[pymvpa] Commonspace

[Swaroop Guntupalli]

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