freq-of-freq.py

#!/usr/bin/env python

import nltk

## Tom Sawyer, by Mark Twain.
## Available from the Gutenberg Project:
## http://www.gutenberg.org/files/74/74.txt
reader = nltk.corpus.reader.PlaintextCorpusReader('.', 'twain-tomsawyer.txt')
words = reader.words('twain-tomsawyer.txt') # List of all the words in the text

fdist = nltk.FreqDist([w.lower() for w in words])

## Simply figures out which of the 13 labels this dist should be sampled under
def group(i):
    if i < 11: return str(i)
    elif i in range(11, 51): return("11-50")
    elif i in range(51, 101): return("51-100")
    else: return(">100")

## Now we can create another frequency distribution of the previously obtained
## values:
fdist_freq = nltk.FreqDist([group(freq) for freq in fdist.values()])

fdist_freq.plot()