def sample(self, n_docs, doc_length, n_topics=None, n_words=None):
(doc_topic_prior,
topic_word_prior) = self._initialize(n_topics, n_words)
n_topics = len(doc_topic_prior)
n_words = len(topic_word_prior)
r = np.random.RandomState(0)
# sample topic-word distributions
topic_word = r.dirichlet(topic_word_prior, n_topics)
# sample doc-topic distributions
doc_topic = r.dirichlet(doc_topic_prior, n_docs)
# sample documents themselves
all_topics = []
all_words = []
for d in range(n_docs):
topics = flatten_counts(r.multinomial(doc_length, doc_topic[d]))
words = []
for (i, topic) in enumerate(topics):
# sample topic for this word, word itself
words.append(categorical(topic_word[topic], r))
# save this document's topics, words
all_topics.append(topics)
all_words.append(words)
return {
'topic_word': topic_word,
'doc_topic': doc_topic,
'word_topic': all_topics,
'documents': all_words
}
def sample(self, n_docs, doc_length, n_topics=None, n_words=None):
(doc_topic_prior, topic_word_prior) = self._initialize(n_topics, n_words)
n_topics = len(doc_topic_prior)
n_words = len(topic_word_prior)
r = np.random.RandomState(0)
# sample topic-word distributions
topic_word = r.dirichlet(topic_word_prior, n_topics)
# sample doc-topic distributions
doc_topic = r.dirichlet(doc_topic_prior, n_docs)
# sample documents themselves
all_topics = []
all_words = []
for d in range(n_docs):
topics = flatten_counts(r.multinomial(doc_length, doc_topic[d]))
words = []
for (i, topic) in enumerate(topics):
# sample topic for this word, word itself
words.append(categorical(topic_word[topic], r))
# save this document's topics, words
all_topics.append(topics)
all_words.append(words)
return {
'topic_word': topic_word,
'doc_topic': doc_topic,
'word_topic': all_topics,
'documents': all_words
}
def infer(self, documents, n_sweeps=1000, word_topic=None):
r = np.random.RandomState(0)
# initialize counts for each doc-topic and topic-word pair using the prior
(doc_topic_counts, topic_word_counts,
word_index) = (self._initialize(documents))
topic_counts = np.sum(topic_word_counts, axis=1)
n_topics = topic_word_counts.shape[0]
n_docs = doc_topic_counts.shape[0]
n_words = len(word_index)
# transform documents into lists of word indices
(documents, word_index) = reindex(documents)
# initialize topics for all words uniformly at random
if word_topic is None:
word_topic = [[
categorical(np.ones(n_topics) / n_topics, r) for word in doc
] for doc in documents]
# initialize doc-topic and topic-word counts
for (d, doc) in enumerate(documents):
for (i, word) in enumerate(doc):
# get topic for this word
t = word_topic[d][i]
# increment counts
doc_topic_counts[d, t] += 1
topic_word_counts[t, word] += 1
topic_counts[t] += 1
# resample word topics
for sweep in range(n_sweeps):
self.logger.debug('starting sweep #%d' % (sweep, ))
for (d, doc) in enumerate(documents):
if d % 100 == 0:
self.logger.debug('starting document #%d' % (d, ))
for (i, word) in enumerate(doc):
# get topic for this word in this document
t = word_topic[d][i]
# remove it from counts
doc_topic_counts[d, t] -= 1
topic_word_counts[t, word] -= 1
topic_counts[t] -= 1
# calculate P(t | everything else)
prob = [
doc_topic_counts[d, t] * topic_word_counts[t, word] /
topic_counts[t] for t in range(n_topics)
]
prob = np.array(prob) / np.sum(prob)
# select topic
t = categorical(prob, r)
# increment counts
doc_topic_counts[d, t] += 1
topic_word_counts[t, word] += 1
topic_counts[t] += 1
# set topic for word
word_topic[d][i] = t
# sum of counts along each row
topic_word_sums = topic_counts[:, np.newaxis]
doc_topic_sums = np.sum(doc_topic_counts, axis=1)[:, np.newaxis]
yield {
'topic_word': np.copy(topic_word_counts) / topic_word_sums,
'doc_topic': np.copy(doc_topic_counts) / doc_topic_sums,
'word_topic': copy.deepcopy(word_topic),
'word_index': word_index
}
def infer(self, documents, n_sweeps=1000, word_topic=None):
r = np.random.RandomState(0)
# initialize counts for each doc-topic and topic-word pair using the prior
(doc_topic_counts, topic_word_counts, word_index) = (
self._initialize(documents)
)
topic_counts = np.sum(topic_word_counts, axis=1)
n_topics = topic_word_counts.shape[0]
n_docs = doc_topic_counts.shape[0]
n_words = len(word_index)
# transform documents into lists of word indices
(documents, word_index) = reindex(documents)
# initialize topics for all words uniformly at random
if word_topic is None:
word_topic = [
[
categorical(np.ones(n_topics)/n_topics, r)
for word in doc
]
for doc in documents
]
# initialize doc-topic and topic-word counts
for (d, doc) in enumerate(documents):
for (i, word) in enumerate(doc):
# get topic for this word
t = word_topic[d][i]
# increment counts
doc_topic_counts[d,t] += 1
topic_word_counts[t,word] += 1
topic_counts[t] += 1
# resample word topics
for sweep in range(n_sweeps):
self.logger.debug('starting sweep #%d' % (sweep,))
for (d, doc) in enumerate(documents):
if d % 100 == 0:
self.logger.debug('starting document #%d' % (d,))
for (i, word) in enumerate(doc):
# get topic for this word in this document
t = word_topic[d][i]
# remove it from counts
doc_topic_counts[d,t] -= 1
topic_word_counts[t,word] -= 1
topic_counts[t] -= 1
# calculate P(t | everything else)
prob = [
doc_topic_counts[d,t] * topic_word_counts[t,word] / topic_counts[t]
for t in range(n_topics)
]
prob = np.array(prob) / np.sum(prob)
# select topic
t = categorical(prob, r)
# increment counts
doc_topic_counts[d,t] += 1
topic_word_counts[t,word] += 1
topic_counts[t] += 1
# set topic for word
word_topic[d][i] = t
# sum of counts along each row
topic_word_sums = topic_counts[:, np.newaxis]
doc_topic_sums = np.sum(doc_topic_counts, axis=1)[:, np.newaxis]
yield {
'topic_word': np.copy(topic_word_counts) / topic_word_sums,
'doc_topic': np.copy(doc_topic_counts) / doc_topic_sums,
'word_topic': copy.deepcopy(word_topic),
'word_index': word_index
}
