[pymvpa] Commonspace

[andrea bertana]

HI Swaroop,

Thanks. This is exactly what we were looking for.
We will run few tests and let you know.

Best,
Andrea


2014-04-09 19:01 GMT+02:00 Swaroop Guntupalli <swaroopgj at gmail.com>:

> Hi Andrea,
>
> The algorithm will do it for you.
>
> I am pasting this from the docstring of Hyperalignment.
> """
>     Level 1 and 2 are performed by the ``train()`` method, and level 3 is
>     performed when the trained Hyperalignment instance is called with a
> list of
>     datasets. This dataset list may or may not be identical to the training
>     datasets.
>
>     Examples
>     --------
>     >>> # get some example data
>     >>> from mvpa2.testing.datasets import datasets
>     >>> from mvpa2.misc.data_generators import random_affine_transformation
>     >>> ds4l = datasets['uni4large']
>     >>> # generate a number of distorted variants of this data
>     >>> dss = [random_affine_transformation(ds4l) for i in xrange(4)]
>     >>> ha = Hyperalignment()
>     >>> ha.train(dss)
>     >>> mappers = ha(dss)
>     >>> len(mappers)
> """
>
> For your case (if I understand it correctly), you can do
> >>> ha.train(ds_others)
> >>> test_subject_mapper = ha(ds_test)
> First line should build common space on a bunch of datasets
> and second line computes the transformation to that common space from
> a new dataset 'ds_test'
>
> Did I miss something?
>
> Best,
> Swaroop
>
> On Wed, Apr 9, 2014 at 3:57 AM, andrea bertana
> <andrea.bertana1 at gmail.com> wrote:
> > Dear all,
> >
> >
> > We are performing a few tests on hyperalignment, and we would want to
> > project a new participant's brain to a commmon space computed over other
> > participants' responses (all participants performed the same task).
> >
> >
> > However, in terms of scripting, it is not clear to us where the common
> space
> > is stored. We would need it in order to compute the transformation matrix
> > directly from our participant brain to the common space (same as step 3
> of
> > hyperalignment).
> >
> >
> > We are mainly referring to the example described in this webpage -
> > http://dev.pymvpa.org/examples/hyperalignment.html
> >
> >
> > What we thought about was to get the 'commonspace' parameter from hyper
> > object (which seems to carry it as general one), and then evaluate
> > algebrically the transformation matrix from the new participant to the
> > common - space.
> >
> >
> > Are we missing something?
> >
> >
> > Thanks,
> >
> > Andrea
> >
> >
> > _______________________________________________
> > Pkg-ExpPsy-PyMVPA mailing list
> > Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> >
> http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
>
> _______________________________________________
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20140410/c08cb257/attachment.html>