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 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 testGeneralPerformanceUsingCrossValidationScore():
# train 28k and test = 7k
# trainDataSize = 35000
trainDataSize = 150000
classifier = classifierSelector.constructGradientBoostingClassifier()
# classifier = classifierSelector.constructRandomForestClassifier()
# classifier = SVC(verbose=1)
xTrain,yTrain = constructTrainingData(trainDataSize)
cv = StratifiedShuffleSplit(yTrain,n_iter=1,train_size=50000,test_size=100000)
cv_scores = cross_val_score(classifier, xTrain, yTrain, cv=cv, n_jobs=-1,scoring="log_loss",verbose=1)
scoreMean = cv_scores.mean()
print "Mean score is {}".format(scoreMean)