def test_transformer_equivalence():
N_NEIGHBORS = 15
EPSILON = 0.15
train = nn_data[:400]
test = nn_data[:200]
# Note we shift N_NEIGHBORS to conform to sklearn's KNeighborTransformer defn
nnd = NNDescent(data=train,
n_neighbors=N_NEIGHBORS + 1,
random_state=42,
compressed=False)
indices, dists = nnd.query(test, k=N_NEIGHBORS, epsilon=EPSILON)
sort_idx = np.argsort(indices, axis=1)
indices_sorted = np.vstack(
[indices[i, sort_idx[i]] for i in range(sort_idx.shape[0])])
dists_sorted = np.vstack(
[dists[i, sort_idx[i]] for i in range(sort_idx.shape[0])])
# Note we shift N_NEIGHBORS to conform to sklearn' KNeighborTransformer defn
transformer = PyNNDescentTransformer(n_neighbors=N_NEIGHBORS,
search_epsilon=EPSILON,
random_state=42).fit(
train, compress_index=False)
Xt = transformer.transform(test).sorted_indices()
assert np.all(Xt.indices == indices_sorted.flatten())
assert np.allclose(Xt.data, dists_sorted.flat)
def test_transformer_pickle_unpickle():
seed = np.random.RandomState(42)
x1 = seed.normal(0, 100, (1000, 50))
x2 = seed.normal(0, 100, (1000, 50))
index1 = PyNNDescentTransformer(n_neighbors=10).fit(x1)
result1 = index1.transform(x2)
pickle.dump(index1, open("test_tmp.pkl", "wb"))
index2 = pickle.load(open("test_tmp.pkl", "rb"))
os.remove("test_tmp.pkl")
result2 = index2.transform(x2)
np.testing.assert_equal(result1.indices, result2.indices)
np.testing.assert_equal(result1.data, result2.data)
def test_transformer_pickle_unpickle():
seed = np.random.RandomState(42)
x1 = seed.normal(0, 100, (1000, 50))
x2 = seed.normal(0, 100, (1000, 50))
index1 = PyNNDescentTransformer(n_neighbors=10).fit(x1)
result1 = index1.transform(x2)
mem_temp = io.BytesIO()
pickle.dump(index1, mem_temp)
mem_temp.seek(0)
index2 = pickle.load(mem_temp)
result2 = index2.transform(x2)
np.testing.assert_equal(result1.indices, result2.indices)
np.testing.assert_equal(result1.data, result2.data)
def test_transformer_equivalence():
N_NEIGHBORS = 15
QUEUE_SIZE = 5.0
train = nn_data[:400]
test = nn_data[:200]
nnd = NNDescent(data=train, n_neighbors=N_NEIGHBORS, random_state=42)
indices, dists = nnd.query(test, k=N_NEIGHBORS, queue_size=QUEUE_SIZE)
sort_idx = np.argsort(indices, axis=1)
indices_sorted = np.vstack(
[indices[i, sort_idx[i]] for i in range(sort_idx.shape[0])]
)
dists_sorted = np.vstack([dists[i, sort_idx[i]] for i in range(sort_idx.shape[0])])
transformer = PyNNDescentTransformer(
n_neighbors=N_NEIGHBORS, search_queue_size=QUEUE_SIZE, random_state=42
).fit(train)
Xt = transformer.transform(test).sorted_indices()
assert np.all(Xt.indices == indices_sorted.flat)
assert np.allclose(Xt.data, dists_sorted.flat)