scikit-learn/sklearn/ensemble/voting.py

494 lines
17 KiB
Python

"""
Soft Voting/Majority Rule classifier and Voting regressor.
This module contains:
- A Soft Voting/Majority Rule classifier for classification estimators.
- A Voting regressor for regression estimators.
"""
# Authors: Sebastian Raschka <se.raschka@gmail.com>,
# Gilles Louppe <g.louppe@gmail.com>,
# Ramil Nugmanov <stsouko@live.ru>
# Mohamed Ali Jamaoui <m.ali.jamaoui@gmail.com>
#
# License: BSD 3 clause
import numpy as np
from abc import abstractmethod
from ..base import ClassifierMixin
from ..base import RegressorMixin
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:
try:
estimator.fit(X, y, sample_weight=sample_weight)
except TypeError as exc:
if "unexpected keyword argument 'sample_weight'" in str(exc):
raise ValueError(
"Underlying estimator {} does not support sample weights."
.format(estimator.__class__.__name__)
) from exc
raise
else:
estimator.fit(X, y)
return estimator
class _BaseVoting(_BaseComposition, TransformerMixin):
"""Base class for voting.
Warning: This class should not be used directly. Use derived classes
instead.
"""
_required_parameters = ['estimators']
@property
def named_estimators(self):
return Bunch(**dict(self.estimators))
@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] not in (None, 'drop')]
def _predict(self, X):
"""Collect results from clf.predict calls. """
return np.asarray([clf.predict(X) for clf in self.estimators_]).T
@abstractmethod
def fit(self, X, y, sample_weight=None):
"""
common fit operations.
"""
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 `estimators` and weights must be equal'
'; got %d weights, %d estimators'
% (len(self.weights), len(self.estimators)))
names, clfs = zip(*self.estimators)
self._validate_names(names)
n_isnone = np.sum(
[clf in (None, 'drop') for _, clf in self.estimators]
)
if n_isnone == len(self.estimators):
raise ValueError(
'All estimators are None or "drop". At least one is required!'
)
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(_parallel_fit_estimator)(clone(clf), X, y,
sample_weight=sample_weight)
for clf in clfs if clf not in (None, 'drop')
)
self.named_estimators_ = Bunch()
for k, e in zip(self.estimators, self.estimators_):
self.named_estimators_[k[0]] = e
return self
def set_params(self, **params):
""" Setting the parameters for the ensemble estimator
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 ensemble estimator,
the individual estimators of the ensemble estimator 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)
"""
return self._set_params('estimators', **params)
def get_params(self, deep=True):
""" Get the parameters of the ensemble estimator
Parameters
----------
deep : bool
Setting it to True gets the various estimators and the parameters
of the estimators as well
"""
return self._get_params('estimators', deep=deep)
class VotingClassifier(_BaseVoting, ClassifierMixin):
"""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`` or ``'drop'``
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(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)
See also
--------
VotingRegressor: Prediction voting regressor.
"""
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
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)
self.le_ = LabelEncoder().fit(y)
self.classes_ = self.le_.classes_
transformed_y = self.le_.transform(y)
return super().fit(X, transformed_y, sample_weight)
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)
class VotingRegressor(_BaseVoting, RegressorMixin):
"""Prediction voting regressor for unfitted estimators.
.. versionadded:: 0.21
A voting regressor is an ensemble meta-estimator that fits base
regressors each on the whole dataset. It, then, averages the individual
predictions to form a final prediction.
Read more in the :ref:`User Guide <voting_regressor>`.
Parameters
----------
estimators : list of (string, estimator) tuples
Invoking the ``fit`` method on the ``VotingRegressor`` will fit clones
of those original estimators that will be stored in the class attribute
``self.estimators_``. An estimator can be set to ``None`` or ``'drop'``
using ``set_params``.
weights : array-like, shape (n_regressors,), optional (default=`None`)
Sequence of weights (`float` or `int`) to weight the occurrences of
predicted values before averaging. 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.
Attributes
----------
estimators_ : list of regressors
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.
Examples
--------
>>> import numpy as np
>>> from sklearn.linear_model import LinearRegression
>>> from sklearn.ensemble import RandomForestRegressor
>>> from sklearn.ensemble import VotingRegressor
>>> r1 = LinearRegression()
>>> r2 = RandomForestRegressor(n_estimators=10, random_state=1)
>>> X = np.array([[1, 1], [2, 4], [3, 9], [4, 16], [5, 25], [6, 36]])
>>> y = np.array([2, 6, 12, 20, 30, 42])
>>> er = VotingRegressor([('lr', r1), ('rf', r2)])
>>> print(er.fit(X, y).predict(X))
[ 3.3 5.7 11.8 19.7 28. 40.3]
See also
--------
VotingClassifier: Soft Voting/Majority Rule classifier.
"""
def __init__(self, estimators, weights=None, n_jobs=None):
self.estimators = estimators
self.weights = weights
self.n_jobs = n_jobs
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
"""
return super().fit(X, y, sample_weight)
def predict(self, X):
"""Predict regression target for X.
The predicted regression target of an input sample is computed as the
mean predicted regression targets of the estimators in the ensemble.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples.
Returns
-------
y : array of shape (n_samples,)
The predicted values.
"""
check_is_fitted(self, "estimators_")
return np.average(self._predict(X), axis=1,
weights=self._weights_not_none)
def transform(self, X):
"""Return predictions for X for each estimator.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
The input samples.
Returns
-------
predictions
array-like of shape (n_samples, n_classifiers), being
values predicted by each regressor.
"""
check_is_fitted(self, 'estimators_')
return self._predict(X)