Python NonNegativeMatrixFactorization.topics_frequency Examples

Example #1

File: infer_topics.py Project: AdrienGuille/TOM

print('Estimating the number of topics...')
viz = Visualization(topic_model)
viz.plot_greene_metric(min_num_topics=10,
                       max_num_topics=11,
                       tao=10, step=1,
                       top_n_words=10)
viz.plot_arun_metric(min_num_topics=5,
                     max_num_topics=30,
                     iterations=10)
viz.plot_brunet_metric(min_num_topics=5,
                       max_num_topics=30,
                       iterations=10)

# Infer topics
print('Inferring topics...')
topic_model.infer_topics(num_topics=15)
# Save model on disk
ut.save_topic_model(topic_model, 'output/NMF_15topics.pickle')

# Print results
print('\nTopics:')
topic_model.print_topics(num_words=10)
print('\nTopic distribution for document 0:',
      topic_model.topic_distribution_for_document(0))
print('\nMost likely topic for document 0:',
      topic_model.most_likely_topic_for_document(0))
print('\nFrequency of topics:',
      topic_model.topics_frequency())
print('\nTop 10 most relevant words for topic 2:',
      topic_model.top_words(2, 10))

Example #2

File: infer_topics.py Project: weizhao-2010/TOM

# print('Estimating the number of topics...')
# viz = Visualization(topic_model)
# viz.plot_greene_metric(min_num_topics=10,
#                        max_num_topics=11,
#                        tao=10, step=1,
#                        top_n_words=10)
# viz.plot_arun_metric(min_num_topics=5,
#                      max_num_topics=30,
#                      iterations=10)
# viz.plot_brunet_metric(min_num_topics=5,
#                        max_num_topics=30,
#                        iterations=10)

# Infer topics
print('Inferring topics...')
topic_model.infer_topics(num_topics=15)
# Save model on disk
ut.save_topic_model(topic_model, 'NMF_EGC_15topics.pickle')
# Load model from disk: topic_model = ut.load_topic_model('NMF_EGC_15topics.pickle')

# Print results
print('\nTopics:')
topic_model.print_topics(num_words=10)
print('\nTopic distribution for document 0:',
      topic_model.topic_distribution_for_document(0))
print('\nMost likely topic for document 0:',
      topic_model.most_likely_topic_for_document(0))
print('\nFrequency of topics:', topic_model.topics_frequency())
print('\nTop 10 most relevant words for topic 2:',
      topic_model.top_words(2, 10))

Example #3

File: topic_model.py Project: OPersian/TOM

print('Estimating the number of topics...')
viz = Visualization(topic_model)
viz.plot_greene_metric(min_num_topics=10,
                       max_num_topics=30,
                       tao=10, step=1,
                       top_n_words=10)
viz.plot_arun_metric(min_num_topics=5,
                     max_num_topics=30,
                     iterations=10)
viz.plot_brunet_metric(min_num_topics=5,
                       max_num_topics=30,
                       iterations=10)

# Infer topics
print('Inferring topics...')
topic_model.infer_topics(num_topics=15)
# Save model on disk
ut.save_topic_model(topic_model, 'output/NMF_15topics.pickle')

# Print results
print('\nTopics:')
topic_model.print_topics(num_words=10)
print('\nTopic distribution for document 0:',
      topic_model.topic_distribution_for_document(0))
print('\nMost likely topic for document 0:',
      topic_model.most_likely_topic_for_document(0))
print('\nFrequency of topics:',
      topic_model.topics_frequency())
print('\nTop 10 most relevant words for topic 2:',
      topic_model.top_words(2, 10))