def test_insert_same(self):
hll = HyperLogLogPlusPlus(random_seed=42)
hll.add(1)
card_one = hll.estimate_cardinality()
hll.add(1)
self.assertEqual(card_one, hll.estimate_cardinality())
def insertion_test_helper(self, number_to_insert, acceptable_error=.05):
hll = HyperLogLogPlusPlus(random_seed=137)
for i in range(number_to_insert):
hll.add(i)
error_ratio = hll.estimate_cardinality() / number_to_insert
self.assertAlmostEqual(error_ratio, 1.0, delta=acceptable_error)
def test_simple_estimate_smaller(self):
hll = HyperLogLogPlusPlus(length=self.vector_length,
random_seed=42,
num_integer_bits=self.num_integer_bits)
one_vector = np.ones(self.vector_length)
hll.buckets = one_vector
alpha_16 = 0.673
hll_should_estimate = alpha_16 * self.vector_length**2 * 2 / self.vector_length
self.assertEqual(alpha_16, hll.alpha)
self.assertEqual(hll.estimate_cardinality(), hll_should_estimate)
def test_simple_estimate_larger(self):
m = 2**14
hll = HyperLogLogPlusPlus(length=m,
random_seed=42,
num_integer_bits=self.num_integer_bits)
thirty_vector = 30 * np.ones(m)
hll.buckets = thirty_vector
alpha_m = 0.7213 / (1 + 1.079 / m)
hll_should_estimate = alpha_m * m**2 * 2**30 / m
self.assertEqual(alpha_m, hll.alpha)
self.assertEqual(hll.estimate_cardinality(), hll_should_estimate)
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())
