def test_topic_coherence(self):
"""Test LdaVowpalWabbit topic coherence."""
if not self.vw_path: # for python 2.6
return
corpus, dictionary = get_corpus()
lda = LdaVowpalWabbit(self.vw_path,
corpus=corpus,
passes=10,
chunksize=256,
id2word=dictionary,
cleanup_files=True,
alpha=0.1,
eta=0.1,
num_topics=len(TOPIC_WORDS),
random_seed=1)
lda.print_topics(5, 10)
# map words in known topic to an ID
topic_map = {}
for i, words in enumerate(TOPIC_WORDS):
topic_map[frozenset(words)] = i
n_coherent = 0
for topic_id in range(lda.num_topics):
topic = lda.show_topic(topic_id, topn=20)
# get all words from LDA topic
topic_words = [w[1] for w in topic]
# get list of original topics that each word actually belongs to
ids = []
for word in topic_words:
for src_topic_words, src_topic_id in six.iteritems(topic_map):
if word in src_topic_words:
ids.append(src_topic_id)
# count the number of times each original topic appears
counts = defaultdict(int)
for found_topic_id in ids:
counts[found_topic_id] += 1
# if at least 6/10 words assigned to same topic, consider it coherent
max_count = 0
for count in six.itervalues(counts):
max_count = max(max_count, count)
if max_count >= 6:
n_coherent += 1
# not 100% deterministic, but should always get 3+ coherent topics
self.assertTrue(n_coherent >= 3)
def test_topic_coherence(self):
"""Test LdaVowpalWabbit topic coherence."""
if not self.vw_path: # for python 2.6
return
corpus, dictionary = get_corpus()
lda = LdaVowpalWabbit(self.vw_path,
corpus=corpus,
passes=10,
chunksize=256,
id2word=dictionary,
cleanup_files=True,
alpha=0.1,
eta=0.1,
num_topics=len(TOPIC_WORDS),
random_seed=1)
lda.print_topics(5, 10)
# map words in known topic to an ID
topic_map = {}
for i, words in enumerate(TOPIC_WORDS):
topic_map[frozenset(words)] = i
n_coherent = 0
for topic_id in range(lda.num_topics):
topic = lda.show_topic(topic_id, topn=20)
# get all words from LDA topic
topic_words = [w[1] for w in topic]
# get list of original topics that each word actually belongs to
ids = []
for word in topic_words:
for src_topic_words, src_topic_id in six.iteritems(topic_map):
if word in src_topic_words:
ids.append(src_topic_id)
# count the number of times each original topic appears
counts = defaultdict(int)
for found_topic_id in ids:
counts[found_topic_id] += 1
# if at least 6/10 words assigned to same topic, consider it coherent
max_count = 0
for count in six.itervalues(counts):
max_count = max(max_count, count)
if max_count >= 6:
n_coherent += 1
# not 100% deterministic, but should always get 3+ coherent topics
self.assertTrue(n_coherent >= 3)
