<div style="line-height:1.7;color:#000000;font-size:14px;font-family:Arial"><div>Dear Mile,</div>
<div>Thanks for your reply. In my script, I have set " ds = remove_invariant_features(ds)". I think this setting has replaced those voxels with zeros.</div>
<div>Cai Fei<br><br></div>
<div></div>
<div id="divNeteaseMailCard"></div>
<div><br></div>At 2014-08-18 08:32:29, "Mike E. Klein" <michaeleklein@gmail.com> wrote:<br>
<blockquote style="BORDER-LEFT: #ccc 1px solid; MARGIN: 0px 0px 0px 0.8ex; PADDING-LEFT: 1ex" id="isReplyContent">
<div dir="ltr">Some of your voxels have a Ħ°NaNĦħ value, perhaps due to preprocessing in SPM. FSL has a tool that will replace these values with zeros (I think), so that might resolve your issue.
<div><br></div>
<div>Best,</div>
<div>Mike</div></div>
<div class="gmail_extra"><br><br>
<div class="gmail_quote">On Sun, Aug 17, 2014 at 10:49 AM, cfygj <span dir="ltr"><<a href="mailto:cfygj@126.com" target="_blank">cfygj@126.com</a>></span> wrote:<br>
<blockquote style="BORDER-LEFT: #ccc 1px solid; MARGIN: 0px 0px 0px 0.8ex; PADDING-LEFT: 1ex" class="gmail_quote">
<div style="LINE-HEIGHT: 1.7; FONT-FAMILY: Arial; COLOR: #000000; FONT-SIZE: 14px">
<div>Hi all, IĦŻm just wondering if anyone has any advice on some ways to deal with my problems. Here is my scipt, which was used to run my data, then come out some error information. Could you tell me how to address its? <br><br><span style="FONT-SIZE: 48px">Scripts</span>:<br># Import necessary modules from os import path<br>import os<br>import numpy as N<br>import numpy.matlib as M<br>import <a href="http://scipy.io/" target="_blank">scipy.io</a> as sio<br>from mvpa2.suite import *<br>from mvpa2.mappers.detrend import poly_detrend<br>from mvpa2.datasets.mri import fmri_dataset<br>from mvpa2.datasets.miscfx import remove_invariant_features<br><br># Load fMRI data<br>attrs = SampleAttributes('attributes.txt')<br>ds = fmri_dataset(samples=('s1.nii.gz'), targets=attrs.targets, chunks=attrs.chunks)<br> <br># Detrend with motion correction parameter<br>mc = McFlirtParams('prefiltered_func_data_mcf.par') # detrend head motion <br>for param in mc:<br> <a href="http://ds.sa/" target="_blank">ds.sa</a>['mc_' + param] = mc[param]<br>res = poly_detrend(ds, opt_regs=['mc_x', 'mc_y', 'mc_z', 'mc_rot1', 'mc_rot2', 'mc_rot3'])<br><br># do chunkswise linear detrending on dataset<br>poly_detrend(ds, polyord=1, chunks_attr='chunks')<br><br># do z-score dataset relative to baseline ('rest') mean<br>zscore(ds, chunks_attr='chunks', param_est=('targets', [0]))<br><br># select subdata for each trial for mvpa analysis<br>ds = ds[N.array([l%6 == 3 for l in ds.sa.time_indices], dtype='bool')]<br>ds=remove_invariant_features(ds)<br><br># try classifier<br>partitioner = NFoldPartitioner()<br>repeater = Repeater(count=10000)<br>permutator = AttributePermutator('targets', limit={'partitions': 1}, count=1)<br>null_cv = CrossValidation(<br> clf, <br> ChainNode(<br> [partitioner, permutator],<br> space=partitioner.get_space()),<br> postproc=mean_sample())<br>distr_est = MCNullDist(repeater, tail='left', measure=null_cv, enable_ca=['dist_samples'])<br>cv_mc_corr = CrossValidation(clf,<br> partitioner,<br> postproc=mean_sample(),<br> null_dist=distr_est,<br> enable_ca=['stats'])<br><br>error = cv_mc_corr(ds)<br>Results_Error[0,0] = error.samples<br>p = cv_mc_corr.ca.null_prob<br>print 'p', p<br>assert(p.shape == (1,1))<br>Results_P[0,0] = p.samples[0,0]<br>Distribution = cv_mc_corr.null_dist.ca.dist_samples<br>distr_est.clean()<br><br><br><br><span style="FONT-SIZE: 48px">errors:</span><br>Traceback (most recent call last):<br> File "mvpa_classifier.py", line 84, in <module><br> error = cv_mc_corr(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/learner.py", line 259, in __call__<br> return super(Learner, self).__call__(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/node.py", line 120, in __call__<br> self._precall(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/measures/base.py", line 118, in _precall<br> self.__null_dist.fit(measure, ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/clfs/stats.py", line 403, in fit<br> res = measure(permuted_ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/learner.py", line 259, in __call__<br> return super(Learner, self).__call__(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/node.py", line 121, in __call__<br> result = self._call(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/measures/base.py", line 497, in _call<br> return super(CrossValidation, self)._call(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/measures/base.py", line 326, in _call<br> result = node(sds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/learner.py", line 259, in __call__<br> return super(Learner, self).__call__(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/node.py", line 121, in __call__<br> result = self._call(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/measures/base.py", line 617, in _call<br> res = measure(dstest)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/learner.py", line 259, in __call__<br> return super(Learner, self).__call__(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/base/node.py", line 121, in __call__<br> result = self._call(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/clfs/base.py", line 434, in _call<br> pred = self.predict(ds)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/clfs/base.py", line 47, in wrap_samples<br> return fx(obj, data, *args, **kwargs)<br> File "/usr/lib/python2.7/dist-packages/mvpa2/clfs/base.py", line 389, in predict<br> "Some input data for predict is not finite (NaN or Inf)")<br><span style="FONT-SIZE: 24px">ValueError: Some input data for predict is not finite (NaN or Inf)</span><br><br><br></div></div><br><br><span title="neteasefooter"><span></span></span><br>_______________________________________________<br>Pkg-ExpPsy-PyMVPA mailing list<br><a href="mailto:Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org">Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org</a><br><a href="http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa" target="_blank">http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa</a><br></blockquote></div><br></div></blockquote></div><br><br><span title="neteasefooter"><span id="netease_mail_footer"></span></span>