benchmark of builtin filter function

benchmark_filter.py

# -*- coding: utf-8 -*-

from timeit import Timer
import random
import string
import sys

def redef_builtin_filter(pred, iterable):
  """redefined builtin filter function"""
  ret = [x for x in iterable if pred(x)]
  
  if isinstance(iterable, str) or isinstance(iterable, unicode):
    return ''.join(ret)
  elif isinstance(iterable, tuple):
    return tuple(ret)
  else:
    return ret

setup="""
from __main__ import redef_builtin_filter, list_10percent_true, tuple_10percent_true,\\
 ascii_str, unicode_str, select_true, select_under_ch_i, select_under_uni_ha 
"""

itemsize = 100

list_10percent_true = [random.randint(0, itemsize) < itemsize/10 for x in range(itemsize)]
tuple_10percent_true = tuple([random.randint(0, itemsize) < itemsize/10 for x in range(itemsize)])
ascii_str = ''.join(random.choice(string.ascii_letters) for x in range(itemsize))
unicode_str = u'あいうえおかきくけこさしすせそたちつてとなにぬねの'

select_true = lambda x: x==True
select_under_ch_i = lambda x: ord(x) < ord('i') 
select_under_uni_ha = lambda x: ord(x) < ord(u'は')

assert redef_builtin_filter(select_true, list_10percent_true) == filter(select_true, list_10percent_true)
assert redef_builtin_filter(select_true, tuple_10percent_true) == filter(select_true, tuple_10percent_true)
assert redef_builtin_filter(select_under_ch_i, ascii_str) == filter(select_under_ch_i, ascii_str)
assert redef_builtin_filter(select_under_uni_ha, unicode_str) == filter(select_under_uni_ha, unicode_str)

print 'python version : %s on %s' % (sys.version, sys.platform)
print ''

print 'list_10percent_true:'
print '  redef_builtin_filter ->', Timer(stmt='redef_builtin_filter(select_true, list_10percent_true)', setup=setup).timeit()
print '  builtin filter ->', Timer(stmt='filter(select_true, list_10percent_true)', setup=setup).timeit()
print ''

print 'tuple_10percent_true:'
print '  redef_builtin_filter ->', Timer(stmt='redef_builtin_filter(select_true, tuple_10percent_true)', setup=setup).timeit()
print '  builtin filter ->', Timer(stmt='filter(select_true, tuple_10percent_true)', setup=setup).timeit()
print ''

print 'ascii_str:'
print '  redef_builtin_filter ->', Timer(stmt='redef_builtin_filter(select_under_ch_i, ascii_str)', setup=setup).timeit()
print '  builtin filter ->', Timer(stmt='filter(select_under_ch_i, ascii_str)', setup=setup).timeit()
print ''

print 'unicode_str:'
print '  redef_builtin_filter ->', Timer(stmt='redef_builtin_filter(select_under_uni_ha, unicode_str)', setup=setup).timeit()
print '  builtin filter ->', Timer(stmt='filter(select_under_uni_ha, unicode_str)', setup=setup).timeit()
print ''

benchmark_result.txt

python version : 2.7.1 (4d824e4fcf57+, Aug 08 2011, 04:03:11)
[PyPy 1.6.0-dev1 with GCC 4.5.2] on linux2

list_10percent_true:
  redef_builtin_filter -> 0.486375808716
  builtin filter -> 15.1048140526

tuple_10percent_true:
  redef_builtin_filter -> 1.58475995064
  builtin filter -> 21.8717570305

ascii_str:
  redef_builtin_filter -> 6.38133001328
  builtin filter -> 25.1767168045

unicode_str:
  redef_builtin_filter -> 1.97318696976
  builtin filter -> 6.94378709793

pc_spec.txt

-----/proc/meminfo
MemTotal:        8264940 kB
MemFree:         6293120 kB
Buffers:          113312 kB
Cached:          1364704 kB
SwapCached:            0 kB
Active:          1423476 kB
Inactive:         443656 kB
Active(anon):     389872 kB
Inactive(anon):     7528 kB
Active(file):    1033604 kB
Inactive(file):   436128 kB
Unevictable:           0 kB
Mlocked:               0 kB
HighTotal:       7475144 kB
HighFree:        5708268 kB
LowTotal:         789796 kB
LowFree:          584852 kB
SwapTotal:       4191228 kB
SwapFree:        4191228 kB
Dirty:                44 kB
Writeback:             0 kB
AnonPages:        389048 kB
Mapped:           121164 kB
Shmem:              8288 kB
Slab:              79180 kB
SReclaimable:      66876 kB
SUnreclaim:        12304 kB
KernelStack:        2784 kB
PageTables:         7656 kB
NFS_Unstable:          0 kB
Bounce:                0 kB
WritebackTmp:          0 kB
CommitLimit:     8323696 kB
Committed_AS:    1920288 kB
VmallocTotal:     122880 kB
VmallocUsed:       72108 kB
VmallocChunk:      47932 kB
HardwareCorrupted:     0 kB
HugePages_Total:       0
HugePages_Free:        0
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB
DirectMap4k:       14328 kB
DirectMap2M:      899072 kB


-----/proc/cpuinfo
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 42
model name	: Intel(R) Core(TM) i7-2600K CPU @ 3.40GHz
stepping	: 7
cpu MHz		: 3274.067
cache size	: 6144 KB
physical id	: 0
siblings	: 4
core id		: 0
cpu cores	: 4
apicid		: 0
initial apicid	: 0
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx lm constant_tsc pni ssse3 lahf_lm
bogomips	: 6548.13
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 42
model name	: Intel(R) Core(TM) i7-2600K CPU @ 3.40GHz
stepping	: 7
cpu MHz		: 3274.067
cache size	: 6144 KB
physical id	: 0
siblings	: 4
core id		: 1
cpu cores	: 4
apicid		: 1
initial apicid	: 1
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx lm constant_tsc pni ssse3 lahf_lm