Fizzy Drinks

Fizzy Drinks.txt

i had;
was a on the of the in the;
upon the
of his,
in his i could he had!
with a,
began to!
and i i was and the the squire
he was.
by the said the
the captain out of the doctor as i!
had been it was!
there was with the in a!
was the and a.
at the of a like a!
from the,
to be
for the to the and then into the;
that i.

zzz-frequent-word-pairs-2.py

#!/usr/bin/env python

import re
import sys
import random


def main(argv):
    filenames = argv[1:]

    def clean(word):
        if word.endswith(('.', '!', '?', ';', ',')):
            word = word[:-1]
        if word.startswith(('"', "'", '(')):
            word = word[1:]
        if word.endswith(('"', "'", ')')):
            word = word[:-1]
        if word.endswith(('.', '!', '?', ';', ',')):
            word = word[:-1]
        return word.lower()

    words = []

    for filename in filenames:
        with open(filename, 'r') as f:
            for line in f:
                bits = line.strip().split()
                for bit in bits:
                    for smidge in bit.split('--'):
                        words.append(clean(smidge))

    freq = {}

    last = []
    for word in words:

        if len(last) < 2:
            last.append(word)
            continue

        key = (last[0], last[1])
        freq[key] = freq.setdefault(key, 0) + 1
        last.pop(0)
        last.append(word)

    freq_list = sorted([(v, k) for k, v in freq.iteritems() if v > 1], reverse=True)
    freq_list = ['%s %s' % (v1, v2) for k, (v1, v2) in freq_list[0:40]]
    random.shuffle(freq_list)

    while freq_list:
        num = random.randint(1, 5)
        some = freq_list[:num]
        freq_list = freq_list[num:]
        line = ' '.join(some)
        if not freq_list:
            line += '.'
        else:
            line += random.choice([',', '.', ';', '', '!'])
        print line


if __name__ == '__main__':
    main(sys.argv)