[pymvpa] Help needed untangling searchlight accuracy bias

[Yaroslav Halchenko]

interesting! it is not your fault at all I bet ;) but we should guard it
(here it tries to guestimate somewhat reasonable C value and I guess it
returns multiple of them instead of a single one)

would you mind sharing a piece of such dataset? e.g.

ds_ = dataset[:, [1,2]]  # just two features
h5save('/tmp/ds_.hdf5', ds_, compression=5)

and emailing it to me?  ideally also trying to run this searchlight on
ds_ to make sure that the same error appears

On Thu, 20 Oct 2011, Mike E. Klein wrote:

> Hi again,

> Yes, it meaned 3 across one dimension with the second dimension
> collapsed together.

> I've pasted below the Errors from PyMVPA if I try to run the script
> without run averaging. Strangely, this error disappears if I use
> LinearNuSVMC() in place of LinearCSVMC(). I'm very much a newbie in
> terms of programming and advanced stats, so I have no idea how these
> two differ.

> Best and thanks again,
> Mike
-- 
=------------------------------------------------------------------=
Keep in touch                                     www.onerussian.com
Yaroslav Halchenko                 www.ohloh.net/accounts/yarikoptic