[pymvpa] load raw 'not nifti' data

[Per B. Sederberg]

Hi Greg:

You can save out that big matrix to a mat file from matlab (say the
matrix is named mymat and you save it to mymatrix.mat) and then read
it in with:

import scipy.io
x = scipy.io.loadmat('mymatrix.mat')['mymat']

Then in pymvpa (depending on the version you are using) you can get it
ready for business with:

from mvpa.suite import *

dat = dataset_wizard(x, targets=cov_of_interest, chunks=range(len(x)))

Then you can can start analyzing away...

Best,
Per


On Tue, Oct 4, 2011 at 9:07 PM, Gregory Kirk <gkirk at wisc.edu> wrote:
> Hi,
>
> i have cortical thickness data i want to use as features, freesurfer has a matlab
> function that allows you to load the thickness data resampled onto the average surface
> as a mat file.
>
>
> say 60 x ~200,000 matrix 60 subjects and about 200000 values per subject ( features )
>
>
> so i can write this out from matlab as binary floats or ASCII and then
> is there something that can load this and reshape it to a pymvpa data set
> with 60 samples and 200000 features each.
>
>
> looked a bit but Dat import ,export and storage section has
>
>
> 'data_formats' is not hot, i.e. i can't click and go there and i could not find a data formats section
> looking around
>
>
> cheers
>
>
> Greg
>
> _______________________________________________
> 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
>