In [15]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline


    

In [3]:

    

df=pd.read_excel('/home/sean/git/algorithms/class4/homework/data/2013_NYC_CD_MedianIncome_Recycle.xlsx')


    

In [6]:

    

df.head()


    

    
Out[6]:






  

    

      

      
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 [9]:

    

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


    

    
Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x7facd008f940>






    

In [14]:

    

df.corr()


    

    
Out[14]:






  

    

      

      
MdHHIncE
      
RecycleRate
    
  
  

    

      
MdHHIncE
      
1.000000
      
0.884783
    
    

      
RecycleRate
      
0.884783
      
1.000000
    
  

In [16]:

    

# i stole this from http://matthiaseisen.com/pp/patterns/p0170/
fig, ax = plt.subplots()
fit = np.polyfit(df['MdHHIncE'], df['RecycleRate'], deg=1)
ax.plot(df['MdHHIncE'], fit[0] * df['MdHHIncE'] + fit[1], color='red')
ax.scatter(df['MdHHIncE'], df['RecycleRate'])


    

    
Out[16]:





<matplotlib.collections.PathCollection at 0x7facca6d1780>






    

In [ ]: