Created
October 16, 2010 13:26
-
-
Save intuited/629781 to your computer and use it in GitHub Desktop.
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
import os | |
import random | |
import re | |
import string | |
import time | |
def n_random_words(num_words=3000): | |
stat = os.stat('/usr/share/dict/words') | |
# the filesize if the 7th element of the array | |
flen = stat[6] | |
f = open('/usr/share/dict/words') | |
min_word_len = 3 | |
max_word_len = 30 | |
word_regexp = re.compile(r'^[a-z]{%s,%s}$' % (min_word_len, max_word_len)) # only allow lower case | |
words = [] | |
while len(words) < num_words: | |
word = None | |
# seek to a random offset in the file | |
f.seek(int(random.random() * flen)) | |
# do a single read with sufficient characters | |
chars = f.read(50) | |
# split it on white space | |
wrds = string.split(chars) | |
# the first element may be only a partial word so use the second | |
# you can also make other tests on the word here | |
if len(wrds) > 1 and re.search(word_regexp, wrds[1]): | |
word = wrds[1] | |
if word and not word in words: | |
words.append(word) | |
return words | |
def test_performance(num_words_in_universe=5000, num_rand_words_to_search=2000, num_tests=10): | |
times = {"set": [], "frozenset": [], | |
"set2": [], "frozenset2": [], | |
"set3": [], "frozenset3": []} | |
for i in range(0, num_tests): | |
words = n_random_words(num_rand_words_to_search) | |
search_words = n_random_words(num_rand_words_to_search) | |
words_frozenset = frozenset(words) | |
words_set = set(words) | |
s = time.time() | |
for w in search_words: | |
if w in words_frozenset: | |
pass | |
e = time.time() | |
times['frozenset'].append(e - s) | |
s = time.time() | |
for w in search_words: | |
if w in words_set: | |
pass | |
e = time.time() | |
times['set'].append(e - s) | |
s = time.time() | |
for w in search_words: | |
if w in words_set: | |
pass | |
e = time.time() | |
times['set2'].append(e - s) | |
s = time.time() | |
for w in search_words: | |
if w in words_frozenset: | |
pass | |
e = time.time() | |
times['frozenset2'].append(e - s) | |
s = time.time() | |
for w in search_words: | |
if w in words_set: | |
pass | |
e = time.time() | |
times['set3'].append(e - s) | |
s = time.time() | |
for w in search_words: | |
if w in words_frozenset: | |
pass | |
e = time.time() | |
times['frozenset3'].append(e - s) | |
avg_times = [] | |
for label,results in times.iteritems(): | |
avg_times.append([label, sum(results)/len(results)]) | |
avg_times.sort(key=lambda x: x[1]) | |
for a in avg_times: | |
print a[1], a[0] | |
if __name__ == '__main__': | |
from pprint import pprint | |
pprint(test_performance()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I think you meant