In [1]:

    

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


    

In [3]:

    

df = pd.read_excel("/home/sean/git/algorithms/class4/homework/data/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 [46]:

    

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


    

In [47]:

    

lm.params


    

    
Out[47]:





Intercept    0.074804
MdHHIncE     0.000002
dtype: float64

In [65]:

    

intercept, slope = lm.params


    

In [57]:

    

slope


    

    
Out[57]:





0.074804136152441802

In [58]:

    

intercept


    

    
Out[58]:





1.8696126676606164e-06

In [63]:

    

plt.yscale?


    

In [67]:

    

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


    

    
Out[67]:





[<matplotlib.lines.Line2D at 0x7faf9250d128>]






    

In [85]:

    

def income_to_rate(income_str):
    income=float(income_str)
    return '%s' % float('%.3g' % ((slope*income+intercept)*100))


    

In [86]:

    

income_to_rate(50000)


    

    
Out[86]:





'16.8'

In [90]:

    

income=input('Enter median neighborhood income: $')
print('Predicted recycle rate for this neighborhood is {}%'.format(income_to_rate(income)))


    

    




Enter median neighborhood income: $1000000
Predicted recycle rate for this neighborhood is 194.0%

In [ ]: