"""
The :mod:`sklearn.kernel_approximation` module implements several
approximate kernel feature maps base on Fourier transforms.
"""
# Author: Andreas Mueller <amueller@ais.uni-bonn.de>
#
# License: BSD 3 clause
import warnings
import numpy as np
import scipy.sparse as sp
from scipy.linalg import svd
from .base import BaseEstimator
from .base import TransformerMixin
from .utils import check_array, check_random_state, as_float_array
from .utils.extmath import safe_sparse_dot
from .utils.validation import check_is_fitted
from .metrics.pairwise import pairwise_kernels, KERNEL_PARAMS
from .utils.validation import check_non_negative, _deprecate_positional_args
class RBFSampler(TransformerMixin, BaseEstimator):
"""Approximates feature map of an RBF kernel by Monte Carlo approximation
of its Fourier transform.
It implements a variant of Random Kitchen Sinks.[1]
Read more in the :ref:`User Guide <rbf_kernel_approx>`.
Parameters
----------
gamma : float
Parameter of RBF kernel: exp(-gamma * x^2)
n_components : int
Number of Monte Carlo samples per original feature.
Equals the dimensionality of the computed feature space.
random_state : int, RandomState instance or None, optional (default=None)
Pseudo-random number generator to control the generation of the random
weights and random offset when fitting the training data.
Pass an int for reproducible output across multiple function calls.
See :term:`Glossary <random_state>`.
Attributes
----------
random_offset_ : ndarray of shape (n_components,), dtype=float64
Random offset used to compute the projection in the `n_components`
dimensions of the feature space.
random_weights_ : ndarray of shape (n_features, n_components),\
dtype=float64
Random projection directions drawn from the Fourier transform
of the RBF kernel.
Examples
--------
>>> from sklearn.kernel_approximation import RBFSampler
>>> from sklearn.linear_model import SGDClassifier
>>> X = [[0, 0], [1, 1], [1, 0], [0, 1]]
>>> y = [0, 0, 1, 1]
>>> rbf_feature = RBFSampler(gamma=1, random_state=1)
>>> X_features = rbf_feature.fit_transform(X)
>>> clf = SGDClassifier(max_iter=5, tol=1e-3)
>>> clf.fit(X_features, y)
SGDClassifier(max_iter=5)
>>> clf.score(X_features, y)
1.0
Notes
-----
See "Random Features for Large-Scale Kernel Machines" by A. Rahimi and
Benjamin Recht.
[1] "Weighted Sums of Random Kitchen Sinks: Replacing
minimization with randomization in learning" by A. Rahimi and
Benjamin Recht.
(https://people.eecs.berkeley.edu/~brecht/papers/08.rah.rec.nips.pdf)
"""
@_deprecate_positional_args
def __init__(self, *, gamma=1., n_components=100, random_state=None):
self.gamma = gamma
self.n_components = n_components
self.random_state = random_state
def fit(self, X, y=None):
"""Fit the model with X.
Samples random projection according to n_features.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Training data, where n_samples in the number of samples
and n_features is the number of features.
Returns
-------
self : object
Returns the transformer.
"""
X = self._validate_data(X, accept_sparse='csr')
random_state = check_random_state(self.random_state)
n_features = X.shape[1]
self.random_weights_ = (np.sqrt(2 * self.gamma) * random_state.normal(
size=(n_features, self.n_components)))
self.random_offset_ = random_state.uniform(0, 2 * np.pi,
size=self.n_components)
return self
def transform(self, X):
"""Apply the approximate feature map to X.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
New data, where n_samples in the number of samples
and n_features is the number of features.
Returns
-------
X_new : array-like, shape (n_samples, n_components)
"""
check_is_fitted(self)
X = check_array(X, accept_sparse='csr')
projection = safe_sparse_dot(X, self.random_weights_)
projection += self.random_offset_
np.cos(projection, projection)
projection *= np.sqrt(2.) / np.sqrt(self.n_components)
return projection
class SkewedChi2Sampler(TransformerMixin, BaseEstimator):
"""Approximates feature map of the "skewed chi-squared" kernel by Monte
Carlo approximation of its Fourier transform.
Read more in the :ref:`User Guide <skewed_chi_kernel_approx>`.
Parameters
----------
skewedness : float
"skewedness" parameter of the kernel. Needs to be cross-validated.
n_components : int
number of Monte Carlo samples per original feature.
Equals the dimensionality of the computed feature space.
random_state : int, RandomState instance or None, optional (default=None)
Pseudo-random number generator to control the generation of the random
weights and random offset when fitting the training data.
Pass an int for reproducible output across multiple function calls.
See :term:`Glossary <random_state>`.
Examples
--------
>>> from sklearn.kernel_approximation import SkewedChi2Sampler
>>> from sklearn.linear_model import SGDClassifier
>>> X = [[0, 0], [1, 1], [1, 0], [0, 1]]
>>> y = [0, 0, 1, 1]
>>> chi2_feature = SkewedChi2Sampler(skewedness=.01,
... n_components=10,
... random_state=0)
>>> X_features = chi2_feature.fit_transform(X, y)
>>> clf = SGDClassifier(max_iter=10, tol=1e-3)
>>> clf.fit(X_features, y)
SGDClassifier(max_iter=10)
>>> clf.score(X_features, y)
1.0
References
----------
See "Random Fourier Approximations for Skewed Multiplicative Histogram
Kernels" by Fuxin Li, Catalin Ionescu and Cristian Sminchisescu.
See also
--------
AdditiveChi2Sampler : A different approach for approximating an additive
variant of the chi squared kernel.
sklearn.metrics.pairwise.chi2_kernel : The exact chi squared kernel.
"""
@_deprecate_positional_args
def __init__(self, *, skewedness=1., n_components=100, random_state=None):
self.skewedness = skewedness
self.n_components = n_components
self.random_state = random_state
def fit(self, X, y=None):
"""Fit the model with X.
Samples random projection according to n_features.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Training data, where n_samples in the number of samples
and n_features is the number of features.
Returns
-------
self : object
Returns the transformer.
"""
X = self._validate_data(X)
random_state = check_random_state(self.random_state)
n_features = X.shape[1]
uniform = random_state.uniform(size=(n_features, self.n_components))
# transform by inverse CDF of sech
self.random_weights_ = (1. / np.pi
* np.log(np.tan(np.pi / 2. * uniform)))
self.random_offset_ = random_state.uniform(0, 2 * np.pi,
size=self.n_components)
return self
def transform(self, X):
"""Apply the approximate feature map to X.
Parameters
----------
X : array-like, shape (n_samples, n_features)
New data, where n_samples in the number of samples
and n_features is the number of features. All values of X must be
strictly greater than "-skewedness".
Returns
-------
X_new : array-like, shape (n_samples, n_components)
"""
check_is_fitted(self)
X = as_float_array(X, copy=True)
X = check_array(X, copy=False)
if (X <= -self.skewedness).any():
raise ValueError("X may not contain entries smaller than"
" -skewedness.")
X += self.skewedness
np.log(X, X)
projection = safe_sparse_dot(X, self.random_weights_)
projection += self.random_offset_
np.cos(projection, projection)
projection *= np.sqrt(2.) / np.sqrt(self.n_components)
return projection
class AdditiveChi2Sampler(TransformerMixin, BaseEstimator):
"""Approximate feature map for additive chi2 kernel.
Uses sampling the fourier transform of the kernel characteristic
at regular intervals.
Since the kernel that is to be approximated is additive, the components of
the input vectors can be treated separately. Each entry in the original
space is transformed into 2*sample_steps+1 features, where sample_steps is
a parameter of the method. Typical values of sample_steps include 1, 2 and
3.
Optimal choices for the sampling interval for certain data ranges can be
computed (see the reference). The default values should be reasonable.
Read more in the :ref:`User Guide <additive_chi_kernel_approx>`.
Parameters
----------
sample_steps : int, optional
Gives the number of (complex) sampling points.
sample_interval : float, optional
Sampling interval. Must be specified when sample_steps not in {1,2,3}.
Attributes
----------
sample_interval_ : float
Stored sampling interval. Specified as a parameter if sample_steps not
in {1,2,3}.
Examples
--------
>>> from sklearn.datasets import load_digits
>>> from sklearn.linear_model import SGDClassifier
>>> from sklearn.kernel_approximation import AdditiveChi2Sampler
>>> X, y = load_digits(return_X_y=True)
>>> chi2sampler = AdditiveChi2Sampler(sample_steps=2)
>>> X_transformed = chi2sampler.fit_transform(X, y)
>>> clf = SGDClassifier(max_iter=5, random_state=0, tol=1e-3)
>>> clf.fit(X_transformed, y)
SGDClassifier(max_iter=5, random_state=0)
>>> clf.score(X_transformed, y)
0.9499...
Notes
-----
This estimator approximates a slightly different version of the additive
chi squared kernel then ``metric.additive_chi2`` computes.
See also
--------
SkewedChi2Sampler : A Fourier-approximation to a non-additive variant of
the chi squared kernel.
sklearn.metrics.pairwise.chi2_kernel : The exact chi squared kernel.
sklearn.metrics.pairwise.additive_chi2_kernel : The exact additive chi
squared kernel.
References
----------
See `"Efficient additive kernels via explicit feature maps"
<http://www.robots.ox.ac.uk/~vedaldi/assets/pubs/vedaldi11efficient.pdf>`_
A. Vedaldi and A. Zisserman, Pattern Analysis and Machine Intelligence,
2011
"""
@_deprecate_positional_args
def __init__(self, *, sample_steps=2, sample_interval=None):
self.sample_steps = sample_steps
self.sample_interval = sample_interval
def fit(self, X, y=None):
"""Set the parameters
Parameters
----------
X : array-like, shape (n_samples, n_features)
Training data, where n_samples in the number of samples
and n_features is the number of features.
Returns
-------
self : object
Returns the transformer.
"""
X = self._validate_data(X, accept_sparse='csr')
check_non_negative(X, 'X in AdditiveChi2Sampler.fit')
if self.sample_interval is None:
# See reference, figure 2 c)
if self.sample_steps == 1:
Loading ...