In [1]:

    

import numpy as np
import pandas as pd
from pandas import DataFrame,Series


    

In [2]:

    

dframe = DataFrame({'key1': list('AABBB'), 'key2': [2,2,2,3,3]})


    

In [3]:

    

dframe


    

    
Out[3]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
1
      
A
      
2
    
    

      
2
      
B
      
2
    
    

      
3
      
B
      
3
    
    

      
4
      
B
      
3
    
  

In [4]:

    

dframe.duplicated()


    

    
Out[4]:





0    False
1     True
2    False
3    False
4     True
dtype: bool

In [5]:

    

dframe.drop_duplicates()


    

    
Out[5]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
2
      
B
      
2
    
    

      
3
      
B
      
3
    
  

In [6]:

    

dframe.drop_duplicates(['key1'])


    

    
Out[6]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
2
      
B
      
2
    
  

In [7]:

    

dframe.drop_duplicates(['key1'], take_last=True)


    

    




/Users/andymeyers/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:1: FutureWarning: the take_last=True keyword is deprecated, use keep='last' instead
  if __name__ == '__main__':






    
Out[7]:






  

    

      

      
key1
      
key2
    
  
  

    

      
1
      
A
      
2
    
    

      
4
      
B
      
3
    
  

In [8]:

    

dframe.drop_duplicates(['key1'], keep='last')


    

    
Out[8]:






  

    

      

      
key1
      
key2
    
  
  

    

      
1
      
A
      
2
    
    

      
4
      
B
      
3
    
  

In [ ]: