winn

import pandas as pd
def getdata(csvFile):
	dat = pd.read_csv(csvFile)
	return dat

winn

import pandas as pd
def getdata(csvFile):
	dat = pd.read_csv(csvFile)
	return dat

winn

def split_data_and_label(dat):
	label = dat['Survived'].values
	dat = dat.drop('Survived',axis=1)
	return label,dat

winn

def feature_extraction(featMat):
	featMat = featMat._get_numeric_data()
	featMat = featMat.fillna(0)
	return featMat

winn

from sklearn.ensemble import GradientBoostingClassifier
def trainclassifer(feat,label):
	mod = GradientBoostingClassifier()
	mod.fit(feat,label)
	return mod

winn

def evaluation_accuracy(prediction,actual):
	acc = sum(prediction==actual)/len(prediction)
	return acc

winn

def pipeline():
	csvFile = 'train.csv'
	tldat = getdata(csvFile)
	trainLabel,trainDat = split_data_and_label(tldat)
	trainFeat = feature_extraction(trainDat)
	csvFile = 'test.csv'
	tldat = getdata(csvFile)
	testLabel,testDat = split_data_and_label(tldat)
	testFeat = feature_extraction(testDat)
	mod = trainclassifer(trainFeat,trainLabel)

winn

def converttobinary(dat,col,attribute):
	dat[attribute] = (dat[col] == attribute).astype('int')
	return dat

winn

def feature_extraction(featMat):
	featMat = converttobinary(featMat,'Sex','male')
	featMat = featMat._get_numeric_data()
	featMat = featMat.fillna(0)
	return featMat

winn

def createdummie(dat,col):
	dummiefeature = pd.get_dummies(dat[col])
	dummiefeature = dummiefeature.iloc[:,0:-1]
	dat = pd.concat([dat,dummiefeature],axis=1)
	return dat