import numpy as np
import pandas as pd
import xgboost as xgb
from sklearn.preprocessing import LabelEncoder

#Print you can execute arbitrary python code
train = pd.read_csv("../input/train.csv")
test = pd.read_csv("../input/test.csv")



#Preprocessing the data

#add new column to includ the title from 'Name'
train['Title'] = train['Name'].str.extract(' ([A-Za-z]+)\.', expand = False)
print(train['Title'][:5])
columns_include = ['Pclass', 'Sex', 'Age', 'Fare', 'SibSp', 'Parch','Embarked']

#Any files you save will be available in the output tab below
#train.to_csv('copy_of_the_training_data.csv', index=False)