这篇博客介绍了如何利用Anaconda中的sklearn模块进行数据预处理，包括初始化、缺失值处理、标签编码等步骤。
sklearn preprocessing代码
代码来自Anaconda软件里sklearn模块
init.py
"""
The :mod:`sklearn.preprocessing` module includes scaling, centering,
normalization, binarization and imputation methods.
"""
from .data import Binarizer
from .data import KernelCenterer
from .data import MinMaxScaler
from .data import Normalizer
from .data import StandardScaler
from .data import add_dummy_feature
from .data import binarize
from .data import normalize
from .data import scale
from .data import OneHotEncoder
from .data import PolynomialFeatures
from .label import label_binarize
from .label import LabelBinarizer
from .label import LabelEncoder
from .label import MultiLabelBinarizer
from .imputation import Imputer
__all__ = [
'Binarizer',
'Imputer',
'KernelCenterer',
'LabelBinarizer',
'LabelEncoder',
'MultiLabelBinarizer',
'MinMaxScaler',
'Normalizer',
'OneHotEncoder',
'StandardScaler',
'add_dummy_feature',
'PolynomialFeatures',
'binarize',
'normalize',
'scale',
'label_binarize',
]
_weights.py
import numpy as np
from ..utils.fixes import bincount
def _balance_weights(y):
"""Compute sample weights such that the class distribution of y becomes
balanced.
Parameters
----------
y : array-like
Labels for the samples.
Returns
-------
weights : array-like
The sample weights.
"""
y = np.asarray(y)
y = np.searchsorted(np.unique(y), y)
bins = bincount(y)
weights = 1. / bins.take(y)
weights *= bins.min()
return weights
data.py
# Authors: Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Mathieu Blondel <mathieu@mblondel.org>
# Olivier Grisel <olivier.grisel@ensta.org>
# Andreas Mueller <amueller@ais.uni-bonn.de>
# Eric Martin <eric@ericmart.in>
# License: BSD 3 clause
from itertools import chain, combinations
import numbers
import warnings
import numpy as np
from scipy import sparse
from ..base import BaseEstimator, TransformerMixin
from ..externals import six
from ..utils import check_array
from ..utils import warn_if_not_float
from ..utils.extmath import row_norms
from ..utils.fixes import (combinations_with_replacement as combinations_w_r,
bincount)
from ..utils.fixes import isclose
from ..utils.sparsefuncs_fast import (inplace_csr_row_normalize_l1,
inplace_csr_row_normalize_l2)
from ..utils.sparsefuncs import (inplace_column_scale, mean_variance_axis)
from ..utils.validation import check_is_fitted
zip = six.moves.zip
map = six.moves.map
range = six.moves.range
__all__ = [
'Binarizer',
'KernelCenterer',
'MinMaxScaler',
'Normalizer',
'OneHotEncoder',
'StandardScaler',
'add_dummy_feature',
'binarize',
'normalize',
'scale',
]
def _mean_and_std(X, axis=0, with_mean=True, with_std=True):
"""Compute mean and std deviation for centering, scaling.
Zero valued std components are reset to 1.0 to avoid NaNs when scaling.
"""
X = np.asarray(X)
Xr = np.rollaxis(X, axis)
if with_mean:
mean_ = Xr.mean(axis=0)
else:
mean_ = None
if with_std:
std_ = Xr.std(axis=0)
if isinstance(std_, np.ndarray):
std_[std_ == 0.] = 1.0
elif std_ == 0.:
std_ = 1.
else:
std_ = None
return mean_, std_
def scale(X, axis=0, with_mean=True, with_std=True, copy=True):
"""Standardize a dataset along any axis
Center to the mean and component wise scale to unit variance.
Parameters
----------
X : array-like or CSR matrix.
The data to center and scale.
axis : int (0 by default)
axis used to compute the means and standard deviations along. If 0,
independently standardize each feature, otherwise (if 1) standardize
each sample.
with_mean : boolean, True by default
If True, center the data before scaling.
with_std : boolean, True by default
If True, scale the data to unit variance (or equivalently,
unit standard deviation).
copy : boolean, optional, default True
set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix and if axis is 1).
Notes
-----
This implementation will refuse to center scipy.sparse matrices
since it would make them non-sparse and would potentially crash the
program with memory exhaustion problems.
Instead the caller is expected to either set explicitly
`with_mean=False` (in that case, only variance scaling will be
performed on the features of the CSR matrix) or to call `X.toarray()`
if he/she expects the materialized dense array to fit in memory.
To avoid memory copy the caller should pass a CSR matrix.
See also
--------
:class:`sklearn.preprocessing.StandardScaler` to perform centering and
scaling using the ``Transformer`` API (e.g. as part of a preprocessing
:class:`sklearn.pipeline.Pipeline`)
"""
X = check_array(X, accept_sparse='csr', copy=copy, ensure_2d=False)
warn_if_not_float(X, estimator='The scale function')
if sparse.issparse(X):
if with_mean:
raise ValueError(
"Cannot center sparse matrices: pass `with_mean=False` instead"
" See docstring for motivation and alternatives.")
if axis != 0:
raise ValueError("Can only scale sparse matrix on axis=0, "
" got axis=%d" % axis)
if not sparse.isspmatrix_csr(X):
X = X.tocsr()
copy = False
if copy:
X = X.copy()
_, var = mean_variance_axis(X, axis=0)
var[var == 0.0] = 1.0
inplace_column_scale(X, 1 / np.sqrt(var))
else:
X = np.asarray(X)
mean_, std_ = _mean_and_std(
X, axis, with_mean=with_mean, with_std=with_std)
if copy:
X = X.copy()
# Xr is a view on the original array that enables easy use of
# broadcasting on the axis in which we are interested in
Xr = np.rollaxis(X, axis)
if with_mean:
Xr -= mean_
mean_1 = Xr.mean(axis=0)
# Verify that mean_1 is 'close to zero'. If X contains very
# large values, mean_1 can also be very large, due to a lack of
# precision of mean_. In this case, a pre-scaling of the
# concerned feature is efficient, for instance by its mean or
# maximum.
if not np.allclose(mean_1, 0):
warnings.warn("Numerical issues were encountered "
"when centering the data "
"and might not be solved. Dataset may "
"contain too large values. You may need "
"to prescale your features.")
Xr -= mean_1
if with_std:
Xr /= std_
if with_mean:
mean_2 = Xr.mean(axis=0)
# If mean_2 is not 'close to zero', it comes from the fact that
# std_ is very small so that mean_2 = mean_1/std_ > 0, even if
# mean_1 was close to zero. The problem is thus essentially due
# to the lack of precision of mean_. A solution is then to
# substract the mean again:
if not np.allclose(mean_2, 0):
warnings.warn("Numerical issues were encountered "
"when scaling the data "
"and might not be solved. The standard "
"deviation of the data is probably "
"very close to 0. ")
Xr -= mean_2
return X
class MinMaxScaler(BaseEstimator, TransformerMixin):
"""Standardizes features by scaling each feature to a given range.
This estimator scales and translates each feature individually such
that it is in the given range on the training set, i.e. between
zero and one.
The standardization is given by::
X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0))
X_scaled = X_std * (max - min) + min
where min, max = feature_range.
This standardization is often used as an alternative to zero mean,
unit variance scaling.
Parameters
----------
feature_range: tuple (min, max), default=(0, 1)
Desired range of transformed data.
copy : boolean, optional, default True
Set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array).
Attributes
----------
min_ : ndarray, shape (n_features,)
Per feature adjustment for minimum.
scale_ : ndarray, shape (n_features,)
Per feature relative scaling of the data.
"""
def __init__(self, feature_range=(0, 1), copy=True):
self.feature_range = feature_range
self.copy = copy
def fit(self, X, y=None):
"""Compute the minimum and maximum to be used for later scaling.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data used to compute the per-feature minimum and maximum
used for later scaling along the features axis.
"""
X = check_array(X, copy=self.copy, ensure_2d=False)
warn_if_not_float(X, estimator=self)
feature_range = self.feature_range
if feature_range[0] >= feature_range[1]:
raise ValueError("Minimum of desired feature range must be smaller"
" than maximum. Got %s." % str(feature_range))
data_min = np.min(X, axis=0)
data_range = np.max(X, axis=0) - data_min
# Do not scale constant features
if isinstance(data_range, np.ndarray):
data_range[data_range == 0.0] = 1.0
elif data_range == 0.:
data_range = 1.
self.scale_ = (feature_range[1] - feature_range[0]) / data_range
self.min_ = feature_range[0] - data_min * self.scale_
self.data_range = data_range
self.data_min = data_min
return self
def transform(self, X):
"""Scaling features of X according to feature_range.
Parameters
----------
X : array-like with shape [n_samples, n_features]
Input data that will be transformed.
"""
check_is_fitted(self, 'scale_')
X = check_array(X, copy=self.copy, ensure_2d=False)
X *= self.scale_
X += self.min_
return X
def inverse_transform(self, X):
"""Undo the scaling of X according to feature_range.
Parameters
----------
X : array-like with shape [n_samples, n_features]
Input data that will be transformed.
"""
check_is_fitted(self, 'scale_')
X = check_array(X, copy=self.copy, ensure_2d=False)
X -= self.min_
X /= self.scale_
return X
class StandardScaler(BaseEstimator, TransformerMixin):
"""Standardize features by removing the mean and scaling to unit variance
Centering and scaling happen independently on each feature by computing
the relevant statistics on the samples in the training set. Mean and
standard deviation are then stored to be used on later data using the
`transform` method.
Standardization of a dataset is a common requirement for many
machine learning estimators: they might behave badly if the
individual feature do not more or less look like standard normally
distributed data (e.g. Gaussian with 0 mean and unit variance).
For instance many elements used in the objective function of
a learning algorithm (such as the RBF kernel of Support Vector
Machines or the L1 and L2 regularizers of linear models) assume that
all features are centered around 0 and have variance in the same
order. If a feature has a variance that is orders of magnitude larger
that others, it might dominate the objective function and make the
estimator unable to learn from other features correctly as expected.
Parameters
----------
with_mean : boolean, True by default
If True, center the data before scaling.
This does not work (and will raise an exception) when attempted on
sparse matrices, because centering them entails building a dense
matrix which in common use cases is likely to be too large to fit in
memory.
with_std : boolean, True by default
If True, scale the data to unit variance (or equivalently,
unit standard deviation).
copy : boolean, optional, default True
If False, try to avoid a copy and do inplace scaling instead.
This is not guaranteed to always work inplace; e.g. if the data is
not a NumPy array or scipy.sparse CSR matrix, a copy may still be
returned.
Attributes
----------
mean_ : array of floats with shape [n_features]
The mean value for each feature in the training set.
std_ : array of floats with shape [n_features]
The standard deviation for each feature in the training set.
See also
--------
:func:`sklearn.preprocessing.scale` to perform centering and
scaling without using the ``Transformer`` object oriented API
:class:`sklearn.decomposition.RandomizedPCA` with `whiten=True`
to further remove the linear correlation across features.
"""
def __init__(self, copy=True, with_mean=True, with_std=True):
self.with_mean = with_mean
self.with_std = with_std
self.copy = copy
def fit(self, X, y=None):
"""Compute the mean and std to be used for later scaling.
Parameters
----------
X : array-like or CSR matrix with shape [n_samples, n_features]
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
"""
X = check_array(X, accept_sparse='csr', copy=self.copy,
ensure_2d=False)
if warn_if_not_float(X, estimator=self):
X = X.astype(np.float)
if sparse.issparse(X):
if self.with_mean:
raise ValueError(
"Cannot center sparse matrices: pass `with_mean=False` "
"instead. See docstring for motivation and alternatives.")
self.mean_ = None
if self.with_std:
var = mean_variance_axis(X, axis=0)[1]
self.std_ = np.sqrt(var)
self.std_[var == 0.0] = 1.0
else:
self.std_ = None
return self
else:
self.mean_, self.std_ = _mean_and_std(
X, axis=0, with_mean=self.with_mean, with_std=self.with_std)
return self
def transform(self, X, y=None, copy=None):
"""Perform standardization by centering and scaling
Parameters
----------
X : array-like with shape [n_samples, n_features]
The data used to scale along the features axis.
"""
check_is_fitted(self, 'std_')
copy = copy if copy is not None else self.copy
X = check_array(X, accept_sparse='csr', copy=copy, ensure_2d=False)
if warn_if_not_float(X, estimator=self):
X = X.astype(np.float)
if sparse.issparse(X):
if self.with_mean:
raise ValueError(
"Cannot center sparse matrices: pass `with_mean=False` "
"instead. See docstring for motivation and alternatives.")
if self.std_ is not None:
inplace_column_scale(X, 1 / self.std_)
else:
if self.with_mean:
X -= self.mean_
if self.with_std:
X /= self.std_
return X
def inverse_transform(self, X, copy=None):
"""Scale back the data to the original representation
Parameters
----------
X : array-like with shape [n_samples, n_features]
The data used to scale along the features axis.
"""
check_is_fitted(self, 'std_')
copy = copy if copy is not None else self.copy
if sparse.issparse(X):
if self.with_mean:
raise ValueError(
"Cannot uncenter sparse matrices: pass `with_mean=False` "
"instead See docstring for motivation and alternatives.")
if not sparse.isspmatrix_csr(X):
X = X.tocsr()
copy = False
if copy:
X = X.copy()
if self.std_ is not None:
inplace_column_scale(X, self.std_)
else:
X = np.asarray(X)
if copy:
X = X.copy()
if self.with_std:
X *= self.std_
if self.with_mean:
X += self.mean_
return X
class PolynomialFeatures(BaseEstimator, TransformerMixin):
"""Generate polynomial and interaction features.
Generate a new feature matrix consisting of all polynomial combinations
of the features with degree less than or equal to the specified degree.
For example, if an input sample is two dimensional and of the form
[a, b], the degree-2 polynomial features are [1, a, b, a^2, ab, b^2].
Parameters
----------
degree : integer
The degree of the polynomial features. Default = 2.
interaction_only : boolean, default = False
If true, only interaction features are produced: features that are
products of at most ``degree`` *distinct* input features (so not
``x[1] ** 2``, ``x[0] * x[2] ** 3``, etc.).
include_bias : boolean
If True (default), then include a bias column, the feature in which
all polynomial powers are zero (i.e. a column of ones - acts as an
intercept term in a linear model).
Examples
--------
>>> X = np.arange(6).reshape(3, 2)
>>> X
array([[0, 1],
[2, 3],
[4, 5]])
>>> poly = PolynomialFeatures(2)
>>> poly.fit_transform(X)
array([[ 1, 0, 1, 0, 0, 1],
[ 1, 2, 3, 4, 6, 9],
[ 1, 4, 5, 16, 20, 25]])
>>> poly = PolynomialFeatures(interaction_only=True)
>>> poly.fit_transform(X)
array([[ 1, 0, 1, 0],
[ 1, 2, 3, 6],
[ 1, 4, 5, 20]])
Attributes
----------
powers_ : array, shape (n_input_features, n_output_features)
powers_[i, j] is the exponent of the jth input in the ith output.
n_input_features_ : int
The total number of input features.
n_output_features_ : int
The total number of polynomial output features. The number of output
features is computed by iterating over all suitably sized combinations
of input features.
Notes
-----
Be aware that the number of features in the output array scales
polynomially in the number of features of the input array, and
exponentially in the degree. High degrees can cause overfitting.
See :ref:`examples/linear_model/plot_polynomial_interpolation.py
<example_linear_model_plot_polynomial_interpolation.py>`
"""
def __init__(self, degree=2, interaction_only=False, include_bias=True):
self.degree = degree
self.interaction_only = interaction_only
self.include_bias = include_bias
@staticmethod
def _combinations(n_features, degree, interaction_only, include_bias):
comb = (combinations if interaction_only else combinations_w_r)
start = int(not include_bias)
return chain.from_iterable(comb(range(n_features), i)
for i in range(start, degree + 1))
@property
def powers_(self):
check_is_fitted(self, 'n_input_features_')
combinations = self._combinations(self.n_input_features_, self.degree,
self.interaction_only,
self.include_bias)
return np.vstack(np.bincount(c, minlength=self.n_input_features_)
for c in combinations)
def fit(self, X, y=None):
"""
Compute number of output features.
"""
n_samples, n_features = check_array(X).shape
combinations = self._combinations(n_features, self.degree,
self.interaction_only,
self.include_bias)
self.n_input_features_ = n_features
self.n_output_features_ = sum(1 for _ in combinations)
return self
def transform(self, X, y=None):
"""Transform data to polynomial features
Parameters
----------
X : array with shape [n_samples, n_features]
The data to transform, row by row.
Returns
-------
XP : np.ndarray shape [n_samples, NP]
The matrix of features, where NP is the number of polynomial
features generated from the combination of inputs.
"""
check_is_fitted(self, ['n_input_features_', 'n_output_features_'])
X = check_array(X)
n_samples, n_features = X.shape
if n_features != self.n_input_features_:
raise ValueError("X shape does not match training shape")
# allocate output data
XP = np.empty((n_samples, self.n_output_features_), dtype=X.dtype)
combinations = self._combinations(n_features, self.degree,
self.interaction_only,
self.include_bias)
for i, c in enumerate(combinations):
XP[:, i] = X[:, c].prod(1)
return XP
def normalize(X, norm='l2', axis=1, copy=True):
"""Scale input vectors individually to unit norm (vector length).
Parameters
----------
X : array or scipy.sparse matrix with shape [n_samples, n_features]
The data to normalize, element by element.
scipy.sparse matrices should be in CSR format to avoid an
un-necessary copy.
norm : 'l1' or 'l2', optional ('l2' by default)
The norm to use to normalize each non zero sample (or each non-zero
feature if axis is 0).
axis : 0 or 1, optional (1 by default)
axis used to normalize the data along. If 1, independently normalize
each sample, otherwise (if 0) normalize each feature.
copy : boolean, optional, default True
set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix and if axis is 1).
See also
--------
:class:`sklearn.preprocessing.Normalizer` to perform normalization
using the ``Transformer`` API (e.g. as part of a preprocessing
:class:`sklearn.pipeline.Pipeline`)
"""
if norm not in ('l1', 'l2'):
raise ValueError("'%s' is not a supported norm" % norm)
if axis == 0:
sparse_format = 'csc'
elif axis == 1:
sparse_format = 'csr'
else:
raise ValueError("'%d' is not a supported axis" % axis)
X = check_array(X, sparse_format, copy=copy)
warn_if_not_float(X, 'The normalize function')
if axis == 0:
X = X.T
if sparse.issparse(X):
if norm == 'l1':
inplace_csr_row_normalize_l1(X)
elif norm == 'l2':
inplace_csr_row_normalize_l2(X)
else:
if norm == 'l1':
norms = np.abs(X).sum(axis=1)
norms[norms == 0.0] = 1.0
elif norm == 'l2':
norms = row_norms(X)
norms[norms == 0.0] = 1.0
X /= norms[:, np.newaxis]
if axis == 0:
X = X.T
return X
class Normalizer(BaseEstimator, TransformerMixin):
"""Normalize samples individually to unit norm.
Each sample (i.e. each row of the data matrix) with at least one
non zero component is rescaled independently of other samples so
that its norm (l1 or l2) equals one.
This transformer is able to work both with dense numpy arrays and
scipy.sparse matrix (use CSR format if you want to avoid the burden of
a copy / conversion).
Scaling inputs to unit norms is a common operation for text
classification or clustering for instance. For instance the dot
product of two l2-normalized TF-IDF vectors is the cosine similarity
of the vectors and is the base similarity metric for the Vector
Space Model commonly used by the Information Retrieval community.
Parameters
----------
norm : 'l1' or 'l2', optional ('l2' by default)
The norm to use to normalize each non zero sample.
copy : boolean, optional, default True
set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix).
Notes
-----
This estimator is stateless (besides constructor parameters), the
fit method does nothing but is useful when used in a pipeline.
See also
--------
:func:`sklearn.preprocessing.normalize` equivalent function
without the object oriented API
"""
def __init__(self, norm='l2', copy=True):
self.norm = norm
self.copy = copy
def fit(self, X, y=None):
"""Do nothing and return the estimator unchanged
This method is just there to implement the usual API and hence
work in pipelines.
"""
X = check_array(X, accept_sparse='csr')
return self
def transform(self, X, y=None, copy=None):
"""Scale each non zero row of X to unit norm
Parameters
----------
X : array or scipy.sparse matrix with shape [n_samples, n_features]
The data to normalize, row by row. scipy.sparse matrices should be
in CSR format to avoid an un-necessary copy.
"""
copy = copy if copy is not None else self.copy
X = check_array(X, accept_sparse='csr')
return normalize(X, norm=self.norm, axis=1, copy=copy)
def binarize(X, threshold=0.0, copy=True):
"""Boolean thresholding of array-like or scipy.sparse matrix
Parameters
----------
X : array or scipy.sparse matrix with shape [n_samples, n_features]
The data to binarize, element by element.
scipy.sparse matrices should be in CSR or CSC format to avoid an
un-necessary copy.
threshold : float, optional (0.0 by default)
Feature values below or equal to this are replaced by 0, above it by 1.
Threshold may not be less than 0 for operations on sparse matrices.
copy : boolean, optional, default True
set to False to perform inplace binarization and avoid a copy
(if the input is already a numpy array or a scipy.sparse CSR / CSC
matrix and if axis is 1).
See also
--------
:class:`sklearn.preprocessing.Binarizer` to perform binarization
using the ``Transformer`` API (e.g. as part of a preprocessing
:class:`sklearn.pipeline.Pipeline`)
"""
X = check_array(X, accept_sparse=['csr', 'csc'], copy=copy)
if sparse.issparse(X):
if threshold < 0:
raise ValueError('Cannot binarize a sparse matrix with threshold '
'< 0')
cond = X.data > threshold
not_cond = np.logical_not(cond)
X.data[cond] = 1
X.data[not_cond] = 0
X.eliminate_zeros()
else:
cond = X > threshold
not_cond = np.logical_not(cond)
X[cond] = 1
X[not_cond] = 0
return X
class Binarizer(BaseEstimator, TransformerMixin):
"""Binarize data (set feature values to 0 or 1) according to a threshold
Values greater than the threshold map to 1, while values less than
or equal to the threshold map to 0. With the default threshold of 0,
only positive values map to 1.
Binarization is a common operation on text count data where the
analyst can decide to only consider the presence or absence of a
feature rather than a quantified number of occurrences for instance.
It can also be used as a pre-processing step for estimators that
consider boolean random variables (e.g. modelled using the Bernoulli
distribution in a Bayesian setting).
Parameters
----------
threshold : float, optional (0.0 by default)
Feature values below or equal to this are replaced by 0, above it by 1.
Threshold may not be less than 0 for operations on sparse matrices.
copy : boolean, optional, default True
set to False to perform inplace binarization and avoid a copy (if
the input is already a numpy array or a scipy.sparse CSR matrix).
Notes
-----
If the input is a sparse matrix, only the non-zero values are subject
to update by the Binarizer class.
This estimator is stateless (besides constructor parameters), the
fit method does nothing but is useful when used in a pipeline.
"""
def __init__(self, threshold=0.0, copy=True):
self.threshold = threshold
self.copy = copy
def fit(self, X, y=None):
"""Do nothing and return the estimator unchanged
This method is just there to implement the usual API and hence
work in pipelines.
"""
check_array(X, accept_sparse='csr')
return self
def transform(self, X, y=None, copy=None):
"""Binarize each element of X
Parameters
----------
X : array or scipy.sparse matrix with shape [n_samples, n_features]
The data to binarize, element by element.
scipy.sparse matrices should be in CSR format to avoid an
un-necessary copy.
"""
copy = copy if copy is not None else self.copy
return binarize(X, threshold=self.threshold, copy=copy)
class KernelCenterer(BaseEstimator, TransformerMixin):
"""Center a kernel matrix
Let K(x, z) be a kernel defined by phi(x)^T phi(z), where phi is a
function mapping x to a Hilbert space. KernelCenterer centers (i.e.,
normalize to have zero mean) the data without explicitly computing phi(x).
It is equivalent to centering phi(x) with
sklearn.preprocessing.StandardScaler(with_std=False).
"""
def fit(self, K, y=None):
"""Fit KernelCenterer
Parameters
----------
K : numpy array of shape [n_samples, n_samples]
Kernel matrix.
Returns
-------
self : returns an instance of self.
"""
K = check_array(K)
n_samples = K.shape[0]
self.K_fit_rows_ = np.sum(K, axis=0) / n_samples
self.K_fit_all_ = self.K_fit_rows_.sum() / n_samples
return self
def transform(self, K, y=None, copy=True):
"""Center kernel matrix.
Parameters
----------
K : numpy array of shape [n_samples1, n_samples2]
Kernel matrix.
copy : boolean, optional, default True
Set to False to perform inplace computation.
Returns
-------
K_new : numpy array of shape [n_samples1, n_samples2]
"""
check_is_fitted(self, 'K_fit_all_')
K = check_array(K)
if copy:
K = K.copy()
K_pred_cols = (np.sum(K, axis=1) /
self.K_fit_rows_.shape[0])[:, np.newaxis]
K -= self.K_fit_rows_
K -= K_pred_cols
K += self.K_fit_all_
return K
def add_dummy_feature(X, value=1.0):
"""Augment dataset with an additional dummy feature.
This is useful for fitting an intercept term with implementations which
cannot otherwise fit it directly.
Parameters
----------
X : array or scipy.sparse matrix with shape [n_samples, n_features]
Data.
value : float
Value to use for the dummy feature.
Returns
-------
X : array or scipy.sparse matrix with shape [n_samples, n_features + 1]
Same data with dummy feature added as first column.
Examples
--------
>>> from sklearn.preprocessing import add_dummy_feature
>>> add_dummy_feature([[0, 1], [1, 0]])
array([[ 1., 0., 1.],
[ 1., 1., 0.]])
"""
X = check_array(X, accept_sparse=['csc', 'csr', 'coo'])
n_samples, n_features = X.shape
shape = (n_samples, n_features + 1)
if sparse.issparse(X):
if sparse.isspmatrix_coo(X):
# Shift columns to the right.
col = X.col + 1
# Column indices of dummy feature are 0 everywhere.
col = np.concatenate((np.zeros(n_samples), col))
# Row indices of dummy feature are 0, ..., n_samples-1.
row = np.concatenate((np.arange(n_samples), X.row))
# Prepend the dummy feature n_samples times.
data = np.concatenate((np.ones(n_samples) * value, X.data))
return sparse.coo_matrix((data, (row, col)), shape)
elif sparse.isspmatrix_csc(X):
# Shift index pointers since we need to add n_samples elements.
indptr = X.indptr + n_samples
# indptr[0] must be 0.
indptr = np.concatenate((np.array([0]), indptr))
# Row indices of dummy feature are 0, ..., n_samples-1.
indices = np.concatenate((np.arange(n_samples), X.indices))
# Prepend the dummy feature n_samples times.
data = np.concatenate((np.ones(n_samples) * value, X.data))
return sparse.csc_matrix((data, indices, indptr), shape)
else:
klass = X.__class__
return klass(add_dummy_feature(X.tocoo(), value))
else:
return np.hstack((np.ones((n_samples, 1)) * value, X))
def _transform_selected(X, transform, selected="all", copy=True):
"""Apply a transform function to portion of selected features
Parameters
----------
X : array-like or sparse matrix, shape=(n_samples, n_features)
Dense array or sparse matrix.
transform : callable
A callable transform(X) -> X_transformed
copy : boolean, optional
Copy X even if it could be avoided.
selected: "all" or array of indices or mask
Specify which features to apply the transform to.
Returns
-------
X : array or sparse matrix, shape=(n_samples, n_features_new)
"""
if selected == "all":
return transform(X)
X = check_array(X, accept_sparse='csc', copy=copy)
if len(selected) == 0:
return X
n_features = X.shape[1]
ind = np.arange(n_features)
sel = np.zeros(n_features, dtype=bool)
sel[np.asarray(selected)] = True
not_sel = np.logical_not(sel)
n_selected = np.sum(sel)
if n_selected == 0:
# No features selected.
return X
elif n_selected == n_features:
# All features selected.
return transform(X)
else:
X_sel = transform(X[:, ind[sel]])
X_not_sel = X[:, ind[not_sel]]
if sparse.issparse(X_sel) or sparse.issparse(X_not_sel):
return sparse.hstack((X_sel, X_not_sel))
else:
return np.hstack((X_sel, X_not_sel))
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Encode categorical integer features using a one-hot aka one-of-K scheme.
The input to this transformer should be a matrix of integers, denoting
the values taken on by categorical (discrete) features. The output will be
a sparse matrix where each column corresponds to one possible value of one
feature. It is assumed that input features take on values in the range
[0, n_values).
This encoding is needed for feeding categorical data to many scikit-learn
estimators, notably linear models and SVMs with the standard kernels.
Parameters
----------
n_values : 'auto', int or array of ints
Number of values per feature.
- 'auto' : determine value range from training data.
- int : maximum value for all features.
- array : maximum value per feature.
categorical_features: "all" or array of indices or mask
Specify what features are treated as categorical.
- 'all' (default): All features are treated as categorical.
- array of indices: Array of categorical feature indices.
- mask: Array of length n_features and with dtype=bool.
Non-categorical features are always stacked to the right of the matrix.
dtype : number type, default=np.float
Desired dtype of output.
sparse : boolean, default=True
Will return sparse matrix if set True else will return an array.
handle_unknown : str, 'error' or 'ignore'
Whether to raise an error or ignore if a unknown categorical feature is
present during transform.
Attributes
----------
active_features_ : array
Indices for active features, meaning values that actually occur
in the training set. Only available when n_values is ``'auto'``.
feature_indices_ : array of shape (n_features,)
Indices to feature ranges.
Feature ``i`` in the original data is mapped to features
from ``feature_indices_[i]`` to ``feature_indices_[i+1]``
(and then potentially masked by `active_features_` afterwards)
n_values_ : array of shape (n_features,)
Maximum number of values per feature.
Examples
--------
Given a dataset with three features and two samples, we let the encoder
find the maximum value per feature and transform the data to a binary
one-hot encoding.
>>> from sklearn.preprocessing import OneHotEncoder
>>> enc = OneHotEncoder()
>>> enc.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], \
[1, 0, 2]]) # doctest: +ELLIPSIS
OneHotEncoder(categorical_features='all', dtype=<... 'float'>,
handle_unknown='error', n_values='auto', sparse=True)
>>> enc.n_values_
array([2, 3, 4])
>>> enc.feature_indices_
array([0, 2, 5, 9])
>>> enc.transform([[0, 1, 1]]).toarray()
array([[ 1., 0., 0., 1., 0., 0., 1., 0., 0.]])
See also
--------
sklearn.feature_extraction.DictVectorizer : performs a one-hot encoding of
dictionary items (also handles string-valued features).
sklearn.feature_extraction.FeatureHasher : performs an approximate one-hot
encoding of dictionary items or strings.
"""
def __init__(self, n_values="auto", categorical_features="all",
dtype=np.float, sparse=True, handle_unknown='error'):
self.n_values = n_values
self.categorical_features = categorical_features
self.dtype = dtype
self.sparse = sparse
self.handle_unknown = handle_unknown
def fit(self, X, y=None):
"""Fit OneHotEncoder to X.
Parameters
----------
X : array-like, shape=(n_samples, n_feature)
Input array of type int.
Returns
-------
self
"""
self.fit_transform(X)
return self
def _fit_transform(self, X):
"""Assumes X contains only categorical features."""
X = check_array(X, dtype=np.int)
if np.any(X < 0):
raise ValueError("X needs to contain only non-negative integers.")
n_samples, n_features = X.shape
if self.n_values == 'auto':
n_values = np.max(X, axis=0) + 1
elif isinstance(self.n_values, numbers.Integral):
if (np.max(X, axis=0) >= self.n_values).any():
raise ValueError("Feature out of bounds for n_values=%d"
% self.n_values)
n_values = np.empty(n_features, dtype=np.int)
n_values.fill(self.n_values)
else:
try:
n_values = np.asarray(self.n_values, dtype=int)
except (ValueError, TypeError):
raise TypeError("Wrong type for parameter `n_values`. Expected"
" 'auto', int or array of ints, got %r"
% type(X))
if n_values.ndim < 1 or n_values.shape[0] != X.shape[1]:
raise ValueError("Shape mismatch: if n_values is an array,"
" it has to be of shape (n_features,).")
self.n_values_ = n_values
n_values = np.hstack([[0], n_values])
indices = np.cumsum(n_values)
self.feature_indices_ = indices
column_indices = (X + indices[:-1]).ravel()
row_indices = np.repeat(np.arange(n_samples, dtype=np.int32),
n_features)
data = np.ones(n_samples * n_features)
out = sparse.coo_matrix((data, (row_indices, column_indices)),
shape=(n_samples, indices[-1]),
dtype=self.dtype).tocsr()
if self.n_values == 'auto':
mask = np.array(out.sum(axis=0)).ravel() != 0
active_features = np.where(mask)[0]
out = out[:, active_features]
self.active_features_ = active_features
return out if self.sparse else out.toarray()
def fit_transform(self, X, y=None):
"""Fit OneHotEncoder to X, then transform X.
Equivalent to self.fit(X).transform(X), but more convenient and more
efficient. See fit for the parameters, transform for the return value.
"""
return _transform_selected(X, self._fit_transform,
self.categorical_features, copy=True)
def _transform(self, X):
"""Assumes X contains only categorical features."""
X = check_array(X, dtype=np.int)
if np.any(X < 0):
raise ValueError("X needs to contain only non-negative integers.")
n_samples, n_features = X.shape
indices = self.feature_indices_
if n_features != indices.shape[0] - 1:
raise ValueError("X has different shape than during fitting."
" Expected %d, got %d."
% (indices.shape[0] - 1, n_features))
# We use only those catgorical features of X that are known using fit.
# i.e lesser than n_values_ using mask.
# This means, if self.handle_unknown is "ignore", the row_indices and
# col_indices corresponding to the unknown categorical feature are
# ignored.
mask = (X < self.n_values_).ravel()
if np.any(~mask):
if self.handle_unknown not in ['error', 'ignore']:
raise ValueError("handle_unknown should be either error or "
"unknown got %s" % self.handle_unknown)
if self.handle_unknown == 'error':
raise ValueError("unknown categorical feature present %s "
"during transform." % X[~mask])
column_indices = (X + indices[:-1]).ravel()[mask]
row_indices = np.repeat(np.arange(n_samples, dtype=np.int32),
n_features)[mask]
data = np.ones(np.sum(mask))
out = sparse.coo_matrix((data, (row_indices, column_indices)),
shape=(n_samples, indices[-1]),
dtype=self.dtype).tocsr()
if self.n_values == 'auto':
out = out[:, self.active_features_]
return out if self.sparse else out.toarray()
def transform(self, X):
"""Transform X using one-hot encoding.
Parameters
----------
X : array-like, shape=(n_samples, n_features)
Input array of type int.
Returns
-------
X_out : sparse matrix if sparse=True else a 2-d array, dtype=int
Transformed input.
"""
return _transform_selected(X, self._transform,
self.categorical_features, copy=True)
imputation.py
# Authors: Nicolas Tresegnie <nicolas.tresegnie@gmail.com>
# License: BSD 3 clause
import warnings
import numpy as np
import numpy.ma as ma
from scipy import sparse
from scipy import stats
from ..base import BaseEstimator, TransformerMixin
from ..utils import array2d
from ..utils import atleast2d_or_csr
from ..utils import atleast2d_or_csc
from ..utils import as_float_array
from ..utils.fixes import astype
from ..externals import six
zip = six.moves.zip
map = six.moves.map
__all__ = [
'Imputer',
]
def _get_mask(X, value_to_mask):
"""Compute the boolean mask X == missing_values."""
if value_to_mask == "NaN" or np.isnan(value_to_mask):
return np.isnan(X)
else:
return X == value_to_mask
def _get_median(data, n_zeros):
"""Compute the median of data with n_zeros additional zeros.
This function is used to support sparse matrices; it modifies data in-place
"""
n_elems = len(data) + n_zeros
if not n_elems:
return np.nan
n_negative = np.count_nonzero(data < 0)
middle, is_odd = divmod(n_elems, 2)
data.sort()
if is_odd:
return _get_elem_at_rank(middle, data, n_negative, n_zeros)
return (_get_elem_at_rank(middle - 1, data, n_negative, n_zeros) +
_get_elem_at_rank(middle, data, n_negative, n_zeros)) / 2.
def _get_elem_at_rank(rank, data, n_negative, n_zeros):
"""Find the value in data augmented with n_zeros for the given rank"""
if rank < n_negative:
return data[rank]
if rank - n_negative < n_zeros:
return 0
return data[rank - n_zeros]
def _most_frequent(array, extra_value, n_repeat):
"""Compute the most frequent value in a 1d array extended with
[extra_value] * n_repeat, where extra_value is assumed to be not part
of the array."""
# Compute the most frequent value in array only
if array.size > 0:
mode = stats.mode(array)
most_frequent_value = mode[0][0]
most_frequent_count = mode[1][0]
else:
most_frequent_value = 0
most_frequent_count = 0
# Compare to array + [extra_value] * n_repeat
if most_frequent_count == 0 and n_repeat == 0:
return np.nan
elif most_frequent_count < n_repeat:
return extra_value
elif most_frequent_count > n_repeat:
return most_frequent_value
elif most_frequent_count == n_repeat:
# Ties the breaks. Copy the behaviour of scipy.stats.mode
if most_frequent_value < extra_value:
return most_frequent_value
else:
return extra_value
class Imputer(BaseEstimator, TransformerMixin):
"""Imputation transformer for completing missing values.
Parameters
----------
missing_values : integer or "NaN", optional (default="NaN")
The placeholder for the missing values. All occurrences of
`missing_values` will be imputed. For missing values encoded as np.nan,
use the string value "NaN".
strategy : string, optional (default="mean")
The imputation strategy.
- If "mean", then replace missing values using the mean along
the axis.
- If "median", then replace missing values using the median along
the axis.
- If "most_frequent", then replace missing using the most frequent
value along the axis.
axis : integer, optional (default=0)
The axis along which to impute.
- If `axis=0`, then impute along columns.
- If `axis=1`, then impute along rows.
verbose : integer, optional (default=0)
Controls the verbosity of the imputer.
copy : boolean, optional (default=True)
If True, a copy of X will be created. If False, imputation will
be done in-place whenever possible. Note that, in the following cases,
a new copy will always be made, even if `copy=False`:
- If X is not an array of floating values;
- If X is sparse and `missing_values=0`;
- If `axis=0` and X is encoded as a CSR matrix;
- If `axis=1` and X is encoded as a CSC matrix.
Attributes
----------
`statistics_` : array of shape (n_features,)
The imputation fill value for each feature if axis == 0.
Notes
-----
- When ``axis=0``, columns which only contained missing values at `fit`
are discarded upon `transform`.
- When ``axis=1``, an exception is raised if there are rows for which it is
not possible to fill in the missing values (e.g., because they only
contain missing values).
"""
def __init__(self, missing_values="NaN", strategy="mean",
axis=0, verbose=0, copy=True):
self.missing_values = missing_values
self.strategy = strategy
self.axis = axis
self.verbose = verbose
self.copy = copy
def fit(self, X, y=None):
"""Fit the imputer on X.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Input data, where ``n_samples`` is the number of samples and
``n_features`` is the number of features.
Returns
-------
self : object
Returns self.
"""
# Check parameters
allowed_strategies = ["mean", "median", "most_frequent"]
if self.strategy not in allowed_strategies:
raise ValueError("Can only use these strategies: {0} "
" got strategy={1}".format(allowed_strategies,
self.strategy))
if self.axis not in [0, 1]:
raise ValueError("Can only impute missing values on axis 0 and 1, "
" got axis={0}".format(self.axis))
# Since two different arrays can be provided in fit(X) and
# transform(X), the imputation data will be computed in transform()
# when the imputation is done per sample (i.e., when axis=1).
if self.axis == 0:
X = atleast2d_or_csc(X, dtype=np.float64, force_all_finite=False)
if sparse.issparse(X):
self.statistics_ = self._sparse_fit(X,
self.strategy,
self.missing_values,
self.axis)
else:
self.statistics_ = self._dense_fit(X,
self.strategy,
self.missing_values,
self.axis)
return self
def _sparse_fit(self, X, strategy, missing_values, axis):
"""Fit the transformer on sparse data."""
# Imputation is done "by column", so if we want to do it
# by row we only need to convert the matrix to csr format.
if axis == 1:
X = X.tocsr()
else:
X = X.tocsc()
# Count the zeros
if missing_values == 0:
n_zeros_axis = np.zeros(X.shape[not axis], dtype=int)
else:
n_zeros_axis = X.shape[axis] - np.diff(X.indptr)
# Mean
if strategy == "mean":
if missing_values != 0:
n_non_missing = n_zeros_axis
# Mask the missing elements
mask_missing_values = _get_mask(X.data, missing_values)
mask_valids = np.logical_not(mask_missing_values)
# Sum only the valid elements
new_data = X.data.copy()
new_data[mask_missing_values] = 0
X = sparse.csc_matrix((new_data, X.indices, X.indptr),
copy=False)
sums = X.sum(axis=0)
# Count the elements != 0
mask_non_zeros = sparse.csc_matrix(
(mask_valids.astype(np.float64),
X.indices,
X.indptr), copy=False)
s = mask_non_zeros.sum(axis=0)
n_non_missing = np.add(n_non_missing, s)
else:
sums = X.sum(axis=axis)
n_non_missing = np.diff(X.indptr)
# Ignore the error, columns with a np.nan statistics_
# are not an error at this point. These columns will
# be removed in transform
with np.errstate(all="ignore"):
return np.ravel(sums) / np.ravel(n_non_missing)
# Median + Most frequent
else:
# Remove the missing values, for each column
columns_all = np.hsplit(X.data, X.indptr[1:-1])
mask_missing_values = _get_mask(X.data, missing_values)
mask_valids = np.hsplit(np.logical_not(mask_missing_values),
X.indptr[1:-1])
# astype necessary for bug in numpy.hsplit before v1.9
columns = [col[astype(mask, bool, copy=False)]
for col, mask in zip(columns_all, mask_valids)]
# Median
if strategy == "median":
median = np.empty(len(columns))
for i, column in enumerate(columns):
median[i] = _get_median(column, n_zeros_axis[i])
return median
# Most frequent
elif strategy == "most_frequent":
most_frequent = np.empty(len(columns))
for i, column in enumerate(columns):
most_frequent[i] = _most_frequent(column,
0,
n_zeros_axis[i])
return most_frequent
def _dense_fit(self, X, strategy, missing_values, axis):
"""Fit the transformer on dense data."""
X = array2d(X, force_all_finite=False)
mask = _get_mask(X, missing_values)
masked_X = ma.masked_array(X, mask=mask)
# Mean
if strategy == "mean":
mean_masked = np.ma.mean(masked_X, axis=axis)
# Avoid the warning "Warning: converting a masked element to nan."
mean = np.ma.getdata(mean_masked)
mean[np.ma.getmask(mean_masked)] = np.nan
return mean
# Median
elif strategy == "median":
if tuple(int(v) for v in np.__version__.split('.')[:2]) < (1, 5):
# In old versions of numpy, calling a median on an array
# containing nans returns nan. This is different is
# recent versions of numpy, which we want to mimic
masked_X.mask = np.logical_or(masked_X.mask,
np.isnan(X))
median_masked = np.ma.median(masked_X, axis=axis)
# Avoid the warning "Warning: converting a masked element to nan."
median = np.ma.getdata(median_masked)
median[np.ma.getmaskarray(median_masked)] = np.nan
return median
# Most frequent
elif strategy == "most_frequent":
# scipy.stats.mstats.mode cannot be used because it will no work
# properly if the first element is masked and if it's frequency
# is equal to the frequency of the most frequent valid element
# See https://github.com/scipy/scipy/issues/2636
# To be able access the elements by columns
if axis == 0:
X = X.transpose()
mask = mask.transpose()
most_frequent = np.empty(X.shape[0])
for i, (row, row_mask) in enumerate(zip(X[:], mask[:])):
row_mask = np.logical_not(row_mask).astype(np.bool)
row = row[row_mask]
most_frequent[i] = _most_frequent(row, np.nan, 0)
return most_frequent
def transform(self, X):
"""Impute all missing values in X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
The input data to complete.
"""
# Copy just once
X = as_float_array(X, copy=self.copy, force_all_finite=False)
# Since two different arrays can be provided in fit(X) and
# transform(X), the imputation data need to be recomputed
# when the imputation is done per sample
if self.axis == 1:
X = atleast2d_or_csr(X, force_all_finite=False, copy=False)
if sparse.issparse(X):
statistics = self._sparse_fit(X,
self.strategy,
self.missing_values,
self.axis)
else:
statistics = self._dense_fit(X,
self.strategy,
self.missing_values,
self.axis)
else:
X = atleast2d_or_csc(X, force_all_finite=False, copy=False)
statistics = self.statistics_
# Delete the invalid rows/columns
invalid_mask = np.isnan(statistics)
valid_mask = np.logical_not(invalid_mask)
valid_statistics = statistics[valid_mask]
valid_statistics_indexes = np.where(valid_mask)[0]
missing = np.arange(X.shape[not self.axis])[invalid_mask]
if self.axis == 0 and invalid_mask.any():
if self.verbose:
warnings.warn("Deleting features without "
"observed values: %s" % missing)
X = X[:, valid_statistics_indexes]
elif self.axis == 1 and invalid_mask.any():
raise ValueError("Some rows only contain "
"missing values: %s" % missing)
# Do actual imputation
if sparse.issparse(X) and self.missing_values != 0:
mask = _get_mask(X.data, self.missing_values)
indexes = np.repeat(np.arange(len(X.indptr) - 1, dtype=np.int),
np.diff(X.indptr))[mask]
X.data[mask] = valid_statistics[indexes].astype(X.dtype)
else:
if sparse.issparse(X):
X = X.toarray()
mask = _get_mask(X, self.missing_values)
n_missing = np.sum(mask, axis=self.axis)
values = np.repeat(valid_statistics, n_missing)
if self.axis == 0:
coordinates = np.where(mask.transpose())[::-1]
else:
coordinates = mask
X[coordinates] = values
return X
label.py
# Authors: Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Mathieu Blondel <mathieu@mblondel.org>
# Olivier Grisel <olivier.grisel@ensta.org>
# Andreas Mueller <amueller@ais.uni-bonn.de>
# Joel Nothman <joel.nothman@gmail.com>
# Hamzeh Alsalhi <ha258@cornell.edu>
# License: BSD 3 clause
from collections import defaultdict
import itertools
import array
import warnings
import numpy as np
import scipy.sparse as sp
from ..base import BaseEstimator, TransformerMixin
from ..utils.fixes import np_version
from ..utils.fixes import sparse_min_max
from ..utils.fixes import astype
from ..utils.fixes import in1d
from ..utils import deprecated, column_or_1d
from ..utils.validation import check_array
from ..utils.validation import _num_samples
from ..utils.multiclass import unique_labels
from ..utils.multiclass import type_of_target
from ..externals import six
zip = six.moves.zip
map = six.moves.map
__all__ = [
'label_binarize',
'LabelBinarizer',
'LabelEncoder',
'MultiLabelBinarizer',
]
def _check_numpy_unicode_bug(labels):
"""Check that user is not subject to an old numpy bug
Fixed in master before 1.7.0:
https://github.com/numpy/numpy/pull/243
"""
if np_version[:3] < (1, 7, 0) and labels.dtype.kind == 'U':
raise RuntimeError("NumPy < 1.7.0 does not implement searchsorted"
" on unicode data correctly. Please upgrade"
" NumPy to use LabelEncoder with unicode inputs.")
class LabelEncoder(BaseEstimator, TransformerMixin):
"""Encode labels with value between 0 and n_classes-1.
Attributes
----------
classes_ : array of shape (n_class,)
Holds the label for each class.
Examples
--------
`LabelEncoder` can be used to normalize labels.
>>> from sklearn import preprocessing
>>> le = preprocessing.LabelEncoder()
>>> le.fit([1, 2, 2, 6])
LabelEncoder()
>>> le.classes_
array([1, 2, 6])
>>> le.transform([1, 1, 2, 6]) #doctest: +ELLIPSIS
array([0, 0, 1, 2]...)
>>> le.inverse_transform([0, 0, 1, 2])
array([1, 1, 2, 6])
It can also be used to transform non-numerical labels (as long as they are
hashable and comparable) to numerical labels.
>>> le = preprocessing.LabelEncoder()
>>> le.fit(["paris", "paris", "tokyo", "amsterdam"])
LabelEncoder()
>>> list(le.classes_)
['amsterdam', 'paris', 'tokyo']
>>> le.transform(["tokyo", "tokyo", "paris"]) #doctest: +ELLIPSIS
array([2, 2, 1]...)
>>> list(le.inverse_transform([2, 2, 1]))
['tokyo', 'tokyo', 'paris']
"""
def _check_fitted(self):
if not hasattr(self, "classes_"):
raise ValueError("LabelEncoder was not fitted yet.")
def fit(self, y):
"""Fit label encoder
Parameters
----------
y : array-like of shape (n_samples,)
Target values.
Returns
-------
self : returns an instance of self.
"""
y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
self.classes_ = np.unique(y)
return self
def fit_transform(self, y):
"""Fit label encoder and return encoded labels
Parameters
----------
y : array-like of shape [n_samples]
Target values.
Returns
-------
y : array-like of shape [n_samples]
"""
y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
self.classes_, y = np.unique(y, return_inverse=True)
return y
def transform(self, y):
"""Transform labels to normalized encoding.
Parameters
----------
y : array-like of shape [n_samples]
Target values.
Returns
-------
y : array-like of shape [n_samples]
"""
self._check_fitted()
classes = np.unique(y)
_check_numpy_unicode_bug(classes)
if len(np.intersect1d(classes, self.classes_)) < len(classes):
diff = np.setdiff1d(classes, self.classes_)
raise ValueError("y contains new labels: %s" % str(diff))
return np.searchsorted(self.classes_, y)
def inverse_transform(self, y):
"""Transform labels back to original encoding.
Parameters
----------
y : numpy array of shape [n_samples]
Target values.
Returns
-------
y : numpy array of shape [n_samples]
"""
self._check_fitted()
y = np.asarray(y)
return self.classes_[y]
class LabelBinarizer(BaseEstimator, TransformerMixin):
"""Binarize labels in a one-vs-all fashion
Several regression and binary classification algorithms are
available in the scikit. A simple way to extend these algorithms
to the multi-class classification case is to use the so-called
one-vs-all scheme.
At learning time, this simply consists in learning one regressor
or binary classifier per class. In doing so, one needs to convert
multi-class labels to binary labels (belong or does not belong
to the class). LabelBinarizer makes this process easy with the
transform method.
At prediction time, one assigns the class for which the corresponding
model gave the greatest confidence. LabelBinarizer makes this easy
with the inverse_transform method.
Parameters
----------
neg_label : int (default: 0)
Value with which negative labels must be encoded.
pos_label : int (default: 1)
Value with which positive labels must be encoded.
sparse_output : boolean (default: False)
True if the returned array from transform is desired to be in sparse
CSR format.
Attributes
----------
classes_ : array of shape [n_class]
Holds the label for each class.
y_type_ : str,
Represents the type of the target data as evaluated by
utils.multiclass.type_of_target. Possible type are 'continuous',
'continuous-multioutput', 'binary', 'multiclass',
'mutliclass-multioutput', 'multilabel-sequences',
'multilabel-indicator', and 'unknown'.
multilabel_ : boolean
True if the transformer was fitted on a multilabel rather than a
multiclass set of labels. The ``multilabel_`` attribute is deprecated
and will be removed in 0.18
sparse_input_ : boolean,
True if the input data to transform is given as a sparse matrix, False
otherwise.
indicator_matrix_ : str
'sparse' when the input data to tansform is a multilable-indicator and
is sparse, None otherwise. The ``indicator_matrix_`` attribute is
deprecated as of version 0.16 and will be removed in 0.18
Examples
--------
>>> from sklearn import preprocessing
>>> lb = preprocessing.LabelBinarizer()
>>> lb.fit([1, 2, 6, 4, 2])
LabelBinarizer(neg_label=0, pos_label=1, sparse_output=False)
>>> lb.classes_
array([1, 2, 4, 6])
>>> lb.transform([1, 6])
array([[1, 0, 0, 0],
[0, 0, 0, 1]])
Binary targets transform to a column vector
>>> lb = preprocessing.LabelBinarizer()
>>> lb.fit_transform(['yes', 'no', 'no', 'yes'])
array([[1],
[0],
[0],
[1]])
Passing a 2D matrix for multilabel classification
>>> import numpy as np
>>> lb.fit(np.array([[0, 1, 1], [1, 0, 0]]))
LabelBinarizer(neg_label=0, pos_label=1, sparse_output=False)
>>> lb.classes_
array([0, 1, 2])
>>> lb.transform([0, 1, 2, 1])
array([[1, 0, 0],
[0, 1, 0],
[0, 0, 1],
[0, 1, 0]])
See also
--------
label_binarize : function to perform the transform operation of
LabelBinarizer with fixed classes.
"""
def __init__(self, neg_label=0, pos_label=1, sparse_output=False):
if neg_label >= pos_label:
raise ValueError("neg_label={0} must be strictly less than "
"pos_label={1}.".format(neg_label, pos_label))
if sparse_output and (pos_label == 0 or neg_label != 0):
raise ValueError("Sparse binarization is only supported with non "
"zero pos_label and zero neg_label, got "
"pos_label={0} and neg_label={1}"
"".format(pos_label, neg_label))
self.neg_label = neg_label
self.pos_label = pos_label
self.sparse_output = sparse_output
@property
@deprecated("Attribute ``indicator_matrix_`` is deprecated and will be "
"removed in 0.17. Use ``y_type_ == 'multilabel-indicator'`` "
"instead")
def indicator_matrix_(self):
return self.y_type_ == 'multilabel-indicator'
@property
@deprecated("Attribute ``multilabel_`` is deprecated and will be removed "
"in 0.17. Use ``y_type_.startswith('multilabel')`` "
"instead")
def multilabel_(self):
return self.y_type_.startswith('multilabel')
def _check_fitted(self):
if not hasattr(self, "classes_"):
raise ValueError("LabelBinarizer was not fitted yet.")
def fit(self, y):
"""Fit label binarizer
Parameters
----------
y : numpy array of shape (n_samples,) or (n_samples, n_classes)
Target values. The 2-d matrix should only contain 0 and 1,
represents multilabel classification.
Returns
-------
self : returns an instance of self.
"""
self.y_type_ = type_of_target(y)
if 'multioutput' in self.y_type_:
raise ValueError("Multioutput target data is not supported with "
"label binarization")
if _num_samples(y) == 0:
raise ValueError('y has 0 samples: %r' % y)
self.sparse_input_ = sp.issparse(y)
self.classes_ = unique_labels(y)
return self
def transform(self, y):
"""Transform multi-class labels to binary labels
The output of transform is sometimes referred to by some authors as the
1-of-K coding scheme.
Parameters
----------
y : numpy array or sparse matrix of shape (n_samples,) or
(n_samples, n_classes) Target values. The 2-d matrix should only
contain 0 and 1, represents multilabel classification. Sparse
matrix can be CSR, CSC, COO, DOK, or LIL.
Returns
-------
Y : numpy array or CSR matrix of shape [n_samples, n_classes]
Shape will be [n_samples, 1] for binary problems.
"""
self._check_fitted()
y_is_multilabel = type_of_target(y).startswith('multilabel')
if y_is_multilabel and not self.y_type_.startswith('multilabel'):
raise ValueError("The object was not fitted with multilabel"
" input.")
return label_binarize(y, self.classes_,
pos_label=self.pos_label,
neg_label=self.neg_label,
sparse_output=self.sparse_output)
def inverse_transform(self, Y, threshold=None):
"""Transform binary labels back to multi-class labels
Parameters
----------
Y : numpy array or sparse matrix with shape [n_samples, n_classes]
Target values. All sparse matrices are converted to CSR before
inverse transformation.
threshold : float or None
Threshold used in the binary and multi-label cases.
Use 0 when:
- Y contains the output of decision_function (classifier)
Use 0.5 when:
- Y contains the output of predict_proba
If None, the threshold is assumed to be half way between
neg_label and pos_label.
Returns
-------
y : numpy array or CSR matrix of shape [n_samples] Target values.
Notes
-----
In the case when the binary labels are fractional
(probabilistic), inverse_transform chooses the class with the
greatest value. Typically, this allows to use the output of a
linear model's decision_function method directly as the input
of inverse_transform.
"""
self._check_fitted()
if threshold is None:
threshold = (self.pos_label + self.neg_label) / 2.
if self.y_type_ == "multiclass":
y_inv = _inverse_binarize_multiclass(Y, self.classes_)
else:
y_inv = _inverse_binarize_thresholding(Y, self.y_type_,
self.classes_, threshold)
if self.sparse_input_:
y_inv = sp.csr_matrix(y_inv)
elif sp.issparse(y_inv):
y_inv = y_inv.toarray()
return y_inv
def label_binarize(y, classes, neg_label=0, pos_label=1,
sparse_output=False, multilabel=None):
"""Binarize labels in a one-vs-all fashion
Several regression and binary classification algorithms are
available in the scikit. A simple way to extend these algorithms
to the multi-class classification case is to use the so-called
one-vs-all scheme.
This function makes it possible to compute this transformation for a
fixed set of class labels known ahead of time.
Parameters
----------
y : array-like
Sequence of integer labels or multilabel data to encode.
classes : array-like of shape [n_classes]
Uniquely holds the label for each class.
neg_label : int (default: 0)
Value with which negative labels must be encoded.
pos_label : int (default: 1)
Value with which positive labels must be encoded.
sparse_output : boolean (default: False),
Set to true if output binary array is desired in CSR sparse format
Returns
-------
Y : numpy array or CSR matrix of shape [n_samples, n_classes]
Shape will be [n_samples, 1] for binary problems.
Examples
--------
>>> from sklearn.preprocessing import label_binarize
>>> label_binarize([1, 6], classes=[1, 2, 4, 6])
array([[1, 0, 0, 0],
[0, 0, 0, 1]])
The class ordering is preserved:
>>> label_binarize([1, 6], classes=[1, 6, 4, 2])
array([[1, 0, 0, 0],
[0, 1, 0, 0]])
Binary targets transform to a column vector
>>> label_binarize(['yes', 'no', 'no', 'yes'], classes=['no', 'yes'])
array([[1],
[0],
[0],
[1]])
See also
--------
LabelBinarizer : class used to wrap the functionality of label_binarize and
allow for fitting to classes independently of the transform operation
"""
if not isinstance(y, list):
# XXX Workaround that will be removed when list of list format is
# dropped
y = check_array(y, accept_sparse='csr', ensure_2d=False, dtype=None)
else:
if _num_samples(y) == 0:
raise ValueError('y has 0 samples: %r' % y)
if neg_label >= pos_label:
raise ValueError("neg_label={0} must be strictly less than "
"pos_label={1}.".format(neg_label, pos_label))
if (sparse_output and (pos_label == 0 or neg_label != 0)):
raise ValueError("Sparse binarization is only supported with non "
"zero pos_label and zero neg_label, got "
"pos_label={0} and neg_label={1}"
"".format(pos_label, neg_label))
if multilabel is not None:
warnings.warn("The multilabel parameter is deprecated as of version "
"0.15 and will be removed in 0.17. The parameter is no "
"longer necessary because the value is automatically "
"inferred.", DeprecationWarning)
# To account for pos_label == 0 in the dense case
pos_switch = pos_label == 0
if pos_switch:
pos_label = -neg_label
y_type = type_of_target(y)
if 'multioutput' in y_type:
raise ValueError("Multioutput target data is not supported with label "
"binarization")
n_samples = y.shape[0] if sp.issparse(y) else len(y)
n_classes = len(classes)
classes = np.asarray(classes)
if y_type == "binary":
if len(classes) == 1:
Y = np.zeros((len(y), 1), dtype=np.int)
Y += neg_label
return Y
elif len(classes) >= 3:
y_type = "multiclass"
sorted_class = np.sort(classes)
if (y_type == "multilabel-indicator" and classes.size != y.shape[1]):
raise ValueError("classes {0} missmatch with the labels {1}"
"found in the data".format(classes, unique_labels(y)))
if y_type in ("binary", "multiclass"):
y = column_or_1d(y)
# pick out the known labels from y
y_in_classes = in1d(y, classes)
y_seen = y[y_in_classes]
indices = np.searchsorted(sorted_class, y_seen)
indptr = np.hstack((0, np.cumsum(y_in_classes)))
data = np.empty_like(indices)
data.fill(pos_label)
Y = sp.csr_matrix((data, indices, indptr),
shape=(n_samples, n_classes))
elif y_type == "multilabel-indicator":
Y = sp.csr_matrix(y)
if pos_label != 1:
data = np.empty_like(Y.data)
data.fill(pos_label)
Y.data = data
elif y_type == "multilabel-sequences":
Y = MultiLabelBinarizer(classes=classes,
sparse_output=sparse_output).fit_transform(y)
if sp.issparse(Y):
Y.data[:] = pos_label
else:
Y[Y == 1] = pos_label
return Y
if not sparse_output:
Y = Y.toarray()
Y = astype(Y, int, copy=False)
if neg_label != 0:
Y[Y == 0] = neg_label
if pos_switch:
Y[Y == pos_label] = 0
else:
Y.data = astype(Y.data, int, copy=False)
# preserve label ordering
if np.any(classes != sorted_class):
indices = np.searchsorted(sorted_class, classes)
Y = Y[:, indices]
if y_type == "binary":
if sparse_output:
Y = Y.getcol(-1)
else:
Y = Y[:, -1].reshape((-1, 1))
return Y
def _inverse_binarize_multiclass(y, classes):
"""Inverse label binarization transformation for multiclass.
Multiclass uses the maximal score instead of a threshold.
"""
classes = np.asarray(classes)
if sp.issparse(y):
# Find the argmax for each row in y where y is a CSR matrix
y = y.tocsr()
n_samples, n_outputs = y.shape
outputs = np.arange(n_outputs)
row_max = sparse_min_max(y, 1)[1]
row_nnz = np.diff(y.indptr)
y_data_repeated_max = np.repeat(row_max, row_nnz)
# picks out all indices obtaining the maximum per row
y_i_all_argmax = np.flatnonzero(y_data_repeated_max == y.data)
# For corner case where last row has a max of 0
if row_max[-1] == 0:
y_i_all_argmax = np.append(y_i_all_argmax, [len(y.data)])
# Gets the index of the first argmax in each row from y_i_all_argmax
index_first_argmax = np.searchsorted(y_i_all_argmax, y.indptr[:-1])
# first argmax of each row
y_ind_ext = np.append(y.indices, [0])
y_i_argmax = y_ind_ext[y_i_all_argmax[index_first_argmax]]
# Handle rows of all 0
y_i_argmax[np.where(row_nnz == 0)[0]] = 0
# Handles rows with max of 0 that contain negative numbers
samples = np.arange(n_samples)[(row_nnz > 0) &
(row_max.ravel() == 0)]
for i in samples:
ind = y.indices[y.indptr[i]:y.indptr[i + 1]]
y_i_argmax[i] = classes[np.setdiff1d(outputs, ind)][0]
return classes[y_i_argmax]
else:
return classes.take(y.argmax(axis=1), mode="clip")
def _inverse_binarize_thresholding(y, output_type, classes, threshold):
"""Inverse label binarization transformation using thresholding."""
if output_type == "binary" and y.ndim == 2 and y.shape[1] > 2:
raise ValueError("output_type='binary', but y.shape = {0}".
format(y.shape))
if output_type != "binary" and y.shape[1] != len(classes):
raise ValueError("The number of class is not equal to the number of "
"dimension of y.")
classes = np.asarray(classes)
# Perform thresholding
if sp.issparse(y):
if threshold > 0:
if y.format not in ('csr', 'csc'):
y = y.tocsr()
y.data = np.array(y.data > threshold, dtype=np.int)
y.eliminate_zeros()
else:
y = np.array(y.toarray() > threshold, dtype=np.int)
else:
y = np.array(y > threshold, dtype=np.int)
# Inverse transform data
if output_type == "binary":
if sp.issparse(y):
y = y.toarray()
if y.ndim == 2 and y.shape[1] == 2:
return classes[y[:, 1]]
else:
if len(classes) == 1:
y = np.empty(len(y), dtype=classes.dtype)
y.fill(classes[0])
return y
else:
return classes[y.ravel()]
elif output_type == "multilabel-indicator":
return y
elif output_type == "multilabel-sequences":
warnings.warn('Direct support for sequence of sequences multilabel '
'representation will be unavailable from version 0.17. '
'Use sklearn.preprocessing.MultiLabelBinarizer to '
'convert to a label indicator representation.',
DeprecationWarning)
mlb = MultiLabelBinarizer(classes=classes).fit([])
return mlb.inverse_transform(y)
else:
raise ValueError("{0} format is not supported".format(output_type))
class MultiLabelBinarizer(BaseEstimator, TransformerMixin):
"""Transform between iterable of iterables and a multilabel format
Although a list of sets or tuples is a very intuitive format for multilabel
data, it is unwieldy to process. This transformer converts between this
intuitive format and the supported multilabel format: a (samples x classes)
binary matrix indicating the presence of a class label.
Parameters
----------
classes : array-like of shape [n_classes] (optional)
Indicates an ordering for the class labels
sparse_output : boolean (default: False),
Set to true if output binary array is desired in CSR sparse format
Attributes
----------
classes_ : array of labels
A copy of the `classes` parameter where provided,
or otherwise, the sorted set of classes found when fitting.
Examples
--------
>>> mlb = MultiLabelBinarizer()
>>> mlb.fit_transform([(1, 2), (3,)])
array([[1, 1, 0],
[0, 0, 1]])
>>> mlb.classes_
array([1, 2, 3])
>>> mlb.fit_transform([set(['sci-fi', 'thriller']), set(['comedy'])])
array([[0, 1, 1],
[1, 0, 0]])
>>> list(mlb.classes_)
['comedy', 'sci-fi', 'thriller']
"""
def __init__(self, classes=None, sparse_output=False):
self.classes = classes
self.sparse_output = sparse_output
def fit(self, y):
"""Fit the label sets binarizer, storing `classes_`
Parameters
----------
y : iterable of iterables
A set of labels (any orderable and hashable object) for each
sample. If the `classes` parameter is set, `y` will not be
iterated.
Returns
-------
self : returns this MultiLabelBinarizer instance
"""
if self.classes is None:
classes = sorted(set(itertools.chain.from_iterable(y)))
else:
classes = self.classes
dtype = np.int if all(isinstance(c, int) for c in classes) else object
self.classes_ = np.empty(len(classes), dtype=dtype)
self.classes_[:] = classes
return self
def fit_transform(self, y):
"""Fit the label sets binarizer and transform the given label sets
Parameters
----------
y : iterable of iterables
A set of labels (any orderable and hashable object) for each
sample. If the `classes` parameter is set, `y` will not be
iterated.
Returns
-------
y_indicator : array or CSR matrix, shape (n_samples, n_classes)
A matrix such that `y_indicator[i, j] = 1` iff `classes_[j]` is in
`y[i]`, and 0 otherwise.
"""
if self.classes is not None:
return self.fit(y).transform(y)
# Automatically increment on new class
class_mapping = defaultdict(int)
class_mapping.default_factory = class_mapping.__len__
yt = self._transform(y, class_mapping)
# sort classes and reorder columns
tmp = sorted(class_mapping, key=class_mapping.get)
# (make safe for tuples)
dtype = np.int if all(isinstance(c, int) for c in tmp) else object
class_mapping = np.empty(len(tmp), dtype=dtype)
class_mapping[:] = tmp
self.classes_, inverse = np.unique(class_mapping, return_inverse=True)
yt.indices = np.take(inverse, yt.indices)
if not self.sparse_output:
yt = yt.toarray()
return yt
def transform(self, y):
"""Transform the given label sets
Parameters
----------
y : iterable of iterables
A set of labels (any orderable and hashable object) for each
sample. If the `classes` parameter is set, `y` will not be
iterated.
Returns
-------
y_indicator : array or CSR matrix, shape (n_samples, n_classes)
A matrix such that `y_indicator[i, j] = 1` iff `classes_[j]` is in
`y[i]`, and 0 otherwise.
"""
class_to_index = dict(zip(self.classes_, range(len(self.classes_))))
yt = self._transform(y, class_to_index)
if not self.sparse_output:
yt = yt.toarray()
return yt
def _transform(self, y, class_mapping):
"""Transforms the label sets with a given mapping
Parameters
----------
y : iterable of iterables
class_mapping : Mapping
Maps from label to column index in label indicator matrix
Returns
-------
y_indicator : sparse CSR matrix, shape (n_samples, n_classes)
Label indicator matrix
"""
indices = array.array('i')
indptr = array.array('i', [0])
for labels in y:
indices.extend(set(class_mapping[label] for label in labels))
indptr.append(len(indices))
data = np.ones(len(indices), dtype=int)
return sp.csr_matrix((data, indices, indptr),
shape=(len(indptr) - 1, len(class_mapping)))
def inverse_transform(self, yt):
"""Transform the given indicator matrix into label sets
Parameters
----------
yt : array or sparse matrix of shape (n_samples, n_classes)
A matrix containing only 1s ands 0s.
Returns
-------
y : list of tuples
The set of labels for each sample such that `y[i]` consists of
`classes_[j]` for each `yt[i, j] == 1`.
"""
if yt.shape[1] != len(self.classes_):
raise ValueError('Expected indicator for {0} classes, but got {1}'
.format(len(self.classes_), yt.shape[1]))
if sp.issparse(yt):
yt = yt.tocsr()
if len(yt.data) != 0 and len(np.setdiff1d(yt.data, [0, 1])) > 0:
raise ValueError('Expected only 0s and 1s in label indicator.')
return [tuple(self.classes_.take(yt.indices[start:end]))
for start, end in zip(yt.indptr[:-1], yt.indptr[1:])]
else:
unexpected = np.setdiff1d(yt, [0, 1])
if len(unexpected) > 0:
raise ValueError('Expected only 0s and 1s in label indicator. '
'Also got {0}'.format(unexpected))
return [tuple(self.classes_.compress(indicators)) for indicators
in yt]
扫一扫
1882
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
