def calculateLearningCurve():
classifier = classifierSelector.constructGradientBoostingClassifier()
trainData = dataReader.getTrainData()
# feature engineering
trainData = featureExtractor.convertTargetFeatureToNumeric(trainData)
xTrain, yTrain = featureExtractor.getRegularFeatures(trainData, True)
trainSizes = np.linspace(100000,500000,5,dtype=int)
plot_learning_curve(classifier,xTrain,yTrain,trainSizes)
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 trainClassifierOnTrainingDataReturnAll(numberOfTrainingExamples = -1):
trainData = dataReader.getTrainData(numberOfTrainingExamples)
# feature engineering
trainData = featureExtractor.convertTargetFeatureToNumeric(trainData)
xTrain, yTrain = featureExtractor.getRegularFeatures(trainData, True)
# classifier training
classifier = classifierSelector.trainClassifier(xTrain, yTrain)
return classifier, xTrain, yTrain
def calculateValidationCurve():
classifier = classifierSelector.constructGradientBoostingClassifier()
numberOfTrainData = 50000
trainData = dataReader.getTrainData(numberOfTrainData)
# feature engineering
trainData = featureExtractor.convertTargetFeatureToNumeric(trainData)
xTrain, yTrain = featureExtractor.getRegularFeatures(trainData, True)
paramRange = [0.1,0.13,0.16]
plot_validation_curve(classifier,xTrain,yTrain,"learning_rate",paramRange)
def trainClassifierOnTrainingData(trainData=None, numberOfTrainingExamples = -1, margins=None):
if trainData is None:
trainData = dataReader.getTrainData(numberOfTrainingExamples,margins)
# feature engineering
trainData = regularFeatExtr.convertTargetFeatureToNumeric(trainData)
xTrain, yTrain = regularFeatExtr.getRegularFeatures(trainData, True)
# classifier training
classifier = classifierSelector.trainClassifier(xTrain, yTrain)
return classifier
def constructTestData(testData):
testData = regularFeatExtr.convertTargetFeatureToNumeric(testData)
xTest, yTest = regularFeatExtr.getRegularFeatures(testData, False)
return xTest,yTest