Skip to content

Commit

Permalink
test(distance): unit tests for distance (#216)
Browse files Browse the repository at this point in the history
  • Loading branch information
@azayz
azayz authored Mar 21, 2022
1 parent eb92f14 commit 3f4774a
Show file tree
Hide file tree
Showing 4 changed files with 402 additions and 0 deletions.
126 changes: 126 additions & 0 deletions tests/unit/math/distance/test_numpy.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,126 @@
import numpy as np
import pytest
from scipy.sparse import csr_matrix

from docarray.math.distance.numpy import (
cosine,
euclidean,
sparse_cosine,
sparse_euclidean,
sparse_sqeuclidean,
sqeuclidean,
)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
np.array([[1, 2, 3], [4, 5, 6]]),
np.array([[1, 2, 3], [4, 5, 6]]),
np.array(
[[0.00000000e00, 2.53681537e-02], [2.53681537e-02, 2.22044605e-16]]
),
),
(np.array([[1, 2, 3]]), np.array([[1, 2, 3]]), np.array([[0]])),
(np.array([[0, 0, 0]]), np.array([[0, 0, 0]]), np.array([[0]])),
(np.array([[1, 2, 3]]), np.array([[19, 53, 201]]), np.array([[0.06788693]])),
),
)
def test_cosine(x_mat, y_mat, result):
np.testing.assert_allclose(cosine(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
csr_matrix([[1, 2, 3], [4, 5, 6]]),
csr_matrix([[1, 2, 3], [4, 5, 6]]),
np.array(
[[0.00000000e00, 2.53681537e-02], [2.53681537e-02, 2.22044605e-16]]
),
),
(csr_matrix([[1, 2, 3]]), csr_matrix([[1, 2, 3]]), np.array([[0]])),
(csr_matrix([[0, 0, 0]]), csr_matrix([[0, 0, 0]]), np.array([[np.nan]])),
(
csr_matrix([[1, 2, 3]]),
csr_matrix([[19, 53, 201]]),
np.array([[0.06788693]]),
),
),
)
def test_sparse_cosine(x_mat, y_mat, result):
np.testing.assert_allclose(sparse_cosine(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
np.array([[1, 2, 3], [4, 5, 6]]),
np.array([[1, 2, 3], [4, 5, 6]]),
np.array([[0, 27], [27, 0]]),
),
(np.array([[1, 2, 3]]), np.array([[1, 2, 3]]), np.array([[0]])),
(np.array([[0, 0, 0]]), np.array([[0, 0, 0]]), np.array([[0]])),
(np.array([[1, 2, 3]]), np.array([[19, 53, 201]]), np.array([[42129]])),
),
)
def test_sqeuclidean(x_mat, y_mat, result):
np.testing.assert_allclose(sqeuclidean(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
csr_matrix([[1, 2, 3], [4, 5, 6]]),
csr_matrix([[1, 2, 3], [4, 5, 6]]),
np.array([[0, 27], [27, 0]]),
),
(csr_matrix([[1, 2, 3]]), csr_matrix([[1, 2, 3]]), np.array([[0]])),
(csr_matrix([[0, 0, 0]]), csr_matrix([[0, 0, 0]]), np.array([[0]])),
(csr_matrix([[1, 2, 3]]), csr_matrix([[19, 53, 201]]), np.array([[42129]])),
),
)
def test_sparse_sqeuclidean(x_mat, y_mat, result):
np.testing.assert_allclose(sparse_sqeuclidean(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
np.array([[1, 2, 3], [4, 5, 6]]),
np.array([[1, 2, 3], [4, 5, 6]]),
np.array([[0, 5.19615242], [5.19615242, 0]]),
),
(np.array([[1, 2, 3]]), np.array([[1, 2, 3]]), np.array([[0]])),
(np.array([[0, 0, 0]]), np.array([[0, 0, 0]]), np.array([[0]])),
(np.array([[1, 2, 3]]), np.array([[19, 53, 201]]), np.array([[205.2535018]])),
),
)
def test_euclidean(x_mat, y_mat, result):
np.testing.assert_allclose(euclidean(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
csr_matrix([[1, 2, 3], [4, 5, 6]]),
csr_matrix([[1, 2, 3], [4, 5, 6]]),
np.array([[0, 5.19615242], [5.19615242, 0]]),
),
(csr_matrix([[1, 2, 3]]), csr_matrix([[1, 2, 3]]), np.array([[0]])),
(csr_matrix([[0, 0, 0]]), csr_matrix([[0, 0, 0]]), np.array([[0]])),
(
csr_matrix([[1, 2, 3]]),
csr_matrix([[19, 53, 201]]),
np.array([[205.2535018]]),
),
),
)
def test_sparse_euclidean(x_mat, y_mat, result):
np.testing.assert_allclose(sparse_euclidean(x_mat, y_mat), result, rtol=1e-5)
92 changes: 92 additions & 0 deletions tests/unit/math/distance/test_paddle.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,92 @@
import numpy as np
import paddle
import pytest

from docarray.math.distance.paddle import cosine, euclidean, sqeuclidean


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
np.array([[1.192093e-07, 2.53681537e-02], [2.53681537e-02, 0]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
np.array([[1.192093e-07]]),
),
(
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
np.array([[1]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[19, 53, 201]], dtype='float32'),
np.array([[0.06788693]]),
),
),
)
def test_cosine(x_mat, y_mat, result):
np.testing.assert_allclose(cosine(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
np.array([[0, 27], [27, 0]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
np.array([[0]]),
),
(
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
np.array([[0]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[19, 53, 201]], dtype='float32'),
np.array([[42129]]),
),
),
)
def test_sqeuclidean(x_mat, y_mat, result):
np.testing.assert_allclose(sqeuclidean(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32'),
np.array([[0, 5.19615242], [5.19615242, 0]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
np.array([[0]]),
),
(
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
paddle.to_tensor([[0, 0, 0]], dtype='float32'),
np.array([[0]]),
),
(
paddle.to_tensor([[1, 2, 3]], dtype='float32'),
paddle.to_tensor([[19, 53, 201]], dtype='float32'),
np.array([[205.2535018]]),
),
),
)
def test_euclidean(x_mat, y_mat, result):
np.testing.assert_allclose(euclidean(x_mat, y_mat), result, rtol=1e-5)
92 changes: 92 additions & 0 deletions tests/unit/math/distance/test_tensorflow.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,92 @@
import numpy as np
import pytest
import tensorflow as tf

from docarray.math.distance.tensorflow import cosine, euclidean, sqeuclidean


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
np.array([[1.192093e-07, 2.53681537e-02], [2.53681537e-02, 0.000000e00]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[1, 2, 3]], dtype=tf.float32),
np.array([[1.192093e-07]]),
),
(
tf.constant([[0, 0, 0]], dtype=tf.float32),
tf.constant([[0, 0, 0]], dtype=tf.float32),
np.array([[1]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[19, 53, 201]], dtype=tf.float32),
np.array([[0.06788693]]),
),
),
)
def test_cosine(x_mat, y_mat, result):
np.testing.assert_allclose(cosine(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
np.array([[0, 27], [27, 0]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[1, 2, 3]], dtype=tf.float32),
np.array([[0]]),
),
(
tf.constant([[0, 0, 0]], dtype=tf.float32),
tf.constant([[0, 0, 0]], dtype=tf.float32),
np.array([[0]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[19, 53, 201]], dtype=tf.float32),
np.array([[42129]]),
),
),
)
def test_sqeuclidean(x_mat, y_mat, result):
np.testing.assert_allclose(sqeuclidean(x_mat, y_mat), result, rtol=1e-5)


@pytest.mark.parametrize(
'x_mat, y_mat, result',
(
(
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32),
np.array([[0, 5.19615242], [5.19615242, 0]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[1, 2, 3]], dtype=tf.float32),
np.array([[0]]),
),
(
tf.constant([[0, 0, 0]], dtype=tf.float32),
tf.constant([[0, 0, 0]], dtype=tf.float32),
np.array([[0]]),
),
(
tf.constant([[1, 2, 3]], dtype=tf.float32),
tf.constant([[19, 53, 201]], dtype=tf.float32),
np.array([[205.2535018]]),
),
),
)
def test_euclidean(x_mat, y_mat, result):
np.testing.assert_allclose(euclidean(x_mat, y_mat), result, rtol=1e-5)
Loading

0 comments on commit 3f4774a

Please sign in to comment.