def __init__(self, inp_size, models, **kwargs):
self.inp_size = inp_size
self.inp = collections.deque(list(), inp_size)
self.out = collections.deque(list(), inp_size)
self.models = self.init_models(models)
self.new_data = False
self.name = kwargs.get("name", "N/A")
self.current_model_name = "N/A"
self.current_model = None
self.current_model_object = None
self.test_size_const = 0.6
self.num_test_lists = 2
self.mchain = markov.Chain(self.models)
import markov
import util
elems = util.readWords('text/spongebob_texas.txt')
chain = markov.Chain(2)
for x in elems:
chain.observe(x)
content = chain.chooseFirst()
for i in range(100):
next = chain.chooseNext()
if not next: break
content.append(next)
content = ' '.join(content)
print(content)
input()
def clear(self):
self.inp = collections.deque(list(), self.inp_size)
self.out = collections.deque(list(), self.inp_size)
self.mchain = markov.Chain(self.models)
return self
def _create_new_chain(self):
return markov.Chain()
#!/usr/bin/env python3
# -*- coding: utf8 -*-
import itertools
from nltk import sent_tokenize, word_tokenize
import markov
if __name__ == '__main__':
with open('text') as f:
data = f.read()
sentences = sent_tokenize(data)
chain = markov.Chain(order=3)
for i, s in enumerate(sentences):
if not i % 1000:
print(i)
chain.feed(word_tokenize(s))
for i in range(10):
print(chain.generate())