def _setup_optimizer(self):
# HEBO internally minimizes, so "max" => -1
if self._mode == "max":
self._metric_op = -1.
elif self._mode == "min":
self._metric_op = 1.
if self._metric is None and self._mode:
# If only a mode was passed, use anonymous metric
self._metric = DEFAULT_METRIC
if not isinstance(self._space,
hebo.design_space.design_space.DesignSpace):
raise ValueError(
f"Invalid search space: {type(self._space)}. Either pass a "
f"valid search space to the `HEBOSearch` class or pass "
f"a `config` parameter to `tune.run()`")
if self._space.num_paras <= 0:
raise ValueError(
"Got empty search space. Please make sure to pass "
"a valid search space with at least one parameter to "
"`HEBOSearch`")
if self._random_state_seed is not None:
np.random.seed(self._random_state_seed)
torch.random.manual_seed(self._random_state_seed)
self._opt = hebo.optimizers.hebo.HEBO(space=self._space,
**self._hebo_config)
if self._points_to_evaluate:
validate_warmstart(self._space.para_names,
self._points_to_evaluate,
self._evaluated_rewards)
if self._evaluated_rewards:
self._opt.observe(
pd.DataFrame(self._points_to_evaluate),
np.array(self._evaluated_rewards) * self._metric_op)
else:
self._initial_points = self._points_to_evaluate
def _setup_skopt(self):
if self._points_to_evaluate and isinstance(self._points_to_evaluate,
list):
if isinstance(self._points_to_evaluate[0], list):
# Keep backwards compatibility
self._points_to_evaluate = [
dict(zip(self._parameter_names, point))
for point in self._points_to_evaluate
]
# Else: self._points_to_evaluate is already in correct format
validate_warmstart(self._parameter_names, self._points_to_evaluate,
self._evaluated_rewards)
if not self._skopt_opt:
if not self._space:
raise ValueError(
"If you don't pass an optimizer instance to SkOptSearch, "
"pass a valid `space` parameter.")
self._skopt_opt = sko.Optimizer(self._parameter_ranges)
if self._points_to_evaluate and self._evaluated_rewards:
skopt_points = [[point[par] for par in self._parameter_names]
for point in self._points_to_evaluate]
self._skopt_opt.tell(skopt_points, self._evaluated_rewards)
elif self._points_to_evaluate:
self._initial_points = self._points_to_evaluate
self._parameters = self._parameter_names
# Skopt internally minimizes, so "max" => -1
if self._mode == "max":
self._metric_op = -1.0
elif self._mode == "min":
self._metric_op = 1.0
if self._metric is None and self._mode:
# If only a mode was passed, use anonymous metric
self._metric = DEFAULT_METRIC
