In [1]:

    

import pandas as pd


    

In [5]:

    

%matplotlib inline


    

In [2]:

    

df = pd.read_excel("2013_NYC_CD_MedianIncome_Recycle.xlsx")


    

In [8]:

    

df.head()


    

    
Out[8]:






  

    

      

      
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
    
    

      
3
      
Chelsea, Clinton & Midtown Business Distric
      
92583
      
0.235125
    
    

      
4
      
Chelsea, Clinton & Midtown Business Distric
      
92583
      
0.246725
    
  

In [6]:

    

df.plot(kind='scatter',x='MdHHIncE',y='RecycleRate')


    

    
Out[6]:





<matplotlib.axes._subplots.AxesSubplot at 0x113be84a8>






    

In [7]:

    

df.corr()


    

    
Out[7]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [ ]:

    

# The correlation is 0.884783.