<div dir="ltr"><div>Hi all,</div><div><br></div><div>I am new user of PyMVPA and I've
been using it for quite a few months now. I'm having trouble getting a
searchlight AUC brain map as the output for my analysis. When I am not
running searchlight, I am able to extract AUC values from the 'stats'
conditional attribute of the CrossValidation object. However, I'm not
sure how to make searchlight use AUC values from the 'stats' conditional
attribute.<br></div><div><br></div><div>The other option I have is to set 'errorfx=mvpa2.misc.errorfx.auc_error' in the C.V. object but that just gives me the following error: <br><div><span class="gmail-m_-7357388952326854139gmail-kw2">AttributeError</span>: <span class="gmail-m_-7357388952326854139gmail-st0">'bool'</span> <span class="gmail-m_-7357388952326854139gmail-kw2">object</span> has no attribute <span class="gmail-m_-7357388952326854139gmail-st0">'sum' in errorfx.pyc ---></span><a href="https://pastebin.com/3MBMsK2M" target="_blank">https://pastebin.com/3MBMsK2M</a>(non-searchlight-code) and <a href="https://pastebin.com/SYXMXt43" target="_blank">https://pastebin.com/SYXMXt43</a>(searchlight code). I have version 2.6.5 of pymvpa installed.</div><div><br></div></div><div>The key parts of the code snippet I am using to generate the searchlight output is as follows:</div><div><br></div><div>mvpa_lsvm_clf = mvpa2.clfs.svm.LinearCSVMC(C=1) <br><br>cv_lsvm_mvpa = CrossValidation(mvpa_lsvm_clf, <br> ChainNode([NFoldPartitioner(),<br> Balancer(attr='targets',count=1,limit='partitions',apply_selection=True)],<br> space='partitions'),<br> errorfx=mvpa2.misc.errorfx.auc_error,<br> enable_ca=['stats'])<br><br>sl = sphere_searchlight(cv_lsvm_mvpa, radius=3, postproc=mean_sample())<br>sl_result_lsvm = sl(evds_binary)<br></div><div><br></div><div>Any
comments or examples of how to make an AUC brain map instead of an
accuracy brain map from searchlight is much appreciated. Thanks!<br></div><div><br></div><div>Best,</div><div>Sean Tey</div></div>