def prepareTest(self, corpus, typeCorpus, indiceSvm = 0):
"""
Prepare CRF test data
Parameters
----------
corpus : Corpus
typeCorpus : int, {1, 2, 3}
1 : corpus 1, 2 : corpus 2...
indiceSvm : int, {0, -1, 2}
0 : normal(corpus 1)
-1 : data04SVM (corpus2),
2 : external data => svm isn't called
"""
listReferences = corpus.getListReferences(typeCorpus)
listReferencesObj = ListReferences(listReferences, typeCorpus)
extractor = Extract_crf(self.options)
nbRef = corpus.nbReference(typeCorpus)
'generation of test index for each reference'
extractor.randomgen(ListReferences(listReferencesObj.getReferences(),typeCorpus), 0)
if indiceSvm == -1:
extractor.extract(typeCorpus, nbRef, self.dirResult+"data04SVM_ori.txt", ListReferences(listReferencesObj.getReferences(),typeCorpus))
else:
'file for CRF training'
if typeCorpus == 2 and indiceSvm != 2 :
extractor.extractIndices4new(self.dirResult+"svm_predictions_new", ListReferences(listReferencesObj.getReferences(),typeCorpus))
extractor.extract(typeCorpus, nbRef, self.dirResult+"testdatawithlabel_CRF.txt",ListReferences(listReferencesObj.getReferences(),typeCorpus), -1, 1)
extractor.extract(typeCorpus, nbRef, self.dirResult+"testdata_CRF.txt",ListReferences(listReferencesObj.getReferences(),typeCorpus), 0, 1)
return ListReferences(listReferencesObj.getReferences(),typeCorpus)
