So that means that bagging can only be applied to trees. How about
implementing a general module so that it can be applied on more learning
algorithms.
On Fri, Jun 21, 2013 at 4:17 PM, Olivier Grisel <olivier.gri...@ensta.org>wrote:
> 2013/6/21 Gilles Louppe <g.lou...@gmail.com>:
> > Hi,
> >
> > Such ensembles are not implemented at the moment.
>
> Ensembles of trees have a `bootstrap` parameter that do bagging,
> although they also randomize the feature selection and optionally
> split locations.
>
> --
> Olivier
>
>
> ------------------------------------------------------------------------------
> This SF.net email is sponsored by Windows:
>
> Build for Windows Store.
>
> http://p.sf.net/sfu/windows-dev2dev
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
------------------------------------------------------------------------------
This SF.net email is sponsored by Windows:
Build for Windows Store.
http://p.sf.net/sfu/windows-dev2dev
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
