def init_reviews(self):
print('init_reviews', time.strftime("%H:%M:%S"))
self.reviews = []
self.specific_reviews = []
self.generic_reviews = []
# for text_review in self.text_reviews:
# self.reviews.append(Review(text_review))
my_file = '/Users/fpena/tmp/reviews_hotel.pkl'
# my_file = '/Users/fpena/tmp/reviews_restaurant.pkl'
# my_file = '/Users/fpena/tmp/sentences_hotel.pkl'
# with open(my_file, 'wb') as write_file:
# pickle.dump(self.reviews, write_file, pickle.HIGHEST_PROTOCOL)
with open(my_file, 'rb') as read_file:
self.reviews = pickle.load(read_file)
# self.reviews = self.reviews
# for review in self.reviews:
# print(review)
cluster_labels = reviews_clusterer.cluster_reviews(self.reviews)
review_clusters =\
reviews_clusterer.split_list_by_labels(self.reviews, cluster_labels)
# print(cluster_labels)
self.specific_reviews = review_clusters[0]
self.generic_reviews = review_clusters[1]
self.all_nouns = context_utils.get_all_nouns(self.reviews)
context_utils.generate_stats(self.specific_reviews, self.generic_reviews)
def test_get_all_nouns(self):
reviews = [
Review(empty_paragraph),
Review(paragraph1),
Review(review_text1),
Review(review_text2)
]
actual_value = context_utils.get_all_nouns(reviews)
expected_value = {'morning', 'Dr.', 'Adams', 'patient', 'room',
'number', 'dinner', 'night', 'food', 'restaurant',
'town', 'bar', 'music', 'beer'}
self.assertEqual(actual_value, expected_value)
def test_get_all_nouns(self):
reviews = [
Review(empty_paragraph),
Review(paragraph1),
Review(review_text1),
Review(review_text2)
]
actual_value = context_utils.get_all_nouns(reviews)
expected_value = {
'morning', 'Dr.', 'Adams', 'patient', 'room', 'number', 'dinner',
'night', 'food', 'restaurant', 'town', 'bar', 'music', 'beer'
}
self.assertEqual(actual_value, expected_value)
def init_reviews(self):
print('init_reviews', time.strftime("%H:%M:%S"))
# self.reviews = reviews
self.specific_reviews = []
self.generic_reviews = []
# for text_review in self.text_reviews:
# self.reviews.append(Review(text_review))
# my_file = '/Users/fpena/UCC/Thesis/projects/yelp/source/python/topicmodeling/context/reviews_hotel.pkl'
records_file = '/Users/fpena/UCC/Thesis/datasets/context/stuff/reviews_hotel_shuffled.json'
reviews_file = '/Users/fpena/UCC/Thesis/datasets/context/stuff/reviews_hotel_shuffled.pkl'
# my_file = '/Users/fpena/UCC/Thesis/datasets/context/stuff/reviews_restaurant_shuffled.pkl'
# my_file = '/Users/fpena/tmp/reviews_restaurant.pkl'
# my_file = '/Users/fpena/tmp/sentences_hotel.pkl'
# with open(my_file, 'wb') as write_file:
# pickle.dump(self.reviews, write_file, pickle.HIGHEST_PROTOCOL)
# self.records = ETLUtils.load_json_file(records_file)
#
# with open(reviews_file, 'rb') as read_file:
# self.reviews = pickle.load(read_file)[:100]
#
# print(self.records[50]['text'])
# print(self.reviews[50].text)
# self.reviews = self.reviews
# for review in self.reviews:
# print(review)
cluster_labels = reviews_clusterer.cluster_reviews(self.reviews)
review_clusters =\
reviews_clusterer.split_list_by_labels(self.reviews, cluster_labels)
# print(cluster_labels)
self.specific_reviews = review_clusters[0]
self.generic_reviews = review_clusters[1]
self.all_nouns = context_utils.get_all_nouns(self.reviews)
context_utils.generate_stats(self.specific_reviews, self.generic_reviews)
