machine-learning - 如何使用递归特征消除？

Question

我是 ML 新手，一直在尝试使用 RFE 方法进行特征选择。我的数据集有 5K 条记录及其二元分类问题。这是我根据教程 online 遵循的代码

#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)
<ipython-input-332-a23dfb331001> in <module>
      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, y, **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'

Answer 1

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))

Optimum number of features: 1

Score with 1 features: 1.000000

测试版本:

sklearn.__version__
'0.20.4'

sklearn.__version__
'0.21.3'