data-cleaning-pandas

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import codecademylib3_seaborn
import glob

globe=glob.glob('states*.csv')
print(globe)

us_census=[]

for file in globe:
  data=pd.read_csv(file)
  us_census.append(data)

#print(us_census)
us_census=pd.concat(us_census)
print(us_census)
print(us_census.columns)
print(us_census.dtypes)

us_census.Income=us_census.Income.replace('\$','',regex=True)
us_census.Income=pd.to_numeric(us_census.Income)
us_census['Men']=us_census.GenderPop.str.split('_',expand=True)[0]
#us_census['Men']=us_census.Men.str.get(0)
us_census['Women']=us_census.GenderPop.str.split('_',expand=True)[1]
#us_census['Women']=us_census.Women.str.get(1)'''
us_census['Men']=us_census['Men'].replace('M','',regex=True)
us_census['Men']=pd.to_numeric(us_census['Men'])
us_census['Women']=us_census['Women'].replace('F','',regex=True)
us_census['Women']=pd.to_numeric(us_census['Women'])
us_census=us_census.fillna(value={'Women':us_census.TotalPop-us_census.Men})
duplicates=us_census.duplicated()
us_census=us_census.drop_duplicates()
print(duplicates.value_counts())

us_census.White=us_census.White.replace('%','',regex=True)
us_census.White=pd.to_numeric(us_census.White)

print(us_census.head())
print(us_census.dtypes)
print(us_census.columns)

plt.scatter(us_census.Women,us_census.Income)
plt.show()