def constructTrainingData(trainDataSize):
#training data
trainData = dataReader.getTrainData(trainDataSize)
trainData = trainData.append(dataReader.getSuffixDataFrame())
# feature engineering
trainData = regularFeatExtr.convertTargetFeatureToNumeric(trainData)
xTrain, yTrain = regularFeatExtr.getRegularFeatures(trainData, True)
return xTrain,yTrain
def testParameterPerformance():
startTime = time.time()
allAlgorithmStartTime = startTime
# define sizes
trainDataSize = 10000
testDataSize = 100000
trainData,testData = utils.getDifferentTrainAndTestData(trainDataSize,testDataSize)
#in order to assure that we have members form each class present
testData = testData.append(dataReader.getSuffixDataFrame())
classifier = trainClassifierOnTrainingData(trainData=trainData)
xTest,yTest = constructTestData(testData)
yPred = classifier.predict(xTest)
validator.performValidation(yPred, yTest)
print("Total run time:{} s".format((time.time() - allAlgorithmStartTime)))