Benchmarking the use of memoize for regular expression transformations

memoize_benchmark.py

#!/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)


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 = 500

import urllib2, 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)
print 'Normal/Memoized : {0}s / {1}s -- {2}%'.format(r1, r2, int(r1 * 100 / r2))