def test_grad_metrics_match_metrics(spatial_data, spatial_distances):
for metric in dist.named_distances_with_gradients:
if metric in spatial_distances:
spatial_check(metric,
spatial_data,
spatial_distances,
with_grad=True)
# Handle the few special distances separately
# SEuclidean
v = np.abs(np.random.randn(spatial_data.shape[1]))
dist_matrix = pairwise_distances(spatial_data, metric="seuclidean", V=v)
test_matrix = np.array([[
dist.standardised_euclidean_grad(spatial_data[i], spatial_data[j],
v)[0]
for j in range(spatial_data.shape[0])
] for i in range(spatial_data.shape[0])])
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match "
"for metric seuclidean",
)
# Weighted minkowski
dist_matrix = pairwise_distances(spatial_data,
metric="wminkowski",
w=v,
p=3)
test_matrix = np.array([[
dist.weighted_minkowski_grad(spatial_data[i], spatial_data[j], v,
p=3)[0]
for j in range(spatial_data.shape[0])
] for i in range(spatial_data.shape[0])])
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match "
"for metric weighted_minkowski",
)
# Mahalanobis
v = np.abs(np.random.randn(spatial_data.shape[1], spatial_data.shape[1]))
dist_matrix = pairwise_distances(spatial_data, metric="mahalanobis", VI=v)
test_matrix = np.array([[
dist.mahalanobis_grad(spatial_data[i], spatial_data[j], v)[0]
for j in range(spatial_data.shape[0])
] for i in range(spatial_data.shape[0])])
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match "
"for metric mahalanobis",
)
# Hellinger
dist_matrix = dist.pairwise_special_metric(np.abs(spatial_data[:-2]),
np.abs(spatial_data[:-2]))
test_matrix = np.array([[
dist.hellinger_grad(np.abs(spatial_data[i]),
np.abs(spatial_data[j]))[0]
for j in range(spatial_data.shape[0] - 2)
] for i in range(spatial_data.shape[0] - 2)])
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match "
"for metric hellinger",
)
def test_grad_metrics_match_metrics():
for metric in dist.named_distances_with_gradients:
if metric in spatial_distances:
dist_matrix = pairwise_distances(spatial_data, metric=metric)
# scipy is bad sometimes
if metric == "braycurtis":
dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0
if metric in ("cosine", "correlation"):
dist_matrix[np.where(~np.isfinite(dist_matrix))] = 1.0
# And because distance between all zero vectors should be zero
dist_matrix[10, 11] = 0.0
dist_matrix[11, 10] = 0.0
dist_function = dist.named_distances_with_gradients[metric]
test_matrix = np.array(
[
[
dist_function(spatial_data[i], spatial_data[j])[0]
for j in range(spatial_data.shape[0])
]
for i in range(spatial_data.shape[0])
]
)
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances with grad don't match "
"for metric {}".format(metric),
)
# Handle the few special distances separately
# SEuclidean
v = np.abs(np.random.randn(spatial_data.shape[1]))
dist_matrix = pairwise_distances(spatial_data, metric="seuclidean", V=v)
test_matrix = np.array(
[
[
dist.standardised_euclidean_grad(spatial_data[i], spatial_data[j], v)[0]
for j in range(spatial_data.shape[0])
]
for i in range(spatial_data.shape[0])
]
)
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match " "for metric seuclidean",
)
# Weighted minkowski
dist_matrix = pairwise_distances(spatial_data, metric="wminkowski", w=v, p=3)
test_matrix = np.array(
[
[
dist.weighted_minkowski_grad(spatial_data[i], spatial_data[j], v, p=3)[
0
]
for j in range(spatial_data.shape[0])
]
for i in range(spatial_data.shape[0])
]
)
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match " "for metric weighted_minkowski",
)
# Mahalanobis
v = np.abs(np.random.randn(spatial_data.shape[1], spatial_data.shape[1]))
dist_matrix = pairwise_distances(spatial_data, metric="mahalanobis", VI=v)
test_matrix = np.array(
[
[
dist.mahalanobis_grad(spatial_data[i], spatial_data[j], v)[0]
for j in range(spatial_data.shape[0])
]
for i in range(spatial_data.shape[0])
]
)
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match " "for metric mahalanobis",
)
# Hellinger
dist_matrix = dist.pairwise_special_metric(
np.abs(spatial_data[:-2]), np.abs(spatial_data[:-2])
)
test_matrix = np.array(
[
[
dist.hellinger_grad(np.abs(spatial_data[i]), np.abs(spatial_data[j]))[0]
for j in range(spatial_data.shape[0] - 2)
]
for i in range(spatial_data.shape[0] - 2)
]
)
assert_array_almost_equal(
test_matrix,
dist_matrix,
err_msg="Distances don't match " "for metric hellinger",
)
def test_chunked_parallel_special_metric_implementation_hellinger(
spatial_data,
stashed_previous_impl_for_regression_test,
):
# Base tests that must pass!
dist_matrix_x = dist.chunked_parallel_special_metric(
np.abs(spatial_data[:-2]))
dist_matrix_xy = dist.chunked_parallel_special_metric(
np.abs(spatial_data[:-2]), np.abs(spatial_data[:-2]))
test_matrix = np.array([[
dist.hellinger_grad(np.abs(spatial_data[i]),
np.abs(spatial_data[j]))[0]
for j in range(spatial_data.shape[0] - 2)
] for i in range(spatial_data.shape[0] - 2)]).astype(np.float32)
assert_array_equal(
test_matrix,
dist_matrix_x,
err_msg="Distances don't match for metric hellinger",
)
assert_array_equal(
test_matrix,
dist_matrix_xy,
err_msg="Distances don't match for metric hellinger",
)
# Test to compare chunked_parallel different implementations
dist_x_stashed = stashed_previous_impl_for_regression_test(
np.abs(spatial_data[:-2]))
dist_xy_stashed = stashed_previous_impl_for_regression_test(
np.abs(spatial_data[:-2]), np.abs(spatial_data[:-2]))
assert_array_equal(
dist_xy_stashed,
dist_matrix_xy,
err_msg=
"Distances don't match between stashed and current chunked_parallel implementations with X and Y!",
)
assert_array_equal(
dist_x_stashed,
dist_matrix_x,
err_msg=
"Distances don't match between stashed and current chunked_parallel implementations with X only!",
)
# test hellinger on different X and Y Pair
spatial_data_two = np.random.randn(10, 20)
dist_stashed_diff_pair = stashed_previous_impl_for_regression_test(
np.abs(spatial_data[:-2]), spatial_data_two)
dist_chunked_diff_pair = dist.chunked_parallel_special_metric(
np.abs(spatial_data[:-2]), spatial_data_two)
assert_array_equal(
dist_stashed_diff_pair,
dist_chunked_diff_pair,
err_msg=
"Distances don't match between stashed and current chunked_parallel implementations",
)
