def createEnsembleBasedODifferentTrainingSets():
# constructing the limits
margins = np.linspace(0,878000,5,dtype=int)
marginTuples=[]
for i in range(len(margins)-1):
marginTuples.append((margins[i],margins[i+1]))
# training classifiers
allClassifiers = Parallel(n_jobs=-1)(delayed(mainScript.trainClassifierOnTrainingData)(margins=marginTuple) for marginTuple in marginTuples)
# Predicting on batch test data
partitionNumber = utils.numberOfPartitions
for batchIndex in range(partitionNumber):
print "Predicting batch {}".format(batchIndex)
miniTestData = dataReader.getSerializedMiniTestData(batchIndex)
xTest,yTest = mainScript.constructTestData(miniTestData)
for classifierIndex,currentClassifier in enumerate(allClassifiers):
constructPredictionWithOutput(currentClassifier,classifierIndex,xTest,batchIndex)
# post process
print "Post processing everything..."
outputFileNames = ["data\\ensembleTraining\\out"+str(index)+".csv" for index in range(len(allClassifiers))]
for outputFileName in outputFileNames:
dataReader.postProcessCsv(outputFileName=outputFileName)
#Merging everything together
print "Merging all solutions...."
fileRegex = "data\\ensembleTraining\\*.csv"
createEnsembleBasedOnExitingPredictions(fileRegex=fileRegex)
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))
