import pandas as pd df = pd.read_csv( 'mortgage-testing-data.csv' ) df.dtypes

import numpy as np # create new columns df['conforming_loan_limit_is_c'] = np.where( df['conforming_loan_limit'] == 'C', 1, 0 ) df['conforming_loan_limit_is_nc'] = np.where( df['conforming_loan_limit'] == 'NC', 1, 0 ) # delete original column del df['conforming_loan_limit'] df

# create new columns df['derived_sex_is_male'] = np.where( df['derived_sex'] == 'Male', 1, 0 ) df['derived_sex_is_female'] = np.where( df['derived_sex'] == 'Female', 1, 0 ) # delete original column del df['derived_sex'] df

# create new column df['application_is_accepted'] = np.where( df['action_taken'] == 1, 1, 0 ) # delete original column del df['action_taken'] df

dict_to_replace_debt_income = { '<20%': 10, '20%-<30%' : 25, '30%-<36%' : 33, '50%-60%' : 55, '>60%': 70 } df['debt_to_income_ratio'] = df['debt_to_income_ratio'].map( dict_to_replace_debt_income )\ .fillna( df['debt_to_income_ratio'] ).astype( 'float64' ) df

df.dtypes

df.to_csv( 'cleaned-mortgage-testing-data.csv' )