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 test_merge(self):
expected = bytearray(4)
expected[0] = 1
expected[3] = 1
hll = HyperLogLog(2)
hll2 = HyperLogLog(2)
hll.set_register(0, 1)
hll2.set_register(3, 1)
hll.merge(hll2)
self.assertEqual(hll.registers(), expected)
def test_merge(self):
expected = bytearray(4)
expected[0] = 1
expected[3] = 1
hll = HyperLogLog(2)
hll2 = HyperLogLog(2)
hll.set_register(0, 1)
hll2.set_register(3, 1)
hll.merge(hll2)
self.assertEqual(hll.registers(), expected)
def test_only_same_size_HyperLogLogs_can_be_merged(self):
hll = HyperLogLog(4)
hll2 = HyperLogLog(5)
with self.assertRaises(ValueError):
hll.merge(hll2)
def test_only_same_size_HyperLogLogs_can_be_merged(self):
hll = HyperLogLog(4)
hll2 = HyperLogLog(5)
with self.assertRaises(ValueError):
hll.merge(hll2)
