Hi Sebastian, Thank You for your answer,
what I mean is that by using a cross validation test I get 100% accuracy (on the testing set, not on the training set). It seemed to me a too good result, thus I changed the y labels (I mean, I replaced the true labels with false ones) to check that, as aspected, the accuracy would decrease. It happened accuracy decreased, but never get values lower than 60%. Isn't it strange a bit?? Should not accuracy get values lower than 50% as higher than 50% by chance? as I replied to Andras, I didn't perform an exhaustive test in replacing the true y labels with false ones, I only manually performed some tests (always retaining the 8 labels =1 and 8 labels = 0 as in the true set). when 8,8 belance was changed (i.e. 6,10 or 4,12) the performances decreased as aspected to something as 50% (chance) thank you for your suggestions, Fabrizio ------------------------------------------------------------------------------ One dashboard for servers and applications across Physical-Virtual-Cloud Widest out-of-the-box monitoring support with 50+ applications Performance metrics, stats and reports that give you Actionable Insights Deep dive visibility with transaction tracing using APM Insight. http://ad.doubleclick.net/ddm/clk/290420510;117567292;y _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
