def readLabelFile(self, labelFilename, entityTypes):
""" read a mallet label file and return the list of labels """
labelLines = open(labelFilename, 'r').readlines()
labelList = []
if len(entityTypes) == 1:
binaryClassification = True
else:
binaryClassification = False
labelConversionList = ['other']
for eType in entityTypes:
labelConversionList.append(eType)
for line in labelLines:
parsedLine = line.strip().split()
if len(parsedLine) > 0:
mClass = int(parsedLine[0])
prob = float(parsedLine[1])
if binaryClassification:
if prob < self.binaryThreshold:
mClass = 0
else:
mClass = 1
label = labelConversionList[mClass]
tLabel = TokenLabel(label)
tLabel.prob = prob
tLabel.sequenceProb = 1
labelList.append([tLabel])
# labelList.append(label)
return labelList
def readLabelFile(self, labelFilename, entityTypes):
""" read a mallet label file and return the list of labels """
labelLines = open(labelFilename, 'r').readlines()
labels = []
lineNo = 1
sequenceProb = []
for i in range(self.topK):
sequenceProb.append(0.0)
currentTopK = self.topK
for line in labelLines:
try:
topKLabels = line.strip().split()
if len(topKLabels) > 0:
if topKLabels[0] == 'k' :
newTopK = int(topKLabels[1])
if newTopK != currentTopK:
currentTopK = newTopK
sequenceProb = []
for i in range(currentTopK):
sequenceProb.append(0.0)
# this is the list of sequence probabilities
for i in range(currentTopK):
sequenceProb[i] = float(topKLabels[i+2])
# print lineNo, topKLabels[1], currentTopK, sequenceProb
elif len(topKLabels) == 2*currentTopK:
tokenLabelList = []
for i in range(0,currentTopK*2,2):
label = topKLabels[i]
prob = float(topKLabels[i+1])
tLabel = TokenLabel(label)
tLabel.prob = prob
tLabel.sequenceProb = sequenceProb[i/2]
tokenLabelList.append(tLabel)
# print 'Read:', tLabel.label, tLabel.sequenceProb, tLabel.prob
labels.append(tokenLabelList)
# if len(topKLabels) == self.topK:
# # for i in range(len(topKLabels)):
# # if topKLabels[i] == 'O':
# # topKLabels[i] = 'other'
# if self.topK == 1:
# labels.append(topKLabels[0])
# else:
# labels.append(topKLabels)
except:
print '%s: Error at line number %d' % (labelFilename, lineNo)
lineNo += 1
return labels
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
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)