def test_abund_similarity_zero():
E1 = MinHash(n=5, ksize=20, track_abundance=True)
E2 = MinHash(n=5, ksize=20, track_abundance=True)
for i in [1]:
E1.add_hash(i)
assert E1.similarity(E2) == 0.0
def test_abund_similarity_zero():
E1 = MinHash(n=5, ksize=20, track_abundance=True)
E2 = MinHash(n=5, ksize=20, track_abundance=True)
for i in [1]:
E1.add_hash(i)
assert E1.similarity(E2) == 0.0
def test_diff_seed(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance, seed=1)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance, seed=2)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
with pytest.raises(ValueError):
E1.count_common(E2)
def test_common_1(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
assert E1.count_common(E2) == 4
assert E2.count_common(E1) == 4
def test_diff_seed(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance, seed=1)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance, seed=2)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
with pytest.raises(ValueError):
E1.count_common(E2)
def test_common_1(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
assert E1.count_common(E2) == 4
assert E2.count_common(E1) == 4
def test_jaccard_2_difflen(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4]:
E2.add_hash(i)
print(E1.jaccard(E2))
assert round(E1.jaccard(E2), 2) == 4 / 5.0
assert round(E2.jaccard(E1), 2) == 4 / 5.0
def test_jaccard_2_difflen(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4]:
E2.add_hash(i)
print(E1.jaccard(E2))
assert round(E1.jaccard(E2), 2) == 4 / 5.0
assert round(E2.jaccard(E1), 2) == 4 / 5.0
def test_abund_similarity():
E1 = MinHash(n=5, ksize=20, track_abundance=True)
E2 = MinHash(n=5, ksize=20, track_abundance=True)
for i in [1]:
E1.add_hash(i)
for i in [1, 2]:
E2.add_hash(i)
assert round(E1.similarity(E1)) == 1.0
assert round(E1.similarity(E2), 2) == 0.5
assert round(E1.similarity(E1, ignore_abundance=True)) == 1.0
assert round(E1.similarity(E2, ignore_abundance=True), 2) == 0.5
def test_jaccard_1(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
# here the union is [1, 2, 3, 4, 5]
# and the intesection is [1, 2, 3, 4] => 4/5.
assert round(E1.jaccard(E2), 2) == round(4 / 5.0, 2)
assert round(E2.jaccard(E1), 2) == round(4 / 5.0, 2)
def test_jaccard_1(track_abundance):
E1 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
E2 = MinHash(n=5, ksize=20, track_abundance=track_abundance)
for i in [1, 2, 3, 4, 5]:
E1.add_hash(i)
for i in [1, 2, 3, 4, 6]:
E2.add_hash(i)
# here the union is [1, 2, 3, 4, 5]
# and the intesection is [1, 2, 3, 4] => 4/5.
assert round(E1.jaccard(E2), 2) == round(4 / 5.0, 2)
assert round(E2.jaccard(E1), 2) == round(4 / 5.0, 2)
def test_abund_similarity():
E1 = MinHash(n=5, ksize=20, track_abundance=True)
E2 = MinHash(n=5, ksize=20, track_abundance=True)
for i in [1]:
E1.add_hash(i)
for i in [1, 2]:
E2.add_hash(i)
assert round(E1.similarity(E1)) == 1.0
assert round(E1.similarity(E2), 2) == 0.5
assert round(E1.similarity(E1, ignore_abundance=True)) == 1.0
assert round(E1.similarity(E2, ignore_abundance=True), 2) == 0.5