Ranker based attribute selections

Hi there,

I have been trying using Ranker as the search method coupled with different
evaluators, such as chi square, information gain, symmetrical uncertainty
and Gain ratio, to evaluate all features of my training data. When I choose
evaluation score >= 0 as a threshold, it seems I always get the same
features with slightly different orders. I am wondering why I get this
effect. Any comments is welcome. Thank you!

Best
--

-- 
View this message in context: http://old.nabble.com/Ranker-based-attribute-selections-tp32171200p32171200.html
Sent from the WEKA mailing list archive at Nabble.com.

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist <at> list.scms.waikato.ac.nz
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html