def load(self, records):
self.records = records
self.ratings_matrix = basic_knn.create_ratings_matrix(records)
self.reviews_matrix = create_reviews_matrix(records)
self.user_dictionary = extractor.initialize_users(self.records, False)
self.user_ids = extractor.get_groupby_list(self.records, 'user_id')
lda_based_context = LdaBasedContext(self.records, self.reviews)
# self.lda_model =\
# lda_context_utils.discover_topics(text_reviews, self.num_topics)
# if self.reviews:
# lda_based_context = LdaBasedContext()
# lda_based_context.reviews = self.reviews
# lda_based_context.init_reviews()
# else:
# text_reviews = []
# for record in self.records:
# text_reviews.append(record['text'])
# lda_based_context = LdaBasedContext(text_reviews)
# lda_based_context.init_reviews()
self.context_rich_topics = lda_based_context.get_context_rich_topics()
self.lda_model = lda_based_context.topic_model
print('building similarity matrix', time.strftime("%H:%M:%S"))
self.context_matrix = self.create_context_matrix(records)
self.similarity_matrix = self.create_similarity_matrix()
print('finished building similarity matrix', time.strftime("%H:%M:%S"))
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 load_context(self, records):
if self.reviews:
lda_based_context = LdaBasedContext()
lda_based_context.reviews = self.reviews
lda_based_context.init_reviews()
else:
text_reviews = []
for record in records:
text_reviews.append(record['text'])
lda_based_context = LdaBasedContext(text_reviews)
lda_based_context.init_reviews()
self.context_rich_topics = lda_based_context.get_context_rich_topics()
self.lda_model = lda_based_context.topic_model
for user in self.user_dictionary.values():
user.item_contexts = lda_context_utils.get_user_item_contexts(
records, self.lda_model, user.user_id, True
)
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
