Least Squares (PLS) methods, with
emphasis on the two-block case. Technical Report 371, Department of
Statistics, University of Washington, Seattle, 2000.
In french but still a reference:
Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
"""
@_deprecate_positional_args
def __init__(self, n_components=2, *, scale=True,
max_iter=500, tol=1e-06, copy=True):
super().__init__(
n_components=n_components, scale=scale,
deflation_mode="regression", mode="A",
norm_y_weights=False, max_iter=max_iter, tol=tol,
copy=copy)
class PLSCanonical(_PLS):
""" PLSCanonical implements the 2 blocks canonical PLS of the original Wold
algorithm [Tenenhaus 1998] p.204, referred as PLS-C2A in [Wegelin 2000].
This class inherits from PLS with mode="A" and deflation_mode="canonical",
norm_y_weights=True and algorithm="nipals", but svd should provide similar
results up to numerical errors.
Read more in the :ref:`User Guide <cross_decomposition>`.
.. versionadded:: 0.8
Parameters
----------
n_components : int, (default 2).
Number of components to keep
scale : boolean, (default True)
Option to scale data
algorithm : string, "nipals" or "svd"
The algorithm used to estimate the weights. It will be called
n_components times, i.e. once for each iteration of the outer loop.
max_iter : an integer, (default 500)
the maximum number of iterations of the NIPALS inner loop (used
only if algorithm="nipals")
tol : non-negative real, default 1e-06
the tolerance used in the iterative algorithm
copy : boolean, default True
Whether the deflation should be done on a copy. Let the default
value to True unless you don't care about side effect
Attributes
----------
x_weights_ : array, shape = [p, n_components]
X block weights vectors.
y_weights_ : array, shape = [q, n_components]
Y block weights vectors.
x_loadings_ : array, shape = [p, n_components]
X block loadings vectors.
y_loadings_ : array, shape = [q, n_components]
Y block loadings vectors.
x_scores_ : array, shape = [n_samples, n_components]
X scores.
y_scores_ : array, shape = [n_samples, n_components]
Y scores.
x_rotations_ : array, shape = [p, n_components]
X block to latents rotations.
y_rotations_ : array, shape = [q, n_components]
Y block to latents rotations.
coef_ : array of shape (p, q)
The coefficients of the linear model: ``Y = X coef_ + Err``
n_iter_ : array-like
Number of iterations of the NIPALS inner loop for each
component. Not useful if the algorithm provided is "svd".
Notes
-----
Matrices::
T: x_scores_
U: y_scores_
W: x_weights_
C: y_weights_
P: x_loadings_
Q: y_loadings__
Are computed such that::
X = T P.T + Err and Y = U Q.T + Err
T[:, k] = Xk W[:, k] for k in range(n_components)
U[:, k] = Yk C[:, k] for k in range(n_components)
x_rotations_ = W (P.T W)^(-1)
y_rotations_ = C (Q.T C)^(-1)
where Xk and Yk are residual matrices at iteration k.
`Slides explaining PLS
<http://www.eigenvector.com/Docs/Wise_pls_properties.pdf>`_
For each component k, find weights u, v that optimize::
max corr(Xk u, Yk v) * std(Xk u) std(Yk u), such that ``|u| = |v| = 1``
Note that it maximizes both the correlations between the scores and the
intra-block variances.
The residual matrix of X (Xk+1) block is obtained by the deflation on the
current X score: x_score.
The residual matrix of Y (Yk+1) block is obtained by deflation on the
current Y score. This performs a canonical symmetric version of the PLS
regression. But slightly different than the CCA. This is mostly used
for modeling.
This implementation provides the same results that the "plspm" package
provided in the R language (R-project), using the function plsca(X, Y).
Results are equal or collinear with the function
``pls(..., mode = "canonical")`` of the "mixOmics" package. The difference
relies in the fact that mixOmics implementation does not exactly implement
the Wold algorithm since it does not normalize y_weights to one.
Examples
--------
>>> from sklearn.cross_decomposition import PLSCanonical
>>> X = [[0., 0., 1.], [1.,0.,0.], [2.,2.,2.], [2.,5.,4.]]
>>> Y = [[0.1, -0.2], [0.9, 1.1], [6.2, 5.9], [11.9, 12.3]]
>>> plsca = PLSCanonical(n_components=2)
>>> plsca.fit(X, Y)
PLSCanonical()
>>> X_c, Y_c = plsca.transform(X, Y)
References
----------
Jacob A. Wegelin. A survey of Partial Least Squares (PLS) methods, with
emphasis on the two-block case. Technical Report 371, Department of
Statistics, University of Washington, Seattle, 2000.
Tenenhaus, M. (1998). La regression PLS: theorie et pratique. Paris:
Editions Technic.
See also
--------
CCA
PLSSVD
"""
@_deprecate_positional_args
def __init__(self, n_components=2, *, scale=True, algorithm="nipals",
max_iter=500, tol=1e-06, copy=True):
super().__init__(
n_components=n_components, scale=scale,
deflation_mode="canonical", mode="A",
norm_y_weights=True, algorithm=algorithm,
max_iter=max_iter, tol=tol, copy=copy)
class PLSSVD(TransformerMixin, BaseEstimator):
"""Partial Least Square SVD
Simply perform a svd on the crosscovariance matrix: X'Y
There are no iterative deflation here.
Read more in the :ref:`User Guide <cross_decomposition>`.
.. versionadded:: 0.8
Parameters
----------
n_components : int, default 2
Number of components to keep.
scale : boolean, default True
Whether to scale X and Y.
copy : boolean, default True
Whether to copy X and Y, or perform in-place computations.
Attributes
----------
x_weights_ : array, [p, n_components]
X block weights vectors.
y_weights_ : array, [q, n_components]
Y block weights vectors.
x_scores_ : array, [n_samples, n_components]
X scores.
y_scores_ : array, [n_samples, n_components]
Y scores.
Examples
--------
>>> import numpy as np
>>> from sklearn.cross_decomposition import PLSSVD
>>> X = np.array([[0., 0., 1.],
... [1.,0.,0.],
... [2.,2.,2.],
... [2.,5.,4.]])
>>> Y = np.array([[0.1, -0.2],
... [0.9, 1.1],
... [6.2, 5.9],
... [11.9, 12.3]])
>>> plsca = PLSSVD(n_components=2)
>>> plsca.fit(X, Y)
PLSSVD()
>>> X_c, Y_c = plsca.transform(X, Y)
>>> X_c.shape, Y_c.shape
((4, 2), (4, 2))
See also
--------
PLSCanonical
CCA
"""
@_deprecate_positional_args
def __init__(self, n_components=2, *, scale=True, copy=True):
self.n_components = n_components
self.scale = scale
self.copy = copy
def fit(self, X, Y):
"""Fit model to data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
Y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
"""
# copy since this will contains the centered data
check_consistent_length(X, Y)
X = self._validate_data(X, dtype=np.float64, copy=self.copy,
ensure_min_samples=2)
Y = check_array(Y, dtype=np.float64, copy=self.copy, ensure_2d=False)
if Y.ndim == 1:
Y = Y.reshape(-1, 1)
if self.n_components > max(Y.shape[1], X.shape[1]):
raise ValueError("Invalid number of components n_components=%d"
" with X of shape %s and Y of shape %s."
% (self.n_components, str(X.shape), str(Y.shape)))
# Scale (in place)
X, Y, self.x_mean_, self.y_mean_, self.x_std_, self.y_std_ = (
_center_scale_xy(X, Y, self.scale))
# svd(X'Y)
C = np.dot(X.T, Y)
# The arpack svds solver only works if the number of extracted
# components is smaller than rank(X) - 1. Hence, if we want to extract
# all the components (C.shape[1]), we have to use another one. Else,
# let's use arpacks to compute only the interesting components.
if self.n_components >= np.min(C.shape):
U, s, V = svd(C, full_matrices=False)
else:
U, s, V = svds(C, k=self.n_components)
# Deterministic output
U, V = svd_flip(U, V)
V = V.T
self.x_scores_ = np.dot(X, U)
self.y_scores_ = np.dot(Y, V)
self.x_weights_ = U
self.y_weights_ = V
return self
def transform(self, X, Y=None):
"""
Apply the dimension reduction learned on the train data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
Y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
"""
check_is_fitted(self)
X = check_array(X, dtype=np.float64)
Xr = (X - self.x_mean_) / self.x_std_
x_scores = np.dot(Xr, self.x_weights_)
if Y is not None:
Y = check_array(Y, ensure_2d=False, dtype=np.float64)
if Y.ndim == 1:
Y = Y.reshape(-1, 1)
Yr = (Y - self.y_mean_) / self.y_std_
y_scores = np.dot(Yr, self.y_weights_)
return x_scores, y_scores
return x_scores
def fit_transform(self, X, y=None):
"""Learn and apply the dimension reduction on the train data.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of predictors.
y : array-like of shape (n_samples, n_targets)
Target vectors, where n_samples is the number of samples and
n_targets is the number of response variables.
Returns
-------
x_scores if Y is not given, (x_scores, y_scores) otherwise.
"""
return self.fit(X, y).transform(X, y)

18
venv/Lib/site-packages/sklearn/cross_decomposition/cca_.py Normal file
View file

@ -0,0 +1,18 @@
# THIS FILE WAS AUTOMATICALLY GENERATED BY deprecated_modules.py
import sys
# mypy error: Module X has no attribute y (typically for C extensions)
from . import _cca # type: ignore
from ..externals._pep562 import Pep562
from ..utils.deprecation import _raise_dep_warning_if_not_pytest
deprecated_path = 'sklearn.cross_decomposition.cca_'
correct_import_path = 'sklearn.cross_decomposition'
_raise_dep_warning_if_not_pytest(deprecated_path, correct_import_path)
def __getattr__(name):
return getattr(_cca, name)
if not sys.version_info >= (3, 7):
Pep562(__name__)

18
venv/Lib/site-packages/sklearn/cross_decomposition/pls_.py Normal file
View file

@ -0,0 +1,18 @@
# THIS FILE WAS AUTOMATICALLY GENERATED BY deprecated_modules.py
import sys
# mypy error: Module X has no attribute y (typically for C extensions)
from . import _pls # type: ignore
from ..externals._pep562 import Pep562
from ..utils.deprecation import _raise_dep_warning_if_not_pytest
deprecated_path = 'sklearn.cross_decomposition.pls_'
correct_import_path = 'sklearn.cross_decomposition'
_raise_dep_warning_if_not_pytest(deprecated_path, correct_import_path)
def __getattr__(name):
return getattr(_pls, name)
if not sys.version_info >= (3, 7):
Pep562(__name__)

0
venv/Lib/site-packages/sklearn/cross_decomposition/tests/__init__.py Normal file
View file

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/tests/__pycache__/__init__.cpython-36.pyc Normal file
View file

Binary file not shown.

BIN
venv/Lib/site-packages/sklearn/cross_decomposition/tests/__pycache__/test_pls.cpython-36.pyc Normal file
View file

Binary file not shown.

450
venv/Lib/site-packages/sklearn/cross_decomposition/tests/test_pls.py Normal file
View file

@ -0,0 +1,450 @@
import numpy as np
from numpy.testing import assert_approx_equal
from sklearn.utils._testing import (assert_array_almost_equal,
assert_array_equal, assert_raise_message,
assert_warns)
from sklearn.datasets import load_linnerud
from sklearn.cross_decomposition import _pls as pls_
from sklearn.cross_decomposition import CCA
from sklearn.preprocessing import StandardScaler
from sklearn.utils import check_random_state
from sklearn.exceptions import ConvergenceWarning
def test_pls():
d = load_linnerud()
X = d.data
Y = d.target
# 1) Canonical (symmetric) PLS (PLS 2 blocks canonical mode A)
# ===========================================================
# Compare 2 algo.: nipals vs. svd
# ------------------------------
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1])
pls_bynipals.fit(X, Y)
pls_bysvd = pls_.PLSCanonical(algorithm="svd", n_components=X.shape[1])
pls_bysvd.fit(X, Y)
# check equalities of loading (up to the sign of the second column)
assert_array_almost_equal(
pls_bynipals.x_loadings_,
pls_bysvd.x_loadings_, decimal=5,
err_msg="nipals and svd implementations lead to different x loadings")
assert_array_almost_equal(
pls_bynipals.y_loadings_,
pls_bysvd.y_loadings_, decimal=5,
err_msg="nipals and svd implementations lead to different y loadings")
# Check PLS properties (with n_components=X.shape[1])
# ---------------------------------------------------
plsca = pls_.PLSCanonical(n_components=X.shape[1])
plsca.fit(X, Y)
T = plsca.x_scores_
P = plsca.x_loadings_
Wx = plsca.x_weights_
U = plsca.y_scores_
Q = plsca.y_loadings_
Wy = plsca.y_weights_
def check_ortho(M, err_msg):
K = np.dot(M.T, M)
assert_array_almost_equal(K, np.diag(np.diag(K)), err_msg=err_msg)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(Wx, "x weights are not orthogonal")
check_ortho(Wy, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(T, "x scores are not orthogonal")
check_ortho(U, "y scores are not orthogonal")
# Check X = TP' and Y = UQ' (with (p == q) components)
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# center scale X, Y
Xc, Yc, x_mean, y_mean, x_std, y_std =\
pls_._center_scale_xy(X.copy(), Y.copy(), scale=True)
assert_array_almost_equal(Xc, np.dot(T, P.T), err_msg="X != TP'")
assert_array_almost_equal(Yc, np.dot(U, Q.T), err_msg="Y != UQ'")
# Check that rotations on training data lead to scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xr = plsca.transform(X)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
Xr, Yr = plsca.transform(X, Y)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
assert_array_almost_equal(Yr, plsca.y_scores_,
err_msg="rotation on Y failed")
# Check that inverse_transform works
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xreconstructed = plsca.inverse_transform(Xr)
assert_array_almost_equal(Xreconstructed, X,
err_msg="inverse_transform failed")
# "Non regression test" on canonical PLS
# --------------------------------------
# The results were checked against the R-package plspm
pls_ca = pls_.PLSCanonical(n_components=X.shape[1])
pls_ca.fit(X, Y)
x_weights = np.array(
[[-0.61330704, 0.25616119, -0.74715187],
[-0.74697144, 0.11930791, 0.65406368],
[-0.25668686, -0.95924297, -0.11817271]])
# x_weights_sign_flip holds columns of 1 or -1, depending on sign flip
# between R and python
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_rotations = np.array(
[[-0.61330704, 0.41591889, -0.62297525],
[-0.74697144, 0.31388326, 0.77368233],
[-0.25668686, -0.89237972, -0.24121788]])
x_rotations_sign_flip = pls_ca.x_rotations_ / x_rotations
y_weights = np.array(
[[+0.58989127, 0.7890047, 0.1717553],
[+0.77134053, -0.61351791, 0.16920272],
[-0.23887670, -0.03267062, 0.97050016]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_rotations = np.array(
[[+0.58989127, 0.7168115, 0.30665872],
[+0.77134053, -0.70791757, 0.19786539],
[-0.23887670, -0.00343595, 0.94162826]])
y_rotations_sign_flip = pls_ca.y_rotations_ / y_rotations
# x_weights = X.dot(x_rotation)
# Hence R/python sign flip should be the same in x_weight and x_rotation
assert_array_almost_equal(x_rotations_sign_flip, x_weights_sign_flip)
# This test that R / python give the same result up to column
# sign indeterminacy
assert_array_almost_equal(np.abs(x_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_rotations_sign_flip, y_weights_sign_flip)
assert_array_almost_equal(np.abs(y_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 2) Regression PLS (PLS2): "Non regression test"
# ===============================================
# The results were checked against the R-packages plspm, misOmics and pls
pls_2 = pls_.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array(
[[-0.61330704, -0.00443647, 0.78983213],
[-0.74697144, -0.32172099, -0.58183269],
[-0.25668686, 0.94682413, -0.19399983]])
x_weights_sign_flip = pls_2.x_weights_ / x_weights
x_loadings = np.array(
[[-0.61470416, -0.24574278, 0.78983213],
[-0.65625755, -0.14396183, -0.58183269],
[-0.51733059, 1.00609417, -0.19399983]])
x_loadings_sign_flip = pls_2.x_loadings_ / x_loadings
y_weights = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_weights_sign_flip = pls_2.y_weights_ / y_weights
y_loadings = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_loadings_sign_flip = pls_2.y_loadings_ / y_loadings
# x_loadings[:, i] = Xi.dot(x_weights[:, i]) \forall i
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 3) Another non-regression test of Canonical PLS on random dataset
# =================================================================
# The results were checked against the R-package plspm
n = 500
p_noise = 10
q_noise = 5
# 2 latents vars:
rng = check_random_state(11)
l1 = rng.normal(size=n)
l2 = rng.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + rng.normal(size=4 * n).reshape((n, 4))
Y = latents + rng.normal(size=4 * n).reshape((n, 4))
X = np.concatenate(
(X, rng.normal(size=p_noise * n).reshape(n, p_noise)), axis=1)
Y = np.concatenate(
(Y, rng.normal(size=q_noise * n).reshape(n, q_noise)), axis=1)
pls_ca = pls_.PLSCanonical(n_components=3)
pls_ca.fit(X, Y)
x_weights = np.array(
[[0.65803719, 0.19197924, 0.21769083],
[0.7009113, 0.13303969, -0.15376699],
[0.13528197, -0.68636408, 0.13856546],
[0.16854574, -0.66788088, -0.12485304],
[-0.03232333, -0.04189855, 0.40690153],
[0.1148816, -0.09643158, 0.1613305],
[0.04792138, -0.02384992, 0.17175319],
[-0.06781, -0.01666137, -0.18556747],
[-0.00266945, -0.00160224, 0.11893098],
[-0.00849528, -0.07706095, 0.1570547],
[-0.00949471, -0.02964127, 0.34657036],
[-0.03572177, 0.0945091, 0.3414855],
[0.05584937, -0.02028961, -0.57682568],
[0.05744254, -0.01482333, -0.17431274]])
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_loadings = np.array(
[[0.65649254, 0.1847647, 0.15270699],
[0.67554234, 0.15237508, -0.09182247],
[0.19219925, -0.67750975, 0.08673128],
[0.2133631, -0.67034809, -0.08835483],
[-0.03178912, -0.06668336, 0.43395268],
[0.15684588, -0.13350241, 0.20578984],
[0.03337736, -0.03807306, 0.09871553],
[-0.06199844, 0.01559854, -0.1881785],
[0.00406146, -0.00587025, 0.16413253],
[-0.00374239, -0.05848466, 0.19140336],
[0.00139214, -0.01033161, 0.32239136],
[-0.05292828, 0.0953533, 0.31916881],
[0.04031924, -0.01961045, -0.65174036],
[0.06172484, -0.06597366, -0.1244497]])
x_loadings_sign_flip = pls_ca.x_loadings_ / x_loadings
y_weights = np.array(
[[0.66101097, 0.18672553, 0.22826092],
[0.69347861, 0.18463471, -0.23995597],
[0.14462724, -0.66504085, 0.17082434],
[0.22247955, -0.6932605, -0.09832993],
[0.07035859, 0.00714283, 0.67810124],
[0.07765351, -0.0105204, -0.44108074],
[-0.00917056, 0.04322147, 0.10062478],
[-0.01909512, 0.06182718, 0.28830475],
[0.01756709, 0.04797666, 0.32225745]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_loadings = np.array(
[[0.68568625, 0.1674376, 0.0969508],
[0.68782064, 0.20375837, -0.1164448],
[0.11712173, -0.68046903, 0.12001505],
[0.17860457, -0.6798319, -0.05089681],
[0.06265739, -0.0277703, 0.74729584],
[0.0914178, 0.00403751, -0.5135078],
[-0.02196918, -0.01377169, 0.09564505],
[-0.03288952, 0.09039729, 0.31858973],
[0.04287624, 0.05254676, 0.27836841]])
y_loadings_sign_flip = pls_ca.y_loadings_ / y_loadings
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_weights_, "x weights are not orthogonal")
check_ortho(pls_ca.y_weights_, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_scores_, "x scores are not orthogonal")
check_ortho(pls_ca.y_scores_, "y scores are not orthogonal")
# 4) Another "Non regression test" of PLS Regression (PLS2):
# Checking behavior when the first column of Y is constant
# ===============================================
# The results were compared against a modified version of plsreg2
# from the R-package plsdepot
X = d.data
Y = d.target
Y[:, 0] = 1
pls_2 = pls_.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array(
[[-0.6273573, 0.007081799, 0.7786994],
[-0.7493417, -0.277612681, -0.6011807],
[-0.2119194, 0.960666981, -0.1794690]])
x_weights_sign_flip = pls_2.x_weights_ / x_weights
x_loadings = np.array(
[[-0.6273512, -0.22464538, 0.7786994],
[-0.6643156, -0.09871193, -0.6011807],
[-0.5125877, 1.01407380, -0.1794690]])
x_loadings_sign_flip = pls_2.x_loadings_ / x_loadings
y_loadings = np.array(
[[0.0000000, 0.0000000, 0.0000000],
[0.4357300, 0.5828479, 0.2174802],
[-0.1353739, -0.2486423, -0.1810386]])
# R/python sign flip should be the same in x_weight and x_rotation
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
# This test that R / python give the same result up to column
# sign indeterminacy
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
# For the PLSRegression with default parameters, it holds that
# y_loadings==y_weights. In this case we only test that R/python
# give the same result for the y_loadings irrespective of the sign
assert_array_almost_equal(np.abs(pls_2.y_loadings_), np.abs(y_loadings), 4)
def test_convergence_fail():
d = load_linnerud()
X = d.data
Y = d.target
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1],
max_iter=2, tol=1e-10)
assert_warns(ConvergenceWarning, pls_bynipals.fit, X, Y)
def test_PLSSVD():
# Let's check the PLSSVD doesn't return all possible component but just
# the specified number
d = load_linnerud()
X = d.data
Y = d.target
n_components = 2
for clf in [pls_.PLSSVD, pls_.PLSRegression, pls_.PLSCanonical]:
pls = clf(n_components=n_components)
pls.fit(X, Y)
assert n_components == pls.y_scores_.shape[1]
def test_univariate_pls_regression():
# Ensure 1d Y is correctly interpreted
d = load_linnerud()
X = d.data
Y = d.target
clf = pls_.PLSRegression()
# Compare 1d to column vector
model1 = clf.fit(X, Y[:, 0]).coef_
model2 = clf.fit(X, Y[:, :1]).coef_
assert_array_almost_equal(model1, model2)
def test_predict_transform_copy():
# check that the "copy" keyword works
d = load_linnerud()
X = d.data
Y = d.target
clf = pls_.PLSCanonical()
X_copy = X.copy()
Y_copy = Y.copy()
clf.fit(X, Y)
# check that results are identical with copy
assert_array_almost_equal(clf.predict(X), clf.predict(X.copy(), copy=False))
assert_array_almost_equal(clf.transform(X), clf.transform(X.copy(), copy=False))
# check also if passing Y
assert_array_almost_equal(clf.transform(X, Y),
clf.transform(X.copy(), Y.copy(), copy=False))
# check that copy doesn't destroy
# we do want to check exact equality here
assert_array_equal(X_copy, X)
assert_array_equal(Y_copy, Y)
# also check that mean wasn't zero before (to make sure we didn't touch it)
assert np.all(X.mean(axis=0) != 0)
def test_scale_and_stability():
# We test scale=True parameter
# This allows to check numerical stability over platforms as well
d = load_linnerud()
X1 = d.data
Y1 = d.target
# causes X[:, -1].std() to be zero
X1[:, -1] = 1.0
# From bug #2821
# Test with X2, T2 s.t. clf.x_score[:, 1] == 0, clf.y_score[:, 1] == 0
# This test robustness of algorithm when dealing with value close to 0
X2 = np.array([[0., 0., 1.],
[1., 0., 0.],
[2., 2., 2.],
[3., 5., 4.]])
Y2 = np.array([[0.1, -0.2],
[0.9, 1.1],
[6.2, 5.9],
[11.9, 12.3]])
for (X, Y) in [(X1, Y1), (X2, Y2)]:
X_std = X.std(axis=0, ddof=1)
X_std[X_std == 0] = 1
Y_std = Y.std(axis=0, ddof=1)
Y_std[Y_std == 0] = 1
X_s = (X - X.mean(axis=0)) / X_std
Y_s = (Y - Y.mean(axis=0)) / Y_std
for clf in [CCA(), pls_.PLSCanonical(), pls_.PLSRegression(),
pls_.PLSSVD()]:
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X, Y)
clf.set_params(scale=False)
X_s_score, Y_s_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
# Scaling should be idempotent
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
def test_pls_errors():
d = load_linnerud()
X = d.data
Y = d.target
for clf in [pls_.PLSCanonical(), pls_.PLSRegression(),
pls_.PLSSVD()]:
clf.n_components = 4
assert_raise_message(ValueError, "Invalid number of components",
clf.fit, X, Y)
def test_pls_scaling():
# sanity check for scale=True
n_samples = 1000
n_targets = 5
n_features = 10
rng = check_random_state(0)
Q = rng.randn(n_targets, n_features)
Y = rng.randn(n_samples, n_targets)
X = np.dot(Y, Q) + 2 * rng.randn(n_samples, n_features) + 1
X *= 1000
X_scaled = StandardScaler().fit_transform(X)
pls = pls_.PLSRegression(n_components=5, scale=True)
pls.fit(X, Y)
score = pls.score(X, Y)
pls.fit(X_scaled, Y)
score_scaled = pls.score(X_scaled, Y)
assert_approx_equal(score, score_scaled)