Skip to content

TST use global_random_seed in sklearn/cross_decomposition/tests/test_pls.py #24526

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Mar 15, 2023
Merged

TST use global_random_seed in sklearn/cross_decomposition/tests/test_pls.py #24526

Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
5fd49b2
Add global_random_seed
yuanx749 Sep 28, 2022
18aa968
Merge remote-tracking branch 'upstream/main' into test_pls
yuanx749 Sep 28, 2022
fb21e27
[all random seeds]
yuanx749 Sep 28, 2022
7a5a8a1
Merge branch 'main' into test_pls
yuanx749 Oct 3, 2022
30f95e6
Merge remote-tracking branch 'upstream/main' into test_pls
yuanx749 Oct 9, 2022
444cde7
[all random seeds]
yuanx749 Oct 9, 2022
883dc68
Merge remote-tracking branch 'upstream/main' into test_pls
yuanx749 Oct 14, 2022
ebcca30
Merge remote-tracking branch 'upstream/main' into test_pls
yuanx749 Nov 13, 2022
00f0747
Merge remote-tracking branch 'upstream/main' into test_pls
yuanx749 Dec 21, 2022
bcc0451
[all random seeds]
yuanx749 Dec 21, 2022
8f68f13
mix between atol and rtol
jeremiedbb Mar 15, 2023
e3a20f2
Merge remote-tracking branch 'upstream/main' into pr/yuanx749/24526
jeremiedbb Mar 15, 2023
2e525d5
[all random seeds]
jeremiedbb Mar 15, 2023
7b9f728
lower tol [all random seeds]
jeremiedbb Mar 15, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 18 additions & 12 deletions sklearn/cross_decomposition/tests/test_pls.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,31 +484,35 @@ def test_n_components_upper_bounds(Estimator):


@pytest.mark.parametrize("n_samples, n_features", [(100, 10), (100, 200)])
@pytest.mark.parametrize("seed", range(10))
def test_singular_value_helpers(n_samples, n_features, seed):
def test_singular_value_helpers(n_samples, n_features, global_random_seed):
# Make sure SVD and power method give approximately the same results
X, Y = make_regression(n_samples, n_features, n_targets=5, random_state=seed)
X, Y = make_regression(
n_samples, n_features, n_targets=5, random_state=global_random_seed
)
u1, v1, _ = _get_first_singular_vectors_power_method(X, Y, norm_y_weights=True)
u2, v2 = _get_first_singular_vectors_svd(X, Y)

_svd_flip_1d(u1, v1)
_svd_flip_1d(u2, v2)

rtol = 1e-1
assert_allclose(u1, u2, rtol=rtol)
assert_allclose(v1, v2, rtol=rtol)
rtol = 1e-3
# Setting atol because some coordinates are very close to zero
assert_allclose(u1, u2, atol=u2.max() * rtol)
assert_allclose(v1, v2, atol=v2.max() * rtol)


def test_one_component_equivalence():
def test_one_component_equivalence(global_random_seed):
# PLSSVD, PLSRegression and PLSCanonical should all be equivalent when
# n_components is 1
X, Y = make_regression(100, 10, n_targets=5, random_state=0)
X, Y = make_regression(100, 10, n_targets=5, random_state=global_random_seed)
svd = PLSSVD(n_components=1).fit(X, Y).transform(X)
reg = PLSRegression(n_components=1).fit(X, Y).transform(X)
canonical = PLSCanonical(n_components=1).fit(X, Y).transform(X)

assert_allclose(svd, reg, rtol=1e-2)
assert_allclose(svd, canonical, rtol=1e-2)
rtol = 1e-3
# Setting atol because some entries are very close to zero
assert_allclose(svd, reg, atol=reg.max() * rtol)
assert_allclose(svd, canonical, atol=canonical.max() * rtol)


def test_svd_flip_1d():
Expand All @@ -526,9 +530,11 @@ def test_svd_flip_1d():
assert_allclose(v, [-1, -2, -3])


def test_loadings_converges():
def test_loadings_converges(global_random_seed):
"""Test that CCA converges. Non-regression test for #19549."""
X, y = make_regression(n_samples=200, n_features=20, n_targets=20, random_state=20)
X, y = make_regression(
n_samples=200, n_features=20, n_targets=20, random_state=global_random_seed
)

cca = CCA(n_components=10, max_iter=500)

Expand Down