Я попытался создать темы с помощью gensim для 20000 записей. При попытке визуализировать темы я получаю ошибку проверки. Я могу распечатать темы после обучения модели, но не с помощью pyLDAvis.
corpus = descriptions_lem_stop
dic=gensim.corpora.Dictionary(corpus)
bow_corpus = [dic.doc2bow(doc) for doc in corpus]
lda_model = gensim.models.LdaMulticore(bow_corpus, num_topics = 30, id2word = dic, passes = 10, workers = 2)
lda_model.show_topics()
pyLDAvis.enable_notebook()
vis = pyLDAvis.gensim.prepare(lda_model, bow_corpus, dic)
vis
Я получил ошибку:
/opt/anaconda3/lib/python3.8/site-packages/pyLDAvis/gensim.py in prepare(topic_model, corpus, dictionary, doc_topic_dist, **kwargs)
117 """
118 opts = fp.merge(_extract_data(topic_model, corpus, dictionary, doc_topic_dist), kwargs)
--> 119 return vis_prepare(**opts)
/opt/anaconda3/lib/python3.8/site-packages/pyLDAvis/_prepare.py in prepare(topic_term_dists, doc_topic_dists, doc_lengths, vocab, term_frequency, R, lambda_step, mds, n_jobs, plot_opts, sort_topics)
372 doc_lengths = _series_with_name(doc_lengths, 'doc_length')
373 vocab = _series_with_name(vocab, 'vocab')
--> 374 _input_validate(topic_term_dists, doc_topic_dists, doc_lengths, vocab, term_frequency)
375 R = min(R, len(vocab))
376
/opt/anaconda3/lib/python3.8/site-packages/pyLDAvis/_prepare.py in _input_validate(*args)
63 res = _input_check(*args)
64 if res:
---> 65 raise ValidationError('\n' + '\n'.join([' * ' + s for s in res]))
66
67
ValidationError:
* Not all rows (distributions) in topic_term_dists sum to 1.
