In [3]:

    

import pandas as pd
import numpy as np


    

In [4]:

    

train_df = pd.DataFrame({'col_1': [3, 2, 1, 0], 'col_2': ['a', 'b', 'c', 'd']})
test_df = pd.DataFrame({'col_1': [3, 2, 5], 'col_2': ['a', 'b', 'e']})


    

In [5]:

    

pd.get_dummies(train_df['col_2'])


    

    
Out[5]:







  

    

      

      
a
      
b
      
c
      
d
    
  
  

    

      
0
      
1
      
0
      
0
      
0
    
    

      
1
      
0
      
1
      
0
      
0
    
    

      
2
      
0
      
0
      
1
      
0
    
    

      
3
      
0
      
0
      
0
      
1
    
  

In [6]:

    

dummy_columns = list(set(train_df['col_2']))


    

In [7]:

    

pd.get_dummies(test_df['col_2'])


    

    
Out[7]:







  

    

      

      
a
      
b
      
e
    
  
  

    

      
0
      
1
      
0
      
0
    
    

      
1
      
0
      
1
      
0
    
    

      
2
      
0
      
0
      
1
    
  

In [10]:

    

test_df_new, train_df_new = pd.get_dummies(test_df['col_2']).align(pd.get_dummies(train_df['col_2']), join='right', axis=1, fill_value=0)


    

In [11]:

    

test_df_new


    

    
Out[11]:







  

    

      

      
a
      
b
      
c
      
d
    
  
  

    

      
0
      
1
      
0
      
0
      
0
    
    

      
1
      
0
      
1
      
0
      
0
    
    

      
2
      
0
      
0
      
0
      
0
    
  

In [ ]: