Creating features for hpp Kaggle

hpp_feature_engg_1.py

# Let us start with the variables having highest correlation with the target variable
# looking at OverallQual, GrLivArea, GarageCars and TotalBsmtSF

# Since it is one of the highest correlated variables with the response, we can create a quadratic variable that might be a part of the regression equation
total_df["OverallQual_2"] = total_df["OverallQual"].astype(int) ** 2
#also creating cubic
total_df["OverallQual_3"] = total_df["OverallQual"].astype(int) ** 3
# another sqrt transformation
total_df["OverallQual_sqrt"] = np.sqrt(total_df["OverallQual"].astype(int))

# OverallQual is just a categorical variable in guise of integers
# Changing OverallQual into a categorical variable
total_df['OverallQual'] = total_df['OverallQual'].astype(str)

 # next variable: GrLivArea
 # creating the polynomial variables from here as well
total_df["GrLivArea_2"] = total_df["GrLivArea"] ** 2
#also creating cubic
total_df["GrLivArea_3"] = total_df["GrLivArea"] ** 3
# another sqrt transformation
total_df["GrLivArea_sqrt"] = np.sqrt(total_df["GrLivArea"])
# log transformed
total_df['GrLivArea_log'] = np.log1p(total_df['GrLivArea'])
# we can also create buckets on GrLivArea
total_df['GrLivArea_Band'] = pd.cut(total_df['GrLivArea'], 6,labels=["1", "2", "3","4","5","6"])
print(total_df['GrLivArea_Band'].unique())

# since these are essential categorical variables,
# let us convert them to string
total_df['GrLivArea_Band'] = total_df['GrLivArea_Band'].astype(str)

# creating polynomial features from TotalBsmtSF
total_df["TotalBsmtSF_2"] = total_df["TotalBsmtSF"] ** 2
#also creating cubic
total_df["TotalBsmtSF_3"] = total_df["TotalBsmtSF"] ** 3
# another sqrt transformation
total_df["TotalBsmtSF_sqrt"] = np.sqrt(total_df["TotalBsmtSF"])

# log transformed variable
total_df['TotalBsmtSF_log'] = np.log1p(total_df['TotalBsmtSF'])

# also creating a 1-0 flag called 'HasBsmt' using 'TotalBsmtSF'
#if area>0 it is 'Y', else 'N'
total_df['HasBsmt'] = np.where(total_df['TotalBsmtSF']>0, 'Y', 'N')

# we can also create buckets on TotalBsmtSF
total_df['TotalBsmtSF_Band'] = pd.cut(total_df['TotalBsmtSF'], 3,labels=["1", "2", "3"])
print(total_df['TotalBsmtSF_Band'].unique())

# since these are essential categorical variables,
# let us convert them to string
total_df['TotalBsmtSF_Band'] = total_df['TotalBsmtSF_Band'].astype(str)

# creating polynomial features from GarageCars
total_df["GarageCars_2"] = total_df["GarageCars"] ** 2
#also creating cubic
total_df["GarageCars_3"] = total_df["GarageCars"] ** 3
# another sqrt transformation
total_df["GarageCars_sqrt"] = np.sqrt(total_df["GarageCars"])

# log transformed variable
total_df['GarageCars_log'] = np.log1p(total_df['GarageCars'])