1

I have used sci-kit learn RFE and RFECV to select the best features. https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.RFE.html, It gives the ranking of the features. can anyone explain the ranking based method that is used in scikit-learn RFECV.?

There are several methods for ranking the feature

  • Information Gain (IG) attribute evaluation
  • Gain Ratio (GR) attribute evaluation,
  • Symmetrical Uncertainty (SU) attribute evaluation,
  • Relief-F (RF) attribute evaluation,
  • One-R (OR) attribute evaluation
  • Chi-Squared (CS) attribute evaluation.

what is the ranking method used in the scikit-learn rfecv.? scikit-learn doesn't provide mathematical methods that used in the libaray.

rk__
  • 11
  • 1
    I'm not sure this should be closed as a "routine programming" question: there's a potential answer about how the algorithm works and what it does. – Matt Krause Feb 16 '22 at 01:42
  • well, the general algorithm works based on the correlation co-efficient ranking method when RFE is published the first time. But I am not sure that sklearn RFE is the same ranking method. @MattKrause. – rk__ Feb 16 '22 at 14:57
  • 1
    Right! We close "routine programming" questions like "How do I read a file in R?" but I think the answer you're hoping for has a more statistical/algorithmic bent. In other words, I think it's on-topic here! – Matt Krause Feb 16 '22 at 21:44

0 Answers0