9 lines
431 B
Python
9 lines
431 B
Python
#!/usr/bin/env python
|
|
import re, string, sys
|
|
|
|
stops = set(open("../stop_words.txt").read().split(",") + list(string.ascii_lowercase))
|
|
words = [x.lower() for x in re.split("[^a-zA-Z]+", open(sys.argv[1]).read()) if len(x) > 0 and x.lower() not in stops]
|
|
unique_words = list(set(words))
|
|
unique_words.sort(lambda x, y: cmp(words.count(y), words.count(x)))
|
|
print "\n".join(["%s - %s" % (x, words.count(x)) for x in unique_words[:25]])
|