Created
November 7, 2014 03:02
-
-
Save alfredodeza/944c3a5b1ecb674a182b to your computer and use it in GitHub Desktop.
a simple markov phrase generator
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import random | |
class Markov(object): | |
def __init__(self, open_file): | |
self.cache = {} | |
self.open_file = open_file | |
self.words = self.file_to_words() | |
self.word_size = len(self.words) | |
self.database() | |
def file_to_words(self): | |
self.open_file.seek(0) | |
data = self.open_file.read() | |
words = data.split() | |
return words | |
def triples(self): | |
""" Generates triples from the given data string. So if our string were | |
"What a lovely day", we'd generate (What, a, lovely) and then | |
(a, lovely, day). | |
""" | |
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 database(self): | |
for w1, w2, w3 in self.triples(): | |
key = (w1, w2) | |
if key in self.cache: | |
self.cache[key].append(w3) | |
else: | |
self.cache[key] = [w3] | |
def generate_markov_text(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.cache[(w1, w2)]) | |
gen_words.append(w2) | |
sentence = ' '.join(gen_words).strip().title().capitalize() | |
return sentence.split('. ')[0] | |
if __name__ == '__main__': | |
with open('text') as t: | |
m = Markov(t) | |
print m.generate_markov_text() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment