On Feb 14, 2013, at 6:52 PM, Lars Buitinck <[email protected]> wrote:
> 2013/2/15 <[email protected]>: >> how about softmax? > > The model is not intended for probability outputs. A predict_proba is > not required; just implement a decision_function instead. Fair enough, and already done. For my own education though, would softmax do the trick, or would something else be suitable? (I thought more or less any classifier could be persuaded to give probabilities somehow…) --- As an aside, should I wait to submit a pull request until some unit tests and examples are written, or should I submit first? ------------------------------------------------------------------------------ Free Next-Gen Firewall Hardware Offer Buy your Sophos next-gen firewall before the end March 2013 and get the hardware for free! Learn more. http://p.sf.net/sfu/sophos-d2d-feb _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
