def test_score(self):
self.recommender.register(User(0))
self.recommender.register(Item(0))
self.recommender.update(Event(User(0), Item(0), 1))
score = self.recommender.score(User(0), np.array([0]))
print(score)
self.assertTrue(score >= -1.0 and score <= 1.0)
def test_update(self):
self.recommender.register(User(0))
self.recommender.register(Item(0))
self.recommender.update(
Event(User(0), Item(0), 1, context=np.array([1, 2, 3])))
self.assertEqual(self.recommender.n_user, 1)
self.assertEqual(self.recommender.n_item, 1)
def test_score(self):
self.recommender.register(User(0))
self.recommender.register(Item(0))
self.recommender.update(
Event(User(0), Item(0), 1, context=np.array([1, 2, 3])))
score = self.recommender.score(User(0),
candidates=np.array([0]),
context=np.array([1, 2, 3]))
self.assertTrue(score >= 0.0 and score <= 1.0)
def test_item(self):
item = Item(1, np.arange(5))
self.assertEqual(item.index, 1)
v = item.encode(dim=None, index=True, feature=True, vertical=False)
assert_array_equal(v, np.array([0, 1, 0, 1, 2, 3, 4]))
v = item.encode(dim=3, index=True, feature=False, vertical=False)
assert_array_equal(v, np.array([0, 1, 0]))
v = item.encode(dim=None, index=False, feature=True, vertical=True)
assert_array_equal(v, np.array([[0], [1], [2], [3], [4]]))
def test_event(self):
user = User(1, np.arange(3))
item = Item(1, np.arange(3))
event = Event(user, item, 5.0, np.arange(5))
self.assertEqual(event.value, 5.0)
v = event.encode(index=False,
feature=True,
context=True,
vertical=False)
assert_array_equal(v, np.array([0, 1, 2, 0, 1, 2, 3, 4, 0, 1, 2]))
v = event.encode(index=True,
feature=True,
context=False,
vertical=False)
assert_array_equal(v, np.array([0, 1, 0, 1, 2, 0, 1, 0, 1, 2]))
v = event.encode(n_user=3,
n_item=3,
index=True,
feature=False,
context=False,
vertical=True)
assert_array_equal(v, np.array([[0], [1], [0], [0], [1], [0]]))
async def process(stream):
async for obj in stream:
event = json.loads(obj)
if event["rating"] < 3:
continue
user, item = User(event["user"] - 1), Item(event["item"] - 1)
print(recommender.recommend(user, np.arange(0, n_item)))
recommender.update(Event(user, item))
def setUp(self):
recommender = Popular()
recommender.initialize()
self.evaluator = Evaluator(recommender=recommender, repeat=False)
self.samples = [
Event(User(0), Item(0), 1),
Event(User(0), Item(1), 1),
Event(User(1), Item(2), 1),
Event(User(0), Item(3), 1),
Event(User(2), Item(4), 1),
Event(User(1), Item(4), 1),
Event(User(0), Item(5), 1),
Event(User(2), Item(1), 1),
Event(User(0), Item(6), 1),
Event(User(2), Item(0), 1),
]
def test_register_item(self):
self.recommender.register(Item(0))
self.assertEqual(self.recommender.n_item, 1)
def test_update(self):
self.recommender.register(User(0))
self.recommender.register(Item(0))
self.recommender.update(Event(User(0), Item(0), 1))
self.assertEqual(self.recommender.n_user, 1)
self.assertEqual(self.recommender.n_item, 1)
app = faust.App(
"flurs-recommender",
broker="kafka://localhost:9092",
value_serializer="raw",
)
topic = app.topic("flurs-events", value_type=bytes)
recommender = MFRecommender(k=40)
recommender.initialize()
n_user, n_item = 943, 1682
for u in range(1, n_user + 1):
recommender.register(User(u - 1))
for i in range(1, n_item + 1):
recommender.register(Item(i - 1))
@app.agent(topic)
async def process(stream):
async for obj in stream:
event = json.loads(obj)
if event["rating"] < 3:
continue
user, item = User(event["user"] - 1), Item(event["item"] - 1)
print(recommender.recommend(user, np.arange(0, n_item)))
recommender.update(Event(user, item))