def getscoreofLP(labeledrecords,unlabeledrecords,shuffledbutlabeled,records):
Y_actualLP = []
for i in range(len(unlabeledrecords)):
Y_actualLP.append(shuffledbutlabeled[i][1])
for i in range((int)(0.7 * len(records)), len(records)): # test data included in LP
Y_actualLP.append(shuffledbutlabeled[i][1])
unlabeledrecordsLP = copy.deepcopy(unlabeledrecords)
temp = copy.deepcopy(records[(int)(0.7 * len(records)):])
for record in temp:
unlabeledrecordsLP.append(record)
for record in unlabeledrecordsLP:
record[1] = -1
probabilities = runlabelprop(labeledrecords, unlabeledrecordsLP)
predictedLP = []
count = 0
for p in probabilities:
maxprob = max(p)
if(math.isnan(maxprob)):
# print 'yes'
predictedLP.append(random.randint(1,len(p)))
else:
index = p.tolist().index(maxprob)
predictedLP.append(index)
count +=1
print 'done with LP, moving ahead'
return metrics.f1_score(y_true=Y_actualLP, y_pred=predictedLP)
def getscoreofLP(labeledrecords, unlabeledrecords, shuffledbutlabeled,
records):
Y_actualLP = []
for i in range(len(unlabeledrecords)):
Y_actualLP.append(shuffledbutlabeled[i][1])
for i in range((int)(0.7 * len(records)),
len(records)): # test data included in LP
Y_actualLP.append(shuffledbutlabeled[i][1])
unlabeledrecordsLP = copy.deepcopy(unlabeledrecords)
temp = copy.deepcopy(records[(int)(0.7 * len(records)):])
for record in temp:
unlabeledrecordsLP.append(record)
for record in unlabeledrecordsLP:
record[1] = -1
probabilities = runlabelprop(labeledrecords, unlabeledrecordsLP)
predictedLP = []
count = 0
for p in probabilities:
maxprob = max(p)
if (math.isnan(maxprob)):
# print 'yes'
predictedLP.append(random.randint(1, len(p)))
else:
index = p.tolist().index(maxprob)
predictedLP.append(index)
count += 1
print 'done with LP, moving ahead'
return metrics.f1_score(y_true=Y_actualLP, y_pred=predictedLP)
labeledrecords = separatedrecords[0]
unlabeledrecords = separatedrecords[1]
nooflabeledrecords = len(labeledrecords)
f1LP = getscoreofLP(labeledrecords,unlabeledrecords,shuffledbutlabeled,records)
initlabeledrecords = nooflabeledrecords
probabiltythreshold = 0.99
noofiterations = 0
perofrecordslabeledperiteration = []
classifier = 'SVM'
while nooflabeledrecords < len(trainingrecords):
probabilities = runlabelprop(labeledrecords,unlabeledrecords)
predictedclasses = runclassifier(labeledrecords,unlabeledrecords,classifier)
newlyadded = 0
foundTarget = False
for i in range(len(probabilities)):
if probabilities[i][predictedclasses[i]-1] >= probabiltythreshold: # predictedclasses[i]-1 if no 0 class label
foundTarget = True
unlabeledrecords[i-newlyadded][1] = predictedclasses[i]
labeledrecords.append(unlabeledrecords.pop(i-newlyadded))
newlyadded+=1
if foundTarget == False:
break
perofrecordslabeledperiteration.append((float(newlyadded)/nooflabeledrecords) *100 )
print 'newly labeled ' , newlyadded,
labeledrecords = separatedrecords[0]
unlabeledrecords = separatedrecords[1]
nooflabeledrecords = len(labeledrecords)
f1LP = getscoreofLP(labeledrecords, unlabeledrecords, shuffledbutlabeled,
records)
initlabeledrecords = nooflabeledrecords
probabiltythreshold = 0.99
noofiterations = 0
perofrecordslabeledperiteration = []
classifier = 'SVM'
while nooflabeledrecords < len(trainingrecords):
probabilities = runlabelprop(labeledrecords, unlabeledrecords)
predictedclasses = runclassifier(labeledrecords, unlabeledrecords,
classifier)
newlyadded = 0
foundTarget = False
for i in range(len(probabilities)):
if probabilities[i][
predictedclasses[i] -
1] >= probabiltythreshold: # predictedclasses[i]-1 if no 0 class label
foundTarget = True
unlabeledrecords[i - newlyadded][1] = predictedclasses[i]
labeledrecords.append(unlabeledrecords.pop(i - newlyadded))
newlyadded += 1
if foundTarget == False:
break
