Created
February 20, 2014 18:43
-
-
Save pablito56/9120441 to your computer and use it in GitHub Desktop.
Benchmarking the use of memoize for regular expression transformations and generators. Based on https://gist.github.com/drslump/9109647
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
def memoize(fn): | |
""" Memoization decorator for a function taking one or more arguments. | |
NOTE: Only hashable values can be given as arguments to the function. | |
http://code.activestate.com/recipes/578231-probably-the-fastest-memoization-decorator-in-the-/#c4 | |
""" | |
class memodict(dict): | |
def __getitem__(self, *args): | |
return dict.__getitem__(self, args) | |
def __missing__(self, args): | |
ret = self[args] = fn(*args) | |
return ret | |
return memodict().__getitem__ | |
import re | |
UNDER_TO_CAMEL = re.compile(r'(^|_)(.)') | |
def underscore_to_camel_case(name): | |
return UNDER_TO_CAMEL.sub(lambda x: x.group(2).upper(), name) | |
@memoize | |
def underscore_to_camel_case_memoized(name): | |
return underscore_to_camel_case(name) | |
from itertools import imap | |
def underscore_to_camel_case_gen(name): | |
return "".join(imap(lambda word: word.capitalize(), name.split("_"))) | |
def underscore_to_camel_case_gen_bis(name): | |
return "".join(word.capitalize() for word in name.split("_")) | |
def convert_case(obj, converter): | |
if isinstance(obj, dict): | |
return dict( | |
(converter(k), convert_case(v, converter)) | |
for k, v in obj.iteritems() | |
) | |
elif isinstance(obj, list): | |
return map(lambda x: convert_case(x, converter), obj) | |
else: | |
return obj | |
ITERATIONS = 1000 | |
import urllib2 | |
import json | |
print("Fetching GitHub's public timeline...") | |
req = urllib2.Request('https://github.com/timeline', None, dict(accept='application/json')) | |
resp = urllib2.urlopen(req) | |
content = json.loads(resp.read()) | |
import timeit | |
print("Benchmarking for {0} iterations".format(ITERATIONS)) | |
r1 = timeit.timeit(lambda: convert_case(content, underscore_to_camel_case), number=ITERATIONS) | |
r2 = timeit.timeit(lambda: convert_case(content, underscore_to_camel_case_memoized), number=ITERATIONS) | |
r3 = timeit.timeit(lambda: convert_case(content, underscore_to_camel_case_gen), number=ITERATIONS) | |
r4 = timeit.timeit(lambda: convert_case(content, underscore_to_camel_case_gen_bis), number=ITERATIONS) | |
print 'Normal/Memoized : {0}s / {1}s -- {2}%'.format(r1, r2, int(r1 * 100 / r2)) | |
print 'Normal/Generator : {0}s / {1}s -- {2}%'.format(r1, r3, int(r1 * 100 / r3)) | |
print 'Normal/Generator 2 : {0}s / {1}s -- {2}%'.format(r1, r4, int(r1 * 100 / r4)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ python memoize_benchmark_gens.py | |
Fetching GitHub's public timeline... | |
Benchmarking for 500 iterations | |
Normal/Memoized : 3.33840179443s / 1.42423510551s -- 234% | |
Normal/Generator : 3.33840179443s / 3.4091398716s -- 97% | |
Normal/Generator 2 : 3.33840179443s / 3.29355096817s -- 101% | |
$ python memoize_benchmark.py | |
Fetching GitHub's public timeline... | |
Benchmarking for 1000 iterations | |
Normal/Memoized : 6.02346777916s / 2.16515493393s -- 278% | |
Normal/Generator : 6.02346777916s / 5.86570096016s -- 102% | |
Normal/Generator 2 : 6.02346777916s / 5.62004804611s -- 107% |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment