failed test_ard_accuracy_on_easy_problem using specific seed #15420
Description
Description
the test failed using seed=45, however, it will pass if other seeds are used such as 46 or 47
Steps/Code to Reproduce
def test_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 = 45
X = 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!
> assert abs_coef_error < 0.0
E assert 1.2070270934527727e-05 < 0.0-->
Expected Results
pass
Actual Results
asser error
Versions
System:
python: 3.6.8 (default, Oct 7 2019, 12:59:55) [GCC 8.3.0]
executable: /usr/local/bin/python
machine: Linux-4.15.0-1039-aws-x86_64-with-Ubuntu-18.04-bionic
Python deps:
pip: 19.3.1
setuptools: 41.6.0
sklearn: 0.22.dev0
numpy: 1.17.3
scipy: 1.3.1
Cython: 0.29.13
pandas: 0.25.2
matplotlib: 3.1.1
joblib: 0.14.0