[pymvpa] how to ignore subsets of data?
Yaroslav Halchenko
debian at onerussian.com
Fri May 6 14:02:18 UTC 2011
I am afraid that new 4D dataset (not a file) would need to be created at
some point sooner or later in the processing pipeline... how and when
(optimally) -- it would depend on the version of PyMVPA are we talking
about? is data that big that subselecting a dataset (not a file ;-)
) samples within the script would be a concern?
On Fri, 06 May 2011, Alexandra Woolgar wrote:
> Apologies if this has been covered already, I couldn't see anything
> about it in the archives.
> Is there a simple way to tell PyMVPA to ignore whole conditions? I have
> 12 conditions, all of which occur in each chunk, and I want to use only
> a subset of the conditions in the classification analysis. Since I'm
> planning to run several analyses each using a different subset of the
> conditions, I was hoping I could tell the toolbox to ignore some of the
> conditions (perhaps by changing the labels, for example?), rather than
> having to create new 4D files each time?
--
=------------------------------------------------------------------=
Keep in touch www.onerussian.com
Yaroslav Halchenko www.ohloh.net/accounts/yarikoptic
More information about the Pkg-ExpPsy-PyMVPA
mailing list