print("Topic %d:" % (topic_idx))
print(" ".join([
tf_feature_names[i]
for i in topic.argsort()[:-args.n_top_words - 1:-1]
]))
for i in topic.argsort()[:-args.n_top_words - 1:-1]:
print("%.4f" % (topic[i] / sum(topic)), end=' ')
print()
else:
word2id = {}
for idx, word in enumerate(tf_feature_names):
word2id[word] = idx
docs = {}
for doc_idx, doc in enumerate(corpus):
doc_list = [word2id[w] for w in doc.split() if w in word2id.keys()]
docs[doc_idx] = doc_list
print("Begin training.")
model = LDA_GIBBS(docs, args.topic, args.iter, tf_feature_names)
model.learn()
print(model.get_perplexity())
for t_id, t in enumerate(model.phi):
print("Topic %d:" % (t_id))
print(" ".join([
tf_feature_names[i] for i in t.argsort()[:-args.n_top_words - 1:-1]
]))
for i in t.argsort()[:-args.n_top_words - 1:-1]:
print("%.4f" % t[i], end=' ')
print()
