Hi Justin. Some regressors already support multiple outputs. I think it would be best if all did. Which one are you using that doesn't support it? For SVC and forests, I guess the best would be to have a meta-estimator for the moment.
This would certainly be a helpful feature. Cheers, Andy Am 30.04.2012 12:20, schrieb Justin Bayer: > Hi, > > I have a regression problem where I map a set of inputs X to a set of > outputs y_1, y_2, .. y_k. From what I see, the current models support > fitting with a single response variable, but not with more. From a > programming perspective this is rather tedious, since I have to treat > those in an outer loop and somehow put them together in a joint array > afterwards again. To be honest, I have not made up my mind what the > best way to deal with this is. I'd probably write some kind of wrapper > class. > > I wonder what the best practice is to do this with sklearn. > > > Best, > -Justin > ------------------------------------------------------------------------------ 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
