CODEWITHSUNDEEP
pandasscikit-learnfeature-selection
Juncheng ZHOU
Juncheng ZHOU

Reputation: 125

How to know which column returned when I use RFE of skLearn

I'm trying to do something with feature engineer. So, I try to use the method RFE of Sklearn to do with it. But after I got the dataset who returned by RFE, I have no idea, which features is choosed, and which featured are deleted. So, is there any solution can make me know that?

v = trainDF.loc[:,['A','B','C','D']].as_matrix()
t = trainDF.loc[:,['y']].values.ravel()
RFE(estimator=LogisticRegression(), n_features_to_select=3).fit_transform(v,t)

=>

array([[2, 0, 0],
       [4, 0, 0],
       [1, 0, 0],
       ..., 
       [2, 0, 0],
       [1, 0, 0],
       [3, 0, 0]])

Upvotes: 1

Views: 1920

Answers (1)

TomDLT
TomDLT

Reputation: 4485

You can use the RFE fitted object:

estimator = RFE(estimator=LogisticRegression(), n_features_to_select=3)
v_transform = estimator.fit_transform(v,t)
print(estimator.support_)  # The mask of selected features.
print(estimator.ranking_)  # The feature ranking

Upvotes: 1

Related Questions