def test_count(self):
"""
Test that count returns appropriately based on table state.
"""
s = MemoryKeyValueStore()
assert s.count() == 0
s._table = {0: 0, 1: 1, 'a': True, None: False}
assert s.count() == 4
def test_count(self):
"""
Test that count returns appropriately based on table state.
"""
s = MemoryKeyValueStore()
assert s.count() == 0
s._table = {
0: 0,
1: 1,
'a': True,
None: False
}
assert s.count() == 4
def test_update_index_no_existing_index(self):
# Test that calling update_index with no existing index acts like
# building the index fresh. This test is basically the same as
# test_build_index_fresh_build but using update_index instead.
descr_set = MemoryDescriptorSet()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(), descr_set,
hash_kvs)
descriptors = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
# Vectors of length 1 for easy dummy hashing prediction.
for d in descriptors:
d.set_vector(np.ones(1, float) * d.uuid())
index.update_index(descriptors)
# Make sure descriptors are now in attached index and in key-value-store
self.assertEqual(descr_set.count(), 5)
for d in descriptors:
self.assertIn(d, descr_set)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_build_index_fresh_build(self):
descr_set = MemoryDescriptorSet()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(), descr_set,
hash_kvs)
descriptors = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
# Vectors of length 1 for easy dummy hashing prediction.
for i, d in enumerate(descriptors):
d.set_vector(np.ones(1, float) * i)
index.build_index(descriptors)
# Make sure descriptors are now in attached index and in
# key-value-store.
self.assertEqual(descr_set.count(), 5)
for d in descriptors:
self.assertIn(d, descr_set)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_count_empty_hash2uid(self):
"""
Test that an empty hash-to-uid mapping results in a 0 return regardless
of descriptor-set state.
"""
descr_set = MemoryDescriptorSet()
hash_kvs = MemoryKeyValueStore()
self.assertEqual(descr_set.count(), 0)
self.assertEqual(hash_kvs.count(), 0)
lsh = LSHNearestNeighborIndex(DummyHashFunctor(), descr_set, hash_kvs)
self.assertEqual(lsh.count(), 0)
# Additions to the descriptor-set should not impact LSH index "size"
lsh.descriptor_set.add_descriptor(DescriptorMemoryElement('t', 0))
self.assertEqual(lsh.descriptor_set.count(), 1)
self.assertEqual(lsh.hash2uuids_kvstore.count(), 0)
self.assertEqual(lsh.count(), 0)
lsh.descriptor_set.add_descriptor(DescriptorMemoryElement('t', 1))
self.assertEqual(lsh.descriptor_set.count(), 2)
self.assertEqual(lsh.hash2uuids_kvstore.count(), 0)
self.assertEqual(lsh.count(), 0)
lsh.hash2uuids_kvstore.add(0, {0})
self.assertEqual(lsh.descriptor_set.count(), 2)
self.assertEqual(lsh.count(), 1)
lsh.hash2uuids_kvstore.add(0, {0, 1})
self.assertEqual(lsh.descriptor_set.count(), 2)
self.assertEqual(lsh.count(), 2)
lsh.hash2uuids_kvstore.add(0, {0, 1, 2})
self.assertEqual(lsh.descriptor_set.count(), 2)
self.assertEqual(lsh.count(), 3)
def test_update_index_no_existing_index(self):
# Test that calling update_index with no existing index acts like
# building the index fresh. This test is basically the same as
# test_build_index_fresh_build but using update_index instead.
descr_index = MemoryDescriptorIndex()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(),
descr_index, hash_kvs)
descriptors = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
# Vectors of length 1 for easy dummy hashing prediction.
for d in descriptors:
d.set_vector(np.ones(1, float) * d.uuid())
index.update_index(descriptors)
# Make sure descriptors are now in attached index and in key-value-store
self.assertEqual(descr_index.count(), 5)
for d in descriptors:
self.assertIn(d, descr_index)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_build_index_fresh_build(self):
descr_index = MemoryDescriptorIndex()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(),
descr_index, hash_kvs)
descriptors = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
# Vectors of length 1 for easy dummy hashing prediction.
for i, d in enumerate(descriptors):
d.set_vector(np.ones(1, float) * i)
index.build_index(descriptors)
# Make sure descriptors are now in attached index and in key-value-store
self.assertEqual(descr_index.count(), 5)
for d in descriptors:
self.assertIn(d, descr_index)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_count_empty_hash2uid(self):
"""
Test that an empty hash-to-uid mapping results in a 0 return regardless
of descriptor-set state.
"""
descr_set = MemoryDescriptorIndex()
hash_kvs = MemoryKeyValueStore()
self.assertEqual(descr_set.count(), 0)
self.assertEqual(hash_kvs.count(), 0)
lsh = LSHNearestNeighborIndex(DummyHashFunctor(), descr_set, hash_kvs)
self.assertEqual(lsh.count(), 0)
# Additions to the descriptor-set should not impact LSH index "size"
lsh.descriptor_index.add_descriptor(DescriptorMemoryElement('t', 0))
self.assertEqual(lsh.descriptor_index.count(), 1)
self.assertEqual(lsh.hash2uuids_kvstore.count(), 0)
self.assertEqual(lsh.count(), 0)
lsh.descriptor_index.add_descriptor(DescriptorMemoryElement('t', 1))
self.assertEqual(lsh.descriptor_index.count(), 2)
self.assertEqual(lsh.hash2uuids_kvstore.count(), 0)
self.assertEqual(lsh.count(), 0)
lsh.hash2uuids_kvstore.add(0, {0})
self.assertEqual(lsh.descriptor_index.count(), 2)
self.assertEqual(lsh.count(), 1)
lsh.hash2uuids_kvstore.add(0, {0, 1})
self.assertEqual(lsh.descriptor_index.count(), 2)
self.assertEqual(lsh.count(), 2)
lsh.hash2uuids_kvstore.add(0, {0, 1, 2})
self.assertEqual(lsh.descriptor_index.count(), 2)
self.assertEqual(lsh.count(), 3)
def test_update_index_add_new_descriptors(self):
# Test that calling update index after a build index causes index
# components to be properly updated.
descr_set = MemoryDescriptorSet()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(), descr_set,
hash_kvs)
descriptors1 = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
descriptors2 = [
DescriptorMemoryElement('t', 5),
DescriptorMemoryElement('t', 6),
]
# Vectors of length 1 for easy dummy hashing prediction.
for d in descriptors1 + descriptors2:
d.set_vector(np.ones(1, float) * d.uuid())
# Build initial index.
index.build_index(descriptors1)
self.assertEqual(descr_set.count(), 5)
for d in descriptors1:
self.assertIn(d, descr_set)
for d in descriptors2:
self.assertNotIn(d, descr_set)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
# Update index and check that components have new data.
index.update_index(descriptors2)
self.assertEqual(descr_set.count(), 7)
for d in descriptors1 + descriptors2:
self.assertIn(d, descr_set)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 7)
for i in range(7):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_update_index_add_new_descriptors(self):
# Test that calling update index after a build index causes index
# components to be properly updated.
descr_index = MemoryDescriptorIndex()
hash_kvs = MemoryKeyValueStore()
index = LSHNearestNeighborIndex(DummyHashFunctor(),
descr_index, hash_kvs)
descriptors1 = [
DescriptorMemoryElement('t', 0),
DescriptorMemoryElement('t', 1),
DescriptorMemoryElement('t', 2),
DescriptorMemoryElement('t', 3),
DescriptorMemoryElement('t', 4),
]
descriptors2 = [
DescriptorMemoryElement('t', 5),
DescriptorMemoryElement('t', 6),
]
# Vectors of length 1 for easy dummy hashing prediction.
for d in descriptors1 + descriptors2:
d.set_vector(np.ones(1, float) * d.uuid())
# Build initial index.
index.build_index(descriptors1)
self.assertEqual(descr_index.count(), 5)
for d in descriptors1:
self.assertIn(d, descr_index)
for d in descriptors2:
self.assertNotIn(d, descr_index)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 5)
for i in range(5):
self.assertSetEqual(hash_kvs.get(i), {i})
# Update index and check that components have new data.
index.update_index(descriptors2)
self.assertEqual(descr_index.count(), 7)
for d in descriptors1 + descriptors2:
self.assertIn(d, descr_index)
# Dummy hash function bins sum of descriptor vectors.
self.assertEqual(hash_kvs.count(), 7)
for i in range(7):
self.assertSetEqual(hash_kvs.get(i), {i})
def test_count(self):
s = MemoryKeyValueStore()
assert s.count() == 0
s._table = {0: 0, 1: 1, 'a': True, None: False}
assert s.count() == 4