Markov Chains in Python

markov.py

import random

class Markov(object):
	def __init__(self, file):
		self.cache = {}
		self.file = file
		self.words = self.file_to_words()
		self.word_size = len(self.words)
		self.database()

	def file_to_words(self):
		'''
		Get all the words in the file
		'''
		self.file.seek(0)
		data = self.file.read()
		return data.split()

	def generate_triplets(self):
		'''
		Generate triplets of words from sentences 
		Example: "Hey How Are You" Will yield [("Hey", "How", "Are"), ("How", "Are", "You")]
		'''
		if self.word_size < 3:
			return

		for i in xrange(self.word_size - 2):
			yield (self.words[i], self.words[i + 1], self.words[i + 2])

	def database(self):
		'''
		Create a cache of all the words
		'''
		for w1, w2, w3 in self.generate_triplets():
			key = (w1, w2)
			if key in self.cache:
				self.cache[key].append(w3)
			else:
				self.cache[key] = [w3]

	def __call__(self, length=25):
		'''
		Generate a random text using markov chains
		'''
		seed = random.randint(0, self.word_size - 3)
		while not self.words[seed][0].isupper():
			seed = random.randint(0, self.word_size - 3)
		w1, w2 = self.words[seed], self.words[seed + 1]
		result = []
		for i in xrange(length):
			result.append(w1)
			w1, w2 = w2, random.choice(self.cache[(w1, w2)])
		result.append(w2)
		return ' '.join(result)