# In[44]:
#looking at the output of our LDA topic model
topics_with_wts = [item[0] for item in topics_coherences]
print('LDA Topics with Weights')
print('=' * 50)
for idx, topic in enumerate(topics_with_wts):
print('Topic #' + str(idx + 1) + ':')
print([(term, round(wt, 3)) for wt, term in topic])
print()
# In[45]:
model = LdaModel(corpus=corpus_tfidf, id2word=dictionary, num_topics=10)
for idx, topic in model.print_topics():
print('Topic: ({}) word: {}'.format(idx, topic))
# In[46]:
#viewing the topics as a list of terms without the weights
print('LDA Topics without Weights')
print('=' * 50)
for idx, topic in enumerate(topics_with_wts):
print('Topic #' + str(idx + 1) + ':')
print([term for wt, term in topic])
print()
# In[52]:
LDA_viz = pyLDAvis.gensim.prepare(lda_model, corpus_tfidf, dictionary)
corpus_tfidf = tfidf[bow_corpus]
from pprint import pprint
for doc in corpus_tfidf:
pprint(doc)
break
#########################
# LDA with BAG OF WORDS
#########################
# train the LDA model
lda_model = gensim.models.LdaMulticore(bow_corpus, num_topics = 10, id2word = dictionary, passes = 2, workers = 2)
# for each topic - explore the words occuring in that topic and their relative weight
for idx, topic in lda_model.print_topics(-1):
print('Topic {}, \nWords: {}'.format(idx, topic))
word_topic = np.array(lda_model.components_)
word_topic = word_topic.transpose()
num_topics = 10
num_top_words = 10
vocab_array = np.asarray(vocab)
#fontsize_base = 70 / np.max(word_topic) # font size for word with largest share in corpus
fontsize_base = 10
for t in range(num_topics):
plt.subplot(1, num_topics, t + 1) # plot numbering starts with 1
