<div dir="ltr">Well,<div>in classical MVPA you must perform feature selection within the cross-validation, that's why it seems that the feature selection is not performed in the snippet.<div>To use feature selection outside the cross-validation you should do</div><div><br></div><div>ds_fs = fsel(ds) # This line lets you to perform feature selection</div><div>res = dsm(ds_fs)</div><div><br></div><div>Bests,</div><div>R<br><div><br></div></div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On 24 August 2016 at 16:20, Alyson Saenz <span dir="ltr"><<a href="mailto:neuro.alyson@gmail.com" target="_blank">neuro.alyson@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"><p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif;background-image:initial;background-repeat:initial">Hey guys, I'm having
problems wrapping my head around this.</span><span lang="EN-US" style="font-size:12pt;font-family:"Times New Roman",serif"></span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">I'm trying to run a representational similarity
analysis RSA, on the same data in which I run a MVPA analysis to compare both
outputs. My problem is that when I introduce the data for MVPA, I use feature
selection like in the tutorial, so I grab 5% of the ANOVA’s output and use it
to train and test the data. But in the tutorial, seems like you grab all the
voxels, not only a selection.</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">How can I grab only the same 5% for RSA?</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">This is the code I use for MVPA:</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">clf = LinearCSVMC()</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">fsel =
SensitivityBasedFeatureSelecti<wbr>on(OneWayAnova(), FractionTailSelector(0.05,
mode='select', tail='upper'))</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">fclf = FeatureSelectionClassifier(<wbr>clf, fsel)</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">cvte = CrossValidation(fclf, NFoldPartitioner(),
errorfx=lambda p, t: np.mean(p == t), enable_ca=['stats'])</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">cv_results = cvte(ds)</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">This is the one I got for RSA:</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif"> </span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">dsm = rsa.PDist(square=True)</span></p>

<p class="MsoNormal" style="margin-bottom:0.0001pt"><span lang="EN-US" style="font-size:12pt;font-family:Arial,sans-serif">res = dsm(ds)</span></p></div>
<br>______________________________<wbr>_________________<br>
Pkg-ExpPsy-PyMVPA mailing list<br>
<a href="mailto:Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org">Pkg-ExpPsy-PyMVPA@lists.<wbr>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.<wbr>org/cgi-bin/mailman/listinfo/<wbr>pkg-exppsy-pymvpa</a><br></blockquote></div><br></div>