<div dir="ltr"><div><div><div><div><div>Hi Yaroslav,<br><br></div>I hope you had some good downtime during holidays.<br><br></div>I am wondering if there is any straightforward solution for getting balanced accuracy using PyMVPA?<br><br></div>Best regards<br></div>Kaustubh<br><br></div>PS: Happy new year!!!<br><div><div><div><br></div></div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Dec 19, 2015 at 11:50 PM, Kaustubh Patil <span dir="ltr"><<a href="mailto:kaustubh.patil@gmail.com" target="_blank">kaustubh.patil@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Hi Yaroslav, thanks for help.<br><br></div>Here is summary for the dataset of one subject:<br><br>Dataset: 180x71039@float64, <sa: chunks,regressors,targets,volumes>, <fa: voxel_indices>, <a: add_regs,imgaffine,imghdr,imgtype,mapper,voxel_dim,voxel_eldim><br>stats: mean=3.55452e-15 std=1 var=1 min=-4.07657 max=3.95942<br><br>Counts of targets in each chunk:<br> chunks\targets 0 1<br> --- ---<br> 1 7 11<br> 2 16 2<br> 3 16 2<br> 4 13 5<br> 5 9 9<br> 6 9 9<br> 7 13 5<br> 8 15 3<br> 9 13 5<br> 10 9 9<br><br>Summary for targets across chunks<br> targets mean std min max #chunks<br> 0 12 3.1 7 16 10<br> 1 6 3.1 2 11 10<br><br>Summary for chunks across targets<br> chunks mean std min max #targets<br> 1 9 2 7 11 2<br> 2 9 7 2 16 2<br> 3 9 7 2 16 2<br> 4 9 4 5 13 2<br> 5 9 0 9 9 2<br> 6 9 0 9 9 2<br> 7 9 4 5 13 2<br> 8 9 6 3 15 2<br> 9 9 4 5 13 2<br> 10 9 0 9 9 2<br>Sequence statistics for 180 entries from set [0, 1]<br>Counter-balance table for orders up to 2:<br>Targets/Order O1 | O2 |<br> 0: 119 1 | 118 2 |<br> 1: 0 59 | 0 58 |<br>Correlations: min=-0.5 max=0.98 mean=-0.0056 sum(abs)=79<br><br><br><br></div><div class="HOEnZb"><div class="h5"><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Dec 19, 2015 at 11:00 PM, Yaroslav Halchenko <span dir="ltr"><<a href="mailto:debian@onerussian.com" target="_blank">debian@onerussian.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span><br>
On Sat, 19 Dec 2015, Kaustubh Patil wrote:<br>
<br>
</span><span>> Thanks a lot Yaroslav. I am following a procedure as described below please<br>
> let me know if it has any clear or potential problems. I am also throwing in<br>
> another questions here but can start another thread if its worth.<br>
<br>
> 1) Alignment procedure: Align all the runs to the middle volume of run1<br>
> (example_func from fsl). Use the mask that was generated by fsl form run1.<br>
<br>
</span>ok<br>
<span><br>
> 2) MVPA: do the classifiers give balanced accuracy as my datasets are not<br>
> balanced?<br>
<br>
</span>might need rebalancing. post output of your dataset.summary() here<br>
<span><br>
> Also, is it recommended to run searchlight on betamap (after fitting<br>
> hrf) or zscored raw data?<br>
<br>
</span>whatever fits your bill. usually betamaps, and possibly z-scored (per<br>
run or across all)<br>
<span><br>
> If betamap after fitting hrf then I using the<br>
> provided function I get only one parameter per target per run, is that how its<br>
> supposed to be?<br>
<br>
</span>ok if that is what you want to classify... some times you might<br>
want model each trial separately. there is no universal answer.<br>
<div><div><br>
--<br>
Yaroslav O. Halchenko<br>
Center for Open Neuroscience <a href="http://centerforopenneuroscience.org" rel="noreferrer" target="_blank">http://centerforopenneuroscience.org</a><br>
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755<br>
Phone: <a href="tel:%2B1%20%28603%29%20646-9834" value="+16036469834" target="_blank">+1 (603) 646-9834</a> Fax: <a href="tel:%2B1%20%28603%29%20646-1419" value="+16036461419" target="_blank">+1 (603) 646-1419</a><br>
WWW: <a href="http://www.linkedin.com/in/yarik" rel="noreferrer" target="_blank">http://www.linkedin.com/in/yarik</a><br>
<br>
_______________________________________________<br>
Pkg-ExpPsy-PyMVPA mailing list<br>
<a href="mailto:Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org" target="_blank">Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org</a><br>
<a href="http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa" rel="noreferrer" target="_blank">http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa</a></div></div></blockquote></div><br></div>
</div></div></blockquote></div><br></div>