[pymvpa] top-n match lists

[Yaroslav Halchenko]

> At the moment I'm using SMLR and kNN, but am hoping to include ENET
> and possibly SVM in the future as well.
SVM might be funnier since it relies on maximal vote across all
pair-wise classifications -- I expect too many ties (different labels
with same votes) which would complicate ranking.  libsvm provides
probability estimates which might help to break them up... or just
values from each binary one -- but that is.... yet to be done

> For kNN, are the values the
> number of votes per sample in the training set, or per class?
per same in TESTING set... if you are interested in ranking on training
data, you would need to predict() on training data explicitly and then
access .states.values...

actually alternative could be -- enable training_confusion, then access
its .sets -- those are lists of tuples:

(targets, predictions, values)

-- 
Yaroslav O. Halchenko
Postdoctoral Fellow,   Department of Psychological and Brain Sciences
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
Phone: +1 (603) 646-9834                       Fax: +1 (603) 646-1419
WWW:   http://www.linkedin.com/in/yarik