def test_remove_from_index_last_element_with_cache(self):
"""
Test removing final element also clears the cache element.
"""
c = DataMemoryElement()
bt = SkLearnBallTreeHashIndex(cache_element=c, random_seed=0)
index = np.ndarray((1, 256), bool)
index[0] = int_to_bit_vector_large(1, 256)
bt.build_index(index)
self.assertEqual(bt.count(), 1)
self.assertFalse(c.is_empty())
bt.remove_from_index(index)
self.assertEqual(bt.count(), 0)
self.assertTrue(c.is_empty())
def test_remove_from_index(self):
# Test that we actually remove from the index.
bt = SkLearnBallTreeHashIndex(random_seed=0)
index = np.ndarray((1000, 256), bool)
for i in range(1000):
index[i] = int_to_bit_vector_large(i, 256)
bt.build_index(index)
# Copy post-build index for checking no removal occurred
bt_data = np.copy(bt.bt.data)
bt.remove_from_index([
int_to_bit_vector_large(42, 256),
int_to_bit_vector_large(998, 256),
])
# Make sure expected arrays are missing from data block.
new_data = np.asarray(bt.bt.data)
self.assertEqual(new_data.shape, (998, 256))
new_data_set = set(tuple(r) for r in new_data.tolist())
self.assertNotIn(tuple(int_to_bit_vector_large(42, 256)), new_data_set)
self.assertNotIn(tuple(int_to_bit_vector_large(998, 256)),
new_data_set)
def test_remove_from_index(self):
# Test that we actually remove from the index.
bt = SkLearnBallTreeHashIndex(random_seed=0)
index = np.ndarray((1000, 256), bool)
for i in range(1000):
index[i] = int_to_bit_vector_large(i, 256)
bt.build_index(index)
# BallTree data should now contain 1000 entries
self.assertEqual(bt.bt.data.shape, (1000, 256))
bt.remove_from_index([
int_to_bit_vector_large(42, 256),
int_to_bit_vector_large(998, 256),
])
# Make sure data block is of the expected shape (two rows shorter)
new_data = np.asarray(bt.bt.data)
self.assertEqual(new_data.shape, (998, 256))
# Make sure expected arrays are missing from data block.
new_data_set = set(tuple(r) for r in new_data.tolist())
self.assertNotIn(tuple(int_to_bit_vector_large(42, 256)), new_data_set)
self.assertNotIn(tuple(int_to_bit_vector_large(998, 256)),
new_data_set)
def test_remove_from_index_last_element(self):
"""
Test removing the final the only element / final elements from the
index.
"""
# Add one hash, remove one hash.
bt = SkLearnBallTreeHashIndex(random_seed=0)
index = np.ndarray((1, 256), bool)
index[0] = int_to_bit_vector_large(1, 256)
bt.build_index(index)
self.assertEqual(bt.count(), 1)
bt.remove_from_index(index)
self.assertEqual(bt.count(), 0)
self.assertIsNone(bt.bt)
# Add many hashes, remove many hashes in batches until zero
bt = SkLearnBallTreeHashIndex(random_seed=0)
index = np.ndarray((1000, 256), bool)
for i in range(1000):
index[i] = int_to_bit_vector_large(i, 256)
bt.build_index(index)
# Remove first 250
bt.remove_from_index(index[:250])
self.assertEqual(bt.count(), 750)
self.assertIsNotNone(bt.bt)
# Remove second 250
bt.remove_from_index(index[250:500])
self.assertEqual(bt.count(), 500)
self.assertIsNotNone(bt.bt)
# Remove third 250
bt.remove_from_index(index[500:750])
self.assertEqual(bt.count(), 250)
self.assertIsNotNone(bt.bt)
# Remove final 250
bt.remove_from_index(index[750:])
self.assertEqual(bt.count(), 0)
self.assertIsNone(bt.bt)