lda_gensim_kw_extract.py

'''
corpus is a list of list of string
like:
[['human', 'interface', 'computer'],
 ['survey', 'user', 'computer', 'system', 'response', 'time'],
 ['eps', 'user', 'interface', 'system'],
 ['system', 'human', 'system', 'eps'],
 ['user', 'response', 'time'],
 ['trees'],
 ['graph', 'trees'],
 ['graph', 'minors', 'trees'],
 ['graph', 'minors', 'survey']]
'''
dic = Dictionary(corpus)
data = [dic.doc2bow(words) for words in corpus]
lda = LdaModel(data, id2word=dic, num_topics=2)
# 1st topic, 10 words
for _, topic in lda.show_topics(num_topics=1, num_words=10, formatted=False):
    result.append([w[0] for w in topic])