def constructPredictionWithOutput(classifier,classifierIndex,xTest, testBatchIndex):
print "Predicting with classifier {}".format(classifierIndex)
yPred = classifier.predict_proba(xTest)
print "Writing to csv..."
outputFileName="data\\ensembleTraining\\out"+str(classifierIndex)+".csv"
dataReader.writePredToCsv(yPred,testBatchIndex,outputFileName=outputFileName)
def predictForSubmission():
startTime = time.time()
allAlgorithmStartTime = startTime
numberOfTrainingExamples = -1
classifier = trainClassifierOnTrainingData(numberOfTrainingExamples)
print "Beginning to load test data..."
partitionNumber = utils.numberOfPartitions
for index in range(partitionNumber):
miniTestData = dataReader.getSerializedMiniTestData(index)
xTest,yTest = constructTestData(miniTestData)
print "Predicting..."
yPred = classifier.predict_proba(xTest)
dataReader.writePredToCsv(yPred,index)
print "Post processing..."
dataReader.postProcessCsv()
print("Total run time:{}".format(time.time() - allAlgorithmStartTime))
