In [5]:

    

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


    

In [5]:

    

cd ..


    

    




C:\Users\Harsha Devulapalli\Desktop\algorithms

In [6]:

    

pwd


    

    
Out[6]:





'C:\\Users\\Harsha Devulapalli\\Desktop\\algorithms\\class5\\homework'

In [7]:

    

cd "C:\Users\Harsha Devulapalli\Desktop\algorithms\class4\homework\data"


    

    




C:\Users\Harsha Devulapalli\Desktop\algorithms\class4\homework\data

In [8]:

    

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


    

In [9]:

    

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


    

    
Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x2bf312b1a90>






    

In [30]:

    

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


    

In [31]:

    

lm.params


    

    
Out[31]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [32]:

    

intercept, slope = lm.params


    

In [33]:

    

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


    

    
Out[33]:





[<matplotlib.lines.Line2D at 0x2bf3299d710>]






    

In [38]:

    

def returnrate(income):
    rate = slope*income+intercept
    return rate


    

In [39]:

    

returnrate(20000)


    

    
Out[39]:





0.11219638950565416