In [1]:
import pandas as pd
import numpy as np
In [ ]:
In [2]:
chunksize = 50000
train_fname = "../input/train_categorical.csv"
test_fname = "../input/test_categorical.csv"
output_fname = "../input/train_categorical_250000.out.csv"
In [ ]:
In [3]:
def cat_values(fname):
setl = set()
for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):
print '*',
data = pd.DataFrame()
data = data.append(chunk, ignore_index=True)
for item in data.itertuples():
setl = setl.union(set(item[1:]))
print setl
In [9]:
%time t1 = cat_values(train_fname)
* * * * * * * * * * * * * * * * * * * * * * * * set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])
Wall time: 9min 52s
In [4]:
%time t2 = cat_values(test_fname)
* * * * * * * * * * * * * * * * * * * * * * * * set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])
Wall time: 9min 51s
In [14]:
t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])
t2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])
In [15]:
print len(t1),
print len(t2)
print len(t1.union(t2))
93 99
107
In [16]:
t1.union(t2)
Out[16]:
{'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'}
In [19]:
from collections import Counter
def count_values(fname):
cat_counter = Counter()
for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):
print '*',
data = pd.DataFrame()
data = data.append(chunk, ignore_index=True)
for item in data.itertuples():
cat_counter.update(list(item[1:]))
return cat_counter
In [20]:
%time c1 = count_values(train_fname)
* * * * * * * * * * * * * * * * * * * * * * * *Wall time: 21min 24s
In [22]:
%time c2 = count_values(test_fname)
* * * * * * * * * * * * * * * * * * * * * * * *Wall time: 20min 46s
In [35]:
c = c1 + c2
c['T-2147482688']
Out[35]:
724
In [45]:
i = 1
for s in sorted(t1.union(t2), key=len, reverse=True):
print 's/%s/S%03d/g' % (s, i)
i += 1
s/T-2147482688/S001/g
s/T-2147483646/S002/g
s/T-2147483647/S003/g
s/T-2147483648/S004/g
s/T-2147482176/S005/g
s/T-2147482944/S006/g
s/T-2147482432/S007/g
s/T-2147482816/S008/g
s/T-2147481664/S009/g
s/T-21474825/S010/g
s/T-18748192/S011/g
s/T134217728/S012/g
s/T-21474819/S013/g
s/T268435456/S014/g
s/T-21474872/S015/g
s/T16777472/S016/g
s/T11141888/S017/g
s/T33554432/S018/g
s/T16777232/S019/g
s/T33554448/S020/g
s/T16793941/S021/g
s/T12582912/S022/g
s/T16777216/S023/g
s/T16777248/S024/g
s/T16779428/S025/g
s/T25165824/S026/g
s/T16777557/S027/g
s/T33554944/S028/g
s/T4718592/S029/g
s/T8651776/S030/g
s/T8912896/S031/g
s/T4325376/S032/g
s/T9175552/S033/g
s/T8389632/S034/g
s/T262656/S035/g
s/T748928/S036/g
s/T618624/S037/g
s/T262144/S038/g
s/T524288/S039/g
s/T331648/S040/g
s/T786432/S041/g
s/T524544/S042/g
s/T113776/S043/g
s/T393216/S044/g
s/T178258/S045/g
s/T786944/S046/g
s/T589824/S047/g
s/T678864/S048/g
s/T63616/S049/g
s/T16384/S050/g
s/T43968/S051/g
s/T96112/S052/g
s/T83888/S053/g
s/T18436/S054/g
s/T36992/S055/g
s/T41944/S056/g
s/T16512/S057/g
s/T32896/S058/g
s/T65536/S059/g
s/T91764/S060/g
s/T26808/S061/g
s/T86752/S062/g
s/T48576/S063/g
s/T55424/S064/g
s/T1152/S065/g
s/T3942/S066/g
s/T1372/S067/g
s/T2516/S068/g
s/T7808/S069/g
s/T1310/S070/g
s/T6553/S071/g
s/T8768/S072/g
s/T9174/S073/g
s/T1132/S074/g
s/T488/S075/g
s/T128/S076/g
s/T145/S077/g
s/T143/S078/g
s/T492/S079/g
s/T256/S080/g
s/T132/S081/g
s/T544/S082/g
s/T518/S083/g
s/T512/S084/g
s/T514/S085/g
s/T917/S086/g
s/T268/S087/g
s/T16/S088/g
s/T12/S089/g
s/T98/S090/g
s/T96/S091/g
s/T97/S092/g
s/T24/S093/g
s/T32/S094/g
s/T48/S095/g
s/T52/S096/g
s/T56/S097/g
s/T64/S098/g
s/T1/S099/g
s/T8/S100/g
s/T9/S101/g
s/T6/S102/g
s/T7/S103/g
s/T4/S104/g
s/T5/S105/g
s/T2/S106/g
s/T3/S107/g
In [46]:
locals()
Out[46]:
{'Counter': collections.Counter,
'In': ['',
u'import pandas as pd\nimport numpy as np',
u'chunksize = 50000\ntrain_fname = "../input/train_categorical.csv"\ntest_fname = "../input/test_categorical.csv"\n\noutput_fname = "../input/train_categorical_250000.out.csv"',
u"def cat_values(fname):\n setl = set()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n setl = setl.union(set(item[1:]))\n print setl",
u"get_ipython().magic(u'time cat_values(test_fname)')",
u"t1 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u't1 - t2',
u't2 - t1',
u"get_ipython().magic(u'time t1 = cat_values(train_fname)')",
u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
u't2 - t1',
u't1',
u't2',
u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
u't1.union(t2)',
u"import collections\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
u"get_ipython().magic(u'time c1 = count_values(train_fname)')",
u"from collections import Counter\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
u"get_ipython().magic(u'time c1 = count_values(train_fname)')",
u'c1.most_common()',
u"get_ipython().magic(u'time c2 = count_values(test_fname)')",
u'c2.most_common()',
u'c1 + c2',
u'c1 - c2',
u'c1 & c2',
u'c1 | c2',
u'c = c1 + c2\nc.most_common()',
u'c = c1 + c2\nlen(c.most_common())',
u'sorted(t1+t2)',
u'sorted(t1.union(t2))',
u'sorted(t1.union(t2), key=str.lower)',
u'sorted(t1.union(t2), key=len)',
u'sorted(t1.union(t2), key=len, reverse=True)',
u"c = c1 + c2\nc['T-2147482688']",
u'for s in sorted(t1.union(t2), key=len, reverse=True):\n print s, c[s]',
u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % c[s]",
u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % s",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/%00d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%00d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%2d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i++",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i += 1",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%03d/g' % (s, i)\n i += 1",
u'locals()'],
'Out': {7: {'T16779428',
'T178258',
'T25165824',
'T26808',
'T678864',
'T786944',
'T91764',
'T96112'},
8: {'T12',
'T132',
'T16793941',
'T262656',
'T268',
'T393216',
'T3942',
'T4325376',
'T43968',
'T488',
'T518',
'T544',
'T7808',
'T9175552'},
13: {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16793941',
'T18436',
'T2',
'T24',
'T2516',
'T256',
'T262144',
'T262656',
'T268',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T7',
'T748928',
'T7808',
'T786432',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T96',
'T97',
'T98'},
16: {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'},
21: [(nan, 2465567643L),
('T1', 66323875),
('T3', 793092),
('T145', 325373),
('T4', 68429),
('T2', 38732),
('T143', 31950),
('T5', 18620),
('T8', 5672),
('T128', 4881),
('T16', 4217),
('T48576', 3388),
('T524288', 2960),
('T512', 2890),
('T32', 2876),
('T-2147483648', 1971),
('T1372', 1922),
('T65536', 1632),
('T48', 1610),
('T16777232', 1601),
('T256', 1264),
('T262144', 1161),
('T16777557', 1101),
('T16777248', 1092),
('T6', 1022),
('T83888', 969),
('T64', 646),
('T786432', 544),
('T6553', 516),
('T8389632', 513),
('T134217728', 421),
('T-2147482816', 385),
('T24', 383),
('T-2147482432', 375),
('T96', 374),
('T-2147482688', 364),
('T12582912', 307),
('T268435456', 298),
('T11141888', 272),
('T917', 272),
('T8912896', 256),
('T9174', 240),
('T7', 234),
('T16777216', 144),
('T98', 142),
('T618624', 133),
('T33554448', 132),
('T-21474872', 115),
('T2516', 112),
('T331648', 104),
('T1152', 103),
('T52', 91),
('T16384', 90),
('T41944', 80),
('T113776', 80),
('T56', 78),
('T8651776', 76),
('T678864', 66),
('T4718592', 64),
('T97', 52),
('T9', 50),
('T18436', 39),
('T748928', 38),
('T36992', 38),
('T32896', 37),
('T-2147481664', 34),
('T524544', 32),
('T786944', 32),
('T33554432', 26),
('T1310', 26),
('T8768', 19),
('T26808', 18),
('T1132', 16),
('T96112', 16),
('T86752', 16),
('T25165824', 16),
('T91764', 16),
('T16777472', 13),
('T16779428', 13),
('T178258', 13),
('T33554944', 13),
('T-21474825', 12),
('T589824', 9),
('T514', 9),
('T-21474819', 5),
('T492', 4),
('T-18748192', 3),
('T16512', 3),
('T63616', 2),
('T-2147483647', 2),
('T-2147483646', 2),
('T-2147482176', 1),
('T-2147482944', 1),
('T55424', 1)],
23: [(nan, 2465604793L),
('T1', 66293462),
('T3', 790068),
('T145', 324001),
('T4', 68544),
('T2', 38809),
('T143', 32458),
('T5', 18506),
('T8', 5696),
('T128', 4917),
('T16', 4152),
('T512', 3128),
('T524288', 3040),
('T48576', 3011),
('T32', 2661),
('T-2147483648', 1938),
('T1372', 1661),
('T16777232', 1646),
('T65536', 1621),
('T48', 1470),
('T262144', 1349),
('T256', 1180),
('T16777557', 1170),
('T83888', 1100),
('T6', 1003),
('T16777248', 923),
('T268435456', 598),
('T134217728', 574),
('T6553', 532),
('T64', 475),
('T-2147482816', 403),
('T8389632', 361),
('T-2147482688', 360),
('T96', 340),
('T8912896', 336),
('T9174', 336),
('T-2147482432', 332),
('T11141888', 288),
('T786432', 288),
('T24', 250),
('T7', 250),
('T12582912', 233),
('T917', 208),
('T52', 195),
('T16777216', 144),
('T16384', 135),
('T33554448', 130),
('T331648', 120),
('T618624', 114),
('T98', 114),
('T113776', 112),
('T-21474872', 101),
('T1152', 98),
('T4718592', 80),
('T748928', 76),
('T56', 65),
('T41944', 48),
('T36992', 44),
('T9', 44),
('T97', 42),
('T16777472', 39),
('T8651776', 38),
('T-2147481664', 37),
('T32896', 34),
('T2516', 32),
('T7808', 32),
('T33554944', 26),
('T1310', 25),
('T33554432', 24),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T8768', 19),
('T262656', 16),
('T43968', 16),
('T1132', 16),
('T524544', 16),
('T86752', 16),
('T9175552', 16),
('T488', 13),
('T132', 13),
('T544', 13),
('T18436', 13),
('T16793941', 13),
('T-21474825', 11),
('T268', 9),
('T16512', 6),
('T514', 6),
('T492', 5),
('T-2147482944', 5),
('T63616', 4),
('T55424', 3),
('T589824', 3),
('T518', 3),
('T-18748192', 2),
('T-21474819', 2),
('T12', 1),
('T-2147483647', 1),
('T-2147482176', 1),
('T-2147483646', 1)],
24: Counter({nan: 4931172436L,
'T-18748192': 5,
'T-2147481664': 71,
'T-21474819': 7,
'T-2147482176': 2,
'T-2147482432': 707,
'T-21474825': 23,
'T-2147482688': 724,
'T-2147482816': 788,
'T-2147482944': 6,
'T-2147483646': 3,
'T-2147483647': 3,
'T-2147483648': 3909,
'T-21474872': 216,
'T1': 132617337,
'T11141888': 560,
'T1132': 32,
'T113776': 192,
'T1152': 201,
'T12': 1,
'T12582912': 540,
'T128': 9798,
'T1310': 51,
'T132': 13,
'T134217728': 995,
'T1372': 3583,
'T143': 64408,
'T145': 649374,
'T16': 8369,
'T16384': 225,
'T16512': 9,
'T16777216': 288,
'T16777232': 3247,
'T16777248': 2015,
'T16777472': 52,
'T16777557': 2271,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 52,
'T2': 77541,
'T24': 633,
'T2516': 144,
'T25165824': 16,
'T256': 2444,
'T262144': 2510,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 896,
'T3': 1583160,
'T32': 5537,
'T32896': 71,
'T331648': 224,
'T33554432': 50,
'T33554448': 262,
'T33554944': 39,
'T36992': 82,
'T393216': 19,
'T3942': 19,
'T4': 136973,
'T41944': 128,
'T4325376': 19,
'T43968': 16,
'T4718592': 144,
'T48': 3080,
'T48576': 6399,
'T488': 13,
'T492': 9,
'T5': 37126,
'T512': 6018,
'T514': 15,
'T518': 3,
'T52': 286,
'T524288': 6000,
'T524544': 48,
'T544': 13,
'T55424': 4,
'T56': 143,
'T589824': 12,
'T6': 2025,
'T618624': 247,
'T63616': 6,
'T64': 1121,
'T6553': 1048,
'T65536': 3253,
'T678864': 66,
'T7': 484,
'T748928': 114,
'T7808': 32,
'T786432': 832,
'T786944': 32,
'T8': 11368,
'T83888': 2069,
'T8389632': 874,
'T8651776': 114,
'T86752': 32,
'T8768': 38,
'T8912896': 592,
'T9': 94,
'T917': 480,
'T9174': 576,
'T9175552': 16,
'T91764': 16,
'T96': 714,
'T96112': 16,
'T97': 94,
'T98': 256}),
25: Counter({'T-18748192': 1,
'T-21474819': 3,
'T-2147482432': 43,
'T-21474825': 1,
'T-2147482688': 4,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 33,
'T-21474872': 14,
'T1': 30413,
'T1152': 5,
'T12582912': 74,
'T1310': 1,
'T1372': 261,
'T145': 1372,
'T16': 65,
'T16777248': 169,
'T16779428': 13,
'T178258': 13,
'T18436': 26,
'T24': 133,
'T2516': 80,
'T25165824': 16,
'T256': 84,
'T26808': 18,
'T3': 3024,
'T32': 215,
'T32896': 3,
'T33554432': 2,
'T33554448': 2,
'T41944': 32,
'T48': 140,
'T48576': 377,
'T5': 114,
'T514': 3,
'T524544': 16,
'T56': 13,
'T589824': 6,
'T6': 19,
'T618624': 19,
'T64': 171,
'T65536': 11,
'T678864': 66,
'T786432': 256,
'T786944': 32,
'T8389632': 152,
'T8651776': 38,
'T9': 6,
'T917': 64,
'T91764': 16,
'T96': 34,
'T96112': 16,
'T97': 10,
'T98': 28}),
26: Counter({nan: 2465567643L,
'T-18748192': 2,
'T-2147481664': 34,
'T-21474819': 2,
'T-2147482176': 1,
'T-2147482432': 332,
'T-21474825': 11,
'T-2147482688': 360,
'T-2147482816': 385,
'T-2147482944': 1,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 1938,
'T-21474872': 101,
'T1': 66293462,
'T11141888': 272,
'T1132': 16,
'T113776': 80,
'T1152': 98,
'T12582912': 233,
'T128': 4881,
'T1310': 25,
'T134217728': 421,
'T1372': 1661,
'T143': 31950,
'T145': 324001,
'T16': 4152,
'T16384': 90,
'T16512': 3,
'T16777216': 144,
'T16777232': 1601,
'T16777248': 923,
'T16777472': 13,
'T16777557': 1101,
'T18436': 13,
'T2': 38732,
'T24': 250,
'T2516': 32,
'T256': 1180,
'T262144': 1161,
'T268435456': 298,
'T3': 790068,
'T32': 2661,
'T32896': 34,
'T331648': 104,
'T33554432': 24,
'T33554448': 130,
'T33554944': 13,
'T36992': 38,
'T4': 68429,
'T41944': 48,
'T4718592': 64,
'T48': 1470,
'T48576': 3011,
'T492': 4,
'T5': 18506,
'T512': 2890,
'T514': 6,
'T52': 91,
'T524288': 2960,
'T524544': 16,
'T55424': 1,
'T56': 65,
'T589824': 3,
'T6': 1003,
'T618624': 114,
'T63616': 2,
'T64': 475,
'T6553': 516,
'T65536': 1621,
'T7': 234,
'T748928': 38,
'T786432': 288,
'T8': 5672,
'T83888': 969,
'T8389632': 361,
'T8651776': 38,
'T86752': 16,
'T8768': 19,
'T8912896': 256,
'T9': 44,
'T917': 208,
'T9174': 240,
'T96': 340,
'T97': 42,
'T98': 114}),
27: Counter({nan: 2465604793L,
'T-18748192': 3,
'T-2147481664': 37,
'T-21474819': 5,
'T-2147482176': 1,
'T-2147482432': 375,
'T-21474825': 12,
'T-2147482688': 364,
'T-2147482816': 403,
'T-2147482944': 5,
'T-2147483646': 2,
'T-2147483647': 2,
'T-2147483648': 1971,
'T-21474872': 115,
'T1': 66323875,
'T11141888': 288,
'T1132': 16,
'T113776': 112,
'T1152': 103,
'T12': 1,
'T12582912': 307,
'T128': 4917,
'T1310': 26,
'T132': 13,
'T134217728': 574,
'T1372': 1922,
'T143': 32458,
'T145': 325373,
'T16': 4217,
'T16384': 135,
'T16512': 6,
'T16777216': 144,
'T16777232': 1646,
'T16777248': 1092,
'T16777472': 39,
'T16777557': 1170,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 39,
'T2': 38809,
'T24': 383,
'T2516': 112,
'T25165824': 16,
'T256': 1264,
'T262144': 1349,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 598,
'T3': 793092,
'T32': 2876,
'T32896': 37,
'T331648': 120,
'T33554432': 26,
'T33554448': 132,
'T33554944': 26,
'T36992': 44,
'T393216': 19,
'T3942': 19,
'T4': 68544,
'T41944': 80,
'T4325376': 19,
'T43968': 16,
'T4718592': 80,
'T48': 1610,
'T48576': 3388,
'T488': 13,
'T492': 5,
'T5': 18620,
'T512': 3128,
'T514': 9,
'T518': 3,
'T52': 195,
'T524288': 3040,
'T524544': 32,
'T544': 13,
'T55424': 3,
'T56': 78,
'T589824': 9,
'T6': 1022,
'T618624': 133,
'T63616': 4,
'T64': 646,
'T6553': 532,
'T65536': 1632,
'T678864': 66,
'T7': 250,
'T748928': 76,
'T7808': 32,
'T786432': 544,
'T786944': 32,
'T8': 5696,
'T83888': 1100,
'T8389632': 513,
'T8651776': 76,
'T86752': 16,
'T8768': 19,
'T8912896': 336,
'T9': 50,
'T917': 272,
'T9174': 336,
'T9175552': 16,
'T91764': 16,
'T96': 374,
'T96112': 16,
'T97': 52,
'T98': 142}),
28: [(nan, 4931172436L),
('T1', 132617337),
('T3', 1583160),
('T145', 649374),
('T4', 136973),
('T2', 77541),
('T143', 64408),
('T5', 37126),
('T8', 11368),
('T128', 9798),
('T16', 8369),
('T48576', 6399),
('T512', 6018),
('T524288', 6000),
('T32', 5537),
('T-2147483648', 3909),
('T1372', 3583),
('T65536', 3253),
('T16777232', 3247),
('T48', 3080),
('T262144', 2510),
('T256', 2444),
('T16777557', 2271),
('T83888', 2069),
('T6', 2025),
('T16777248', 2015),
('T64', 1121),
('T6553', 1048),
('T134217728', 995),
('T268435456', 896),
('T8389632', 874),
('T786432', 832),
('T-2147482816', 788),
('T-2147482688', 724),
('T96', 714),
('T-2147482432', 707),
('T24', 633),
('T8912896', 592),
('T9174', 576),
('T11141888', 560),
('T12582912', 540),
('T7', 484),
('T917', 480),
('T16777216', 288),
('T52', 286),
('T33554448', 262),
('T98', 256),
('T618624', 247),
('T16384', 225),
('T331648', 224),
('T-21474872', 216),
('T1152', 201),
('T113776', 192),
('T2516', 144),
('T4718592', 144),
('T56', 143),
('T41944', 128),
('T748928', 114),
('T8651776', 114),
('T97', 94),
('T9', 94),
('T36992', 82),
('T32896', 71),
('T-2147481664', 71),
('T678864', 66),
('T16777472', 52),
('T18436', 52),
('T1310', 51),
('T33554432', 50),
('T524544', 48),
('T33554944', 39),
('T8768', 38),
('T1132', 32),
('T7808', 32),
('T86752', 32),
('T786944', 32),
('T-21474825', 23),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T26808', 18),
('T262656', 16),
('T43968', 16),
('T96112', 16),
('T25165824', 16),
('T91764', 16),
('T9175552', 16),
('T514', 15),
('T488', 13),
('T132', 13),
('T544', 13),
('T16793941', 13),
('T16779428', 13),
('T178258', 13),
('T589824', 12),
('T492', 9),
('T16512', 9),
('T268', 9),
('T-21474819', 7),
('T63616', 6),
('T-2147482944', 6),
('T-18748192', 5),
('T55424', 4),
('T-2147483647', 3),
('T518', 3),
('T-2147483646', 3),
('T-2147482176', 2),
('T12', 1)],
29: 108,
31: ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
32: ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
33: ['T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664'],
34: ['T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3'],
35: 724},
'_': 724,
'_13': {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16793941',
'T18436',
'T2',
'T24',
'T2516',
'T256',
'T262144',
'T262656',
'T268',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T7',
'T748928',
'T7808',
'T786432',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T96',
'T97',
'T98'},
'_16': {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'},
'_21': [(nan, 2465567643L),
('T1', 66323875),
('T3', 793092),
('T145', 325373),
('T4', 68429),
('T2', 38732),
('T143', 31950),
('T5', 18620),
('T8', 5672),
('T128', 4881),
('T16', 4217),
('T48576', 3388),
('T524288', 2960),
('T512', 2890),
('T32', 2876),
('T-2147483648', 1971),
('T1372', 1922),
('T65536', 1632),
('T48', 1610),
('T16777232', 1601),
('T256', 1264),
('T262144', 1161),
('T16777557', 1101),
('T16777248', 1092),
('T6', 1022),
('T83888', 969),
('T64', 646),
('T786432', 544),
('T6553', 516),
('T8389632', 513),
('T134217728', 421),
('T-2147482816', 385),
('T24', 383),
('T-2147482432', 375),
('T96', 374),
('T-2147482688', 364),
('T12582912', 307),
('T268435456', 298),
('T11141888', 272),
('T917', 272),
('T8912896', 256),
('T9174', 240),
('T7', 234),
('T16777216', 144),
('T98', 142),
('T618624', 133),
('T33554448', 132),
('T-21474872', 115),
('T2516', 112),
('T331648', 104),
('T1152', 103),
('T52', 91),
('T16384', 90),
('T41944', 80),
('T113776', 80),
('T56', 78),
('T8651776', 76),
('T678864', 66),
('T4718592', 64),
('T97', 52),
('T9', 50),
('T18436', 39),
('T748928', 38),
('T36992', 38),
('T32896', 37),
('T-2147481664', 34),
('T524544', 32),
('T786944', 32),
('T33554432', 26),
('T1310', 26),
('T8768', 19),
('T26808', 18),
('T1132', 16),
('T96112', 16),
('T86752', 16),
('T25165824', 16),
('T91764', 16),
('T16777472', 13),
('T16779428', 13),
('T178258', 13),
('T33554944', 13),
('T-21474825', 12),
('T589824', 9),
('T514', 9),
('T-21474819', 5),
('T492', 4),
('T-18748192', 3),
('T16512', 3),
('T63616', 2),
('T-2147483647', 2),
('T-2147483646', 2),
('T-2147482176', 1),
('T-2147482944', 1),
('T55424', 1)],
'_23': [(nan, 2465604793L),
('T1', 66293462),
('T3', 790068),
('T145', 324001),
('T4', 68544),
('T2', 38809),
('T143', 32458),
('T5', 18506),
('T8', 5696),
('T128', 4917),
('T16', 4152),
('T512', 3128),
('T524288', 3040),
('T48576', 3011),
('T32', 2661),
('T-2147483648', 1938),
('T1372', 1661),
('T16777232', 1646),
('T65536', 1621),
('T48', 1470),
('T262144', 1349),
('T256', 1180),
('T16777557', 1170),
('T83888', 1100),
('T6', 1003),
('T16777248', 923),
('T268435456', 598),
('T134217728', 574),
('T6553', 532),
('T64', 475),
('T-2147482816', 403),
('T8389632', 361),
('T-2147482688', 360),
('T96', 340),
('T8912896', 336),
('T9174', 336),
('T-2147482432', 332),
('T11141888', 288),
('T786432', 288),
('T24', 250),
('T7', 250),
('T12582912', 233),
('T917', 208),
('T52', 195),
('T16777216', 144),
('T16384', 135),
('T33554448', 130),
('T331648', 120),
('T618624', 114),
('T98', 114),
('T113776', 112),
('T-21474872', 101),
('T1152', 98),
('T4718592', 80),
('T748928', 76),
('T56', 65),
('T41944', 48),
('T36992', 44),
('T9', 44),
('T97', 42),
('T16777472', 39),
('T8651776', 38),
('T-2147481664', 37),
('T32896', 34),
('T2516', 32),
('T7808', 32),
('T33554944', 26),
('T1310', 25),
('T33554432', 24),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T8768', 19),
('T262656', 16),
('T43968', 16),
('T1132', 16),
('T524544', 16),
('T86752', 16),
('T9175552', 16),
('T488', 13),
('T132', 13),
('T544', 13),
('T18436', 13),
('T16793941', 13),
('T-21474825', 11),
('T268', 9),
('T16512', 6),
('T514', 6),
('T492', 5),
('T-2147482944', 5),
('T63616', 4),
('T55424', 3),
('T589824', 3),
('T518', 3),
('T-18748192', 2),
('T-21474819', 2),
('T12', 1),
('T-2147483647', 1),
('T-2147482176', 1),
('T-2147483646', 1)],
'_24': Counter({nan: 4931172436L,
'T-18748192': 5,
'T-2147481664': 71,
'T-21474819': 7,
'T-2147482176': 2,
'T-2147482432': 707,
'T-21474825': 23,
'T-2147482688': 724,
'T-2147482816': 788,
'T-2147482944': 6,
'T-2147483646': 3,
'T-2147483647': 3,
'T-2147483648': 3909,
'T-21474872': 216,
'T1': 132617337,
'T11141888': 560,
'T1132': 32,
'T113776': 192,
'T1152': 201,
'T12': 1,
'T12582912': 540,
'T128': 9798,
'T1310': 51,
'T132': 13,
'T134217728': 995,
'T1372': 3583,
'T143': 64408,
'T145': 649374,
'T16': 8369,
'T16384': 225,
'T16512': 9,
'T16777216': 288,
'T16777232': 3247,
'T16777248': 2015,
'T16777472': 52,
'T16777557': 2271,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 52,
'T2': 77541,
'T24': 633,
'T2516': 144,
'T25165824': 16,
'T256': 2444,
'T262144': 2510,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 896,
'T3': 1583160,
'T32': 5537,
'T32896': 71,
'T331648': 224,
'T33554432': 50,
'T33554448': 262,
'T33554944': 39,
'T36992': 82,
'T393216': 19,
'T3942': 19,
'T4': 136973,
'T41944': 128,
'T4325376': 19,
'T43968': 16,
'T4718592': 144,
'T48': 3080,
'T48576': 6399,
'T488': 13,
'T492': 9,
'T5': 37126,
'T512': 6018,
'T514': 15,
'T518': 3,
'T52': 286,
'T524288': 6000,
'T524544': 48,
'T544': 13,
'T55424': 4,
'T56': 143,
'T589824': 12,
'T6': 2025,
'T618624': 247,
'T63616': 6,
'T64': 1121,
'T6553': 1048,
'T65536': 3253,
'T678864': 66,
'T7': 484,
'T748928': 114,
'T7808': 32,
'T786432': 832,
'T786944': 32,
'T8': 11368,
'T83888': 2069,
'T8389632': 874,
'T8651776': 114,
'T86752': 32,
'T8768': 38,
'T8912896': 592,
'T9': 94,
'T917': 480,
'T9174': 576,
'T9175552': 16,
'T91764': 16,
'T96': 714,
'T96112': 16,
'T97': 94,
'T98': 256}),
'_25': Counter({'T-18748192': 1,
'T-21474819': 3,
'T-2147482432': 43,
'T-21474825': 1,
'T-2147482688': 4,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 33,
'T-21474872': 14,
'T1': 30413,
'T1152': 5,
'T12582912': 74,
'T1310': 1,
'T1372': 261,
'T145': 1372,
'T16': 65,
'T16777248': 169,
'T16779428': 13,
'T178258': 13,
'T18436': 26,
'T24': 133,
'T2516': 80,
'T25165824': 16,
'T256': 84,
'T26808': 18,
'T3': 3024,
'T32': 215,
'T32896': 3,
'T33554432': 2,
'T33554448': 2,
'T41944': 32,
'T48': 140,
'T48576': 377,
'T5': 114,
'T514': 3,
'T524544': 16,
'T56': 13,
'T589824': 6,
'T6': 19,
'T618624': 19,
'T64': 171,
'T65536': 11,
'T678864': 66,
'T786432': 256,
'T786944': 32,
'T8389632': 152,
'T8651776': 38,
'T9': 6,
'T917': 64,
'T91764': 16,
'T96': 34,
'T96112': 16,
'T97': 10,
'T98': 28}),
'_26': Counter({nan: 2465567643L,
'T-18748192': 2,
'T-2147481664': 34,
'T-21474819': 2,
'T-2147482176': 1,
'T-2147482432': 332,
'T-21474825': 11,
'T-2147482688': 360,
'T-2147482816': 385,
'T-2147482944': 1,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 1938,
'T-21474872': 101,
'T1': 66293462,
'T11141888': 272,
'T1132': 16,
'T113776': 80,
'T1152': 98,
'T12582912': 233,
'T128': 4881,
'T1310': 25,
'T134217728': 421,
'T1372': 1661,
'T143': 31950,
'T145': 324001,
'T16': 4152,
'T16384': 90,
'T16512': 3,
'T16777216': 144,
'T16777232': 1601,
'T16777248': 923,
'T16777472': 13,
'T16777557': 1101,
'T18436': 13,
'T2': 38732,
'T24': 250,
'T2516': 32,
'T256': 1180,
'T262144': 1161,
'T268435456': 298,
'T3': 790068,
'T32': 2661,
'T32896': 34,
'T331648': 104,
'T33554432': 24,
'T33554448': 130,
'T33554944': 13,
'T36992': 38,
'T4': 68429,
'T41944': 48,
'T4718592': 64,
'T48': 1470,
'T48576': 3011,
'T492': 4,
'T5': 18506,
'T512': 2890,
'T514': 6,
'T52': 91,
'T524288': 2960,
'T524544': 16,
'T55424': 1,
'T56': 65,
'T589824': 3,
'T6': 1003,
'T618624': 114,
'T63616': 2,
'T64': 475,
'T6553': 516,
'T65536': 1621,
'T7': 234,
'T748928': 38,
'T786432': 288,
'T8': 5672,
'T83888': 969,
'T8389632': 361,
'T8651776': 38,
'T86752': 16,
'T8768': 19,
'T8912896': 256,
'T9': 44,
'T917': 208,
'T9174': 240,
'T96': 340,
'T97': 42,
'T98': 114}),
'_27': Counter({nan: 2465604793L,
'T-18748192': 3,
'T-2147481664': 37,
'T-21474819': 5,
'T-2147482176': 1,
'T-2147482432': 375,
'T-21474825': 12,
'T-2147482688': 364,
'T-2147482816': 403,
'T-2147482944': 5,
'T-2147483646': 2,
'T-2147483647': 2,
'T-2147483648': 1971,
'T-21474872': 115,
'T1': 66323875,
'T11141888': 288,
'T1132': 16,
'T113776': 112,
'T1152': 103,
'T12': 1,
'T12582912': 307,
'T128': 4917,
'T1310': 26,
'T132': 13,
'T134217728': 574,
'T1372': 1922,
'T143': 32458,
'T145': 325373,
'T16': 4217,
'T16384': 135,
'T16512': 6,
'T16777216': 144,
'T16777232': 1646,
'T16777248': 1092,
'T16777472': 39,
'T16777557': 1170,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 39,
'T2': 38809,
'T24': 383,
'T2516': 112,
'T25165824': 16,
'T256': 1264,
'T262144': 1349,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 598,
'T3': 793092,
'T32': 2876,
'T32896': 37,
'T331648': 120,
'T33554432': 26,
'T33554448': 132,
'T33554944': 26,
'T36992': 44,
'T393216': 19,
'T3942': 19,
'T4': 68544,
'T41944': 80,
'T4325376': 19,
'T43968': 16,
'T4718592': 80,
'T48': 1610,
'T48576': 3388,
'T488': 13,
'T492': 5,
'T5': 18620,
'T512': 3128,
'T514': 9,
'T518': 3,
'T52': 195,
'T524288': 3040,
'T524544': 32,
'T544': 13,
'T55424': 3,
'T56': 78,
'T589824': 9,
'T6': 1022,
'T618624': 133,
'T63616': 4,
'T64': 646,
'T6553': 532,
'T65536': 1632,
'T678864': 66,
'T7': 250,
'T748928': 76,
'T7808': 32,
'T786432': 544,
'T786944': 32,
'T8': 5696,
'T83888': 1100,
'T8389632': 513,
'T8651776': 76,
'T86752': 16,
'T8768': 19,
'T8912896': 336,
'T9': 50,
'T917': 272,
'T9174': 336,
'T9175552': 16,
'T91764': 16,
'T96': 374,
'T96112': 16,
'T97': 52,
'T98': 142}),
'_28': [(nan, 4931172436L),
('T1', 132617337),
('T3', 1583160),
('T145', 649374),
('T4', 136973),
('T2', 77541),
('T143', 64408),
('T5', 37126),
('T8', 11368),
('T128', 9798),
('T16', 8369),
('T48576', 6399),
('T512', 6018),
('T524288', 6000),
('T32', 5537),
('T-2147483648', 3909),
('T1372', 3583),
('T65536', 3253),
('T16777232', 3247),
('T48', 3080),
('T262144', 2510),
('T256', 2444),
('T16777557', 2271),
('T83888', 2069),
('T6', 2025),
('T16777248', 2015),
('T64', 1121),
('T6553', 1048),
('T134217728', 995),
('T268435456', 896),
('T8389632', 874),
('T786432', 832),
('T-2147482816', 788),
('T-2147482688', 724),
('T96', 714),
('T-2147482432', 707),
('T24', 633),
('T8912896', 592),
('T9174', 576),
('T11141888', 560),
('T12582912', 540),
('T7', 484),
('T917', 480),
('T16777216', 288),
('T52', 286),
('T33554448', 262),
('T98', 256),
('T618624', 247),
('T16384', 225),
('T331648', 224),
('T-21474872', 216),
('T1152', 201),
('T113776', 192),
('T2516', 144),
('T4718592', 144),
('T56', 143),
('T41944', 128),
('T748928', 114),
('T8651776', 114),
('T97', 94),
('T9', 94),
('T36992', 82),
('T32896', 71),
('T-2147481664', 71),
('T678864', 66),
('T16777472', 52),
('T18436', 52),
('T1310', 51),
('T33554432', 50),
('T524544', 48),
('T33554944', 39),
('T8768', 38),
('T1132', 32),
('T7808', 32),
('T86752', 32),
('T786944', 32),
('T-21474825', 23),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T26808', 18),
('T262656', 16),
('T43968', 16),
('T96112', 16),
('T25165824', 16),
('T91764', 16),
('T9175552', 16),
('T514', 15),
('T488', 13),
('T132', 13),
('T544', 13),
('T16793941', 13),
('T16779428', 13),
('T178258', 13),
('T589824', 12),
('T492', 9),
('T16512', 9),
('T268', 9),
('T-21474819', 7),
('T63616', 6),
('T-2147482944', 6),
('T-18748192', 5),
('T55424', 4),
('T-2147483647', 3),
('T518', 3),
('T-2147483646', 3),
('T-2147482176', 2),
('T12', 1)],
'_29': 108,
'_31': ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
'_32': ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
'_33': ['T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664'],
'_34': ['T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3'],
'_35': 724,
'_7': {'T16779428',
'T178258',
'T25165824',
'T26808',
'T678864',
'T786944',
'T91764',
'T96112'},
'_8': {'T12',
'T132',
'T16793941',
'T262656',
'T268',
'T393216',
'T3942',
'T4325376',
'T43968',
'T488',
'T518',
'T544',
'T7808',
'T9175552'},
'__': ['T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3'],
'___': ['T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664'],
'__builtin__': <module '__builtin__' (built-in)>,
'__builtins__': <module '__builtin__' (built-in)>,
'__doc__': 'Automatically created module for IPython interactive environment',
'__name__': '__main__',
'__package__': None,
'_dh': [u'D:\\Kaggle_ws\\Bosch\\src'],
'_i': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%03d/g' % (s, i)\n i += 1",
'_i1': u'import pandas as pd\nimport numpy as np',
'_i10': u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
'_i11': u't2 - t1',
'_i12': u't1',
'_i13': u't2',
'_i14': u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
'_i15': u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
'_i16': u't1.union(t2)',
'_i17': u"import collections\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
'_i18': u'%time c1 = count_values(train_fname)',
'_i19': u"from collections import Counter\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
'_i2': u'chunksize = 50000\ntrain_fname = "../input/train_categorical.csv"\ntest_fname = "../input/test_categorical.csv"\n\noutput_fname = "../input/train_categorical_250000.out.csv"',
'_i20': u'%time c1 = count_values(train_fname)',
'_i21': u'c1.most_common()',
'_i22': u'%time c2 = count_values(test_fname)',
'_i23': u'c2.most_common()',
'_i24': u'c1 + c2',
'_i25': u'c1 - c2',
'_i26': u'c1 & c2',
'_i27': u'c1 | c2',
'_i28': u'c = c1 + c2\nc.most_common()',
'_i29': u'c = c1 + c2\nlen(c.most_common())',
'_i3': u"def cat_values(fname):\n setl = set()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n setl = setl.union(set(item[1:]))\n print setl",
'_i30': u'sorted(t1+t2)',
'_i31': u'sorted(t1.union(t2))',
'_i32': u'sorted(t1.union(t2), key=str.lower)',
'_i33': u'sorted(t1.union(t2), key=len)',
'_i34': u'sorted(t1.union(t2), key=len, reverse=True)',
'_i35': u"c = c1 + c2\nc['T-2147482688']",
'_i36': u'for s in sorted(t1.union(t2), key=len, reverse=True):\n print s, c[s]',
'_i37': u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % c[s]",
'_i38': u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % s",
'_i39': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/%00d/g' % (s, i)",
'_i4': u'%time cat_values(test_fname)',
'_i40': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%00d/g' % (s, i)",
'_i41': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%2d/g' % (s, i)",
'_i42': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)",
'_i43': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i++",
'_i44': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i += 1",
'_i45': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%03d/g' % (s, i)\n i += 1",
'_i46': u'locals()',
'_i5': u"t1 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
'_i6': u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
'_i7': u't1 - t2',
'_i8': u't2 - t1',
'_i9': u'%time t1 = cat_values(train_fname)',
'_ih': ['',
u'import pandas as pd\nimport numpy as np',
u'chunksize = 50000\ntrain_fname = "../input/train_categorical.csv"\ntest_fname = "../input/test_categorical.csv"\n\noutput_fname = "../input/train_categorical_250000.out.csv"',
u"def cat_values(fname):\n setl = set()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n setl = setl.union(set(item[1:]))\n print setl",
u"get_ipython().magic(u'time cat_values(test_fname)')",
u"t1 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set([nan, 'T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u't1 - t2',
u't2 - t1',
u"get_ipython().magic(u'time t1 = cat_values(train_fname)')",
u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
u't2 - t1',
u't1',
u't2',
u"t1 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T618624', 'T6553', 'T-2147482432', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T262144', 'T128', 'T512', 'T16777216', 'T589824', 'T514', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T86752', 'T8912896', 'T256', 'T-21474872', 'T32896', 'T16779428', 'T2516', 'T-2147482688', 'T25165824', 'T91764', 'T917', 'T331648', 'T16', 'T11141888', 'T8389632', 'T786432', 'T178258', 'T26808', 'T1132', 'T-2147483647', 'T786944', 'T-2147483648', 'T56', 'T145', 'T98', 'T7', 'T96', 'T97', 'T16777557', 'T33554432', 'T268435456', 'T8768', 'T8', 'T9', 'T6', 'T96112', 'T4', 'T5', 'T2', 'T3', 'T16777248', 'T1310', 'T143', 'T9174', 'T-2147483646', 'T-2147482176', 'T1', 'T678864', 'T24', 'T41944', 'T18436', 'T-2147481664', 'T48576', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T8651776', 'T52'])\n\nt2 = set(['T16777232', 'T524544', 'T33554448', 'T1152', 'T63616', 'T262656', 'T83888', 'T32', 'T748928', 'T-21474825', 'T4718592', 'T-2147483648', 'T618624', 'T6553', 'T3942', 'T16793941', 'T16777472', 'T12582912', 'T-2147482816', 'T36992', 'T134217728', 'T-18748192', 'T518', 'T262144', 'T128', 'T145', 'T16777216', 'T16777248', 'T86752', 'T524288', 'T-21474819', 'T492', 'T1372', 'T33554944', 'T16384', 'T16512', 'T113776', 'T48', 'T43968', 'T8912896', 'T143', 'T256', 'T48576', 'T32896', 'T393216', 'T2516', 'T-2147482688', 'T7808', 'T4325376', 'T917', 'T132', 'T331648', 'T9175552', 'T16', 'T11141888', 'T12', 'T8389632', 'T786432', 'T-21474872', 'T1132', 'T-2147483647', 'T268', 'T488', 'T52', 'T56', 'T512', 'T98', 'T96', 'T97', 'T4', 'T16777557', 'T33554432', 'T268435456', 'T8', 'T9', 'T6', 'T7', 'T-2147482432', 'T5', 'T2', 'T3', 'T1', 'T1310', 'T514', 'T9174', 'T-2147483646', 'T-2147482176', 'T24', 'T589824', 'T41944', 'T-2147481664', 'T8651776', 'T8768', 'T64', 'T-2147482944', 'T65536', 'T55424', 'T18436', 'T544'])",
u'print len(t1),\nprint len(t2)\n\nprint len(t1.union(t2))',
u't1.union(t2)',
u"import collections\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
u"get_ipython().magic(u'time c1 = count_values(train_fname)')",
u"from collections import Counter\n\ndef count_values(fname):\n cat_counter = Counter()\n for chunk in pd.read_csv(fname, index_col='Id', iterator=True, chunksize=chunksize, dtype=object):\n print '*',\n data = pd.DataFrame()\n data = data.append(chunk, ignore_index=True)\n\n for item in data.itertuples():\n cat_counter.update(list(item[1:]))\n return cat_counter",
u"get_ipython().magic(u'time c1 = count_values(train_fname)')",
u'c1.most_common()',
u"get_ipython().magic(u'time c2 = count_values(test_fname)')",
u'c2.most_common()',
u'c1 + c2',
u'c1 - c2',
u'c1 & c2',
u'c1 | c2',
u'c = c1 + c2\nc.most_common()',
u'c = c1 + c2\nlen(c.most_common())',
u'sorted(t1+t2)',
u'sorted(t1.union(t2))',
u'sorted(t1.union(t2), key=str.lower)',
u'sorted(t1.union(t2), key=len)',
u'sorted(t1.union(t2), key=len, reverse=True)',
u"c = c1 + c2\nc['T-2147482688']",
u'for s in sorted(t1.union(t2), key=len, reverse=True):\n print s, c[s]',
u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % c[s]",
u"for s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s//g' % s",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/%00d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%00d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%2d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i++",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i += 1",
u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%03d/g' % (s, i)\n i += 1",
u'locals()'],
'_ii': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i += 1",
'_iii': u"i = 1\nfor s in sorted(t1.union(t2), key=len, reverse=True):\n print 's/%s/S%02d/g' % (s, i)\n i++",
'_oh': {7: {'T16779428',
'T178258',
'T25165824',
'T26808',
'T678864',
'T786944',
'T91764',
'T96112'},
8: {'T12',
'T132',
'T16793941',
'T262656',
'T268',
'T393216',
'T3942',
'T4325376',
'T43968',
'T488',
'T518',
'T544',
'T7808',
'T9175552'},
13: {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16793941',
'T18436',
'T2',
'T24',
'T2516',
'T256',
'T262144',
'T262656',
'T268',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T7',
'T748928',
'T7808',
'T786432',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T96',
'T97',
'T98'},
16: {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'},
21: [(nan, 2465567643L),
('T1', 66323875),
('T3', 793092),
('T145', 325373),
('T4', 68429),
('T2', 38732),
('T143', 31950),
('T5', 18620),
('T8', 5672),
('T128', 4881),
('T16', 4217),
('T48576', 3388),
('T524288', 2960),
('T512', 2890),
('T32', 2876),
('T-2147483648', 1971),
('T1372', 1922),
('T65536', 1632),
('T48', 1610),
('T16777232', 1601),
('T256', 1264),
('T262144', 1161),
('T16777557', 1101),
('T16777248', 1092),
('T6', 1022),
('T83888', 969),
('T64', 646),
('T786432', 544),
('T6553', 516),
('T8389632', 513),
('T134217728', 421),
('T-2147482816', 385),
('T24', 383),
('T-2147482432', 375),
('T96', 374),
('T-2147482688', 364),
('T12582912', 307),
('T268435456', 298),
('T11141888', 272),
('T917', 272),
('T8912896', 256),
('T9174', 240),
('T7', 234),
('T16777216', 144),
('T98', 142),
('T618624', 133),
('T33554448', 132),
('T-21474872', 115),
('T2516', 112),
('T331648', 104),
('T1152', 103),
('T52', 91),
('T16384', 90),
('T41944', 80),
('T113776', 80),
('T56', 78),
('T8651776', 76),
('T678864', 66),
('T4718592', 64),
('T97', 52),
('T9', 50),
('T18436', 39),
('T748928', 38),
('T36992', 38),
('T32896', 37),
('T-2147481664', 34),
('T524544', 32),
('T786944', 32),
('T33554432', 26),
('T1310', 26),
('T8768', 19),
('T26808', 18),
('T1132', 16),
('T96112', 16),
('T86752', 16),
('T25165824', 16),
('T91764', 16),
('T16777472', 13),
('T16779428', 13),
('T178258', 13),
('T33554944', 13),
('T-21474825', 12),
('T589824', 9),
('T514', 9),
('T-21474819', 5),
('T492', 4),
('T-18748192', 3),
('T16512', 3),
('T63616', 2),
('T-2147483647', 2),
('T-2147483646', 2),
('T-2147482176', 1),
('T-2147482944', 1),
('T55424', 1)],
23: [(nan, 2465604793L),
('T1', 66293462),
('T3', 790068),
('T145', 324001),
('T4', 68544),
('T2', 38809),
('T143', 32458),
('T5', 18506),
('T8', 5696),
('T128', 4917),
('T16', 4152),
('T512', 3128),
('T524288', 3040),
('T48576', 3011),
('T32', 2661),
('T-2147483648', 1938),
('T1372', 1661),
('T16777232', 1646),
('T65536', 1621),
('T48', 1470),
('T262144', 1349),
('T256', 1180),
('T16777557', 1170),
('T83888', 1100),
('T6', 1003),
('T16777248', 923),
('T268435456', 598),
('T134217728', 574),
('T6553', 532),
('T64', 475),
('T-2147482816', 403),
('T8389632', 361),
('T-2147482688', 360),
('T96', 340),
('T8912896', 336),
('T9174', 336),
('T-2147482432', 332),
('T11141888', 288),
('T786432', 288),
('T24', 250),
('T7', 250),
('T12582912', 233),
('T917', 208),
('T52', 195),
('T16777216', 144),
('T16384', 135),
('T33554448', 130),
('T331648', 120),
('T618624', 114),
('T98', 114),
('T113776', 112),
('T-21474872', 101),
('T1152', 98),
('T4718592', 80),
('T748928', 76),
('T56', 65),
('T41944', 48),
('T36992', 44),
('T9', 44),
('T97', 42),
('T16777472', 39),
('T8651776', 38),
('T-2147481664', 37),
('T32896', 34),
('T2516', 32),
('T7808', 32),
('T33554944', 26),
('T1310', 25),
('T33554432', 24),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T8768', 19),
('T262656', 16),
('T43968', 16),
('T1132', 16),
('T524544', 16),
('T86752', 16),
('T9175552', 16),
('T488', 13),
('T132', 13),
('T544', 13),
('T18436', 13),
('T16793941', 13),
('T-21474825', 11),
('T268', 9),
('T16512', 6),
('T514', 6),
('T492', 5),
('T-2147482944', 5),
('T63616', 4),
('T55424', 3),
('T589824', 3),
('T518', 3),
('T-18748192', 2),
('T-21474819', 2),
('T12', 1),
('T-2147483647', 1),
('T-2147482176', 1),
('T-2147483646', 1)],
24: Counter({nan: 4931172436L,
'T-18748192': 5,
'T-2147481664': 71,
'T-21474819': 7,
'T-2147482176': 2,
'T-2147482432': 707,
'T-21474825': 23,
'T-2147482688': 724,
'T-2147482816': 788,
'T-2147482944': 6,
'T-2147483646': 3,
'T-2147483647': 3,
'T-2147483648': 3909,
'T-21474872': 216,
'T1': 132617337,
'T11141888': 560,
'T1132': 32,
'T113776': 192,
'T1152': 201,
'T12': 1,
'T12582912': 540,
'T128': 9798,
'T1310': 51,
'T132': 13,
'T134217728': 995,
'T1372': 3583,
'T143': 64408,
'T145': 649374,
'T16': 8369,
'T16384': 225,
'T16512': 9,
'T16777216': 288,
'T16777232': 3247,
'T16777248': 2015,
'T16777472': 52,
'T16777557': 2271,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 52,
'T2': 77541,
'T24': 633,
'T2516': 144,
'T25165824': 16,
'T256': 2444,
'T262144': 2510,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 896,
'T3': 1583160,
'T32': 5537,
'T32896': 71,
'T331648': 224,
'T33554432': 50,
'T33554448': 262,
'T33554944': 39,
'T36992': 82,
'T393216': 19,
'T3942': 19,
'T4': 136973,
'T41944': 128,
'T4325376': 19,
'T43968': 16,
'T4718592': 144,
'T48': 3080,
'T48576': 6399,
'T488': 13,
'T492': 9,
'T5': 37126,
'T512': 6018,
'T514': 15,
'T518': 3,
'T52': 286,
'T524288': 6000,
'T524544': 48,
'T544': 13,
'T55424': 4,
'T56': 143,
'T589824': 12,
'T6': 2025,
'T618624': 247,
'T63616': 6,
'T64': 1121,
'T6553': 1048,
'T65536': 3253,
'T678864': 66,
'T7': 484,
'T748928': 114,
'T7808': 32,
'T786432': 832,
'T786944': 32,
'T8': 11368,
'T83888': 2069,
'T8389632': 874,
'T8651776': 114,
'T86752': 32,
'T8768': 38,
'T8912896': 592,
'T9': 94,
'T917': 480,
'T9174': 576,
'T9175552': 16,
'T91764': 16,
'T96': 714,
'T96112': 16,
'T97': 94,
'T98': 256}),
25: Counter({'T-18748192': 1,
'T-21474819': 3,
'T-2147482432': 43,
'T-21474825': 1,
'T-2147482688': 4,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 33,
'T-21474872': 14,
'T1': 30413,
'T1152': 5,
'T12582912': 74,
'T1310': 1,
'T1372': 261,
'T145': 1372,
'T16': 65,
'T16777248': 169,
'T16779428': 13,
'T178258': 13,
'T18436': 26,
'T24': 133,
'T2516': 80,
'T25165824': 16,
'T256': 84,
'T26808': 18,
'T3': 3024,
'T32': 215,
'T32896': 3,
'T33554432': 2,
'T33554448': 2,
'T41944': 32,
'T48': 140,
'T48576': 377,
'T5': 114,
'T514': 3,
'T524544': 16,
'T56': 13,
'T589824': 6,
'T6': 19,
'T618624': 19,
'T64': 171,
'T65536': 11,
'T678864': 66,
'T786432': 256,
'T786944': 32,
'T8389632': 152,
'T8651776': 38,
'T9': 6,
'T917': 64,
'T91764': 16,
'T96': 34,
'T96112': 16,
'T97': 10,
'T98': 28}),
26: Counter({nan: 2465567643L,
'T-18748192': 2,
'T-2147481664': 34,
'T-21474819': 2,
'T-2147482176': 1,
'T-2147482432': 332,
'T-21474825': 11,
'T-2147482688': 360,
'T-2147482816': 385,
'T-2147482944': 1,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 1938,
'T-21474872': 101,
'T1': 66293462,
'T11141888': 272,
'T1132': 16,
'T113776': 80,
'T1152': 98,
'T12582912': 233,
'T128': 4881,
'T1310': 25,
'T134217728': 421,
'T1372': 1661,
'T143': 31950,
'T145': 324001,
'T16': 4152,
'T16384': 90,
'T16512': 3,
'T16777216': 144,
'T16777232': 1601,
'T16777248': 923,
'T16777472': 13,
'T16777557': 1101,
'T18436': 13,
'T2': 38732,
'T24': 250,
'T2516': 32,
'T256': 1180,
'T262144': 1161,
'T268435456': 298,
'T3': 790068,
'T32': 2661,
'T32896': 34,
'T331648': 104,
'T33554432': 24,
'T33554448': 130,
'T33554944': 13,
'T36992': 38,
'T4': 68429,
'T41944': 48,
'T4718592': 64,
'T48': 1470,
'T48576': 3011,
'T492': 4,
'T5': 18506,
'T512': 2890,
'T514': 6,
'T52': 91,
'T524288': 2960,
'T524544': 16,
'T55424': 1,
'T56': 65,
'T589824': 3,
'T6': 1003,
'T618624': 114,
'T63616': 2,
'T64': 475,
'T6553': 516,
'T65536': 1621,
'T7': 234,
'T748928': 38,
'T786432': 288,
'T8': 5672,
'T83888': 969,
'T8389632': 361,
'T8651776': 38,
'T86752': 16,
'T8768': 19,
'T8912896': 256,
'T9': 44,
'T917': 208,
'T9174': 240,
'T96': 340,
'T97': 42,
'T98': 114}),
27: Counter({nan: 2465604793L,
'T-18748192': 3,
'T-2147481664': 37,
'T-21474819': 5,
'T-2147482176': 1,
'T-2147482432': 375,
'T-21474825': 12,
'T-2147482688': 364,
'T-2147482816': 403,
'T-2147482944': 5,
'T-2147483646': 2,
'T-2147483647': 2,
'T-2147483648': 1971,
'T-21474872': 115,
'T1': 66323875,
'T11141888': 288,
'T1132': 16,
'T113776': 112,
'T1152': 103,
'T12': 1,
'T12582912': 307,
'T128': 4917,
'T1310': 26,
'T132': 13,
'T134217728': 574,
'T1372': 1922,
'T143': 32458,
'T145': 325373,
'T16': 4217,
'T16384': 135,
'T16512': 6,
'T16777216': 144,
'T16777232': 1646,
'T16777248': 1092,
'T16777472': 39,
'T16777557': 1170,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 39,
'T2': 38809,
'T24': 383,
'T2516': 112,
'T25165824': 16,
'T256': 1264,
'T262144': 1349,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 598,
'T3': 793092,
'T32': 2876,
'T32896': 37,
'T331648': 120,
'T33554432': 26,
'T33554448': 132,
'T33554944': 26,
'T36992': 44,
'T393216': 19,
'T3942': 19,
'T4': 68544,
'T41944': 80,
'T4325376': 19,
'T43968': 16,
'T4718592': 80,
'T48': 1610,
'T48576': 3388,
'T488': 13,
'T492': 5,
'T5': 18620,
'T512': 3128,
'T514': 9,
'T518': 3,
'T52': 195,
'T524288': 3040,
'T524544': 32,
'T544': 13,
'T55424': 3,
'T56': 78,
'T589824': 9,
'T6': 1022,
'T618624': 133,
'T63616': 4,
'T64': 646,
'T6553': 532,
'T65536': 1632,
'T678864': 66,
'T7': 250,
'T748928': 76,
'T7808': 32,
'T786432': 544,
'T786944': 32,
'T8': 5696,
'T83888': 1100,
'T8389632': 513,
'T8651776': 76,
'T86752': 16,
'T8768': 19,
'T8912896': 336,
'T9': 50,
'T917': 272,
'T9174': 336,
'T9175552': 16,
'T91764': 16,
'T96': 374,
'T96112': 16,
'T97': 52,
'T98': 142}),
28: [(nan, 4931172436L),
('T1', 132617337),
('T3', 1583160),
('T145', 649374),
('T4', 136973),
('T2', 77541),
('T143', 64408),
('T5', 37126),
('T8', 11368),
('T128', 9798),
('T16', 8369),
('T48576', 6399),
('T512', 6018),
('T524288', 6000),
('T32', 5537),
('T-2147483648', 3909),
('T1372', 3583),
('T65536', 3253),
('T16777232', 3247),
('T48', 3080),
('T262144', 2510),
('T256', 2444),
('T16777557', 2271),
('T83888', 2069),
('T6', 2025),
('T16777248', 2015),
('T64', 1121),
('T6553', 1048),
('T134217728', 995),
('T268435456', 896),
('T8389632', 874),
('T786432', 832),
('T-2147482816', 788),
('T-2147482688', 724),
('T96', 714),
('T-2147482432', 707),
('T24', 633),
('T8912896', 592),
('T9174', 576),
('T11141888', 560),
('T12582912', 540),
('T7', 484),
('T917', 480),
('T16777216', 288),
('T52', 286),
('T33554448', 262),
('T98', 256),
('T618624', 247),
('T16384', 225),
('T331648', 224),
('T-21474872', 216),
('T1152', 201),
('T113776', 192),
('T2516', 144),
('T4718592', 144),
('T56', 143),
('T41944', 128),
('T748928', 114),
('T8651776', 114),
('T97', 94),
('T9', 94),
('T36992', 82),
('T32896', 71),
('T-2147481664', 71),
('T678864', 66),
('T16777472', 52),
('T18436', 52),
('T1310', 51),
('T33554432', 50),
('T524544', 48),
('T33554944', 39),
('T8768', 38),
('T1132', 32),
('T7808', 32),
('T86752', 32),
('T786944', 32),
('T-21474825', 23),
('T3942', 19),
('T393216', 19),
('T4325376', 19),
('T26808', 18),
('T262656', 16),
('T43968', 16),
('T96112', 16),
('T25165824', 16),
('T91764', 16),
('T9175552', 16),
('T514', 15),
('T488', 13),
('T132', 13),
('T544', 13),
('T16793941', 13),
('T16779428', 13),
('T178258', 13),
('T589824', 12),
('T492', 9),
('T16512', 9),
('T268', 9),
('T-21474819', 7),
('T63616', 6),
('T-2147482944', 6),
('T-18748192', 5),
('T55424', 4),
('T-2147483647', 3),
('T518', 3),
('T-2147483646', 3),
('T-2147482176', 2),
('T12', 1)],
29: 108,
31: ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
32: ['T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T16793941',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T262656',
'T268',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T7808',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T91764',
'T96',
'T96112',
'T97',
'T98'],
33: ['T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664'],
34: ['T-2147482688',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-2147482176',
'T-2147482944',
'T-2147482432',
'T-2147482816',
'T-2147481664',
'T-21474825',
'T-18748192',
'T134217728',
'T-21474819',
'T268435456',
'T-21474872',
'T16777472',
'T11141888',
'T33554432',
'T16777232',
'T33554448',
'T16793941',
'T12582912',
'T16777216',
'T16777248',
'T16779428',
'T25165824',
'T16777557',
'T33554944',
'T4718592',
'T8651776',
'T8912896',
'T4325376',
'T9175552',
'T8389632',
'T262656',
'T748928',
'T618624',
'T262144',
'T524288',
'T331648',
'T786432',
'T524544',
'T113776',
'T393216',
'T178258',
'T786944',
'T589824',
'T678864',
'T63616',
'T16384',
'T43968',
'T96112',
'T83888',
'T18436',
'T36992',
'T41944',
'T16512',
'T32896',
'T65536',
'T91764',
'T26808',
'T86752',
'T48576',
'T55424',
'T1152',
'T3942',
'T1372',
'T2516',
'T7808',
'T1310',
'T6553',
'T8768',
'T9174',
'T1132',
'T488',
'T128',
'T145',
'T143',
'T492',
'T256',
'T132',
'T544',
'T518',
'T512',
'T514',
'T917',
'T268',
'T16',
'T12',
'T98',
'T96',
'T97',
'T24',
'T32',
'T48',
'T52',
'T56',
'T64',
'T1',
'T8',
'T9',
'T6',
'T7',
'T4',
'T5',
'T2',
'T3'],
35: 724},
'_sh': <module 'IPython.core.shadowns' from 'd:\anaconda\envs\Deep\lib\site-packages\IPython\core\shadowns.pyc'>,
'c': Counter({nan: 4931172436L,
'T-18748192': 5,
'T-2147481664': 71,
'T-21474819': 7,
'T-2147482176': 2,
'T-2147482432': 707,
'T-21474825': 23,
'T-2147482688': 724,
'T-2147482816': 788,
'T-2147482944': 6,
'T-2147483646': 3,
'T-2147483647': 3,
'T-2147483648': 3909,
'T-21474872': 216,
'T1': 132617337,
'T11141888': 560,
'T1132': 32,
'T113776': 192,
'T1152': 201,
'T12': 1,
'T12582912': 540,
'T128': 9798,
'T1310': 51,
'T132': 13,
'T134217728': 995,
'T1372': 3583,
'T143': 64408,
'T145': 649374,
'T16': 8369,
'T16384': 225,
'T16512': 9,
'T16777216': 288,
'T16777232': 3247,
'T16777248': 2015,
'T16777472': 52,
'T16777557': 2271,
'T16779428': 13,
'T16793941': 13,
'T178258': 13,
'T18436': 52,
'T2': 77541,
'T24': 633,
'T2516': 144,
'T25165824': 16,
'T256': 2444,
'T262144': 2510,
'T262656': 16,
'T268': 9,
'T26808': 18,
'T268435456': 896,
'T3': 1583160,
'T32': 5537,
'T32896': 71,
'T331648': 224,
'T33554432': 50,
'T33554448': 262,
'T33554944': 39,
'T36992': 82,
'T393216': 19,
'T3942': 19,
'T4': 136973,
'T41944': 128,
'T4325376': 19,
'T43968': 16,
'T4718592': 144,
'T48': 3080,
'T48576': 6399,
'T488': 13,
'T492': 9,
'T5': 37126,
'T512': 6018,
'T514': 15,
'T518': 3,
'T52': 286,
'T524288': 6000,
'T524544': 48,
'T544': 13,
'T55424': 4,
'T56': 143,
'T589824': 12,
'T6': 2025,
'T618624': 247,
'T63616': 6,
'T64': 1121,
'T6553': 1048,
'T65536': 3253,
'T678864': 66,
'T7': 484,
'T748928': 114,
'T7808': 32,
'T786432': 832,
'T786944': 32,
'T8': 11368,
'T83888': 2069,
'T8389632': 874,
'T8651776': 114,
'T86752': 32,
'T8768': 38,
'T8912896': 592,
'T9': 94,
'T917': 480,
'T9174': 576,
'T9175552': 16,
'T91764': 16,
'T96': 714,
'T96112': 16,
'T97': 94,
'T98': 256}),
'c1': Counter({nan: 2465567643L,
'T-18748192': 3,
'T-2147481664': 34,
'T-21474819': 5,
'T-2147482176': 1,
'T-2147482432': 375,
'T-21474825': 12,
'T-2147482688': 364,
'T-2147482816': 385,
'T-2147482944': 1,
'T-2147483646': 2,
'T-2147483647': 2,
'T-2147483648': 1971,
'T-21474872': 115,
'T1': 66323875,
'T11141888': 272,
'T1132': 16,
'T113776': 80,
'T1152': 103,
'T12582912': 307,
'T128': 4881,
'T1310': 26,
'T134217728': 421,
'T1372': 1922,
'T143': 31950,
'T145': 325373,
'T16': 4217,
'T16384': 90,
'T16512': 3,
'T16777216': 144,
'T16777232': 1601,
'T16777248': 1092,
'T16777472': 13,
'T16777557': 1101,
'T16779428': 13,
'T178258': 13,
'T18436': 39,
'T2': 38732,
'T24': 383,
'T2516': 112,
'T25165824': 16,
'T256': 1264,
'T262144': 1161,
'T26808': 18,
'T268435456': 298,
'T3': 793092,
'T32': 2876,
'T32896': 37,
'T331648': 104,
'T33554432': 26,
'T33554448': 132,
'T33554944': 13,
'T36992': 38,
'T4': 68429,
'T41944': 80,
'T4718592': 64,
'T48': 1610,
'T48576': 3388,
'T492': 4,
'T5': 18620,
'T512': 2890,
'T514': 9,
'T52': 91,
'T524288': 2960,
'T524544': 32,
'T55424': 1,
'T56': 78,
'T589824': 9,
'T6': 1022,
'T618624': 133,
'T63616': 2,
'T64': 646,
'T6553': 516,
'T65536': 1632,
'T678864': 66,
'T7': 234,
'T748928': 38,
'T786432': 544,
'T786944': 32,
'T8': 5672,
'T83888': 969,
'T8389632': 513,
'T8651776': 76,
'T86752': 16,
'T8768': 19,
'T8912896': 256,
'T9': 50,
'T917': 272,
'T9174': 240,
'T91764': 16,
'T96': 374,
'T96112': 16,
'T97': 52,
'T98': 142}),
'c2': Counter({nan: 2465604793L,
'T-18748192': 2,
'T-2147481664': 37,
'T-21474819': 2,
'T-2147482176': 1,
'T-2147482432': 332,
'T-21474825': 11,
'T-2147482688': 360,
'T-2147482816': 403,
'T-2147482944': 5,
'T-2147483646': 1,
'T-2147483647': 1,
'T-2147483648': 1938,
'T-21474872': 101,
'T1': 66293462,
'T11141888': 288,
'T1132': 16,
'T113776': 112,
'T1152': 98,
'T12': 1,
'T12582912': 233,
'T128': 4917,
'T1310': 25,
'T132': 13,
'T134217728': 574,
'T1372': 1661,
'T143': 32458,
'T145': 324001,
'T16': 4152,
'T16384': 135,
'T16512': 6,
'T16777216': 144,
'T16777232': 1646,
'T16777248': 923,
'T16777472': 39,
'T16777557': 1170,
'T16793941': 13,
'T18436': 13,
'T2': 38809,
'T24': 250,
'T2516': 32,
'T256': 1180,
'T262144': 1349,
'T262656': 16,
'T268': 9,
'T268435456': 598,
'T3': 790068,
'T32': 2661,
'T32896': 34,
'T331648': 120,
'T33554432': 24,
'T33554448': 130,
'T33554944': 26,
'T36992': 44,
'T393216': 19,
'T3942': 19,
'T4': 68544,
'T41944': 48,
'T4325376': 19,
'T43968': 16,
'T4718592': 80,
'T48': 1470,
'T48576': 3011,
'T488': 13,
'T492': 5,
'T5': 18506,
'T512': 3128,
'T514': 6,
'T518': 3,
'T52': 195,
'T524288': 3040,
'T524544': 16,
'T544': 13,
'T55424': 3,
'T56': 65,
'T589824': 3,
'T6': 1003,
'T618624': 114,
'T63616': 4,
'T64': 475,
'T6553': 532,
'T65536': 1621,
'T7': 250,
'T748928': 76,
'T7808': 32,
'T786432': 288,
'T8': 5696,
'T83888': 1100,
'T8389632': 361,
'T8651776': 38,
'T86752': 16,
'T8768': 19,
'T8912896': 336,
'T9': 44,
'T917': 208,
'T9174': 336,
'T9175552': 16,
'T96': 340,
'T97': 42,
'T98': 114}),
'cat_values': <function __main__.cat_values>,
'chunksize': 50000,
'collections': <module 'collections' from 'd:\anaconda\envs\Deep\lib\collections.pyc'>,
'count_values': <function __main__.count_values>,
'exit': <IPython.core.autocall.ZMQExitAutocall at 0x3e816d8>,
'get_ipython': <bound method ZMQInteractiveShell.get_ipython of <ipykernel.zmqshell.ZMQInteractiveShell object at 0x0000000003E81F60>>,
'i': 108,
'np': <module 'numpy' from 'd:\anaconda\envs\Deep\lib\site-packages\numpy\__init__.pyc'>,
'output_fname': '../input/train_categorical_250000.out.csv',
'pd': <module 'pandas' from 'd:\anaconda\envs\Deep\lib\site-packages\pandas\__init__.pyc'>,
'quit': <IPython.core.autocall.ZMQExitAutocall at 0x3e816d8>,
's': 'T3',
't1': {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12582912',
'T128',
'T1310',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16779428',
'T178258',
'T18436',
'T2',
'T24',
'T2516',
'T25165824',
'T256',
'T262144',
'T26808',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T4',
'T41944',
'T4718592',
'T48',
'T48576',
'T492',
'T5',
'T512',
'T514',
'T52',
'T524288',
'T524544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T678864',
'T7',
'T748928',
'T786432',
'T786944',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T91764',
'T96',
'T96112',
'T97',
'T98'},
't2': {'T-18748192',
'T-2147481664',
'T-21474819',
'T-2147482176',
'T-2147482432',
'T-21474825',
'T-2147482688',
'T-2147482816',
'T-2147482944',
'T-2147483646',
'T-2147483647',
'T-2147483648',
'T-21474872',
'T1',
'T11141888',
'T1132',
'T113776',
'T1152',
'T12',
'T12582912',
'T128',
'T1310',
'T132',
'T134217728',
'T1372',
'T143',
'T145',
'T16',
'T16384',
'T16512',
'T16777216',
'T16777232',
'T16777248',
'T16777472',
'T16777557',
'T16793941',
'T18436',
'T2',
'T24',
'T2516',
'T256',
'T262144',
'T262656',
'T268',
'T268435456',
'T3',
'T32',
'T32896',
'T331648',
'T33554432',
'T33554448',
'T33554944',
'T36992',
'T393216',
'T3942',
'T4',
'T41944',
'T4325376',
'T43968',
'T4718592',
'T48',
'T48576',
'T488',
'T492',
'T5',
'T512',
'T514',
'T518',
'T52',
'T524288',
'T524544',
'T544',
'T55424',
'T56',
'T589824',
'T6',
'T618624',
'T63616',
'T64',
'T6553',
'T65536',
'T7',
'T748928',
'T7808',
'T786432',
'T8',
'T83888',
'T8389632',
'T8651776',
'T86752',
'T8768',
'T8912896',
'T9',
'T917',
'T9174',
'T9175552',
'T96',
'T97',
'T98'},
'test_fname': '../input/test_categorical.csv',
'train_fname': '../input/train_categorical.csv'}
Content source: zakkum42/Bosch
Similar notebooks: