Skip to content

Instantly share code, notes, and snippets.

@aaronbassett
Last active October 7, 2015 01:17
Show Gist options
  • Save aaronbassett/3082454 to your computer and use it in GitHub Desktop.
Save aaronbassett/3082454 to your computer and use it in GitHub Desktop.
Generate a "Markov" tweet from a user's timeline
import requests
import json
import random
class Markov(object):
def __init__(self, words):
self.cache = {}
self.words = words
self.word_size = len(self.words)
self.database()
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)
return ' '.join(gen_words)
r = requests.get("http://api.twitter.com/1/statuses/user_timeline.json?count=200&screen_name=jaqmdor")
data = json.loads(r.text)
words = []
for tweet in data:
words.extend(tweet["text"].split())
m = Markov(words)
print m.generate_markov_text()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment