Load and clean Loan data

loan_data_clean.py

import numpy as np
import pandas as pd

#import loan dataset
df = pd.read_csv('loan.csv').dropna(axis=1,how='any')

#convert loan grades to numerical values
df['sub_grade'] = df['sub_grade'].str.slice(start=1).astype(int)
grade_dict = {k:i for i,k in enumerate(['A', 'B', 'C', 'D', 'E', 'F', 'G'])}
term_dict = {k:i for i,k in enumerate(['36 months', '60 months'])}
df['grade'] = np.array([grade_dict[i] for i in df['grade'].values])
df['grade'] = (df['grade']*df['sub_grade'].max())+df['sub_grade']

#define loan condition, this will be our target for classificaiton
bad_loan = ["Charged Off", "Default", "Does not meet the credit policy. Status:Charged Off", "In Grace Period", 
            "Late (16-30 days)", "Late (31-120 days)"]

def loan_condition(status):
    if status in bad_loan:
        return 1
    else:
        return 0

df['loan_condition'] = df['loan_status'].apply(loan_condition)

#select features to use for classification

features = ['loan_condition','loan_amnt','term','int_rate',
  'installment','grade','home_ownership','verification_status',
  'purpose','addr_state','dti','revol_bal']

#sample portion of data for demonstration purposes
df = df[features].convert_dtypes().sample(frac=.1)