[pymvpa] searchlight for data with different runs with different masks

[Kaustubh Patil]

Hi Yaroslav,

I hope you had some good downtime during holidays.

I am wondering if there is any straightforward solution for getting
balanced accuracy using PyMVPA?

Best regards
Kaustubh

PS: Happy new year!!!


On Sat, Dec 19, 2015 at 11:50 PM, Kaustubh Patil <kaustubh.patil at gmail.com>
wrote:

> Hi Yaroslav, thanks for help.
>
> Here is summary for the dataset of one subject:
>
> Dataset: 180x71039 at float64, <sa: chunks,regressors,targets,volumes>, <fa:
> voxel_indices>, <a:
> add_regs,imgaffine,imghdr,imgtype,mapper,voxel_dim,voxel_eldim>
> stats: mean=3.55452e-15 std=1 var=1 min=-4.07657 max=3.95942
>
> Counts of targets in each chunk:
>   chunks\targets  0   1
>                  --- ---
>         1         7   11
>         2         16  2
>         3         16  2
>         4         13  5
>         5         9   9
>         6         9   9
>         7         13  5
>         8         15  3
>         9         13  5
>        10         9   9
>
> Summary for targets across chunks
>   targets mean std min max #chunks
>     0      12  3.1  7   16    10
>     1       6  3.1  2   11    10
>
> Summary for chunks across targets
>   chunks mean std min max #targets
>     1      9   2   7   11     2
>     2      9   7   2   16     2
>     3      9   7   2   16     2
>     4      9   4   5   13     2
>     5      9   0   9   9      2
>     6      9   0   9   9      2
>     7      9   4   5   13     2
>     8      9   6   3   15     2
>     9      9   4   5   13     2
>    10      9   0   9   9      2
> Sequence statistics for 180 entries from set [0, 1]
> Counter-balance table for orders up to 2:
> Targets/Order  O1     |   O2     |
>       0:      119  1  |  118  2  |
>       1:       0  59  |   0  58  |
> Correlations: min=-0.5 max=0.98 mean=-0.0056 sum(abs)=79
>
>
>
>
> On Sat, Dec 19, 2015 at 11:00 PM, Yaroslav Halchenko <
> debian at onerussian.com> wrote:
>
>>
>> On Sat, 19 Dec 2015, Kaustubh Patil wrote:
>>
>> > Thanks a lot Yaroslav. I am following a procedure as described below
>> please
>> > let  me know if it has any clear or potential problems. I am also
>> throwing in
>> > another questions here but can start another thread if its worth.
>>
>> > 1) Alignment procedure: Align all the runs to the middle volume of run1
>> > (example_func from fsl). Use the mask that was generated by fsl form
>> run1.
>>
>> ok
>>
>> > 2) MVPA: do the classifiers give balanced accuracy as my datasets are
>> not
>> > balanced?
>>
>> might need rebalancing.  post output of your dataset.summary() here
>>
>> > Also, is it recommended to run searchlight on betamap (after fitting
>> > hrf) or zscored raw data?
>>
>> whatever fits your bill.  usually betamaps, and possibly z-scored (per
>> run or across all)
>>
>> > If betamap after fitting hrf then I using the
>> > provided function I get only one parameter per target per run, is that
>> how its
>> > supposed to be?
>>
>> ok if that is what you want to classify... some times you might
>> want model each trial separately.  there is no universal answer.
>>
>> --
>> Yaroslav O. Halchenko
>> Center for Open Neuroscience     http://centerforopenneuroscience.org
>> Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
>> Phone: +1 (603) 646-9834                       Fax: +1 (603) 646-1419
>> WWW:   http://www.linkedin.com/in/yarik
>>
>> _______________________________________________
>> 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/20160105/dbd55f1b/attachment.html>