Hi all,
Thanks so much for your quick and thoughtful suggestions! I'm still
processing all the info, and will most likely try out a few different
methods (all of this in tandem with learning the PyMVPA software, itself!).
I hadn't previously considered the smoothing effects of interpolation from
Hi all,
I'm trying to get a very basic script working that implements RFE. I'm not
a coder, but I've read the tutorial and am trying to follow others' scripts
as best as possible. Generally, I hope to do small modifications of standard
scripts (changing my 4d bold data, my mask, attributes.txt
shogun.svmocas = no
have shogun.svrlight = no
have skl = yes
have weave = yes
On Mon, Oct 10, 2011 at 3:55 AM, Michael Hanke m...@debian.org wrote:
Hey,
On Sat, Oct 08, 2011 at 01:35:06PM -0400, Mike E. Klein wrote:
Just wondering if anyone had any advice on this… I'm pretty hopelessly
stuck
Thanks…I'll take a look and see if I can figure out what's going on there.
On Wed, Oct 12, 2011 at 2:54 PM, Michael Hanke m...@debian.org wrote:
On Tue, Oct 11, 2011 at 10:12:30AM -0400, Mike E. Klein wrote:
PyMVPA:
Version: 0.6.0~rc3
Hash
...@onerussian.com wrote:
just for completeness :
what is the output of
print ds.summary()
?
also, if you crossplot A against A* -- how does it look?
On Thu, 20 Oct 2011, Mike E. Klein wrote:
Hi everyone,
Thanks in advance for any help and sorry for the length of this:
I've been performing
',
argument 2 of type 'double'
On Thu, Oct 20, 2011 at 3:11 PM, Yaroslav Halchenko
deb...@onerussian.com wrote:
On Thu, 20 Oct 2011, Mike E. Klein wrote:
little runs or 9 big runs. I've initially gone with the 27-run
route (i.e. created an attribute file with 27 chunks), mainly for the
somewhat
Ha! Yes, I'm very much beholden to the developers and community: I'm a
cog neuro person who admittedly lacks some fundamental skills here
(though trying!).
I wasn't getting that error… at the time of zscoring I hadn't yet
removed category #3, so it was seeing -exactly- 3 samples per chunk.
On
deb...@onerussian.comwrote:
On Thu, 20 Oct 2011, Mike E. Klein wrote:
I wasn't getting that error… at the time of zscoring I hadn't yet
removed category #3, so it was seeing -exactly- 3 samples per chunk.
aha... indeed... may be we should warn if number of samples per chunk
some reasonable
I'd recommend using this person's guide, which I found very helpful:
http://www.jonaskaplan.com/lab/pymvpainstallation.php/
On Wed, Oct 26, 2011 at 11:43 AM, Yaroslav Halchenko
deb...@onerussian.comwrote:
well -- then nibabel need to be installed one way or another... not sure
if ports have
Hi all,
I realize now (after a boneheaded mistake), that PyMVPA's zscore() function
is normalizing for all the values across a chunk (looking at each voxel
individually). I'm wondering if it's possible to, instead, find the zscores
for all the voxels in a single volume (against each voxel's
-= np.mean(ds, axis=1)[:, None]
ds.samples /= np.std(ds, axis=1)[:, None]
* I do care about per-voxel estimates of diagnosticity
DO NOT ZSCORE ACROSS FEATURES (VOXELS)! ;)
On Mon, 07 Nov 2011, Mike E. Klein wrote:
Hi all,
I realize now (after a boneheaded mistake), that PyMVPA's
Hi,
Yes, that makes sense now. Thanks for the time and thought you put into it!
Best,
Mike
On Mon, Nov 7, 2011 at 6:20 PM, Yaroslav Halchenko deb...@onerussian.comwrote:
On Mon, 07 Nov 2011, Mike E. Klein wrote:
- My reason for wanting to do this is because of a relative paucity
Hi all,
I'm wondering if someone could point me in the direction of calculating the
effect sizes of voxels in time series against the series' baseline
conditions. Ideally over multiple experimental chunks/runs.
For reasons that I simply can't figure out, zscore-ing my data *always* brings
down
wondered to get
better idea of what might be happening in your case
On Fri, 16 Dec 2011, Mike E. Klein wrote:
where my baseline condition is silence. Without zscoring, SVMs can
tell
any of the sound conditions vs. the silence condition at 98-100%
accuracy...which makes sense
of subjects) or why using zscore
against rest has such a detrimental effect on my accuracies…
Thanks and best,
Mike
On Fri, Dec 16, 2011 at 11:53 PM, Mike E. Klein michaelekl...@gmail.comwrote:
Thanks for the response!
I just took a really quick first look (just a single 2-way comparison
(but more representative) examples.
Hopefully all of the above made sense. Happy holidays, everyone, and thanks
as always!
-Mike
On Thu, Dec 22, 2011 at 11:43 PM, Mike E. Klein michaelekl...@gmail.comwrote:
OK, I think I'm starting to get this… after mightily confusing myself!
So my subjects
Hi Jonas and Jo,
Thanks for helping out with this!
So:
(1) I haven't done a permutation test. By chance distribution I just
meant the bulk of the data points using my real-label-coded data. While I'm
obviously hoping for a histogram that contains a positive skew, *at worst* I'd
expect a normal
Hi all,
Could anyone tell me if there's a tangible difference between using the
LinearNuSVMC() and LinearCSVMC() classifiers? Also, in order to have the
classifier choose its own best fit, is it best practice to leave the area
between the brackets blank, or to but in a value of C=-1 ? I think
Hi all,
Thanks again for the continued help. I think the skews are for the reasons
suggested here… I'm seeing them in a couple subjects in the positive
direction as well as the negative, and I've made quite certain that my
preprocessing is correct. I'll be mindful of the histos and, for now,
Hi everyone,
I'm attempting to threshold group data for a searchlight-based MVPA . I am
performing the group-wise stats via a standard top-level analysis in SPM
(using single-subject searchlight accuracy maps as inputs). I am having
difficulty figuring out where to set significance thresholds.
significant than you might hope.
good luck,
Jo
On 7/5/2012 12:21 PM, Mike E. Klein wrote:
Hi everyone,
I'm attempting to threshold group data for a searchlight-based MVPA . I
am performing the group-wise stats via a standard top-level analysis in
SPM (using single-subject searchlight accuracy
www.princeton.edu/~matthewb/Publications/*tutorial*.pdf
http://scan.oxfordjournals.org/content/4/1/101.full
www.bcn-nic.nl/txt/people/publications/*Etzel*2009.pdf
On Wed, Sep 19, 2012 at 11:22 AM, Abduljalil Sireis kentman...@gmail.comwrote:
On Wed, Sep 19, 2012 at 4:56 PM, J.A. Etzel
Hi all,
I’m running some searchlights where (due to task mis-performance and the
need to throw out some volumes) there are unbalanced categories, where the
exact number of examples/target differ from subject to subject (and from
chunk to chunk within subjects!). There aren’t -too- many of these
Hi all,
I’m attempting to use pymvpa2-prep-afni-surf to preprocess my freesurfer
data before running surface searchlights. As I can’t get AFNI/SUMA
installed on my Mavericks osx system, I’m doing this all through VMware and
NeuroDebian (with PyMVPA and AFNI/SUMA installed).
I believe I’m
Thanks, got it now on my native OSX.
On Sat, May 10, 2014 at 8:20 PM, Yaroslav Halchenko
deb...@onerussian.comwrote:
On Fri, 09 May 2014, Mike E. Klein wrote:
Hi all,
I’m attempting to use pymvpa2-prep-afni-surf to preprocess my
freesurfer
data before running surface
on the resolution/voxel size I should
use!) And thank you again for all of this assistance…I can’t overemphasize
how much I appreciate it.
Best,
Mike
On Mon, Feb 9, 2015 at 10:10 AM, Nick Oosterhof
n.n.ooster...@googlemail.com wrote:
Hello Mike,
On 08 Feb 2015, at 20:58, Mike E. Klein michaelekl
Many thanks, once again Nick! The full pipeline now works for me.
On Thu, Apr 16, 2015 at 8:50 AM, Nick Oosterhof
n.n.ooster...@googlemail.com wrote:
On 12 Apr 2015, at 00:53, Mike E. Klein michaelekl...@gmail.com wrote:
I’m trying to run a sample top-level analysis on surface-based
, Mike E. Klein michaelekl...@gmail.com wrote:
I’m trying to run a sample top-level analysis on surface-based
searchlight data using Nick’s afni_surface_alphasim script. I’ve never
tried this before, and am getting a ZeroDivisionError (bottom of output). I
tried re-running the script, leaving out
Thanks, Nick. I’ll send you a message separately.
Best,
Mike
On Sun, Apr 12, 2015 at 10:52 AM, Nick Oosterhof
n.n.ooster...@googlemail.com wrote:
On 12 Apr 2015, at 15:30, Mike E. Klein michael.e.kl...@gmail.com wrote:
No luck, unfortunately: the script is yielding the same errors with -N
Hi Nick and PyMVPA group,
I’m trying to run a sample top-level analysis on surface-based searchlight
data using Nick’s afni_surface_alphasim script. I’ve never tried this
before, and am getting a ZeroDivisionError (bottom of output). I tried
re-running the script, leaving out some subjects (in
30 matches
Mail list logo