def test(self, absList, modelfilename='', fold=None):
""" Apply ensemble of classifiers to given list of abstracts.
Ignores any given model file.
"""
for i in range(self.nClassifiers):
print 'test:', self.entityTypesString, i
if self.type == 'abstract':
self.finder.test(absList, self.modelFilenames[i])
else:
self.useBaggedFeatures(self.baggedFeatures[i], absList, self.modelFilenames[i], self.finder.test)
self.renameLabels(absList, i)
# resultFilename = '%s%s.r%d.ensemble.txt'%(self.entityTypesString, self.getFoldString(fold), self.randomSeed)
# resultsOut = open(resultFilename,'w')
print self.entityTypesString
for abstract in absList:
# resultsOut.write('---%s---' % abstract.id)
for sentence in abstract.sentences:
for token in sentence:
token.topKLabels[self.entityTypesString] = []
for i in range(self.nClassifiers):
token.topKLabels[self.entityTypesString].append(TokenLabel('other'))
eLabelMatches = token.getLabelMatches(self.ensembleTypes)
for eLabel in eLabelMatches:
[label, i] = self.toRegularLabel(eLabel)
tLabel = TokenLabel(label)
token.topKLabels[self.entityTypesString][i] = tLabel
# tLabel.prob = prob
# tLabel.sequenceProb = sequenceProb[i/2]
token.removeLabel(eLabel)
# if label != 'other':
# token.addLabel(label)
# resultsOut.write(str(ensembleLabels)+'\n')
# resultsOut.write('%s, %s\n' %(token.text.ljust(12), eLabelMatches))
self.finder.rerankLabelsAndAssign(absList, rerankType=self.rerankType, topKMax=5, fold=fold, countOther=self.countOther)
def getTopKLabelings(self, sentence, finder, topK):
""" return list of top k sequence labelings for the sentence """
labelings = []
for k in range(min(topK,finder.tokenClassifier.topK)):
topKLabelingExists = False
sequenceLabels = []
for token in sentence:
if finder.entityTypesString in token.topKLabels and k < len(token.topKLabels[finder.entityTypesString]):
label = token.topKLabels[finder.entityTypesString][k]
topKLabelingExists = True
else:
# give each token a label. number finder labelings typically only label numbers and not other tokens.
label = TokenLabel('other')
label.prob = 0
sequenceLabels.append(label)
if topKLabelingExists or k == 0:
# only keep labeling if it is the first one (may be all 'other'), or if the labeling exists.
labelings.append(sequenceLabels)
return labelings