In [1]:

    

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


    

In [2]:

    

df = DataFrame({'key1':['A']*2 + ['B']*3,
                'key2':[2,2,2,3,3]})
df


    

    
Out[2]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
1
      
A
      
2
    
    

      
2
      
B
      
2
    
    

      
3
      
B
      
3
    
    

      
4
      
B
      
3
    
  

In [3]:

    

df.duplicated()


    

    
Out[3]:





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

In [5]:

    

df.drop_duplicates()


    

    
Out[5]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
2
      
B
      
2
    
    

      
3
      
B
      
3
    
  

In [7]:

    

# keeps first value found
df.drop_duplicates(['key1'])


    

    
Out[7]:






  

    

      

      
key1
      
key2
    
  
  

    

      
0
      
A
      
2
    
    

      
2
      
B
      
2
    
  

In [8]:

    

# keeps last value found
df.drop_duplicates(['key1'],take_last=True)


    

    




/home/juanc/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/ipykernel/__main__.py:2: FutureWarning: the take_last=True keyword is deprecated, use keep='last' instead
  from ipykernel import kernelapp as app






    
Out[8]:






  

    

      

      
key1
      
key2
    
  
  

    

      
1
      
A
      
2
    
    

      
4
      
B
      
3
    
  

In [9]:

    

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


    

    
Out[9]:






  

    

      

      
key1
      
key2
    
  
  

    

      
1
      
A
      
2
    
    

      
4
      
B
      
3
    
  

In [ ]: