Word count stats

wordcount.py

# Pipe text into this to get a word count list in decreasing order, e.g.:
#
# $ detex ms.tex | python wordcount.py
#  model:9
#  star:8
#  formation:7
#  YSOs:7
#  ...

import sys

text = sys.stdin.read()
text = text.replace('\n',' ')
words = text.split()

count = {}

for word in words:
    if word in count:
        count[word] += 1
    else:
        count[word] = 1

values = list(set(count.values()))
values.sort()
values = values[::-1]

for value in values:
    for word in count:
        if count[word] == value:
            print "%s:%i" % (word, count[word])