def get_records_to_predict_topn(self):
print('get_records_to_predict_topn: %s' %
time.strftime("%Y/%m/%d-%H:%M:%S"))
self.top_n_evaluator = TopNEvaluator(self.records, self.test_records,
Constants.ITEM_TYPE, 10,
Constants.TOPN_NUM_ITEMS)
self.top_n_evaluator.initialize()
self.important_records = self.top_n_evaluator.important_records
if Constants.TEST_CONTEXT_REVIEWS_ONLY:
self.important_records = ETLUtils.filter_records(
self.important_records, Constants.HAS_CONTEXT_FIELD, [True])
self.records_to_predict =\
self.top_n_evaluator.get_records_to_predict()
if Constants.MAX_SAMPLE_TEST_SET is not None:
print('important_records %d' % len(self.important_records))
if len(self.important_records) > Constants.MAX_SAMPLE_TEST_SET:
self.important_records = random.sample(
self.important_records, Constants.MAX_SAMPLE_TEST_SET)
else:
message = 'WARNING max_sample_test_set is greater than the ' \
'number of important records'
print(message)
self.top_n_evaluator.important_records = self.important_records
self.records_to_predict = self.top_n_evaluator.get_records_to_predict()
self.test_records = None
gc.collect()
def test_get_items_to_predict(self):
top_n_evaluator = TopNEvaluator(ratings, test_set)
top_n_evaluator.I = 4
top_n_evaluator.N = 2
top_n_evaluator.initialize()
items_to_predict = top_n_evaluator.get_records_to_predict()
predictions = [0] * len(test_set) * (top_n_evaluator.I + 1)
top_n_evaluator.evaluate(predictions)
print(items_to_predict)
for item in items_to_predict:
print(item)
def get_records_to_predict_topn(self):
print('get_records_to_predict_topn: %s' %
time.strftime("%Y/%m/%d-%H:%M:%S"))
with open(Constants.USER_ITEM_MAP_FILE, 'rb') as read_file:
user_item_map = pickle.load(read_file)
self.top_n_evaluator = TopNEvaluator(self.records, self.test_records,
Constants.ITEM_TYPE, 10,
Constants.TOPN_NUM_ITEMS)
self.top_n_evaluator.initialize(user_item_map)
self.records_to_predict = self.top_n_evaluator.get_records_to_predict()
self.important_records = self.top_n_evaluator.important_records
self.test_records = None
gc.collect()
def export(self):
print('export: %s' % time.strftime("%Y/%m/%d-%H:%M:%S"))
with open(Constants.USER_ITEM_MAP_FILE, 'rb') as read_file:
user_item_map = pickle.load(read_file)
self.top_n_evaluator = TopNEvaluator(
self.records, self.test_records, Constants.ITEM_TYPE, 10,
Constants.TOPN_NUM_ITEMS)
self.top_n_evaluator.initialize(user_item_map)
self.records_to_predict = self.top_n_evaluator.get_records_to_predict()
self.important_records = self.top_n_evaluator.important_records
self.important_reviews = [
review for review in self.test_reviews if review.rating == 5
]
def test_calculate_recall(self):
N = 5
top_n_evaluator = TopNEvaluator([], [], N)
top_n_list = ['I1', 'I2', 'I3', 'I4', 'I5']
item = 'I3'
top_n_evaluator.update_num_hits(top_n_list, item)
top_n_list = ['I1', 'I2', 'I3', 'I4', 'I5']
item = 'I6'
top_n_evaluator.update_num_hits(top_n_list, item)
top_n_list = ['I1', 'I6', 'I3', 'I4', 'I5']
item = 'I4'
top_n_evaluator.update_num_hits(top_n_list, item)
self.assertEqual(2.0 / 3, top_n_evaluator.calculate_recall())
def test_get_irrelevant_items(self):
top_n_evaluator = TopNEvaluator(ratings, None)
top_n_evaluator.initialize()
actual_irrelevant_items = top_n_evaluator.get_irrelevant_items('U1')
expected_irrelevant_items = [
'I10', 'I11', 'I12', 'I13', 'I14', 'I15', 'I16'
]
self.assertItemsEqual(expected_irrelevant_items,
actual_irrelevant_items)
actual_irrelevant_items = top_n_evaluator.get_irrelevant_items('U5')
expected_irrelevant_items = [
'I1', 'I2', 'I3', 'I4', 'I5', 'I6', 'I7', 'I8', 'I9', 'I10', 'I11',
'I12', 'I13', 'I14', 'I15'
]
self.assertItemsEqual(expected_irrelevant_items,
actual_irrelevant_items)
# top_n_evaluator.get_irrelevant_items('U6')
self.assertRaises(KeyError, top_n_evaluator.get_irrelevant_items, 'U6')
def test_update_num_hits(self):
top_n_evaluator = TopNEvaluator([], [])
self.assertEqual(0, top_n_evaluator.num_generic_hits)
self.assertEqual(0, top_n_evaluator.num_generic_misses)
top_n_list = ['I1', 'I2', 'I3', 'I4', 'I5']
item = 'I3'
top_n_evaluator.update_num_hits(top_n_list, item)
self.assertEqual(1, top_n_evaluator.num_generic_hits)
self.assertEqual(0, top_n_evaluator.num_generic_misses)
top_n_list = ['I1', 'I2', 'I3', 'I4', 'I5']
item = 'I6'
top_n_evaluator.update_num_hits(top_n_list, item)
self.assertEqual(1, top_n_evaluator.num_generic_hits)
self.assertEqual(1, top_n_evaluator.num_generic_misses)
top_n_list = ['I1', 'I6', 'I3', 'I4', 'I5']
item = 'I4'
top_n_evaluator.update_num_hits(top_n_list, item)
self.assertEqual(2, top_n_evaluator.num_generic_hits)
self.assertEqual(1, top_n_evaluator.num_generic_misses)
