scikit-learn/sklearn/ensemble/voting_classifier.py

"""
Soft Voting/Majority Rule classifier.

This module contains a Soft Voting/Majority Rule classifier for
classification estimators.

"""

# Authors: Sebastian Raschka <se.raschka@gmail.com>,
#          Gilles Louppe <g.louppe@gmail.com>
#
# License: BSD 3 clause

import numpy as np

from ..base import ClassifierMixin
from ..base import TransformerMixin
from ..base import clone
from ..preprocessing import LabelEncoder
from ..utils._joblib import Parallel, delayed
from ..utils.validation import has_fit_parameter, check_is_fitted
from ..utils.metaestimators import _BaseComposition
from ..utils import Bunch


def _parallel_fit_estimator(estimator, X, y, sample_weight=None):
    """Private function used to fit an estimator within a job."""
    if sample_weight is not None:
        estimator.fit(X, y, sample_weight=sample_weight)
    else:
        estimator.fit(X, y)
    return estimator


class VotingClassifier(_BaseComposition, ClassifierMixin, TransformerMixin):
    """Soft Voting/Majority Rule classifier for unfitted estimators.

    .. versionadded:: 0.17

    Read more in the :ref:`User Guide <voting_classifier>`.

    Parameters
    ----------
    estimators : list of (string, estimator) tuples
        Invoking the ``fit`` method on the ``VotingClassifier`` will fit clones
        of those original estimators that will be stored in the class attribute
        ``self.estimators_``. An estimator can be set to `None` using
        ``set_params``.

    voting : str, {'hard', 'soft'} (default='hard')
        If 'hard', uses predicted class labels for majority rule voting.
        Else if 'soft', predicts the class label based on the argmax of
        the sums of the predicted probabilities, which is recommended for
        an ensemble of well-calibrated classifiers.

    weights : array-like, shape = [n_classifiers], optional (default=`None`)
        Sequence of weights (`float` or `int`) to weight the occurrences of
        predicted class labels (`hard` voting) or class probabilities
        before averaging (`soft` voting). Uses uniform weights if `None`.

    n_jobs : int or None, optional (default=None)
        The number of jobs to run in parallel for ``fit``.
        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
        for more details.

    flatten_transform : bool, optional (default=True)
        Affects shape of transform output only when voting='soft'
        If voting='soft' and flatten_transform=True, transform method returns
        matrix with shape (n_samples, n_classifiers * n_classes). If
        flatten_transform=False, it returns
        (n_classifiers, n_samples, n_classes).

    Attributes
    ----------
    estimators_ : list of classifiers
        The collection of fitted sub-estimators as defined in ``estimators``
        that are not `None`.

    named_estimators_ : Bunch object, a dictionary with attribute access
        Attribute to access any fitted sub-estimators by name.

        .. versionadded:: 0.20

    classes_ : array-like, shape = [n_predictions]
        The classes labels.

    Examples
    --------
    >>> import numpy as np
    >>> from sklearn.linear_model import LogisticRegression
    >>> from sklearn.naive_bayes import GaussianNB
    >>> from sklearn.ensemble import RandomForestClassifier, VotingClassifier
    >>> clf1 = LogisticRegression(solver='lbfgs', multi_class='multinomial',
    ...                           random_state=1)
    >>> clf2 = RandomForestClassifier(n_estimators=50, random_state=1)
    >>> clf3 = GaussianNB()
    >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
    >>> y = np.array([1, 1, 1, 2, 2, 2])
    >>> eclf1 = VotingClassifier(estimators=[
    ...         ('lr', clf1), ('rf', clf2), ('gnb', clf3)], voting='hard')
    >>> eclf1 = eclf1.fit(X, y)
    >>> print(eclf1.predict(X))
    [1 1 1 2 2 2]
    >>> np.array_equal(eclf1.named_estimators_.lr.predict(X),
    ...                eclf1.named_estimators_['lr'].predict(X))
    True
    >>> eclf2 = VotingClassifier(estimators=[
    ...         ('lr', clf1), ('rf', clf2), ('gnb', clf3)],
    ...         voting='soft')
    >>> eclf2 = eclf2.fit(X, y)
    >>> print(eclf2.predict(X))
    [1 1 1 2 2 2]
    >>> eclf3 = VotingClassifier(estimators=[
    ...        ('lr', clf1), ('rf', clf2), ('gnb', clf3)],
    ...        voting='soft', weights=[2,1,1],
    ...        flatten_transform=True)
    >>> eclf3 = eclf3.fit(X, y)
    >>> print(eclf3.predict(X))
    [1 1 1 2 2 2]
    >>> print(eclf3.transform(X).shape)
    (6, 6)
    """

    def __init__(self, estimators, voting='hard', weights=None, n_jobs=None,
                 flatten_transform=True):
        self.estimators = estimators
        self.voting = voting
        self.weights = weights
        self.n_jobs = n_jobs
        self.flatten_transform = flatten_transform

    @property
    def named_estimators(self):
        return Bunch(**dict(self.estimators))

    def fit(self, X, y, sample_weight=None):
        """ Fit the estimators.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_samples, n_features]
            Training vectors, where n_samples is the number of samples and
            n_features is the number of features.

        y : array-like, shape = [n_samples]
            Target values.

        sample_weight : array-like, shape = [n_samples] or None
            Sample weights. If None, then samples are equally weighted.
            Note that this is supported only if all underlying estimators
            support sample weights.

        Returns
        -------
        self : object
        """
        if isinstance(y, np.ndarray) and len(y.shape) > 1 and y.shape[1] > 1:
            raise NotImplementedError('Multilabel and multi-output'
                                      ' classification is not supported.')

        if self.voting not in ('soft', 'hard'):
            raise ValueError("Voting must be 'soft' or 'hard'; got (voting=%r)"
                             % self.voting)

        if self.estimators is None or len(self.estimators) == 0:
            raise AttributeError('Invalid `estimators` attribute, `estimators`'
                                 ' should be a list of (string, estimator)'
                                 ' tuples')

        if (self.weights is not None and
                len(self.weights) != len(self.estimators)):
            raise ValueError('Number of classifiers and weights must be equal'
                             '; got %d weights, %d estimators'
                             % (len(self.weights), len(self.estimators)))

        if sample_weight is not None:
            for name, step in self.estimators:
                if not has_fit_parameter(step, 'sample_weight'):
                    raise ValueError('Underlying estimator \'%s\' does not'
                                     ' support sample weights.' % name)
        names, clfs = zip(*self.estimators)
        self._validate_names(names)

        n_isnone = np.sum([clf is None for _, clf in self.estimators])
        if n_isnone == len(self.estimators):
            raise ValueError('All estimators are None. At least one is '
                             'required to be a classifier!')

        self.le_ = LabelEncoder().fit(y)
        self.classes_ = self.le_.classes_
        self.estimators_ = []

        transformed_y = self.le_.transform(y)

        self.estimators_ = Parallel(n_jobs=self.n_jobs)(
            delayed(_parallel_fit_estimator)(clone(clf), X, transformed_y,
                                             sample_weight=sample_weight)
            for clf in clfs if clf is not None)

        self.named_estimators_ = Bunch(**dict())
        for k, e in zip(self.estimators, self.estimators_):
            self.named_estimators_[k[0]] = e
        return self

    @property
    def _weights_not_none(self):
        """Get the weights of not `None` estimators"""
        if self.weights is None:
            return None
        return [w for est, w in zip(self.estimators,
                                    self.weights) if est[1] is not None]

    def predict(self, X):
        """ Predict class labels for X.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_samples, n_features]
            The input samples.

        Returns
        ----------
        maj : array-like, shape = [n_samples]
            Predicted class labels.
        """

        check_is_fitted(self, 'estimators_')
        if self.voting == 'soft':
            maj = np.argmax(self.predict_proba(X), axis=1)

        else:  # 'hard' voting
            predictions = self._predict(X)
            maj = np.apply_along_axis(
                lambda x: np.argmax(
                    np.bincount(x, weights=self._weights_not_none)),
                axis=1, arr=predictions)

        maj = self.le_.inverse_transform(maj)

        return maj

    def _collect_probas(self, X):
        """Collect results from clf.predict calls. """
        return np.asarray([clf.predict_proba(X) for clf in self.estimators_])

    def _predict_proba(self, X):
        """Predict class probabilities for X in 'soft' voting """
        if self.voting == 'hard':
            raise AttributeError("predict_proba is not available when"
                                 " voting=%r" % self.voting)
        check_is_fitted(self, 'estimators_')
        avg = np.average(self._collect_probas(X), axis=0,
                         weights=self._weights_not_none)
        return avg

    @property
    def predict_proba(self):
        """Compute probabilities of possible outcomes for samples in X.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_samples, n_features]
            The input samples.

        Returns
        ----------
        avg : array-like, shape = [n_samples, n_classes]
            Weighted average probability for each class per sample.
        """
        return self._predict_proba

    def transform(self, X):
        """Return class labels or probabilities for X for each estimator.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_samples, n_features]
            Training vectors, where n_samples is the number of samples and
            n_features is the number of features.

        Returns
        -------
        probabilities_or_labels
            If `voting='soft'` and `flatten_transform=True`:
                returns array-like of shape (n_classifiers, n_samples *
                n_classes), being class probabilities calculated by each
                classifier.
            If `voting='soft' and `flatten_transform=False`:
                array-like of shape (n_classifiers, n_samples, n_classes)
            If `voting='hard'`:
                array-like of shape (n_samples, n_classifiers), being
                class labels predicted by each classifier.
        """
        check_is_fitted(self, 'estimators_')

        if self.voting == 'soft':
            probas = self._collect_probas(X)
            if not self.flatten_transform:
                return probas
            return np.hstack(probas)

        else:
            return self._predict(X)

    def set_params(self, **params):
        """ Setting the parameters for the voting classifier

        Valid parameter keys can be listed with get_params().

        Parameters
        ----------
        **params : keyword arguments
            Specific parameters using e.g. set_params(parameter_name=new_value)
            In addition, to setting the parameters of the ``VotingClassifier``,
            the individual classifiers of the ``VotingClassifier`` can also be
            set or replaced by setting them to None.

        Examples
        --------
        # In this example, the RandomForestClassifier is removed
        clf1 = LogisticRegression()
        clf2 = RandomForestClassifier()
        eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)]
        eclf.set_params(rf=None)

        """
        super()._set_params('estimators', **params)
        return self

    def get_params(self, deep=True):
        """ Get the parameters of the VotingClassifier

        Parameters
        ----------
        deep : bool
            Setting it to True gets the various classifiers and the parameters
            of the classifiers as well
        """
        return super(VotingClassifier,
                     self)._get_params('estimators', deep=deep)

    def _predict(self, X):
        """Collect results from clf.predict calls. """
        return np.asarray([clf.predict(X) for clf in self.estimators_]).T