On Sat, Jan 19, 2013 at 1:38 AM, Andreas Mueller <amuel...@ais.uni-bonn.de> wrote: > I don't see the problem with semi-supervised algorithm actually. The API > is pretty straight-forward > and there are well-established algorithms like self-taught learning.
The API feels natural and is flexible but retrieving all labeled examples and all unlabeled examples (an operation which is common for semi-supervised algorithms) is prone to memory copy, in particular in the sparse case: https://github.com/scipy/scipy/blob/master/scipy/sparse/compressed.py#L387 I think we have never really taken the time to study the pros and cons of different possible APIs. Mathieu ------------------------------------------------------------------------------ Master HTML5, CSS3, ASP.NET, MVC, AJAX, Knockout.js, Web API and much more. Get web development skills now with LearnDevNow - 350+ hours of step-by-step video tutorials by Microsoft MVPs and experts. SALE $99.99 this month only -- learn more at: http://p.sf.net/sfu/learnmore_122812 _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
