In [14]:

    

import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
import statsmodels.formula.api as smf


    

In [15]:

    

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


    

In [23]:

    

df.head(2)


    

    
Out[23]:






  

    

      

      
CD_Name
      
MdHHIncE
      
RecycleRate
    
  
  

    

      
0
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.286771
    
    

      
1
      
Battery Park City, Greenwich Village & Soho
      
119596
      
0.264074
    
  

In [16]:

    

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


    

In [18]:

    

lm.params


    

    
Out[18]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [20]:

    

intercept, slope = lm.params


    

In [21]:

    

df.plot(kind="scatter",x="MdHHIncE",y="RecycleRate")
plt.plot(df["MdHHIncE"],slope*df["MdHHIncE"]+intercept,"-",color="red")


    

    
Out[21]:





[<matplotlib.lines.Line2D at 0x108b1d550>]






    

In [22]:

    

def income_predictor(your_income): 
    recycle_rate = your_income * lm.params.MdHHIncE + lm.params.Intercept
    return recycle_rate


    

In [25]:

    

# Example
income_predictor(119596)


    

    
Out[25]:





0.29840233275398087

In [ ]: