LassoLarsCV chatty but not that helpful. #8475
Description
I'm running a grid search with a LassoLarsCV inside (yeah nested cv hurray!).
I get many many warnings like this
/home/andy/checkout/scikit-learn/sklearn/linear_model/least_angle.py:309: ConvergenceWarning: Regressors in active set degenerate. Dropping a regressor, after 61 iterations, i.e. alpha=1.187e+00, with an active set of 53 regressors, and the smallest cholesky pivot element being 9.186e-08
ConvergenceWarning)
/home/andy/checkout/scikit-learn/sklearn/linear_model/least_angle.py:334: ConvergenceWarning: Early stopping the lars path, as the residues are small and the current value of alpha is no longer well controlled. 62 iterations, alpha=1.189e+00, previous alpha=1.186e+00, with an active set of 53 regressors.
I find these message hard to understand because they tell me what went wrong, but they don't tell me the consequence or how to fix it.
Also, there is just waaay to many messages. Does that mean that this mostly fails to converge?
cc @agramfort