class MarkovOnTopic(object):
'''
TODO: ngrams bumped to four or five-grams
TODO: first ngram is the technical noun topic of the tweet
TODO: stem the topics to narrow them. or even better find a way to standardize synonyms to the same word and then stem
TODO: db key has no hashmarks but the values do
TODO: db key in lowercase, but values are original
'''
def __init__(self, db_path='markov.db'):
try:
self.mc = MarkovChain(db_path, verbose=False)
except:
print('No database found at path. Creating new database.')
self.mc = seed_db(db_path)
def generate_db(self, docs, filename=None):
self.docs = docs
pass
def generate_topics(self):
pass
def generate_string(self, seed=None):
regen = True
while regen:
if seed:
gen_text = self.mc.generateStringWithSeed(seed)
else:
gen_text = self.mc.generateString()
if not drop(gen_text):
print gen_text
regen = False
class MarkovOnTopic(object):
'''
TODO: ngrams bumped to four or five-grams
TODO: first ngram is the technical noun topic of the tweet
TODO: stem the topics to narrow them. or even better find a way to standardize synonyms to the same word and then stem
TODO: db key has no hashmarks but the values do
TODO: db key in lowercase, but values are original
'''
def __init__(self, db_path='markov.db'):
try:
self.mc = MarkovChain(db_path, verbose=False)
except:
print('No database found at path. Creating new database.')
self.mc = seed_db(db_path)
def generate_db(self, docs, filename=None):
self.docs = docs
pass
def generate_topics(self):
pass
def generate_string(self, seed=None):
regen = True
while regen:
if seed:
gen_text = self.mc.generateStringWithSeed(seed)
else:
gen_text = self.mc.generateString()
if not drop(gen_text):
print gen_text
regen = False
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)
