In [1]:

    

import pandas as pd
%matplotlib inline


    

    




/Users/zhizhou/.virtualenvs/data-analysis/lib/python3.5/site-packages/matplotlib/__init__.py:1035: UserWarning: Duplicate key in file "/Users/zhizhou/.matplotlib/matplotlibrc", line #2
  (fname, cnt))
/Users/zhizhou/.virtualenvs/data-analysis/lib/python3.5/site-packages/matplotlib/__init__.py:1035: UserWarning: Duplicate key in file "/Users/zhizhou/.matplotlib/matplotlibrc", line #3
  (fname, cnt))

In [3]:

    

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


    

In [4]:

    

df.head()


    

    
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
    
  

In [5]:

    

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


    

    
Out[5]:





<matplotlib.axes._subplots.AxesSubplot at 0x11116aac8>






    

In [6]:

    

df.corr()


    

    
Out[6]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [ ]: