Codecademy export

script.py

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import codecademylib3_seaborn

import glob

files = glob.glob('states*.csv')

df_list = []
for filename in files:
  data = pd.read_csv(filename)
  df_list.append(data)

us_census = pd.concat(df_list)

#print(us_census.head())
#print(us_census.columns)

us_census.Income = us_census['Income'].replace('[\$,]', '', regex=True)

#print(us_census.head())

us_census['pop_split'] = us_census['GenderPop'].str.split('_')

us_census['Men'] = us_census['pop_split'].str.get(0)
us_census['Men'] = us_census['Men'].str.split('(\d+)', expand=True)[1]
us_census['Men'] = pd.to_numeric(us_census['Men'])

us_census['Women'] = us_census['pop_split'].str.get(1)
us_census['Women'] = us_census['Women'].str.split('(\d+)', expand=True)[1]
us_census['Women'] = pd.to_numeric(us_census['Women'])

estimate_pop = us_census.TotalPop - us_census.Men

us_census['Women'] = us_census['Women'].fillna(value=estimate_pop)
us_census['Women'] = us_census['Women'].astype(int)

#print(us_census.Women)

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

us_census = us_census.drop('pop_split', 1)

#print(us_census.head())

duplicated = us_census.duplicated()
#print(duplicated)
us_census = us_census.drop_duplicates()

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

#print(us_census.columns)

us_census['Hispanic'] = us_census['Hispanic'].replace('[\%,]', '', regex=True)
us_census['Hispanic'] = pd.to_numeric(us_census.Hispanic)
us_census['White'] = us_census['White'].replace('[\%,]', '', regex=True)
us_census['White'] = pd.to_numeric(us_census.White)
us_census['Black'] = us_census['Black'].replace('[\%,]', '', regex=True)
us_census['Black'] = pd.to_numeric(us_census.Black)
us_census['Native'] = us_census['Native'].replace('[\%,]', '', regex=True)
us_census['Native'] = pd.to_numeric(us_census.Native)
us_census['Asian'] = us_census['Asian'].replace('[\%,]', '', regex=True)
us_census['Asian'] = pd.to_numeric(us_census.Asian)
us_census['Pacific'] = us_census['Pacific'].replace('[\%,]', '', regex=True)
us_census['Pacific'] = pd.to_numeric(us_census.Pacific)

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