Hi Scott The paper is quite new, and sklearn has a policy <http://scikit-learn.org/stable/faq.html#can-i-add-this-new-algorithm-that-i-or-someone-else-just-published> about introducing new algorithms. I'd say we need more time for others to test it and prove its usefulness.
On Thu, Dec 10, 2015 at 9:40 PM, Scott Turner <srt19...@gmail.com> wrote: > Canonical correlation forests are an extension of decision trees with > improved performance, particularly on datasets with correlated features. > Paper is available here: > > http://arxiv.org/abs/1507.05444 > > and reference implementation (in Matlab) is here: > > https://bitbucket.org/twgr/ccf > > Is there any interest in adding this? Since there's already an > implementation of CCA, it seems to me (perhaps naively) straightforward. > I'm not sure I know enough about the sklearn implementation of decision > trees or CCA to add this, but I'm hoping there's someone on this list with > the right skills & interest. > > -- Scott Turner > > > ------------------------------------------------------------------------------ > > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > >
------------------------------------------------------------------------------
_______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
