In [1]:

    

import pandas as pd
from geopy.geocoders import Nominatim
import folium
import matplotlib.pyplot as plt
import numpy as np


    

In [2]:

    

df = pd.read_csv("data/zip_info.csv")


    

In [3]:

    

df.head()


    

    
Out[3]:






  

    

      

      
state_fips
      
state
      
state_abbr
      
zipcode
      
county
      
city
      
Average_Household_Income
      
Per_capita_Income
      
High_Income_Households
    
  
  

    

      
0
      
1
      
Alabama
      
AL
      
36093
      
Elmore
      
Zcta 36093
      
$97,493
      
$35,689
      
5.70%
    
    

      
1
      
1
      
Alabama
      
AL
      
35173
      
Jefferson
      
Trussville
      
$96,314
      
$35,053
      
6.70%
    
    

      
2
      
1
      
Alabama
      
AL
      
35757
      
Madison
      
Zcta 35757
      
$95,882
      
$35,317
      
5.30%
    
    

      
3
      
1
      
Alabama
      
AL
      
36527
      
Baldwin
      
Spanish fort
      
$95,431
      
$37,820
      
9.10%
    
    

      
4
      
1
      
Alabama
      
AL
      
35114
      
Shelby
      
Maylene
      
$95,145
      
$32,961
      
5.50%
    
  

In [4]:

    

# Convert columns into floats
df['Average_Household_Income'] = df['Average_Household_Income'].replace('[\$,]', '', regex=True).astype(float)
df['Per_capita_Income'] = df['Per_capita_Income'].replace('[\$,]', '', regex=True).astype(float)
df['High_Income_Households'] = df['High_Income_Households'].replace('[\%,]', '', regex=True).astype(float)


    

In [5]:

    

state_income = df.groupby(['state_abbr'], axis=0).mean().reset_index()
state_income.drop(['state_fips','zipcode'],inplace=True,axis=1)


    

In [6]:

    

state_income.head()


    

    
Out[6]:






  

    

      

      
state_abbr
      
Average_Household_Income
      
Per_capita_Income
      
High_Income_Households
    
  
  

    

      
0
      
AK
      
61664.676724
      
23540.732759
      
2.426724
    
    

      
1
      
AL
      
53461.360976
      
21633.505691
      
1.937724
    
    

      
2
      
AR
      
48642.797927
      
20237.065630
      
1.497582
    
    

      
3
      
AZ
      
57926.386431
      
23647.486726
      
2.643658
    
    

      
4
      
CA
      
80201.422101
      
30944.696860
      
6.808756
    
  

In [7]:

    

stateslis = ['AL','AK','AZ','AR','CA','CO','CT','DE','FL','GA','HI','ID','IL',
             'IN','IA','KS','KY','LA','ME','MD','MA','MI','MN','MS','MO','MT', 
             'NE','NV','NH','NJ','NM','NY','NC','ND','OH','OK','OR','PA','RI',
             'SC','SD','TN','TX','UT','VT','VA','WA','WV','WI','WY']


    

In [8]:

    

# States that are not in our dataframe will be filled with a None value
states_not_in_df = pd.DataFrame([i for i in stateslis if i not in list(state_income.state_abbr)])
states_not_in_df.columns = ['state_abbr']
states_not_in_df['Average_Household_Income'] = None
states_not_in_df['Per_capita_Income'] = None
states_not_in_df['High_Income_Households'] = None


    

In [9]:

    

state_income = state_income.append(states_not_in_df, ignore_index=True)


    

In [10]:

    

state_income.sort(['High_Income_Households'], ascending=False).head()


    

    




//anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: FutureWarning: sort(columns=....) is deprecated, use sort_values(by=.....)
  if __name__ == '__main__':






    
Out[10]:






  

    

      

      
state_abbr
      
Average_Household_Income
      
Per_capita_Income
      
High_Income_Households
    
  
  

    

      
27
      
NJ
      
177262.000000
      
90205.000000
      
28.000000
    
    

      
6
      
DC
      
108644.782609
      
53724.043478
      
14.282609
    
    

      
18
      
MD
      
98351.824444
      
37717.428889
      
9.681778
    
    

      
4
      
CA
      
80201.422101
      
30944.696860
      
6.808756
    
    

      
30
      
NY
      
80380.302109
      
31981.285980
      
5.960360
    
  

In [11]:

    

map = folium.Map(location=[48, -102], zoom_start=3)
map.choropleth(geo_path='us-states.json', data=state_income,
                columns=['state_abbr', 'High_Income_Households'],
                key_on='feature.id', 
                threshold_scale=[1, 2, 3, 4, 10],
                fill_color='Spectral', fill_opacity=0.7, line_opacity=0.2,
                legend_name='High Income Households (%)',reset=True )

map


    

    
Out[11]: