Я хочу интерпретировать темы в моей модели темы lda, поэтому я использую pyldavis ..
Но почему-то я не могу заставить Пилдависа бежать. Вот код:
import gensim
from gensim import corpora
from gensim.corpora import Dictionary
dictionary = corpora.Dictionary(lemmatized_list)
print(dictionary)
print(dictionary.token2id)
corpus = [dictionary.doc2bow(text) for text in lemmatized_list]
print(corpus)
ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=5, id2word =
dictionary, passes=10)
print(ldamodel.print_topics(num_topics=5, num_words=3))
import pyLDAvis.gensim
pyLDAvis.enable_notebook()
pyLDAvis.gensim.prepare(ldamodel, corpus, dictionary)
затем, после того как я добрался до последней части кода, где я должен визуализировать с помощью pyldavis, он показывает следующую ошибку:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-16-a16bc334f38f> in <module>()
1 import pyLDAvis.gensim
2 pyLDAvis.enable_notebook()
----> 3 pyLDAvis.gensim.prepare(ldamodel, corpus, dictionary)
4 term_ix = np.sort(topic_info.index.unique().values)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pyLDAvis\gensim.py in prepare(topic_model, corpus, dictionary, doc_topic_dist, **kwargs)
108 """
109 opts = fp.merge(_extract_data(topic_model, corpus, dictionary, doc_topic_dist), kwargs)
--> 110 return vis_prepare(**opts)
~\AppData\Local\Continuum\anaconda3\lib\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)
396
397 topic_info = _topic_info(topic_term_dists, topic_proportion, term_frequency, term_topic_freq, vocab, lambda_step, R, n_jobs)
--> 398 token_table = _token_table(topic_info, term_topic_freq, vocab, term_frequency)
399 topic_coordinates = _topic_coordinates(mds, topic_term_dists, topic_proportion)
400 client_topic_order = [x + 1 for x in topic_order]
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pyLDAvis\_prepare.py in _token_table(topic_info, term_topic_freq, vocab, term_frequency)
265 # term-topic frequency table of unique terms across all topics and all values of lambda
266 term_ix = topic_info.index.unique()
--> 267 term_ix.sort()
268 top_topic_terms_freq = term_topic_freq[term_ix]
269 # use the new ordering for the topics
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\indexes\base.py in sort(self, *args, **kwargs)
2098
2099 def sort(self, *args, **kwargs):
-> 2100 raise TypeError("cannot sort an Index object in-place, use "
2101 "sort_values instead")
2102
TypeError: cannot sort an Index object in-place, use sort_values instead
Любые предложения о том, как разобраться с этой ошибкой ... были бы очень полезны. Спасибо!