Jeepers, okay. I was gonna work out some way of bundling a thread-sucker with it so you could gen posts based on one particular thread, but I can just post the script here too.
Note: this is not my code. It is in fact sourced from
this. I wrote some code surrounding it, but that's kinda buggy and not really important.
import random
class Markov(object):
def __init__(self, open_file, chain_size=3):
self.chain_size = chain_size
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 words_at_position(self, i):
"""Uses the chain size to find a list of the words at an index."""
chain = []
for chain_index in range(0, self.chain_size):
chain.append(self.words[i + chain_index])
return chain
def chains(self):
"""Generates chains from the given data string based on passed chain size.
So if our string were:
"What a lovely day"
With a chain size of 3, we'd generate:
(What, a, lovely)
and
(a, lovely, day)
"""
if len(self.words) < self.chain_size:
return
for i in range(len(self.words) - self.chain_size - 1):
yield tuple(self.words_at_position(i))
def database(self):
for chain_set in self.chains():
key = chain_set[:self.chain_size - 1]
next_word = chain_set[-1]
if key in self.cache:
self.cache[key].append(next_word)
else:
self.cache[key] = [next_word]
def generate_markov_text(self, size=25):
seed = random.randint(0, self.word_size - 3)
gen_words = []
seed_words = self.words_at_position(seed)[:-1]
gen_words.extend(seed_words)
for i in xrange(size):
last_word_len = self.chain_size - 1
last_words = gen_words[-1 * last_word_len:]
next_word = random.choice(self.cache[tuple(last_words)])
gen_words.append(next_word)
return ' '.join(gen_words)
Is this an acceptable tribute?
Author
Topic: Things that made you laugh today: some people notice when 1 change the title (Read 1560963 times)