In [1]:

    

import pandas as pd


    

In [2]:

    

dbpedia_file ='politician-data' #make sure the file is parallel to the program
SPLIT_SIZE = 10000


    

In [3]:

    

dbpedia_data = pd.read_csv(dbpedia_file, sep='\t')
dbpedia_data.head()


    

    
Out[3]:






  

    

      

      
#DBpURL
      
ID
      
WikiURL
      
gender
      
name
      
birthDate
      
deathDate
      
occupation
      
nationality
      
party
    
  
  

    

      
0
      
http://dbpedia.org/resource/Quincy_Timberlake
      
11
      
http://en.wikipedia.org/wiki/Quincy_Timberlake
      
male
      
[' quincy timberlake ', ' timberlake quincy ']
      
[' 1980-04-22 ']
      
NaN
      
['politician']
      
['kenyan']
      
NaN
    
    

      
1
      
http://dbpedia.org/resource/Fanny_Edelman
      
29
      
http://en.wikipedia.org/wiki/Fanny_Edelman
      
female
      
[' fanny edelman ', ' edelman fanny ']
      
[' 1911-02-27 ']
      
[' 2011-11-01 ']
      
['politician']
      
['argentine']
      
NaN
    
    

      
2
      
http://dbpedia.org/resource/Stojan_Novaković
      
65
      
http://en.wikipedia.org/wiki/Stojan_Novaković
      
NaN
      
[' stojan novaković ', ' (стојан новаковић) ',...
      
[' 1842-11-01 ']
      
[' 1915-02-18 ']
      
['historian', 'philology', 'politician', 'dipl...
      
['serbian']
      
[' serbian progressive party (historical) ']
    
    

      
3
      
http://dbpedia.org/resource/Paul_Scheffer
      
102
      
http://en.wikipedia.org/wiki/Paul_Scheffer
      
male
      
[' scheffer paul ']
      
[' 1954-09-03 ']
      
NaN
      
['politician']
      
NaN
      
NaN
    
    

      
4
      
http://dbpedia.org/resource/Ed_Robb
      
127
      
http://en.wikipedia.org/wiki/Ed_Robb
      
male
      
NaN
      
NaN
      
NaN
      
['politician']
      
['american']
      
NaN
    
  

In [4]:

    

len = dbpedia_data.shape[0] - 1
idx = 0
limit = SPLIT_SIZE
file_name = ''
while (idx < len) :
    rows = dbpedia_data.iloc[idx:limit,:]
    file_name = dbpedia_file+'-'+str(idx)+'-'+str(limit)
    rows.to_csv(file_name,sep='\t')
    idx = limit
    limit = idx + SPLIT_SIZE
    if(limit > len):
        limit = len


    

In [ ]: