Example Program: Most Frequent Words


import string, sys

text = open(sys.argv[1],'r').read()
text = text.lower()
for ch in string.punctuation:
    text = text.replace(ch, ' ')

counts = {}
for w in text.split():
    counts[w] = counts.get(w,0) + 1

items = [(c,w) for (w,c) in counts.items()]
items.sort()
items.reverse()

for c,w in items[:10]:
    print w, c