def train_context_extractor(records, stable=True):
print('%s: train context topics model' % time.strftime("%Y/%m/%d-%H:%M:%S"))
if Constants.TOPIC_MODEL_TYPE == 'lda':
context_extractor = LdaBasedContext(records)
context_extractor.generate_review_corpus()
context_extractor.build_topic_model()
context_extractor.update_reviews_with_topics()
context_extractor.get_context_rich_topics()
context_extractor.clear_reviews()
elif Constants.TOPIC_MODEL_TYPE == 'nmf':
context_extractor = NmfContextExtractor(records)
context_extractor.generate_review_bows()
context_extractor.build_document_term_matrix()
if stable:
context_extractor.build_stable_topic_model()
else:
context_extractor.build_topic_model()
context_extractor.update_reviews_with_topics()
context_extractor.get_context_rich_topics()
context_extractor.clear_reviews()
else:
raise ValueError('Unrecognized topic model type: \'%s\'' %
Constants.TOPIC_MODEL_TYPE)
print('%s: Trained Topic Model' % time.strftime("%Y/%m/%d-%H:%M:%S"))
return context_extractor
def train_context_topics_model(records):
print('%s: train context topics model' % time.strftime("%Y/%m/%d-%H:%M:%S"))
lda_based_context = LdaBasedContext(records)
lda_based_context.generate_review_corpus()
lda_based_context.build_topic_model()
lda_based_context.update_reviews_with_topics()
print('%s: Trained LDA Model' % time.strftime("%Y/%m/%d-%H:%M:%S"))
return lda_based_context
def train_context_topics_model(records):
print('%s: train context topics model' %
time.strftime("%Y/%m/%d-%H:%M:%S"))
lda_based_context = LdaBasedContext(records)
lda_based_context.generate_review_corpus()
lda_based_context.build_topic_model()
lda_based_context.update_reviews_with_topics()
print('%s: Trained LDA Model' % time.strftime("%Y/%m/%d-%H:%M:%S"))
return lda_based_context
def train_topic_model(self, cycle_index, fold_index):
if Constants.CACHE_TOPIC_MODEL:
print('loading topic model')
lda_based_context = topic_model_creator.load_topic_model(
cycle_index, fold_index)
else:
print('train topic model: %s' % time.strftime("%Y/%m/%d-%H:%M:%S"))
lda_based_context = LdaBasedContext(self.train_records)
lda_based_context.generate_review_corpus()
lda_based_context.build_topic_model()
lda_based_context.update_reviews_with_topics()
lda_based_context.get_context_rich_topics()
self.context_rich_topics = lda_based_context.context_rich_topics
print('Trained LDA Model: %s' % time.strftime("%Y/%m/%d-%H:%M:%S"))
return lda_based_context
def train_topic_model(self, cycle_index, fold_index):
if Constants.CACHE_TOPIC_MODEL:
print('loading topic model')
lda_based_context = topic_model_creator.load_topic_model(
cycle_index, fold_index)
else:
print('train topic model: %s' % time.strftime("%Y/%m/%d-%H:%M:%S"))
lda_based_context = LdaBasedContext(self.train_records)
lda_based_context.generate_review_corpus()
lda_based_context.build_topic_model()
lda_based_context.update_reviews_with_topics()
lda_based_context.get_context_rich_topics()
self.context_rich_topics = lda_based_context.context_rich_topics
print('Trained LDA Model: %s' % time.strftime("%Y/%m/%d-%H:%M:%S"))
return lda_based_context
