In [7]:

    

import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt 
import statsmodels.formula.api as smf 
!pip3 install xlrd


    

    




Collecting xlrd
  Using cached xlrd-1.0.0-py3-none-any.whl
Installing collected packages: xlrd
Successfully installed xlrd-1.0.0

In [10]:

    

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


    

In [11]:

    

df.head()


    

    
Out[11]:






  

    

      

      
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 [20]:

    

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


    

In [21]:

    

lm.params


    

    
Out[21]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [22]:

    

intercept, slope = lm.params


    

In [27]:

    

df.plot(kind='scatter',x='MdHHIncE',y='RecycleRate',color='gray',alpha=0.8,linewidth=0)
plt.plot(df["MdHHIncE"],slope*df["MdHHIncE"]+intercept,"-",color="red",alpha=0.5)


    

    
Out[27]:





[<matplotlib.lines.Line2D at 0x10b883828>]






    

In [28]:

    

print("The module is: Recycle rate =", slope,"* medianincome +",intercept)


    

    




The module is: Recycle rate = 1.86961266766e-06 * medianincome + 0.0748041361524

In [31]:

    

def get_rrate(income):
    recycle_rate = income * slope + intercept
    return recycle_rate


    

In [ ]: