[pymvpa] pymvpa help

ibinliu at sina.com ibinliu at sina.com
Sun Feb 14 02:04:34 UTC 2016


Hi all,I'm new to pymvpa and need some help.My experiment contained 2 tasks (only 1 run). I performed single trial analysis to generate a beta map for every trial. I'd like to run classification analysis on these beta maps.The first column of attributes was taskA, taskA, ..., taskB, taskB... and the second column were 0s (since I only got 1 run).Is this right?
For each suject, I merged all the beta images into a single 4D file and used attr = SampleAttributes('attributes.txt') and ds=fmri_dataset(samples=‘bold.nii.gz’, targets=attr.targets, chunks=attr.chunks, mask=‘mask.nii.gz’) to load data.
How should I perform normalization? just zscore(ds)?
I want to run cross-validation (say 5 fold or leave-one-out), how could I set the partitioner?
Thanks in advance,Best regards,Bin Liu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20160214/1d6decf1/attachment.html>


More information about the Pkg-ExpPsy-PyMVPA mailing list