A Python Implementation of a Markov Chain Text Generator

chain.py

import random

class Markov(object):
    def __init__(self, open_file):
        self.dist = {}
        self.open_file = open_file
        self.words = self.split_to_words()
        self.word_size = len(self.words)
        self.create_distribution()
        

    def split_to_words(self):
        self.open_file.seek(0)
        data = self.open_file.read()
        words = data.split()
        return words
        

    def triples(self):
        if len(self.words) < 3:
            return
        
        for i in range(len(self.words) - 2):
            yield (self.words[i], self.words[i+1], self.words[i+2])
            
    def create_distribution(self):
        for w1, w2, w3 in self.triples():
            key = (w1, w2)
            if key in self.dist:
                self.dist[key].append(w3)
            else:
                self.dist[key] = [w3]
        print(self.dist)
                
    def generate_song(self, size=25):
        seed = random.randint(0, self.word_size-3)
        seed_word, next_word = self.words[seed], self.words[seed+1]
        w1, w2 = seed_word, next_word
        gen_words = []
        for i in xrange(size):
            gen_words.append(w1)
            w1, w2 = w2, random.choice(self.dist[(w1, w2)])
        gen_words.append(w2)
        return ' '.join(gen_words)

if(__name__ == "__main__"):
    lyrics_file = open("lyrics.txt","r")
    markov = Markov(lyrics_file)
    print(markov.generate_song())
    
# purposefully uncommented so you're obliged to read my blog post. :) 
# https://authomaton.blogspot.co.uk/2017/10/machine-learning-but-funner-01-rap-bot.html