如何使用递归特征消除？

我是ML新手，一直在尝试使用RFE方法进行功能选择。我的数据集有5K条记录及其二进制分类问题。这是基于教程online

#no of features
nof_list=np.arange(1,13)
high_score=0
#Variable to store the optimum features
nof=0
score_list =[]
for n in range(len(nof_list)):
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.3,random_state = 0)
model = RandomForestClassifier()
rfe = RFE(model,nof_list[n])
X_train_rfe = rfe.fit_transform(X_train,y_train)
X_test_rfe = rfe.transform(X_test)
model.fit(X_train_rfe,y_train)
score = model.score(X_test_rfe,y_test)
score_list.append(score)
if(score>high_score):
high_score = score
nof = nof_list[n]
print("Optimum number of features: %d" %nof)
print("Score with %d features: %f" % (nof,high_score))


我遇到以下错误。有人可以帮忙吗

TypeError Traceback (most recent call last)
in
9 model = RandomForestClassifier()
10 rfe = RFE(model,nof_list[n])
---> 11 X_train_rfe = rfe.fit_transform(X_train,y_train)
12 X_test_rfe = rfe.transform(X_test)
13 model.fit(X_train_rfe,y_train)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\base.py in fit_transform(self,X,**fit_params)
554 Training set.
555
--> 556 y : numpy array of shape [n_samples]
557 Target values.
558
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\feature_selection\_base.py in transform(self,X)
75 X = check_array(X,dtype=None,accept_sparse='csr',76 force_all_finite=not tags.get('allow_nan',True))
---> 77 mask = self.get_support()
78 if not mask.any():
79 warn("No features were selected: either the data is"
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\feature_selection\_base.py in get_support(self,indices)
44 values are indices into the input feature vector.
45 """
---> 46 mask = self._get_support_mask()
47 return mask if not indices else np.where(mask)[0]
48
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\feature_selection\_rfe.py in _get_support_mask(self)
269
270 def _get_support_mask(self):
--> 271 check_is_fitted(self)
272 return self.support_
273
TypeError: check_is_fitted() missing 1 required positional argument: 'attributes'


您的sklearn版本是什么？

以下（使用人工数据）应该可以正常工作：

from sklearn.model_selection import train_test_split
import numpy as np
from sklearn.feature_selection import RFE
from sklearn.ensemble import RandomForestClassifier
X = np.random.rand(100,20)
y = np.ones((X.shape[0]))
#no of features
nof_list=np.arange(1,13)
high_score=0
#Variable to store the optimum features
nof=0
score_list =[]
for n in range(len(nof_list)):
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.3,random_state = 0)
model = RandomForestClassifier()
rfe = RFE(model,nof_list[n])
X_train_rfe = rfe.fit_transform(X_train,y_train)
X_test_rfe = rfe.transform(X_test)
model.fit(X_train_rfe,y_train)
score = model.score(X_test_rfe,y_test)
score_list.append(score)
if(score>high_score):
high_score = score
nof = nof_list[n]
print("Optimum number of features: %d" %nof)
print("Score with %d features: %f" % (nof,high_score))


  

最佳功能数：1

  
  

具有1个功能的得分：1.000000

测试版本：

sklearn.__version__
'0.20.4'
sklearn.__version__
'0.21.3'