In [1]:

    

df_in = pd.read_csv('download/euro2014.csv.gz', compression='gzip', delimiter=',', low_memory=False)


    

In [2]:

    

keep = [
    'CodeInsee',
    'Inscrits',
    'Abstentions',
    'Votants',
    'Blancs',
    'Nuls',
    'Exprimés',
    'LEXG',
    'LUG',
    'LFG',
    'LDVG',
    'LVEC',
    'LDIV',
    'LUC',
    'LUMP',
    'LDVD',
    'LFN',
    'LEXD',
    'NbCand',
]

df_out = df_in[keep]
# df_out['dc'] = df_out.CodeInsee.str.encode('ascii')
# df_out.drop(['CodeInsee'], axis=1, inplace=True)


    

In [3]:

    

df_out.set_index('CodeInsee', inplace=True)
df_out.index.name = 'dc'
df_out.index.get_duplicates()


    

    
Out[3]:





[]

In [4]:

    

df_out.index


    

    
Out[4]:





Index([u'01001', u'01002', u'01004', u'01005', u'01006', u'01007', u'01008', u'01009', u'01010', u'01011', u'01012', u'01013', u'01014', u'01015', u'01016', u'01017', u'01019', u'01021', u'01022', u'01023', u'01024', u'01025', u'01026', u'01027', u'01028', u'01029', u'01030', u'01031', u'01032', u'01033', u'01034', u'01035', u'01036', u'01037', u'01038', u'01039', u'01040', u'01041', u'01042', u'01043', u'01044', u'01045', u'01046', u'01047', u'01049', u'01050', u'01051', u'01052', u'01053', u'01054', u'01056', u'01057', u'01058', u'01059', u'01060', u'01061', u'01062', u'01063', u'01064', u'01065', u'01066', u'01067', u'01068', u'01069', u'01071', u'01072', u'01073', u'01074', u'01075', u'01076', u'01077', u'01078', u'01079', u'01080', u'01081', u'01082', u'01083', u'01084', u'01085', u'01087', u'01088', u'01089', u'01090', u'01091', u'01092', u'01093', u'01094', u'01095', u'01096', u'01097', u'01098', u'01099', u'01100', u'01101', u'01102', u'01103', u'01104', u'01105', u'01106', u'01107', ...], dtype='object')

In [5]:

    

df_out.columns


    

    
Out[5]:





Index([u'Inscrits', u'Abstentions', u'Votants', u'Blancs', u'Nuls', u'Exprimés', u'LEXG', u'LUG', u'LFG', u'LDVG', u'LVEC', u'LDIV', u'LUC', u'LUMP', u'LDVD', u'LFN', u'LEXD', u'NbCand'], dtype='object')

In [6]:

    

df_out.tail()


    

    
Out[6]:






  

    

      

      
Inscrits
      
Abstentions
      
Votants
      
Blancs
      
Nuls
      
Exprimés
      
LEXG
      
LUG
      
LFG
      
LDVG
      
LVEC
      
LDIV
      
LUC
      
LUMP
      
LDVD
      
LFN
      
LEXD
      
NbCand
    
    

      
dc
      

      

      

      

      

      

      

      

      

      

      

      

      

      

      

      

      

      

    
  
  

    

      
ZS501
      
   496
      
   393
      
  103
      
   7
      
   0
      
   96
      
  4
      
   21
      
 0
      
    5
      
  0
      
 0
      
  13
      
   38
      
 0
      
  15
      
 0
      
 19
    
    

      
ZS502
      
  4449
      
  3701
      
  748
      
  48
      
  22
      
  678
      
 33
      
  210
      
 0
      
   23
      
  0
      
 0
      
  94
      
  190
      
 0
      
 105
      
 0
      
 19
    
    

      
ZW001
      
  9333
      
  4774
      
 4559
      
  33
      
  30
      
 4496
      
 53
      
 1282
      
 0
      
 1077
      
  0
      
 0
      
 308
      
 1568
      
 0
      
  91
      
 0
      
 19
    
    

      
ZX701
      
  4874
      
  4147
      
  727
      
  22
      
   4
      
  701
      
  3
      
   28
      
 0
      
   11
      
 27
      
 0
      
  53
      
  305
      
 0
      
 222
      
 0
      
 19
    
    

      
ZX801
      
 18389
      
 16429
      
 1960
      
 158
      
 107
      
 1695
      
 82
      
  257
      
 0
      
  104
      
  0
      
 0
      
  93
      
  640
      
 0
      
 287
      
 0
      
 19
    
  

In [7]:

    

df_out.to_csv('data/euro2014.tsv', delimiter='\t')


    

In [8]:

    

#st = pd.HDFStore('data/data.h5')
#del st['euro2014']
#st['euro2014'] = df_out
# st.append('euro2014',df_out)
#st.close()


    

In [9]:

    

df_out.to_hdf('data/data.h5','euro2014', format='f')