def test_occurence_index_user_to_item(self):
#Not the best of names, but we attribute this to fields
#which have no impact on the test.
no_impact = 1
a1 = data_parser.to_json(1, 1, no_impact, no_impact)
a2 = data_parser.to_json(1, 2, no_impact, no_impact)
a3 = data_parser.to_json(1, 1, no_impact, no_impact)
a4 = data_parser.to_json(2, 2, no_impact, no_impact)
a5 = data_parser.to_json(2, 3, no_impact, no_impact)
index = create_occurrence_index([a1, a2, a3, a4, a5], 'user', 'item')
self.assertEqual(index[1], set([1, 2, 1]))
self.assertEqual(index[2], set([2, 3]))
def test_occurence_index_user_to_item(self):
#Not the best of names, but we attribute this to fields
#which have no impact on the test.
no_impact = 1
a1 = data_parser.to_json(1, 1, no_impact, no_impact)
a2 = data_parser.to_json(1, 2, no_impact, no_impact)
a3 = data_parser.to_json(1, 1, no_impact, no_impact)
a4 = data_parser.to_json(2, 2, no_impact, no_impact)
a5 = data_parser.to_json(2, 3, no_impact, no_impact)
index = create_occurrence_index([a1, a2, a3, a4, a5], 'user', 'item')
self.assertEqual(index[1], set([1, 2, 1]))
self.assertEqual(index[2], set([2, 3]))
def _base_metrics(self, use_user):
'''Creates and counts the popularity of random tags. The
test will compare this with the result of the indices.'''
#Generating some random annotations
any_date = time.time()
tag_pop = defaultdict(int)
post_tag_pop = defaultdict(lambda: defaultdict(int))
annotations = []
for i in xrange(32):
user = random.randint(0, 4)
tag = random.randint(0, 4)
item = random.randint(0, 4)
annotations.append(data_parser.to_json(user, item, tag, any_date))
post = user if use_user else item
tag_pop[tag] += 1
post_tag_pop[post][tag] += 1
if use_user:
index = create_metrics_index(annotations, 'user', 'tag')
else:
index = create_metrics_index(annotations, 'item', 'tag')
self.assertEquals(post_tag_pop, index[0])
self.assertEquals(tag_pop, index[2])
def _base_metrics(self, use_user):
'''Creates and counts the popularity of random tags. The
test will compare this with the result of the indices.'''
#Generating some random annotations
any_date = time.time()
tag_pop = defaultdict(int)
post_tag_pop = defaultdict(lambda: defaultdict(int))
annotations = []
for i in xrange(32):
user = random.randint(0, 4)
tag = random.randint(0, 4)
item = random.randint(0, 4)
annotations.append(data_parser.to_json(user, item, tag, any_date))
post = user if use_user else item
tag_pop[tag] += 1
post_tag_pop[post][tag] += 1
if use_user:
index = create_metrics_index(annotations, 'user', 'tag')
else:
index = create_metrics_index(annotations, 'item', 'tag')
self.assertEquals(post_tag_pop, index[0])
self.assertEquals(tag_pop, index[2])
def test_double_occurrence_index(self):
no_impact = 1
a1 = data_parser.to_json(1, no_impact, 1, no_impact)
a2 = data_parser.to_json(1, no_impact, 2, no_impact)
a3 = data_parser.to_json(1, no_impact, 1, no_impact)
a4 = data_parser.to_json(2, no_impact, 2, no_impact)
a5 = data_parser.to_json(2, no_impact, 3, no_impact)
from_to, inv = create_double_occurrence_index([a1, a2, a3, a4, a5],
'user', 'tag')
self.assertEqual(from_to[1], set([1, 2, 1]))
self.assertEqual(from_to[2], set([2, 3]))
self.assertEqual(inv[1], set([1]))
self.assertEqual(inv[2], set([1, 2]))
self.assertEqual(inv[3], set([2]))
def test_double_occurrence_index(self):
no_impact = 1
a1 = data_parser.to_json(1, no_impact, 1, no_impact)
a2 = data_parser.to_json(1, no_impact, 2, no_impact)
a3 = data_parser.to_json(1, no_impact, 1, no_impact)
a4 = data_parser.to_json(2, no_impact, 2, no_impact)
a5 = data_parser.to_json(2, no_impact, 3, no_impact)
from_to, inv = create_double_occurrence_index([a1, a2, a3, a4, a5],
'user', 'tag')
self.assertEqual(from_to[1], set([1, 2, 1]))
self.assertEqual(from_to[2], set([2, 3]))
self.assertEqual(inv[1], set([1]))
self.assertEqual(inv[2], set([1, 2]))
self.assertEqual(inv[3], set([2]))
