In [1]:

    

import pandas as pd
%matplotlib inline


    

In [2]:

    

import matplotlib.pyplot as plt
import statsmodels.formula.api as smf


    

In [3]:

    

df = pd.read_excel("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 [40]:

    

lm = smf.ols(formula="RecycleRate ~ MdHHIncE",data=df).fit()


    

In [41]:

    

lm.params


    

    
Out[41]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [42]:

    

intercept, slope = lm.params


    

In [45]:

    

def guess_median_income(recycle_rate):
    for item in df['RecycleRate']:
        recycle_rate = median_income * slope + intercept
    return recycle_rate


    

In [46]:

    

guess_recyclerate(119596)


    

    
Out[46]:





0.29840233275398087

In [ ]: