def _hll_merge(v: pd.DataFrame) -> bytes:
hll_res = HyperLogLog(k)
hll = HyperLogLog(k)
for x in v:
hll.set_registers(bytearray(x))
hll_res.merge(hll)
return hll_res.registers()
def _hll_merge(v):
hll_res = HyperLogLog(k)
hll = HyperLogLog(k)
for x in v:
hll.set_registers(bytearray(x))
hll_res.merge(hll)
return hll_res.registers()
def _hll_init_agg(v: pd.DataFrame) -> bytes:
hll_res = HyperLogLog(k)
hll = HyperLogLog(k)
for x in v:
if isinstance(x, (bytes, bytearray)):
hll.set_registers(bytearray(x))
hll_res.merge(hll)
elif x is not None:
hll_res.add(str(x))
return hll_res.registers()
def _stats_from_json(json: Dict[str, Any]) -> Dict[str, Any]:
stats = {}
if 'messages_sent' in json:
stats['messages_sent'] = json['messages_sent']
if 'messages_received' in json:
stats['messages_received'] = json['messages_received']
if 'users_active' in json:
hll = HyperLogLog(12)
hll.set_registers(bytearray(json['users_active']))
stats['users_active'] = hll
return stats
class TestRegisterFunctions(unittest.TestCase):
def setUp(self):
self.k = 5
self.hll = HyperLogLog(5)
def test_set_last_register(self):
self.hll.set_register(self.k - 1, 1)
self.assertTrue(self.hll.registers()[self.k - 1] == 1)
def test_set_first_register(self):
self.hll.set_register(0, 1)
self.assertTrue(self.hll.registers()[0] == 1)
def test_set_register_with_negative_value_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, -1)
def test_set_register_with_greater_than_max_rank_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, 33)
def test_set_register_with_index_out_of_bounds(self):
with self.assertRaises(IndexError):
self.hll.set_register(32, 1)
def test_set_register_with_negative_index_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, -1)
def test_bytesarray_has_correct_values(self):
expected = bytearray(randint(0, 16) for x in range(32))
for i in range(32):
self.hll.set_register(i, expected[i])
registers = self.hll.registers()
self.assertEqual(expected, registers)
def test_registers_returns_bytesarray(self):
self.assertTrue(type(self.hll.registers()) is bytearray)
def test_bytesarray_has_correct_length(self):
self.assertTrue(len(self.hll.registers()) == pow(2, self.k))
def test_set_registers(self):
expected = bytearray(randint(0, 16) for x in range(32))
self.hll.set_registers(expected)
registers=self.hll.registers()
self.assertEqual(expected, registers)
class TestRegisterFunctions(unittest.TestCase):
def setUp(self):
self.k = 5
self.hll = HyperLogLog(5)
def test_set_last_register(self):
self.hll.set_register(self.k - 1, 1)
self.assertTrue(self.hll.registers()[self.k - 1] == 1)
def test_set_first_register(self):
self.hll.set_register(0, 1)
self.assertTrue(self.hll.registers()[0] == 1)
def test_set_register_with_negative_value_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, -1)
def test_set_register_with_greater_than_max_rank_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, 33)
def test_set_register_with_index_out_of_bounds(self):
with self.assertRaises(IndexError):
self.hll.set_register(32, 1)
def test_set_register_with_negative_index_fails(self):
with self.assertRaises(ValueError):
self.hll.set_register(0, -1)
def test_bytesarray_has_correct_values(self):
expected = bytearray(randint(0, 16) for x in range(32))
for i in range(32):
self.hll.set_register(i, expected[i])
registers = self.hll.registers()
self.assertEqual(expected, registers)
def test_registers_returns_bytesarray(self):
self.assertTrue(type(self.hll.registers()) is bytearray)
def test_bytesarray_has_correct_length(self):
self.assertTrue(len(self.hll.registers()) == pow(2, self.k))
def test_set_registers(self):
expected = bytearray(randint(0, 16) for x in range(32))
self.hll.set_registers(expected)
registers = self.hll.registers()
self.assertEqual(expected, registers)