Skip to content

Make test_ridge_regression_dtype_stability less random #13816

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 1 commit into from
May 8, 2019
Merged

Make test_ridge_regression_dtype_stability less random #13816

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 8 additions & 6 deletions sklearn/linear_model/tests/test_ridge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -998,16 +998,18 @@ def test_dtype_match_cholesky():

@pytest.mark.parametrize(
'solver', ['svd', 'cholesky', 'lsqr', 'sparse_cg', 'sag', 'saga'])
def test_ridge_regression_dtype_stability(solver):
random_state = np.random.RandomState(0)
@pytest.mark.parametrize('seed', range(1))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This range looks a bit funny

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's meant to make it easy to edit this test to run on 100s of different seeds. We probably need a more generic way to achieve this with a fixture.

def test_ridge_regression_dtype_stability(solver, seed):
random_state = np.random.RandomState(seed)
n_samples, n_features = 6, 5
X = random_state.randn(n_samples, n_features)
coef = random_state.randn(n_features)
y = np.dot(X, coef) + 0.01 * rng.randn(n_samples)
y = np.dot(X, coef) + 0.01 * random_state.randn(n_samples)
alpha = 1.0
rtol = 1e-2 if os.name == 'nt' and _IS_32BIT else 1e-5

results = dict()
# XXX: Sparse CG seems to be far less numerically stable than the
# others, maybe we should not enable float32 for this one.
atol = 1e-3 if solver == "sparse_cg" else 1e-5
for current_dtype in (np.float32, np.float64):
results[current_dtype] = ridge_regression(X.astype(current_dtype),
y.astype(current_dtype),
Expand All @@ -1022,4 +1024,4 @@ def test_ridge_regression_dtype_stability(solver):

assert results[np.float32].dtype == np.float32
assert results[np.float64].dtype == np.float64
assert_allclose(results[np.float32], results[np.float64], rtol=rtol)
assert_allclose(results[np.float32], results[np.float64], atol=atol)