CODEWITHSUNDEEP
pythonmachine-learningscikit-learn
Munichong
Munichong

Reputation: 4031

sklearn univariate feature selection

I am trying to use sklearn univariate feature selection to filter out irrelevant features:

ufs = feature_selection.SelectPercentile(feature_selection.f_classif, percentile = 60)
X_default_cvtrain = ufs.fit_transform( X_cvtrain, Y_cvtrain )

However, I get this warning: 

UserWarning: Duplicate scores. Result may depend on feature ordering.
             There are probably duplicate features, or you used a classification score for a regression task.
warn("Duplicate scores. Result may depend on feature ordering."

What does it mean? What is going on here?

Thanks.

Upvotes: 3

Views: 1571

Answers (1)

Andreas Mueller
Andreas Mueller

Reputation: 28748

It means that there are duplicate scores, so the selected features depend on the feature ordering. A probable cause is that you have duplicate features.

Upvotes: 5

Related Questions