In [ ]:

    

#Using the 2013_NYC_CD_MedianIncome_Recycle.xlsx file, calculate the correlation between the recycling rate 
#and the median income. Discuss your findings in your PR.


    

In [1]:

    

import pandas as pd
import numpy as np


    

In [3]:

    

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


    

In [4]:

    

df.head(10)


    

    
Out[4]:






  

    

      

      
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
    
    

      
5
      
Murray Hill, Gramercy & Stuyvesant Town
      
101769
      
0.222046
    
    

      
6
      
Upper West Side & West Side
      
96009
      
0.256809
    
    

      
7
      
Upper East Side
      
104602
      
0.253719
    
    

      
8
      
Hamilton Heights, Manhattanville & West Harlem
      
41736
      
0.155888
    
    

      
9
      
Central Harlem
      
36468
      
0.133018
    
  

In [5]:

    

df.corr()


    

    
Out[5]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [ ]: