In [1]:

    

import pandas as pd
%matplotlib inline
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


    

In [2]:

    

df = pd.read_csv("data/heights_weights_genders.csv")


    

In [3]:

    

df.plot(kind="scatter",x="Height",y="Weight")


    

    
Out[3]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f819e1a2438>






    

In [4]:

    

lm = smf.ols(formula="Weight~Height",data=df).fit() #notice the formula regresses Y on X (Y~X)


    

In [5]:

    

lm.params #get the parameters from the model fit


    

    
Out[5]:





Intercept   -350.737192
Height         7.717288
dtype: float64

In [6]:

    

intercept, slope = lm.params #assign those values to variables


    

In [7]:

    

df.plot(kind="scatter",x="Height",y="Weight")
plt.plot(df["Height"],slope*df["Height"]+intercept,"-",color="red") #we create the best fit line from the values in the fit model


    

    
Out[7]:





[<matplotlib.lines.Line2D at 0x7f819bb43438>]






    

In [8]:

    

lm.summary()


    

    
Out[8]:





OLS Regression Results

  
Dep. Variable:
         
Weight
      
  R-squared:         
 
   0.855
 


  
Model:
                   
OLS
       
  Adj. R-squared:    
 
   0.855
 


  
Method:
             
Least Squares
  
  F-statistic:       
 
5.904e+04


  
Date:
             
Tue, 26 Jul 2016
 
  Prob (F-statistic):
  
  0.00
  


  
Time:
                 
16:09:00
     
  Log-Likelihood:    
 
 -39219.
 


  
No. Observations:
      
 10000
      
  AIC:               
 
7.844e+04


  
Df Residuals:
          
  9998
      
  BIC:               
 
7.846e+04


  
Df Model:
              
     1
      
                     
     
 
    


  
Covariance Type:
      
nonrobust
    
                     
     
 
    




      
         
coef
     
std err
      
t
      
P>|t|
 
[95.0% Conf. Int.]
 


  
Intercept
 
 -350.7372
 
    2.111
 
 -166.109
 
 0.000
 
 -354.876  -346.598


  
Height
    
    7.7173
 
    0.032
 
  242.975
 
 0.000
 
    7.655     7.780




  
Omnibus:
       
 2.141
 
  Durbin-Watson:     
 
   1.677


  
Prob(Omnibus):
 
 0.343
 
  Jarque-Bera (JB):  
 
   2.150


  
Skew:
          
 0.036
 
  Prob(JB):          
 
   0.341


  
Kurtosis:
      
 2.991
 
  Cond. No.          
 
1.15e+03

In [ ]: