In [47]:

    

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
plt.style.use('ggplot')


    

In [24]:

    

df=pd.read_excel('//Users/mercyemelike/Desktop/Lede-Program/algorithms/class4/homework/data/2013_NYC_CD_MedianIncome_Recycle.xlsx')


    

In [16]:

    

df.head()


    

    
Out[16]:






  

    

      

      
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 [49]:

    

ax = df.plot(x='MdHHIncE', y='RecycleRate', kind='scatter', figsize = (10,10))

ax.set(xlabel="Median Household Income", ylabel="Recycle Rate")
ax.set_title("Strong Positive Correlation between Median Household Income and Recycle Rate")


    

    
Out[49]:





<matplotlib.text.Text at 0x10aa145f8>






    

In [50]:

    

df.corr()


    

    
Out[50]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [ ]: