Assignment 3

In [1]:

    

import pandas as pd
import matplotlib.pyplot as plt # package for doing plotting (necessary for adding the line)
import statsmodels.formula.api as smf # package we'll be using for linear regression
%matplotlib inline


    

In [3]:

    

df = pd.read_excel('../../class4/homework/data/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]:

    

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


    

In [14]:

    

# Function using the built math. 
def simplest_predictor(income, height, intercept):
    height = float(height)
    intercept = float(intercept)
    income = float(income)
    return height*income+intercept


    

In [15]:

    

income = input("How high is the houshold income? ")
print("We predict a recycling rate of", simplest_predictor(income,height,intercept))


    

    




How high is the houshold income? 50000
We predict a recycling rate of 0.16828476953547256