In [12]:

    

import pandas as pd
import statsmodels.formula.api as smf


    

In [13]:

    

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


    

In [14]:

    

df.head()


    

    
Out[14]:






  

    

      

      
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 [25]:

    

lm = smf.ols(formula="RecycleRate~MdHHIncE",data=df).fit()
intercept,slope = lm.params
def pre_weight(income):
    recyclerate = intercept + income * slope
    return recyclerate


    

In [26]:

    

pre_weight(2929292)


    

    
Out[26]:





5.551445566629349

In [ ]: