CI failure of the GPR with not issuing a ConvergenceWarning #21327
Description
Our build based on conda and MKL updated the NumPy version from 1.20.3 to 1.21.2.
A GPR test fails because it does not raise anymore a ConvergenceWarning. It should be investigated to know what is the reason and fix the test to ensure a case that we trigger a convergence issue.
E Failed: DID NOT WARN. No warnings of type (<class 'sklearn.exceptions.ConvergenceWarning'>,) matching ('The optimal value found for dimension 0 of parameter length_scale is close to the specified upper bound 0.001. Increasing the bound and calling fit again may find a better value.') was emitted. The list of emitted warnings is: [ConvergenceWarning('The optimal value found for dimension 0 of parameter length_scale is close to the specified upper bound 1e-03. Increasing the bound and calling fit again may find a better value.')].