On 07/09/2012 01:56 PM, Peter Prettenhofer wrote: > 2012/7/9 Emanuele Olivetti <[email protected]>: >> Hi Peter, >> >> Thanks for your answer and the interesting thread you linked >> (I should have catch it before sending my email ;-)). >> >> I agree that Platt scaling would be of help. As far as I understand >> in the multiclass case [0] it should be like: >> >> s = clf.decision_function(x) >> p(s) = exp(A*s+B) / exp(A*s+B).sum() >> >> where s is, say, the distance from the separating plane for the >> example x, while A and B should be estimated by minimizing the >> loss of interest on a new set of examples {(x_1,y_1),...,(x_n,y_n)}. > To be honest, I haven't worked with Platt scaling yet - Paolo has > discussed it on the mailing list a while ago [1] - maybe he has some > code to share. > Furthermore, Mathieu has a PR on calibration plots which might be > handy as well [2] - AFAIK it should allow you to assess the > probability calibration. > > > [1] http://sourceforge.net/mailarchive/message.php?msg_id=27518584 > [2] https://github.com/scikit-learn/scikit-learn/pull/882 > >
That is another very interesting thread. Thanks for pointing it out. As far as I can read my formulas above seem correct (provided that A and B are vectors, which was not explicit in my previous post). The code from Paolo might require some care before merge (for example it handles the binary case only and has some minor issues) but seems to be on the right track. The code from Mathieu addresses the plots and not the optimization problem. Nevertheless the plots should be definitely checked out. I'll do some experiment when I have some time and will keep you posted if something useful pops up. Best, Emanuele ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
