bibscy

import csv
import pandas as pd
import numpy as np
import re
import string


myDataFrame = pd.read_csv('Loan_payments_data_2020_unclean.csv')

bibscy

#check total number of males
totalMales = newDF.loc[(newDF.Gender=='Male')].count() #409
print("totalMales" + str(totalMales))


totalFemales = newDF.loc[(newDF.Gender=='Female')].count()  #77
print("totalFemales" + str(totalFemales))

#males are more likely to borrow than females 409 > 77