def test_update_index_new_index(self):
# Virtually the same as `test_build_index` but using update_index.
bt = SkLearnBallTreeHashIndex(random_seed=0)
# Make 1000 random bit vectors of length 256
m = np.random.randint(0, 2, 1000 * 256).reshape(1000, 256).astype(bool)
bt.update_index(m)
# deterministically sort index of built and source data to determine
# that an index was built.
self.assertIsNotNone(bt.bt)
np.testing.assert_array_almost_equal(
sorted(np.array(bt.bt.data).tolist()), sorted(m.tolist()))
def test_update_index_additive(self):
# Test updating an existing index, i.e. rebuilding using the union of
# previous and new data.
bt = SkLearnBallTreeHashIndex(random_seed=0)
# Make 1000 random bit vectors of length 256
m1 = np.random.randint(0, 2, 1000 * 256).reshape(1000, 256)\
.astype(bool)
m2 = np.random.randint(0, 2, 100 * 256).reshape(100, 256).astype(bool)
# Build initial index
bt.build_index(m1)
# Current model should only contain m1's data.
np.testing.assert_array_almost_equal(
sorted(np.array(bt.bt.data).tolist()), sorted(m1.tolist()))
# "Update" index with new hashes
bt.update_index(m2)
# New model should contain the union of the data.
np.testing.assert_array_almost_equal(
sorted(np.array(bt.bt.data).tolist()),
sorted(np.concatenate([m1, m2], 0).tolist()))