Skip to content

Fix check_decision_proba_consistency random failure #19225

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 5 commits into from
Jan 23, 2021
Merged

Fix check_decision_proba_consistency random failure #19225

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
171485e
FIX more deterministic check_decision_proba_consistency
ogrisel Jan 21, 2021
d638f73
Trigger [cd build]
ogrisel Jan 21, 2021
4d1113d
Re-add rounding
ogrisel Jan 21, 2021
489875e
Trigger [cd build]
ogrisel Jan 21, 2021
8d2ed45
Avoid redundant phrasing in comment [ci skip]
ogrisel Jan 21, 2021
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
9 changes: 6 additions & 3 deletions sklearn/utils/estimator_checks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2907,16 +2907,19 @@ def check_decision_proba_consistency(name, estimator_orig):
centers = [(2, 2), (4, 4)]
X, y = make_blobs(n_samples=100, random_state=0, n_features=4,
centers=centers, cluster_std=1.0, shuffle=True)
X_test = np.random.randn(20, 2) + 4
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=0)
estimator = clone(estimator_orig)

if (hasattr(estimator, "decision_function") and
hasattr(estimator, "predict_proba")):

estimator.fit(X, y)
estimator.fit(X_train, y_train)
# Since the link function from decision_function() to predict_proba()
# is sometimes not precise enough (typically expit), we round to the
# 10th decimal to avoid numerical issues.
# 10th decimal to avoid numerical issues: we compare the rank
# with deterministic ties rather than get platform specific rank
# inversions in case of machine level differences.
a = estimator.predict_proba(X_test)[:, 1].round(decimals=10)
b = estimator.decision_function(X_test).round(decimals=10)
assert_array_equal(rankdata(a), rankdata(b))
Expand Down