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 count_items_in_common(self):
"""
Counts the number of items each user has in common with every other user
and stores the results in a dictionary.
:return: a dictionary with the count of the number of times users have
a certain number of items in common. For example, the dictionary
{0:4, 1:10, 2:6, 3:3, 4:1} means that there a 4 users who have 0 items
in common with the rest of users, there are 10 users who have rated 1
item in common with the rest of users, 6 users who have rated 6 items in
common with the rest of the users, and so on.
"""
common_item_counts = {}
user_dictionary = extractor.initialize_users(self.reviews, False)
for i in range(self.num_users):
for j in range(i + 1, self.num_users):
user1 = self.user_ids[i]
user2 = self.user_ids[j]
num_common_items = len(extractor.get_common_items(user_dictionary, user1, user2))
if num_common_items in common_item_counts:
common_item_counts[num_common_items] += 1
else:
common_item_counts[num_common_items] = 1
return common_item_counts
def count_items_in_common(self):
"""
Counts the number of items each user has in common with every other user
and stores the results in a dictionary.
:return: a dictionary with the count of the number of times users have
a certain number of items in common. For example, the dictionary
{0:4, 1:10, 2:6, 3:3, 4:1} means that there a 4 users who have 0 items
in common with the rest of users, there are 10 users who have rated 1
item in common with the rest of users, 6 users who have rated 6 items in
common with the rest of the users, and so on.
"""
common_item_counts = {}
user_dictionary = extractor.initialize_users(self.reviews, False)
for i in range(self.num_users):
for j in range(i + 1, self.num_users):
user1 = self.user_ids[i]
user2 = self.user_ids[j]
num_common_items = len(
extractor.get_common_items(user_dictionary, user1, user2))
if num_common_items in common_item_counts:
common_item_counts[num_common_items] += 1
else:
common_item_counts[num_common_items] = 1
return common_item_counts
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')
# 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 test_build_similarity_matrix_pearson(self):
user_dictionary =\
extractor.initialize_users(reviews_matrix_5, False)
user_ids = extractor.get_groupby_list(reviews_matrix_5, 'user_id')
similarity_matrix_builder = SingleSimilarityMatrixBuilder('pearson')
self.assertEqual(
pearson_matrix,
similarity_matrix_builder.build_similarity_matrix(
user_dictionary, user_ids))
def load(self, reviews):
self.reviews = reviews
self.user_dictionary =\
extractor.initialize_users(
self.reviews,
self._similarity_matrix_builder._is_multi_criteria)
self.user_ids = extractor.get_groupby_list(self.reviews, 'user_id')
if self._similarity_matrix_builder._similarity_metric is not None:
self.user_similarity_matrix =\
self._similarity_matrix_builder.build_similarity_matrix(
self.user_dictionary, self.user_ids)
def load(self, reviews):
self.reviews = reviews
self.user_dictionary =\
extractor.initialize_users(
self.reviews,
self._similarity_matrix_builder._is_multi_criteria)
self.user_ids = extractor.get_groupby_list(self.reviews, 'user_id')
if self._similarity_matrix_builder._similarity_metric is not None:
self.user_similarity_matrix =\
self._similarity_matrix_builder.build_similarity_matrix(
self.user_dictionary, self.user_ids)
def load(self, records):
# self.records = records
self.user_dictionary = extractor.initialize_users(records, False)
self.user_ids = extractor.get_groupby_list(records, 'user_id')
if self.has_context:
self.load_context(records)
self.user_similarity_calculator.load(
self.user_ids, self.user_dictionary, self.context_rich_topics)
self.neighbourhood_calculator.load(
self.user_ids, self.user_dictionary, self.context_rich_topics,
self.num_neighbours)
self.user_baseline_calculator.load(
self.user_dictionary, self.context_rich_topics)
self.neighbour_contribution_calculator.load(
self.user_baseline_calculator)
def test_build_similarity_matrix_pearson(self):
user_dictionary = extractor.initialize_users(reviews_matrix_5, False)
user_ids = extractor.get_groupby_list(reviews_matrix_5, "user_id")
similarity_matrix_builder = SingleSimilarityMatrixBuilder("pearson")
self.assertEqual(pearson_matrix, similarity_matrix_builder.build_similarity_matrix(user_dictionary, user_ids))
def load(self, reviews):
self.reviews = reviews
self.user_dictionary = extractor.initialize_users(self.reviews, False)
self.user_ids = extractor.get_groupby_list(self.reviews, "user_id")
def load(self, reviews):
self.reviews = reviews
self.ratings_matrix = create_ratings_matrix(reviews)
self.user_dictionary = extractor.initialize_users(self.reviews, False)
self.user_ids = extractor.get_groupby_list(self.reviews, 'user_id')
self.similarity_matrix = self.create_similarity_matrix()
def load(self, reviews):
self.reviews = reviews
self.user_dictionary = extractor.initialize_users(self.reviews, False)
self.user_ids = extractor.get_groupby_list(self.reviews, 'user_id')