aniruddha27

#multiple indexes
table = pd.pivot_table(df,index=['Sex','Pclass'])
table

aniruddha27

#different aggregate functions
table = pd.pivot_table(df,index=['Sex','Pclass'],aggfunc={'Age':np.mean,'Survived':np.sum})
table

aniruddha27

table = pd.pivot_table(df,index=['Sex','Pclass'],values=['Survived'], aggfunc=np.mean)
table

aniruddha27

table.plot(kind='bar');

aniruddha27

#columns
table = pd.pivot_table(df,index=['Sex'],columns=['Pclass'],values=['Survived'],aggfunc=np.sum)
table

aniruddha27

table.plot(kind='bar');

aniruddha27

#display null values
table = pd.pivot_table(df,index=['Sex','Survived','Pclass'],columns=['Embarked'],values=['Age'],aggfunc=np.mean)
table

aniruddha27

#handling null values
table = pd.pivot_table(df,index=['Sex','Survived','Pclass'],columns=['Embarked'],values=['Age'],aggfunc=np.mean,fill_value=np.mean(df['Age']))
table

aniruddha27

# Total surface area of house
train['TotalSF'] = train.apply(lambda x: x['1stFlrSF'] + x['2ndFlrSF'] + x['TotalBsmtSF'], axis=1)

# Total number of bathrooms in the house
train['TotalBath'] = train.apply(lambda x: x['FullBath'] + 0.5*x['HalfBath'] + x['BsmtFullBath'] + 0.5*x['BsmtHalfBath'], axis=1)

# Total Porch area in the house
train['TotalPorch'] = train.apply(lambda x: x['OpenPorchSF'] + x['EnclosedPorch'] + x['3SsnPorch'] + x['ScreenPorch'], axis=1)

# New house or an old house

aniruddha27

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

col = train.columns

for i in col:
    if train[i].dtype!='object':
        train[i] = scaler.fit_transform(train[[i]])