def generate_seedless_markov_sentence():
mc = MarkovChain(verbose=False)
mc.generateDatabase((' '.join(get_text())))
sent = mc.generateString()
if check_blacklist(sent):
return ''
else:
return sentence_case(sent)
def generate_topic_markov_sentence(texts, index):
topics = get_topics(texts, index)
mc = MarkovChain(verbose=False)
mc.generateDatabase((' '.join(get_text())))
sent = mc.generateStringWithTopics(topics)
if check_blacklist(sent):
return ''
else:
return sentence_case(sent)
def generate_database(self, captured_text_path='captured_raw_text.txt'):
p = PrepareText()
with open(captured_text_path) as f:
raw_text = f.readlines()
print('Preparing texts')
pbar = ProgressBar()
prepared_texts = [p.prepare(i) for i in pbar(raw_text)]
clean_texts = set(filter(lambda x: not self._drop(x) if x else False, prepared_texts))
print('Generating database')
mc = MarkovChain(self.db_path, verbose=False)
mc.generateDatabase('\n'.join(clean_texts), n=4, make_lowercase=True)
mc.dumpdb()
self.markov = mc
def generate_database(self, captured_text_path='captured_raw_text.txt'):
p = PrepareText()
with open(captured_text_path) as f:
raw_text = f.readlines()
print('Preparing texts')
pbar = ProgressBar()
prepared_texts = [p.prepare(i) for i in pbar(raw_text)]
clean_texts = set(
filter(lambda x: not self._drop(x)
if x else False, prepared_texts))
print('Generating database')
mc = MarkovChain(self.db_path, verbose=False)
mc.generateDatabase('\n'.join(clean_texts), n=4, make_lowercase=True)
mc.dumpdb()
self.markov = mc
def generate_markov_sentence(original_sentence):
mc = MarkovChain(verbose=False)
mc.generateDatabase((' '.join(get_text())))
stripped = strip_tags(original_sentence)
try:
seed = ' '.join(stripped.split()[0:3])
sent = mc.generateStringWithSeed(seed)
except:
try:
seed = ' '.join(stripped.split()[0:2])
sent = mc.generateStringWithSeed(seed)
except:
return generate_seedless_markov_sentence()
if check_blacklist(sent):
return ''
else:
return sentence_case(sent)
