1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
|
"""
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 BaseEstimator
from ..base import ClassifierMixin
from ..base import TransformerMixin
from ..base import clone
from ..preprocessing import LabelEncoder
from ..externals import six
from ..externals.joblib import Parallel, delayed
from ..utils.validation import has_fit_parameter, check_is_fitted
def _parallel_fit_estimator(estimator, X, y, sample_weight):
"""Private function used to fit an estimator within a job."""
if sample_weight is not None:
estimator.fit(X, y, sample_weight)
else:
estimator.fit(X, y)
return estimator
class VotingClassifier(BaseEstimator, 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_`.
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, optional (default=1)
The number of jobs to run in parallel for ``fit``.
If -1, then the number of jobs is set to the number of cores.
Attributes
----------
estimators_ : list of classifiers
The collection of fitted sub-estimators.
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(random_state=1)
>>> clf2 = RandomForestClassifier(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]
>>> 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])
>>> eclf3 = eclf3.fit(X, y)
>>> print(eclf3.predict(X))
[1 1 1 2 2 2]
>>>
"""
def __init__(self, estimators, voting='hard', weights=None, n_jobs=1):
self.estimators = estimators
self.named_estimators = dict(estimators)
self.voting = voting
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
"""
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 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)
self.le_ = LabelEncoder()
self.le_.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)
for _, clf in self.estimators)
return self
def predict(self, X):
""" Predict class labels for X.
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
----------
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)),
axis=1,
arr=predictions.astype('int'))
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)
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]
Training vectors, where n_samples is the number of samples and
n_features is the number of features.
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
-------
If `voting='soft'`:
array-like = [n_classifiers, n_samples, n_classes]
Class probabilities calculated by each classifier.
If `voting='hard'`:
array-like = [n_samples, n_classifiers]
Class labels predicted by each classifier.
"""
check_is_fitted(self, 'estimators_')
if self.voting == 'soft':
return self._collect_probas(X)
else:
return self._predict(X)
def get_params(self, deep=True):
"""Return estimator parameter names for GridSearch support"""
if not deep:
return super(VotingClassifier, self).get_params(deep=False)
else:
out = super(VotingClassifier, self).get_params(deep=False)
out.update(self.named_estimators.copy())
for name, step in six.iteritems(self.named_estimators):
for key, value in six.iteritems(step.get_params(deep=True)):
out['%s__%s' % (name, key)] = value
return out
def _predict(self, X):
"""Collect results from clf.predict calls. """
return np.asarray([clf.predict(X) for clf in self.estimators_]).T
|
