if os.path.exists('browser/static/data'):
shutil.rmtree('browser/static/data')
os.makedirs('browser/static/data')
# Export topic cloud
utils.save_topic_cloud(topic_model, 'browser/static/data/topic_cloud.json')
# Export details about topics
for topic_id in range(topic_model.nb_topics):
utils.save_word_distribution(topic_model.top_words(topic_id, 20),
'browser/static/data/word_distribution' + str(topic_id) + '.tsv')
utils.save_affiliation_repartition(topic_model.affiliation_repartition(topic_id),
'browser/static/data/affiliation_repartition' + str(topic_id) + '.tsv')
evolution = []
for i in range(2012, 2016):
evolution.append((i, topic_model.topic_frequency(topic_id, date=i)))
utils.save_topic_evolution(evolution, 'browser/static/data/frequency' + str(topic_id) + '.tsv')
# Export details about documents
for doc_id in range(topic_model.corpus.size):
utils.save_topic_distribution(topic_model.topic_distribution_for_document(doc_id),
'browser/static/data/topic_distribution_d' + str(doc_id) + '.tsv')
# Export details about words
for word_id in range(len(topic_model.corpus.vocabulary)):
utils.save_topic_distribution(topic_model.topic_distribution_for_word(word_id),
'browser/static/data/topic_distribution_w' + str(word_id) + '.tsv')
# Associate documents with topics
topic_associations = topic_model.documents_per_topic()
topic_model.print_topics(num_words=10)
# Export topic cloud
utils.save_topic_cloud(topic_model, path.join(timeframe_dir, 'topic_cloud.json'))
# Export details about topics
for topic_id in range(topic_model.nb_topics):
custom_save_word_distribution(custom_top_words(topic_model, topic_id, 20),
path.join(timeframe_dir,'word_distribution' + str(topic_id) + '.tsv'))
utils.save_affiliation_repartition(topic_model.affiliation_repartition(topic_id),
path.join(timeframe_dir,
'affiliation_repartition' + str(topic_id) + '.tsv'))
evolution = []
for i in range(timeframe):
d = today - dt.timedelta(days=timeframe)+dt.timedelta(days=i)
evolution.append((d.strftime("%Y-%m-%d"), topic_model.topic_frequency(topic_id, date=d.strftime("%Y-%m-%d"))))
utils.save_topic_evolution(evolution, path.join(timeframe_dir,'frequency' + str(topic_id) + '.tsv'))
# Export details about documents
for doc_id in range(topic_model.corpus.size):
utils.save_topic_distribution(topic_model.topic_distribution_for_document(doc_id),
path.join(timeframe_dir,'topic_distribution_d' + str(doc_id) + '.tsv'))
# Export details about words
for word_id in range(len(topic_model.corpus.vocabulary)):
utils.save_topic_distribution(
topic_model.topic_distribution_for_word(word_id),
path.join(timeframe_dir, 'topic_distribution_w' + str(word_id) + '.tsv'))
# Associate documents with topics
topic_associations = topic_model.documents_per_topic()