<html><body><div style="color:#000; background-color:#fff; font-family:arial, helvetica, sans-serif;font-size:10pt"><div><span>Hello Everyone,</span></div><div><br></div><div>I have a question about MaximalVote. I'm getting an error on:</div><div><span><br></span></div><div><span>voting=MaximalVote(enable_ca=['estimates'])   </span></div><div><span><br></span></div><div><span>TypeError: __init__() got an unexpected keyword argument 'enable_ca'<br></span></div><div><span><br></span></div><div><span>The documentation page : http://www.pymvpa.org/generated/mvpa.clfs.meta.MaximalVote.html#mvpa.clfs.meta.MaximalVote </span></div><div><span>shows "enable_ca" as a valid argument.</span></div><div><span><br></span></div><div><span>I am using python-pymvpa-snapshot from neuro-debian in ubuntu 10.10, 64bit.</span></div><div><br></div><div>I am using this object in the following context:</div><div><span class="Apple-tab-span"
 style="white-space:pre">                                  </span># inner_part is a custom partitioner which provides random subsets of the training set </div><div><div><span class="Apple-tab-span" style="white-space:pre">                                      </span>voting = MaximalVote()<span class="Apple-tab-span" style="white-space:pre">      </span> </div><div>                                        # voting=MaximalVote(enable_ca=['estimates'])    # desired but produces error</div><div>   <span class="Apple-tab-span" style="white-space:pre">                              </span>   <span class="Apple-tab-span" style="white-space:pre">    </span>comb_clf = SplitClassifier(LinearCSVMC(C=1), </div><div><span class="Apple-tab-span" style="white-space:pre">                                                                                           </span>partitioner=inner_part, </div><div><span class="Apple-tab-span" style="white-space:pre">                                                                                        
        </span>splitter=splitter, </div><div><span class="Apple-tab-span" style="white-space:pre">                                                                                             </span>combiner=voting)</div><div> <span class="Apple-tab-span" style="white-space:pre">                                       </span>spartitions = partitions[:, indices]</div><div>  <span class="Apple-tab-span" style="white-space:pre">                                     </span>tm = TransferMeasure(comb_clf, splitter, </div><div><span class="Apple-tab-span" style="white-space:pre">                                                                                       </span>postproc=BinaryFxNode(mean_mismatch_error, space='targets'),  </div><div><span class="Apple-tab-span" style="white-space:pre">                                                                                  </span>enable_ca=['stats','raw_results'])</div><div> <span class="Apple-tab-span" style="white-space:pre">     </span><span class="Apple-tab-span" style="white-space:pre">                            </span>tm(spartitions)</div><div><br></div><div>I would like to see the "<span class="Apple-style-span" style="font-family: Arial, sans-serif; font-size: 18px; line-height: 23px; "><tt
 class="xref py py-obj docutils literal" style="background-color: transparent; padding-top: 0px; padding-right: 1px; padding-bottom: 0px; padding-left: 1px; font-size: 16px; font-weight: bold; "><span class="pre">estimates</span></tt>: Estimates keep counts across classifiers for each label/sample</span>"</div><div><br></div><div>As you might have guessed, this intends to be example-wise bagging.</div><div><br></div><div><br></div><div>Any suggestions on how to circumvent this issue or make sure the voting procedure operates as expected?</div><div><br></div><div><br></div><div>Many thanks!</div></div><div><font size="2">Andrei<br></font></div></div></body></html>