On Tue, Dec 17, 2013 at 2:19 AM, Arnaud Joly <[email protected]> wrote:
> > This is a known problem. Currently Joel proposed a solution
> to this problem in https://github.com/scikit-learn/scikit-learn/pull/2610.
Although part of me thinks this default behaviour will stay, if only to
make scoring='f1' work by default, rather than having to build a custom
scorer, or having scoring='binary f1', etc. It's a tricky issue, but I've
not had much feedback from other devs on what they'd like to see.
In some parts of the codebase, we have near duplicate implementations with
different names (e.g. classifiers and regressors), but for metrics we make
implicit distinctions on the basis of y. What's the right choice here?
- Joel
------------------------------------------------------------------------------
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, & PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349831&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
