def test_merge_sparse_with_sparse_to_dense(self):
hll1 = HyperLogLogPlusPlus(length=16, random_seed=234)
hll2 = HyperLogLogPlusPlus(length=16, random_seed=234)
for i in range(int(16 * 6 / 2)):
hll1.add(i)
hll2.add(i + 100)
merged_hll = hll1.merge(hll2)
self.assertTrue(merged_hll.sparse_mode,
'Merged sketch should be in sparse mode.')
self.assertEqual(merged_hll.estimate_cardinality(), 96,
'Estimated cardinality not correct under sparse mode.')
hll1.add(1000)
merged_hll = hll1.merge(hll2)
self.assertFalse(merged_hll.sparse_mode,
'Merged sketch should not be in sparse mode.')
self.assertAlmostEqual(
merged_hll.estimate_cardinality(), 97, delta=97 * 0.05,
msg='Estimated cardinality not correct under dense mode.'
)
def test_merge_sparse_with_sparse_to_sparse(self):
hll1 = HyperLogLogPlusPlus(length=16, random_seed=234)
hll1.add(1)
hll2 = HyperLogLogPlusPlus(length=16, random_seed=234)
hll2.add(1)
merged_hll = hll1.merge(hll2)
self.assertTrue(merged_hll.sparse_mode,
'Merged sketch is not in sparse mode.')
self.assertTrue(all(hll1.buckets == merged_hll.buckets),
'Merged sketch is not correct.')
self.assertSameElements(merged_hll.temp_set, set([1]),
'Temp set is not correct.')
self.assertEqual(merged_hll.estimate_cardinality(), 1,
'Estimated cardinality is not correct.')
def test_merge_dense_with_dense(self):
hll1 = HyperLogLogPlusPlus(length=16, random_seed=234)
hll2 = HyperLogLogPlusPlus(length=16, random_seed=234)
for i in range(16 * 6 + 1):
hll1.add(i)
hll2.add(i + 100)
merged_hll = hll1.merge(hll2)
self.assertFalse(merged_hll.sparse_mode,
'Merged sketch should not be in sparse mode.')
self.assertGreater(sum(hll2.buckets == merged_hll.buckets), 0,
'Merged sketch is not correct.')
self.assertSameElements(merged_hll.temp_set, set(),
'Temp set is not correct.')
self.assertAlmostEqual(
merged_hll.estimate_cardinality(), 194, delta=194 * 0.1
)
def test_merge_sparse_with_dense(self):
hll1 = HyperLogLogPlusPlus(length=16, random_seed=234)
hll1.add(100)
hll2 = HyperLogLogPlusPlus(length=16, random_seed=234)
for i in range(16 * 6 + 1):
hll2.add(i)
merged_hll = hll1.merge(hll2)
self.assertFalse(merged_hll.sparse_mode,
'Merged sketch should not be in sparse mode.')
# Should change one bucket value given this random seed.
self.assertEqual(sum(hll2.buckets == merged_hll.buckets), 16 - 1,
'Merged sketch is not correct.')
self.assertSameElements(merged_hll.temp_set, set(),
'Temp set is not correct.')
self.assertGreater(merged_hll.estimate_cardinality(),
hll2.estimate_cardinality())