<html>
  <head>
    <meta http-equiv="content-type" content="text/html;
      charset=ISO-8859-1">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    Hi,<br>
    <br>
    I try to use sphere_gnbsearchlight for Monte Carlo Testing to speed
    things up a bit. After figuring out the difference of arguments
    between sphere_gnbsearchlight and sphere_searchlight, I was able to
    set up everything without an argument error. However, when I run the
    searchlight analysis, it produces an error. Maybe, I misunderstood
    the usage of the arguments for sphere_gnbsearchlight, especially the
    generator argument. Any ideas what I am doing wrong here?<br>
    <br>
    thanks,<br>
    wolf<br>
    <br>
    <small><tt>clf  = GNB() </tt><tt><br>
      </tt><tt>splt = NFoldPartitioner(cvtype=2, attr='chunks') </tt><tt><br>
      </tt><tt>repeater   = Repeater(count=100) </tt><tt><br>
      </tt><tt>permutator = AttributePermutator('targets',
        limit={'partitions': 1}, count=1) </tt><tt><br>
      </tt><tt>null_cv = CrossValidation( clf, ChainNode([splt,
        permutator], space=splt.get_space()),
        errorfx=mean_mismatch_error, postproc=mean_sample()) </tt><tt><br>
      </tt><tt>distr_est = MCNullDist(repeater, tail='left',
        measure=null_cv, enable_ca=['dist_samples']) </tt><tt><br>
      </tt><tt>cv = CrossValidation(clf, splt,
        errorfx=mean_mismatch_error, enable_ca=['stats'], </tt><tt>postproc=mean_sample(),

        null_dist=distr_est) </tt><tt><br>
      </tt><tt>sl = sphere_gnbsearchlight(clf, cv, radius=3,
        space='voxel_indices', enable_ca=['roi_sizes']) </tt><tt><br>
      </tt></small>
    <blockquote type="cite">---------------------------------------------------------------------------<br>
      ValueError                                Traceback (most recent
      call last)<br>
      <br>
      /home/data/exppsy/zinke/binding/pub_related/mvpa_splitset_epispace/comb/<ipython

      console> in <module>()<br>
      <br>
      /usr/lib/pymodules/python2.6/mvpa2/base/learner.pyc in
      __call__(self, ds)<br>
          237                                    "used and auto training
      is disabled."<br>
          238                                    % str(self))<br>
      --> 239         return super(Learner, self).__call__(ds)<br>
          240 <br>
          241 <br>
      <br>
      /usr/lib/pymodules/python2.6/mvpa2/base/node.pyc in __call__(self,
      ds)<br>
           82 <br>
           83         self._precall(ds)<br>
      ---> 84         result = self._call(ds)<br>
           85         result = self._postcall(ds, result)<br>
           86 <br>
      <br>
      /usr/lib/pymodules/python2.6/mvpa2/measures/searchlight.pyc in
      _call(self, dataset)<br>
          132 <br>
          133         # pass to subclass<br>
      <br>
      --> 134         results = self._sl_call(dataset, roi_ids,
      nproc)<br>
          135 <br>
          136         if 'mapper' in dataset.a:<br>
      <br>
      /usr/lib/pymodules/python2.6/mvpa2/measures/adhocsearchlightbase.pyc

      in _sl_call(self, dataset, roi_ids, nproc)<br>
          366         # labels<br>
      <br>
          367         combinations[:, 0] = labels_numeric<br>
      --> 368         for ipartition, (split1, split2) in
      enumerate(splits):<br>
          369             combinations[split1.samples[:, 0],
      1+ipartition] = 1<br>
          370             combinations[split2.samples[:, 0],
      1+ipartition] = 2<br>
      <br>
      ValueError: need more than 1 value to unpack<br>
    </blockquote>
    <br>
    <br>
  </body>
</html>