In [13]:

    

%matplotlib inline

# imports needed for the following examples
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# read a local file (path is relative to python's working directory) 
# sep, header=True/None
df = pd.read_table('house_price.txt', sep=" ", header=None, index_col=1)

# set column name
# df.columns = ['comp_code', 'comp_name', 'vendor_code', 'vendor_name', 'which_day', 'po', 'amt']


#  np.polyfit(x, y, 1)


    

In [14]:

    

df.head()


    

    
Out[14]:






  

    

      

      
0
      
2
      
3
      
4
      
5
      
6
      
7
      
8
      
9
      
10
      
11
      
12
      
13
      
14
    
    

      
1
      

      

      

      

      

      

      

      

      

      

      

      

      

      

    
  
  

    

      
1
      
NaN
      
1
      
4.9176
      
1
      
3.472
      
0.998
      
1
      
7
      
4
      
42
      
3
      
1
      
0
      
25.9
    
    

      
2
      
NaN
      
1
      
5.0208
      
1
      
3.531
      
1.500
      
2
      
7
      
4
      
62
      
1
      
1
      
0
      
29.5
    
    

      
3
      
NaN
      
1
      
4.5429
      
1
      
2.275
      
1.175
      
1
      
6
      
3
      
40
      
2
      
1
      
0
      
27.9
    
    

      
4
      
NaN
      
1
      
4.5573
      
1
      
4.050
      
1.232
      
1
      
6
      
3
      
54
      
4
      
1
      
0
      
25.9
    
    

      
5
      
NaN
      
1
      
5.0597
      
1
      
4.455
      
1.121
      
1
      
6
      
3
      
42
      
3
      
1
      
0
      
29.9
    
  

In [17]:

    

df.columns


    

    
Out[17]:





Int64Index([0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], dtype='int64')

In [24]:

    

x = df[3]
y = df[5]


    

In [25]:

    

plt.scatter(x, y)


    

    
Out[25]:





<matplotlib.collections.PathCollection at 0x107887828>






    

In [ ]: