2013/8/28 abhishek <[email protected]>:
> Im using the SelectPercentile function with chi2 feature selection in an NLP
> task. I have created a sparse matrix using the feature extraction techniques
> in sklearn. However, when I do the feature selection it thows a warning
> saying:
>
> "UserWarning: Duplicate scores. Result may depend on feature ordering.There
> are probably duplicate features, or you used a classification score for a
> regression task."
>
> Can anyone explain what does this mean? Am I doing something wrong?

Probably not. This warning pops up when you have two features with the
same chi² score. When working with term frequencies, that's
practically impossible to avoid, so we removed the warning in the
development version. It'll be gone in 0.15. Please ignore it for now,
it's harmless.

-- 
Lars Buitinck
Scientific programmer, ILPS
University of Amsterdam

------------------------------------------------------------------------------
Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
Discover the easy way to master current and previous Microsoft technologies
and advance your career. Get an incredible 1,500+ hours of step-by-step
tutorial videos with LearnDevNow. Subscribe today and save!
http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to