You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
the test failed using seed=45, however, it will pass if other seeds are used such as 46 or 47
Steps/Code to Reproduce
deftest_ard_accuracy_on_easy_problem():
# Check that ARD converges with reasonable accuracy on an easy problem# (Github issue #14055)# This particular seed seems to converge poorly in the failure-case# (scipy==1.3.0, sklearn==0.21.2)seed=45X=np.random.RandomState(seed=seed).normal(size=(250, 3))
y=X[:, 1]
regressor=ARDRegression()
regressor.fit(X, y)
abs_coef_error=np.abs(1-regressor.coef_[1])
# Expect an accuracy of better than 1E-4 in most cases -# Failure-case produces 0.16!>assertabs_coef_error<0.0Eassert1.2070270934527727e-05<0.0
Some tests are reasonably expected to work with any seed, some are more
like a "proof of existence" and only need to test one seed. Why do you
think this should be the former?
Description
the test failed using
seed=45
, however, it will pass if other seeds are used such as46
or47
Steps/Code to Reproduce
-->
Expected Results
pass
Actual Results
asser error
Versions
The text was updated successfully, but these errors were encountered: