Closed krfricke closed 3 years ago
This Ray PR adds points_to_evaluate for all search algorithms (except random search): https://github.com/ray-project/ray/pull/12790
points_to_evaluate
This PR here adds tests for this in tune-sklearn. Points that should be evaluated first can be passed via the search_kwargs argument. E.g.:
search_kwargs
points = [{ "alpha": 0.4, "epsilon": 0.01, "penalty": "elasticnet" }, { "alpha": 0.3, "epsilon": 0.02, "penalty": "l1" }] tune_search = TuneSearchCV( self.clf, self.parameter_grid, search_optimization=search_method, cv=2, n_trials=3, n_jobs=1, refit=True, points_to_evaluate=points)
Closes #73
Looks like something breaks with Hyperopt
Might fix itself after https://github.com/ray-project/tune-sklearn/pull/160 gets merged.
This Ray PR adds
points_to_evaluate
for all search algorithms (except random search): https://github.com/ray-project/ray/pull/12790This PR here adds tests for this in tune-sklearn. Points that should be evaluated first can be passed via the
search_kwargs
argument. E.g.:Closes #73