Created
December 1, 2012 03:21
-
-
Save zed/4180407 to your computer and use it in GitHub Desktop.
Python: measure time performance of counting words in corpus/gutenberg
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 | |
""" | |
http://stackoverflow.com/q/13655169 | |
""" | |
import inspect | |
import sys | |
import timeit | |
from collections import Counter, defaultdict | |
from functools import partial | |
from itertools import groupby | |
import nltk # pip install nltk | |
WORDS = nltk.corpus.gutenberg.words() | |
def count_words_Counter(words): | |
return sorted(Counter(words).items()) | |
def count_words_groupby(words): | |
return [(w, len(list(gr))) for w, gr in groupby(sorted(words))] | |
def count_words_groupby_sum(words): | |
return [(w, sum(1 for _ in gr)) for w, gr in groupby(sorted(words))] | |
def count_words_defaultdict(words): | |
d = defaultdict(int) | |
for w in words: | |
d[w] += 1 | |
return sorted(d.items()) | |
def count_words_dict(words): | |
d = {} | |
for w in words: | |
try: | |
d[w] += 1 | |
except KeyError: | |
d[w] = 1 | |
return sorted(d.items()) | |
def count_words_freqdist(words): | |
# note: .items() returns words sorted by word frequency (descreasing order) | |
# (same as `Counter.most_common()`) | |
# so the code sorts twice (the second time in alphabetical order) | |
return sorted(nltk.FreqDist(words).items()) | |
def get_count_words_functions(): | |
all_funcs = inspect.getmembers(sys.modules[__name__], inspect.isfunction) | |
return [f for name, f in all_funcs if name.startswith('count_words_')] | |
def test_func(f, words, expected): | |
assert f(words) == expected | |
def test(): | |
funcs = get_count_words_functions() | |
words = list(WORDS[:1000]) | |
expected = funcs[0](words) | |
for f in funcs: | |
test_func(f, words, expected) | |
def measure_func(f, words): | |
return min(timeit.repeat(partial(f, words), number=1)) | |
def measure(): | |
funcs = get_count_words_functions() | |
words = list(WORDS) | |
w = max(len(f.__name__) for f in funcs) | |
for f in [sorted] + funcs: | |
print("{:{}s} {:.2f}".format(f.__name__, w, measure_func(f, words))) | |
test() | |
measure() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment