In [10]:

    

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
df = pd.read_excel('2013_NYC_CD_MedianIncome_Recycle.xlsx')


    

In [3]:

    

df.head(3)


    

    
Out[3]:






  

    

      

      
CD_Name
      
MdHHIncE
      
RecycleRate
    
  
  

    

      
0
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.286771
    
    

      
1
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.264074
    
    

      
2
      
Chinatown & Lower East Side
      
40919
      
0.156485
    
  

In [4]:

    

df.corr()


    

    
Out[4]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [16]:

    

df.plot(kind='scatter', x='MdHHIncE', y='RecycleRate')
plt.title('Correlation between Median Income and Recycle Rate')
plt.xlabel('Median Income')


    

    
Out[16]:





<matplotlib.text.Text at 0x114686940>