In [1]:

    

%pylab inline
pylab.style.use('ggplot')
import pandas as pd
import numpy as np


    

    




Populating the interactive namespace from numpy and matplotlib

In [20]:

    

url = 'http://www.stat.ufl.edu/~winner/data/millcost.dat'
data_df  = pd.read_csv(url, header=None, sep='\s+')


    

In [22]:

    

data_df.columns = ['month', 'production', 'cost']


    

In [23]:

    

data_df.head()


    

    
Out[23]:






  

    

      

      
month
      
production
      
cost
    
  
  

    

      
0
      
1
      
46.75
      
92.64
    
    

      
1
      
2
      
42.18
      
88.81
    
    

      
2
      
3
      
41.86
      
86.44
    
    

      
3
      
4
      
43.29
      
88.80
    
    

      
4
      
5
      
42.12
      
86.38
    
  

In [24]:

    

import seaborn as sns
sns.jointplot(x='production', y='cost', data=data_df)


    

    
Out[24]:





<seaborn.axisgrid.JointGrid at 0x20657812ba8>






    

In [57]:

    

sns.regplot(x='production', y='cost', data=data_df)
pylab.title('Linear regression: cost ~ production')


    

    
Out[57]:





<matplotlib.text.Text at 0x2065d357128>






    

In [59]:

    

sns.residplot(x='production', y='cost', data=data_df)
pylab.title('cost ~ production: Residuals')


    

    
Out[59]:





<matplotlib.text.Text at 0x2065d442358>