sklearn preprocessing

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 
#          Mathieu Blondel 
#          Olivier Grisel 
#          Andreas Mueller 
#          Eric Martin 
# 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.isspmat