# Word Frequency

import re

fn = "ttlg.txt"
fh = open(fn)

# to store word frequencies
freq = {}

# iterate over the file
for text in fh:
    
    # same transformation as before
    text = re.sub("[^\w]", " ", text)
    text = text.lower()
    text = re.sub("\s+", " ", text)
    text = text.lstrip()
    text = text.rstrip()

    # iterate over words
    for word in text.split():

        # need to test if word is in dictionary
        # if it isn't, trying to access it is an error!
        if freq.has_key(word):
            freq[word] = freq[word] + 1
        else:
            freq[word] = 1

# let's also make a list of words sorted by frequency

# need to flip around key/value pairs so we can sort by value
items = [(item[1], item[0]) for item in freq.items()]

# sort the list
items.sort()

# reverse it
items.reverse()

# alternatively, items.sort(reverse=True) will sort in reverse order

# pull out the words
words = [pair[1] for pair in items]