In [2]:

    

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


    

In [4]:

    

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


    

In [5]:

    

df.head()


    

    
Out[5]:






  

    

      

      
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 [6]:

    

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


    

    
Out[6]:





<matplotlib.axes._subplots.AxesSubplot at 0x10e26eb38>






    

In [7]:

    

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


    

In [8]:

    

lm.params


    

    
Out[8]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [21]:

    

intercept, slope = lm.params


    

In [29]:

    

def find_recycle_rate(user_income):
    user_recycle_rate = slope * float(user_income) + intercept
    return user_recycle_rate


    

In [30]:

    

user_income = input("What is your monthly household income?: ")
find_recycle_rate(user_income)


    

    




What is your monthly household income?: 50000






    
Out[30]:





0.16828476953547267

In [ ]:

    




    

In [ ]: