def _inference_one_chain(self, doc_tokens, rand):
"""Inference topics with one markov chain.
Returns the sparse topics p(z|d).
"""
document = Document(self.model.num_topics)
document.parse_from_tokens(doc_tokens, rand, self.vocabulary,
self.model)
if document.num_words() == 0:
return dict()
accumulated_topic_hist = {}
for i in xrange(self.total_iterations):
# one iteration
for word in document.words:
# --
document.decrease_topic(word.topic, 1)
new_topic = self._sample_word_topic(document, word.id, rand)
assert new_topic != None
word.topic = new_topic
# ++
document.increase_topic(new_topic, 1)
if i >= self.burn_in_iterations:
for non_zero in document.doc_topic_hist.non_zeros:
if non_zero.topic in accumulated_topic_hist:
accumulated_topic_hist[
non_zero.topic] += non_zero.count
else:
accumulated_topic_hist[non_zero.topic] = non_zero.count
topic_dist = self._l1normalize_distribution(accumulated_topic_hist)
return topic_dist
def _inference_one_chain(self, doc_tokens, rand):
"""Inference topics with one markov chain.
Returns the sparse topics p(z|d).
"""
document = Document(self.model.num_topics)
document.parse_from_tokens(doc_tokens, rand,
self.vocabulary, self.model)
if document.num_words() == 0:
return dict()
accumulated_topic_hist = {}
for i in xrange(self.total_iterations):
# one iteration
for word in document.words:
# --
document.decrease_topic(word.topic, 1)
new_topic = self._sample_word_topic(document, word.id, rand)
assert new_topic != None
word.topic = new_topic
# ++
document.increase_topic(new_topic, 1)
if i >= self.burn_in_iterations:
for non_zero in document.doc_topic_hist.non_zeros:
if non_zero.topic in accumulated_topic_hist:
accumulated_topic_hist[non_zero.topic] += non_zero.count
else:
accumulated_topic_hist[non_zero.topic] = non_zero.count
topic_dist = self._l1normalize_distribution(accumulated_topic_hist)
return topic_dist
