-
Notifications
You must be signed in to change notification settings - Fork 3
/
SA_RFE.py
491 lines (400 loc) · 18.2 KB
/
SA_RFE.py
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
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
# Authors: Alexandre Gramfort <[email protected]>
# Vincent Michel <[email protected]>
# Gilles Louppe <[email protected]>
#
# License: BSD 3 clause
"""Recursive feature elimination for feature ranking"""
import numpy as np
from sklearn.feature_selection.base import SelectorMixin
from sklearn.feature_selection import mutual_info_
from sklearn.base import BaseEstimator
from sklearn.base import MetaEstimatorMixin
from sklearn.base import clone
from sklearn.base import is_classifier
from sklearn.externals.joblib import Parallel, delayed
from sklearn.model_selection import check_cv
from sklearn.model_selection._validation import _safe_split, _score
from sklearn.metrics.scorer import check_scoring
from sklearn.utils import check_X_y, safe_sqr
from sklearn.utils.metaestimators import if_delegate_has_method
def _rfe_single_fit(rfe, estimator, X, y, train, test, scorer):
"""
Return the score for a fit across one fold.
"""
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
return rfe._fit(
X_train, y_train, lambda estimator, features:
_score(estimator, X_test[:, features], y_test, scorer)).scores_
class SA_RFE(BaseEstimator, MetaEstimatorMixin, SelectorMixin):
"""Feature ranking with recursive feature elimination.
Given an external estimator that assigns weights to features (e.g., the
coefficients of a linear model), the goal of recursive feature elimination
(RFE) is to select features by recursively considering smaller and smaller
sets of features. First, the estimator is trained on the initial set of
features and weights are assigned to each one of them. Then, features whose
absolute weights are the smallest are pruned from the current set features.
That procedure is recursively repeated on the pruned set until the desired
number of features to select is eventually reached.
Read more in the :ref:`User Guide <rfe>`.
Parameters
----------
estimator : object
A supervised learning estimator with a `fit` method that updates a
`coef_` attribute that holds the fitted parameters. Important features
must correspond to high absolute values in the `coef_` array.
For instance, this is the case for most supervised learning
algorithms such as Support Vector Classifiers and Generalized
Linear Models from the `svm` and `linear_model` modules.
n_features_to_select : int or None (default=None)
The number of features to select. If `None`, half of the features
are selected.
step : int or float, optional (default=1)
If greater than or equal to 1, then `step` corresponds to the (integer)
number of features to remove at each iteration.
If within (0.0, 1.0), then `step` corresponds to the percentage
(rounded down) of features to remove at each iteration.
verbose : int, default=0
Controls verbosity of output.
Attributes
----------
n_features_ : int
The number of selected features.
support_ : array of shape [n_features]
The mask of selected features.
ranking_ : array of shape [n_features]
The feature ranking, such that ``ranking_[i]`` corresponds to the
ranking position of the i-th feature. Selected (i.e., estimated
best) features are assigned rank 1.
estimator_ : object
The external estimator fit on the reduced dataset.
Examples
--------
The following example shows how to retrieve the 5 right informative
features in the Friedman #1 dataset.
>>> from sklearn.datasets import make_friedman1
>>> from sklearn.feature_selection import RFE
>>> from sklearn.svm import SVR
>>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
>>> estimator = SVR(kernel="linear")
>>> selector = RFE(estimator, 5, step=1)
>>> selector = selector.fit(X, y)
>>> selector.support_ # doctest: +NORMALIZE_WHITESPACE
array([ True, True, True, True, True,
False, False, False, False, False], dtype=bool)
>>> selector.ranking_
array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5])
References
----------
.. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection
for cancer classification using support vector machines",
Mach. Learn., 46(1-3), 389--422, 2002.
"""
def __init__(self, estimator, n_features_to_select=None, step=1,
verbose=0):
self.estimator = estimator
self.n_features_to_select = n_features_to_select
self.step = step
self.verbose = verbose
@property
def _estimator_type(self):
return self.estimator._estimator_type
def fit(self, X, y):
"""Fit the RFE model and then the underlying estimator on the selected
features.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
The training input samples.
y : array-like, shape = [n_samples]
The target values.
"""
return self._fit(X, y)
def _fit(self, X, y, step_score=None):
X, y = check_X_y(X, y, "csc")
# Initialization
n_features = X.shape[1]
if self.n_features_to_select is None:
n_features_to_select = n_features // 2
else:
n_features_to_select = self.n_features_to_select
if 0.0 < self.step < 1.0:
step = int(max(1, self.step * n_features))
else:
step = int(self.step)
if step <= 0:
raise ValueError("Step must be >0")
support_ = np.ones(n_features, dtype=np.bool)
ranking_ = np.ones(n_features, dtype=np.int)
if step_score:
self.scores_ = []
# Elimination
iter = 0
while np.sum(support_) > n_features_to_select:
print("迭代次数:", iter, '剩余特征数:', np.sum(support_))
iter += 1
# Remaining features, features为剩余特征的索引列表
features = np.arange(n_features)[support_]
# Rank the remaining features
estimator = clone(self.estimator)
if self.verbose > 0:
print("Fitting estimator with %d features." % np.sum(support_))
estimator.fit(X[:, features], y) # 每次循环都重新训练一次
# Get coefs 此处得到就是SVM中的权重w
if hasattr(estimator, 'coef_'):
coefs = estimator.coef_
else:
coefs = getattr(estimator, 'feature_importances_', None)
if coefs is None:
raise RuntimeError('The classifier does not expose '
'"coef_" or "feature_importances_" '
'attributes')
# ----------------------代码修改处-----------------------
rfe_rank = safe_sqr(coefs).sum(axis=0) # rfe算法得到的特征打分
# mrmr_rank = [] # mrmr算法得到的特征打分
# combine_rank = [] # 两种算法结合的特征打分
# beta = 0.5
#
# D = []
# R = []
# for fea in features:
# D.append(mutual_info_._compute_mi(X[:, fea], y, True, True)) # 后两个参数是不是传True????
# # D = D / len(features)
#
# for fea_i in features:
# R_sum = 0
# for fea_j in features:
# if fea_j == fea_i:
# continue
# R_sum += mutual_info_._compute_mi(X[:, fea_i], X[:, fea_j], True, True)
# R.append(R_sum / len(features))
#
# for i in range(len(D)):
# mrmr_rank.append(D[i] / R[i])
#
# combine_rank = 0.6 * rfe_rank + 0.4 * np.asarray(mrmr_rank)
#
# combine_ranks = np.argsort(combine_rank)
# rfe_ranks = np.argsort(rfe_rank)
# Get ranks, 求权值平方w^2, -----ranks存储的元素的索引位置的排序
# [[0.4, -0.3,...,0.4]]
if coefs.ndim > 1:
ranks = np.argsort(rfe_rank)
else:
ranks = np.argsort(safe_sqr(coefs))
# for sparse case ranks is matrix
ranks = np.ravel(ranks)
# Eliminate the worse features, ----得到要移除的特征个数
step = 1 / (iter + 1) * np.sum(support_) # 模拟退火的思想,每次去除1/(iter+1)个特征
step = max(step, 1) # 防止step小于1时,下面的式子中强转后为0
threshold = int(min(step, np.sum(support_) - n_features_to_select))
# Compute step score on the previous selection iteration
# because 'estimator' must use features
# that have not been eliminated yet
if step_score:
self.scores_.append(step_score(estimator, features))
support_[features[ranks][:threshold]] = False
ranking_[np.logical_not(support_)] += 1 # False对应的特征加一
# Set final attributes
features = np.arange(n_features)[support_]
self.estimator_ = clone(self.estimator)
self.estimator_.fit(X[:, features], y)
# Compute step score when only n_features_to_select features left
if step_score:
self.scores_.append(step_score(self.estimator_, features))
self.n_features_ = support_.sum()
self.support_ = support_
self.ranking_ = ranking_
return self
@if_delegate_has_method(delegate='estimator')
def predict(self, X):
"""Reduce X to the selected features and then predict using the
underlying estimator.
Parameters
----------
X : array of shape [n_samples, n_features]
The input samples.
Returns
-------
y : array of shape [n_samples]
The predicted target values.
"""
return self.estimator_.predict(self.transform(X))
@if_delegate_has_method(delegate='estimator')
def score(self, X, y):
"""Reduce X to the selected features and then return the score of the
underlying estimator.
Parameters
----------
X : array of shape [n_samples, n_features]
The input samples.
y : array of shape [n_samples]
The target values.
"""
return self.estimator_.score(self.transform(X), y)
def _get_support_mask(self):
return self.support_
@if_delegate_has_method(delegate='estimator')
def decision_function(self, X):
return self.estimator_.decision_function(self.transform(X))
@if_delegate_has_method(delegate='estimator')
def predict_proba(self, X):
return self.estimator_.predict_proba(self.transform(X))
@if_delegate_has_method(delegate='estimator')
def predict_log_proba(self, X):
return self.estimator_.predict_log_proba(self.transform(X))
class RFECV(SA_RFE, MetaEstimatorMixin):
"""Feature ranking with recursive feature elimination and cross-validated
selection of the best number of features.
Read more in the :ref:`User Guide <rfe>`.
Parameters
----------
estimator : object
A supervised learning estimator with a `fit` method that updates a
`coef_` attribute that holds the fitted parameters. Important features
must correspond to high absolute values in the `coef_` array.
For instance, this is the case for most supervised learning
algorithms such as Support Vector Classifiers and Generalized
Linear Models from the `svm` and `linear_model` modules.
step : int or float, optional (default=1)
If greater than or equal to 1, then `step` corresponds to the (integer)
number of features to remove at each iteration.
If within (0.0, 1.0), then `step` corresponds to the percentage
(rounded down) of features to remove at each iteration.
cv : int, cross-validation generator or an iterable, optional
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 3-fold cross-validation,
- integer, to specify the number of folds.
- An object to be used as a cross-validation generator.
- An iterable yielding train/test splits.
For integer/None inputs, if ``y`` is binary or multiclass,
:class:`sklearn.model_selection.StratifiedKFold` is used. If the
estimator is a classifier or if ``y`` is neither binary nor multiclass,
:class:`sklearn.model_selection.KFold` is used.
Refer :ref:`User Guide <cross_validation>` for the various
cross-validation strategies that can be used here.
scoring : string, callable or None, optional, default: None
A string (see model evaluation documentation) or
a scorer callable object / function with signature
``scorer(estimator, X, y)``.
verbose : int, default=0
Controls verbosity of output.
n_jobs : int, default 1
Number of cores to run in parallel while fitting across folds.
Defaults to 1 core. If `n_jobs=-1`, then number of jobs is set
to number of cores.
Attributes
----------
n_features_ : int
The number of selected features with cross-validation.
support_ : array of shape [n_features]
The mask of selected features.
ranking_ : array of shape [n_features]
The feature ranking, such that `ranking_[i]`
corresponds to the ranking
position of the i-th feature.
Selected (i.e., estimated best)
features are assigned rank 1.
grid_scores_ : array of shape [n_subsets_of_features]
The cross-validation scores such that
``grid_scores_[i]`` corresponds to
the CV score of the i-th subset of features.
estimator_ : object
The external estimator fit on the reduced dataset.
Notes
-----
The size of ``grid_scores_`` is equal to ceil((n_features - 1) / step) + 1,
where step is the number of features removed at each iteration.
Examples
--------
The following example shows how to retrieve the a-priori not known 5
informative features in the Friedman #1 dataset.
>>> from sklearn.datasets import make_friedman1
>>> from sklearn.feature_selection import RFECV
>>> from sklearn.svm import SVR
>>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
>>> estimator = SVR(kernel="linear")
>>> selector = RFECV(estimator, step=1, cv=5)
>>> selector = selector.fit(X, y)
>>> selector.support_ # doctest: +NORMALIZE_WHITESPACE
array([ True, True, True, True, True,
False, False, False, False, False], dtype=bool)
>>> selector.ranking_
array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5])
References
----------
.. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection
for cancer classification using support vector machines",
Mach. Learn., 46(1-3), 389--422, 2002.
"""
def __init__(self, estimator, step=1, cv=None, scoring=None, verbose=0,
n_jobs=1):
self.estimator = estimator
self.step = step
self.cv = cv
self.scoring = scoring
self.verbose = verbose
self.n_jobs = n_jobs
def fit(self, X, y):
"""Fit the RFE model and automatically tune the number of selected
features.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Training vector, where `n_samples` is the number of samples and
`n_features` is the total number of features.
y : array-like, shape = [n_samples]
Target values (integers for classification, real numbers for
regression).
"""
X, y = check_X_y(X, y, "csr")
# Initialization
cv = check_cv(self.cv, y, is_classifier(self.estimator))
scorer = check_scoring(self.estimator, scoring=self.scoring)
n_features = X.shape[1]
n_features_to_select = 1
if 0.0 < self.step < 1.0:
step = int(max(1, self.step * n_features))
else:
step = int(self.step)
if step <= 0:
raise ValueError("Step must be >0")
rfe = SA_RFE(estimator=self.estimator,
n_features_to_select=n_features_to_select,
step=self.step, verbose=self.verbose)
# Determine the number of subsets of features by fitting across
# the train folds and choosing the "features_to_select" parameter
# that gives the least averaged error across all folds.
# Note that joblib raises a non-picklable error for bound methods
# even if n_jobs is set to 1 with the default multiprocessing
# backend.
# This branching is done so that to
# make sure that user code that sets n_jobs to 1
# and provides bound methods as scorers is not broken with the
# addition of n_jobs parameter in version 0.18.
if self.n_jobs == 1:
parallel, func = list, _rfe_single_fit
else:
parallel, func, = Parallel(n_jobs=self.n_jobs), delayed(_rfe_single_fit)
scores = parallel(
func(rfe, self.estimator, X, y, train, test, scorer)
for train, test in cv.split(X, y))
scores = np.sum(scores, axis=0)
n_features_to_select = max(
n_features - (np.argmax(scores) * step),
n_features_to_select)
# Re-execute an elimination with best_k over the whole set
rfe = SA_RFE(estimator=self.estimator,
n_features_to_select=n_features_to_select, step=self.step)
rfe.fit(X, y)
# Set final attributes
self.support_ = rfe.support_
self.n_features_ = rfe.n_features_
self.ranking_ = rfe.ranking_
self.estimator_ = clone(self.estimator)
self.estimator_.fit(self.transform(X), y)
# Fixing a normalization error, n is equal to get_n_splits(X, y) - 1
# here, the scores are normalized by get_n_splits(X, y)
self.grid_scores_ = scores[::-1] / cv.get_n_splits(X, y)
return self