def test_suggest_discrete_uniform_range(storage_mode: str, range_config: Dict[str, float]) -> None:
sampler = samplers.RandomSampler()
# Check upper endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.high
with patch.object(sampler, "sample_independent", mock) as mock_object, StorageSupplier(
storage_mode
) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(UserWarning):
x = trial.suggest_discrete_uniform(
"x", range_config["low"], range_config["high"], range_config["q"]
)
assert x == range_config["mod_high"]
assert mock_object.call_count == 1
# Check lower endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.low
with patch.object(sampler, "sample_independent", mock) as mock_object, StorageSupplier(
storage_mode
) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(UserWarning):
x = trial.suggest_discrete_uniform(
"x", range_config["low"], range_config["high"], range_config["q"]
)
assert x == range_config["low"]
assert mock_object.call_count == 1
def test_check_distribution_suggest_float(storage_init_func):
# type: (Callable[[], storages.BaseStorage]) -> None
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
x1 = trial.suggest_float("x1", 10, 20)
x2 = trial.suggest_uniform("x1", 10, 20)
assert x1 == x2
x3 = trial.suggest_float("x2", 1e-5, 1e-3, log=True)
x4 = trial.suggest_loguniform("x2", 1e-5, 1e-3)
assert x3 == x4
x5 = trial.suggest_float("x3", 10, 20, step=1.0)
x6 = trial.suggest_discrete_uniform("x3", 10, 20, 1.0)
assert x5 == x6
with pytest.raises(ValueError):
trial.suggest_float("x4", 1e-5, 1e-2, step=1e-5, log=True)
with pytest.raises(ValueError):
trial.suggest_int("x1", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x1", 10, 20)
def test_get_param_importances(storage_init_func: Callable[[], storages.BaseStorage]) -> None:
def objective(trial: Trial) -> float:
x1 = trial.suggest_uniform("x1", 0.1, 3)
x2 = trial.suggest_loguniform("x2", 0.1, 3)
x3 = trial.suggest_discrete_uniform("x3", 0, 3, 1)
x4 = trial.suggest_int("x4", -3, 3)
x5 = trial.suggest_categorical("x5", [1.0, 1.1, 1.2])
if trial.number % 2 == 0:
# Conditional parameters are ignored unless `params` is specified and is not `None`.
x6 = trial.suggest_uniform("x6", 0.1, 3)
assert isinstance(x5, float)
value = x1 ** 4 + x2 + x3 - x4 ** 2 - x5
if trial.number % 2 == 0:
value += x6
return value
study = create_study(storage_init_func(), sampler=samplers.RandomSampler())
study.optimize(objective, n_trials=3)
param_importance = get_param_importances(study, evaluator=FanovaImportanceEvaluator())
assert isinstance(param_importance, OrderedDict)
assert len(param_importance) == 5
assert all(param_name in param_importance for param_name in ["x1", "x2", "x3", "x4", "x5"])
for param_name, importance in param_importance.items():
assert isinstance(param_name, str)
assert isinstance(importance, float)
assert math.isclose(1.0, sum(i for i in param_importance.values()))
def __init__(
self,
independent_sampler: Optional[BaseSampler] = None,
warn_independent_sampling: bool = True,
skopt_kwargs: Optional[Dict[str, Any]] = None,
n_startup_trials: int = 1,
*,
consider_pruned_trials: bool = False,
) -> None:
_imports.check()
self._skopt_kwargs = skopt_kwargs or {}
if "dimensions" in self._skopt_kwargs:
del self._skopt_kwargs["dimensions"]
self._independent_sampler = independent_sampler or samplers.RandomSampler(
)
self._warn_independent_sampling = warn_independent_sampling
self._n_startup_trials = n_startup_trials
self._search_space = samplers.IntersectionSearchSpace()
self._consider_pruned_trials = consider_pruned_trials
if self._consider_pruned_trials:
warnings.warn(
"`consider_pruned_trials` option is an experimental feature."
" The interface can change in the future.",
ExperimentalWarning,
)
def test_suggest_loguniform(storage_init_func):
# type: (Callable[[], storages.BaseStorage]) -> None
with pytest.raises(ValueError):
LogUniformDistribution(low=1.0, high=0.9)
with pytest.raises(ValueError):
LogUniformDistribution(low=0.0, high=0.9)
mock = Mock()
mock.side_effect = [1.0, 2.0, 3.0]
sampler = samplers.RandomSampler()
with patch.object(sampler, "sample_independent", mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
distribution = LogUniformDistribution(low=0.1, high=4.0)
assert trial._suggest("x",
distribution) == 1.0 # Test suggesting a param.
assert trial._suggest(
"x", distribution) == 1.0 # Test suggesting the same param.
assert trial._suggest(
"y", distribution) == 3.0 # Test suggesting a different param.
assert trial.params == {"x": 1.0, "y": 3.0}
assert mock_object.call_count == 3
def test_suggest_loguniform(storage_mode: str) -> None:
with pytest.raises(ValueError):
LogUniformDistribution(low=1.0, high=0.9)
with pytest.raises(ValueError):
LogUniformDistribution(low=0.0, high=0.9)
mock = Mock()
mock.side_effect = [1.0, 2.0]
sampler = samplers.RandomSampler()
with patch.object(
sampler, "sample_independent",
mock) as mock_object, StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
distribution = LogUniformDistribution(low=0.1, high=4.0)
assert trial._suggest("x",
distribution) == 1.0 # Test suggesting a param.
assert trial._suggest(
"x", distribution) == 1.0 # Test suggesting the same param.
assert trial._suggest(
"y", distribution) == 2.0 # Test suggesting a different param.
assert trial.params == {"x": 1.0, "y": 2.0}
assert mock_object.call_count == 2
def test_suggest_int_range(
storage_init_func: Callable[[], storages.BaseStorage], range_config: Dict[str, int]
) -> None:
sampler = samplers.RandomSampler()
# Check upper endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.high
with patch.object(sampler, "sample_independent", mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(UserWarning):
x = trial.suggest_int(
"x", range_config["low"], range_config["high"], step=range_config["step"]
)
assert x == range_config["mod_high"]
assert mock_object.call_count == 1
# Check lower endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.low
with patch.object(sampler, "sample_independent", mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(UserWarning):
x = trial.suggest_int(
"x", range_config["low"], range_config["high"], step=range_config["step"]
)
assert x == range_config["low"]
assert mock_object.call_count == 1
def test_suggest_int_log(storage_init_func: Callable[[], storages.BaseStorage]) -> None:
mock = Mock()
mock.side_effect = [1, 2]
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
distribution = IntLogUniformDistribution(low=1, high=3)
with patch.object(sampler, "sample_independent", mock) as mock_object:
assert trial._suggest("x", distribution) == 1 # Test suggesting a param.
assert trial._suggest("x", distribution) == 1 # Test suggesting the same param.
assert trial._suggest("y", distribution) == 2 # Test suggesting a different param.
assert trial.params == {"x": 1, "y": 2}
assert mock_object.call_count == 2
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with warnings.catch_warnings():
# UserWarning will be raised since [0.5, 10] is not divisible by 1.
warnings.simplefilter("ignore", category=UserWarning)
with pytest.raises(ValueError):
trial.suggest_int("z", 0.5, 10, log=True) # type: ignore
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("w", 1, 3, step=2, log=True)
def test_suggest_discrete_uniform_range(storage_init_func, range_config):
# type: (typing.Callable[[], storages.BaseStorage], typing.Dict[str, float]) -> None
sampler = samplers.RandomSampler()
# Check upper endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.high
with patch.object(sampler, 'sample_independent', mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study.storage.create_new_trial_id(study.study_id))
x = trial.suggest_discrete_uniform('x', range_config['low'], range_config['high'],
range_config['q'])
assert x == range_config['mod_high']
assert mock_object.call_count == 1
# Check lower endpoints.
mock = Mock()
mock.side_effect = lambda study, trial, param_name, distribution: distribution.low
with patch.object(sampler, 'sample_independent', mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study.storage.create_new_trial_id(study.study_id))
x = trial.suggest_discrete_uniform('x', range_config['low'], range_config['high'],
range_config['q'])
assert x == range_config['low']
assert mock_object.call_count == 1
def test_check_distribution_suggest_float(storage_mode: str) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
x1 = trial.suggest_float("x1", 10, 20)
x2 = trial.suggest_uniform("x1", 10, 20)
assert x1 == x2
x3 = trial.suggest_float("x2", 1e-5, 1e-3, log=True)
x4 = trial.suggest_loguniform("x2", 1e-5, 1e-3)
assert x3 == x4
x5 = trial.suggest_float("x3", 10, 20, step=1.0)
x6 = trial.suggest_discrete_uniform("x3", 10, 20, 1.0)
assert x5 == x6
with pytest.raises(ValueError):
trial.suggest_float("x4", 1e-5, 1e-2, step=1e-5, log=True)
with pytest.raises(ValueError):
trial.suggest_int("x1", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x1", 10, 20)
def __init__(self, independent_sampler=None, warn_independent_sampling=True,
skopt_kwargs=None):
# type: (Optional[BaseSampler], bool, Optional[Dict[str, Any]]) -> None
_check_skopt_availability()
self._skopt_kwargs = skopt_kwargs or {}
if 'dimensions' in self._skopt_kwargs:
del self._skopt_kwargs['dimensions']
self._independent_sampler = independent_sampler or samplers.RandomSampler()
self._warn_independent_sampling = warn_independent_sampling
def test_check_distribution_suggest_discrete_uniform(storage_init_func):
# type: (typing.Callable[[], storages.BaseStorage]) -> None
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_discrete_uniform("x", 10, 20, 2)
trial.suggest_discrete_uniform("x", 10, 20, 2)
trial.suggest_discrete_uniform("x", 10, 22, 2)
# we expect exactly one warning
assert len(record) == 1
def test_check_distribution_suggest_int(
storage_init_func: Callable[[], storages.BaseStorage], enable_log: bool
) -> None:
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_int("x", 10, 20, log=enable_log)
trial.suggest_int("x", 10, 20, log=enable_log)
trial.suggest_int("x", 10, 22, log=enable_log)
# We expect exactly one warning.
assert len(record) == 1
def test_check_distribution_suggest_float(storage_init_func):
# type: (typing.Callable[[], storages.BaseStorage]) -> None
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
x1 = trial.suggest_float("x1", 10, 20)
x2 = trial.suggest_uniform("x1", 10, 20)
assert x1 == x2
x3 = trial.suggest_float("x2", 1e-5, 1e-3, log=True)
x4 = trial.suggest_loguniform("x2", 1e-5, 1e-3)
assert x3 == x4
def test_suggest_int(storage_init_func: Callable[[], storages.BaseStorage]) -> None:
mock = Mock()
mock.side_effect = [1, 2]
sampler = samplers.RandomSampler()
with patch.object(sampler, "sample_independent", mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
distribution = IntUniformDistribution(low=0, high=3)
assert trial._suggest("x", distribution) == 1 # Test suggesting a param.
assert trial._suggest("x", distribution) == 1 # Test suggesting the same param.
assert trial._suggest("y", distribution) == 2 # Test suggesting a different param.
assert trial.params == {"x": 1, "y": 2}
assert mock_object.call_count == 2
def test_suggest_int_log_invalid_range(storage_mode: str) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with warnings.catch_warnings():
# UserWarning will be raised since [0.5, 10] is not divisible by 1.
warnings.simplefilter("ignore", category=UserWarning)
with pytest.raises(ValueError):
trial.suggest_int("z", 0.5, 10, log=True) # type: ignore
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("w", 1, 3, step=2, log=True)
def test_suggest_discrete_uniform(storage_init_func):
# type: (typing.Callable[[], storages.BaseStorage]) -> None
mock = Mock()
mock.side_effect = [1., 2., 3.]
sampler = samplers.RandomSampler()
with patch.object(sampler, 'sample_independent', mock) as mock_object:
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study.storage.create_new_trial_id(study.study_id))
distribution = distributions.DiscreteUniformDistribution(low=0., high=3., q=1.)
assert trial._suggest('x', distribution) == 1. # Test suggesting a param.
assert trial._suggest('x', distribution) == 1. # Test suggesting the same param.
assert trial._suggest('y', distribution) == 3. # Test suggesting a different param.
assert trial.params == {'x': 1., 'y': 3.}
assert mock_object.call_count == 3
def test_check_distribution_suggest_categorical(
storage_init_func: Callable[[], storages.BaseStorage]) -> None:
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
trial.suggest_categorical("x", [10, 20, 30])
with pytest.raises(ValueError):
trial.suggest_categorical("x", [10, 20])
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
def test_check_distribution_suggest_categorical(storage_mode: str) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
trial.suggest_categorical("x", [10, 20, 30])
with pytest.raises(ValueError):
trial.suggest_categorical("x", [10, 20])
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
def __init__(
self,
independent_sampler=None,
warn_independent_sampling=True,
skopt_kwargs=None,
n_startup_trials=1,
):
# type: (Optional[BaseSampler], bool, Optional[Dict[str, Any]], int) -> None
_check_skopt_availability()
self._skopt_kwargs = skopt_kwargs or {}
if "dimensions" in self._skopt_kwargs:
del self._skopt_kwargs["dimensions"]
self._independent_sampler = independent_sampler or samplers.RandomSampler()
self._warn_independent_sampling = warn_independent_sampling
self._n_startup_trials = n_startup_trials
def test_get_param_importances(storage_mode: str,
evaluator_init_func: Callable[
[], BaseImportanceEvaluator],
normalize: bool) -> None:
def objective(trial: Trial) -> float:
x1 = trial.suggest_float("x1", 0.1, 3)
x2 = trial.suggest_float("x2", 0.1, 3, log=True)
x3 = trial.suggest_float("x3", 0, 3, step=1)
x4 = trial.suggest_int("x4", -3, 3)
x5 = trial.suggest_int("x5", 1, 5, log=True)
x6 = trial.suggest_categorical("x6", [1.0, 1.1, 1.2])
if trial.number % 2 == 0:
# Conditional parameters are ignored unless `params` is specified and is not `None`.
x7 = trial.suggest_float("x7", 0.1, 3)
assert isinstance(x6, float)
value = x1**4 + x2 + x3 - x4**2 - x5 + x6
if trial.number % 2 == 0:
value += x7
return value
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=samplers.RandomSampler())
study.optimize(objective, n_trials=3)
param_importance = get_param_importances(
study, evaluator=evaluator_init_func(), normalize=normalize)
assert isinstance(param_importance, OrderedDict)
assert len(param_importance) == 6
assert all(param_name in param_importance
for param_name in ["x1", "x2", "x3", "x4", "x5", "x6"])
prev_importance = float("inf")
for param_name, importance in param_importance.items():
assert isinstance(param_name, str)
assert isinstance(importance, float)
assert importance <= prev_importance
prev_importance = importance
# Sanity check for param importances
assert all(0 <= x < float("inf") for x in param_importance.values())
if normalize:
assert np.isclose(sum(param_importance.values()), 1.0)
def __init__(
self,
independent_sampler=None,
warn_independent_sampling=True,
skopt_kwargs=None,
n_startup_trials=1,
):
# type: (Optional[BaseSampler], bool, Optional[Dict[str, Any]], int) -> None
_imports.check()
self._skopt_kwargs = skopt_kwargs or {}
if "dimensions" in self._skopt_kwargs:
del self._skopt_kwargs["dimensions"]
self._independent_sampler = independent_sampler or samplers.RandomSampler(
)
self._warn_independent_sampling = warn_independent_sampling
self._n_startup_trials = n_startup_trials
self._search_space = samplers.IntersectionSearchSpace()
def test_suggest_int(storage_mode: str) -> None:
mock = Mock()
mock.side_effect = [1, 2]
sampler = samplers.RandomSampler()
with patch.object(
sampler, "sample_independent",
mock) as mock_object, StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
distribution = IntDistribution(low=0, high=3)
assert trial._suggest("x",
distribution) == 1 # Test suggesting a param.
assert trial._suggest(
"x", distribution) == 1 # Test suggesting the same param.
assert trial._suggest(
"y", distribution) == 2 # Test suggesting a different param.
assert trial.params == {"x": 1, "y": 2}
assert mock_object.call_count == 2
def test_check_distribution_suggest_int(storage_mode: str, enable_log: bool) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_int("x", 10, 20, log=enable_log)
trial.suggest_int("x", 10, 20, log=enable_log)
trial.suggest_int("x", 10, 22, log=enable_log)
# We expect exactly one warning.
assert len(record) == 1
with pytest.raises(ValueError):
trial.suggest_float("x", 10, 20, log=enable_log)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_float("x", 10, 20, log=enable_log)
def test_check_distribution_suggest_loguniform(storage_mode: str) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_loguniform("x", 10, 20)
trial.suggest_loguniform("x", 10, 20)
trial.suggest_loguniform("x", 10, 30)
# we expect exactly one warning (not counting ones caused by deprecation)
assert len([r for r in record if r.category != FutureWarning]) == 1
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
def test_check_distribution_suggest_uniform(
storage_init_func: Callable[[], storages.BaseStorage]) -> None:
sampler = samplers.RandomSampler()
study = create_study(storage_init_func(), sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_uniform("x", 10, 20)
trial.suggest_uniform("x", 10, 20)
trial.suggest_uniform("x", 10, 30)
# we expect exactly one warning
assert len(record) == 1
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
def test_check_distribution_suggest_loguniform(storage_mode: str) -> None:
sampler = samplers.RandomSampler()
with StorageSupplier(storage_mode) as storage:
study = create_study(storage=storage, sampler=sampler)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.warns(None) as record:
trial.suggest_loguniform("x", 10, 20)
trial.suggest_loguniform("x", 10, 20)
trial.suggest_loguniform("x", 10, 30)
# we expect exactly one warning
assert len(record) == 1
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
trial = Trial(study, study._storage.create_new_trial(study._study_id))
with pytest.raises(ValueError):
trial.suggest_int("x", 10, 20)
def __init__(self,
independent_sampler: Optional[BaseSampler] = None,
warn_independent_sampling: bool = True,
skopt_kwargs: Optional[Dict[str, Any]] = None,
n_startup_trials: int = 1,
*,
consider_pruned_trials: bool = False) -> None:
_imports.check()
self._skopt_kwargs = skopt_kwargs or {}
if "dimensions" in self._skopt_kwargs:
del self._skopt_kwargs["dimensions"]
self._independent_sampler = independent_sampler or samplers.RandomSampler(
)
self._warn_independent_sampling = warn_independent_sampling
self._n_startup_trials = n_startup_trials
self._search_space = samplers.IntersectionSearchSpace()
self._consider_pruned_trials = consider_pruned_trials
if self._consider_pruned_trials:
self._raise_experimental_warning_for_consider_pruned_trials()
def fit(
self,
X: MultipleDataType,
y: Optional[TargetDataType] = None,
cat_features: Optional[FeatureType] = None,
text_features: Optional[FeatureType] = None,
pairs: Optional[PairsType] = None,
sample_weight: SampleWeightType = None,
group_id: Optional[FeatureType] = None,
group_weight: Optional[FeatureType] = None,
subgroup_id: Optional[FeatureType] = None,
pairs_weight: Optional[FeatureType] = None,
baseline: Optional[FeatureType] = None,
use_best_model: Optional[bool] = None,
eval_set: Optional[cb.Pool] = None,
verbose: Optional[Union[bool, int]] = None,
logging_level: Optional[str] = None,
plot: bool = False,
column_description: Optional[str] = None,
verbose_eval: Optional[Union[bool, int]] = None,
metric_period: Optional[int] = None,
silent: Optional[bool] = None,
early_stopping_rounds: Optional[int] = None,
save_snapshot: Optional[bool] = None,
snapshot_file: Optional[str] = None,
snapshot_interval: Optional[int] = None,
init_model: Optional[str] = None,
):
logger = logging.getLogger(__name__)
# catboost\core.py
# CatBoost._prepare_train_params
train_params = self._prepare_train_params(
X,
y,
cat_features,
text_features,
pairs,
sample_weight,
group_id,
group_weight,
subgroup_id,
pairs_weight,
baseline,
use_best_model,
eval_set,
verbose,
logging_level,
plot,
column_description,
verbose_eval,
metric_period,
silent,
early_stopping_rounds,
save_snapshot,
snapshot_file,
snapshot_interval,
init_model,
)
n_samples = len(X)
# get_params
params = train_params["params"]
eval_name = params.get("loss_function")
early_stopping_rounds = early_stopping_rounds
n_estimators = params.get("iterations")
is_classifier = self._estimator_type == "classifier"
is_higher_better = _is_higher_better(eval_name)
cv = check_cv(cv=self.cv, y=y, classifier=is_classifier)
if self.study is None:
sampler = samplers.RandomSampler()
direction = "maximize" if is_higher_better else "minimize"
self.study = study_module.create_study(direction=direction, sampler=sampler)
# hyper_parameter tuning
dataset = cb.Pool(X, label=y)
objective = _Objective(
params,
dataset=dataset,
cv=cv,
eval_name=eval_name,
n_samples=n_samples,
is_higher_better=is_higher_better,
early_stopping_rounds=early_stopping_rounds,
n_estimators=n_estimators,
param_distributions=self.param_distributions,
)
logger.info("Searching the best hyper_parameters")
self.study.optimize(objective, n_trials=self.n_trials, timeout=self.timeout)
logger.info("Done")
logger.info("Starting refit")
if self.refit:
pass
return self
def create_study(
storage: Optional[Union[str, storages.BaseStorage]] = None,
sampler: Optional["samplers.BaseSampler"] = None,
pruner: Optional[pruners.BasePruner] = None,
study_name: Optional[str] = None,
direction: Optional[str] = None,
load_if_exists: bool = False,
*,
directions: Optional[Sequence[str]] = None,
) -> Study:
"""Create a new :class:`~optuna.study.Study`.
Example:
.. testcode::
import optuna
def objective(trial):
x = trial.suggest_uniform("x", 0, 10)
return x ** 2
study = optuna.create_study()
study.optimize(objective, n_trials=3)
Args:
storage:
Database URL. If this argument is set to None, in-memory storage is used, and the
:class:`~optuna.study.Study` will not be persistent.
.. note::
When a database URL is passed, Optuna internally uses `SQLAlchemy`_ to handle
the database. Please refer to `SQLAlchemy's document`_ for further details.
If you want to specify non-default options to `SQLAlchemy Engine`_, you can
instantiate :class:`~optuna.storages.RDBStorage` with your desired options and
pass it to the ``storage`` argument instead of a URL.
.. _SQLAlchemy: https://www.sqlalchemy.org/
.. _SQLAlchemy's document:
https://docs.sqlalchemy.org/en/latest/core/engines.html#database-urls
.. _SQLAlchemy Engine: https://docs.sqlalchemy.org/en/latest/core/engines.html
sampler:
A sampler object that implements background algorithm for value suggestion.
If :obj:`None` is specified, :class:`~optuna.samplers.TPESampler` is used
as the default. See also :class:`~optuna.samplers`.
pruner:
A pruner object that decides early stopping of unpromising trials. If :obj:`None`
is specified, :class:`~optuna.pruners.MedianPruner` is used as the default. See
also :class:`~optuna.pruners`.
study_name:
Study's name. If this argument is set to None, a unique name is generated
automatically.
direction:
Direction of optimization. Set ``minimize`` for minimization and ``maximize`` for
maximization.
.. note::
If none of `direction` and `directions` are specified, the direction of the study
is set to "minimize".
directions:
A sequence of directions during multi-objective optimization.
load_if_exists:
Flag to control the behavior to handle a conflict of study names.
In the case where a study named ``study_name`` already exists in the ``storage``,
a :class:`~optuna.exceptions.DuplicatedStudyError` is raised if ``load_if_exists`` is
set to :obj:`False`.
Otherwise, the creation of the study is skipped, and the existing one is returned.
Returns:
A :class:`~optuna.study.Study` object.
Raises:
:exc:`ValueError`:
If the length of ``directions`` is zero.
Or, if ``direction`` is neither 'minimize' nor 'maximize' when it is a string.
Or, if the element of ``directions`` is neither `minimize` nor `maximize`.
Or, if both ``direction`` and ``directions`` are specified.
See also:
:func:`optuna.create_study` is an alias of :func:`optuna.study.create_study`.
"""
if direction is None and directions is None:
directions = ["minimize"]
elif direction is not None and directions is not None:
raise ValueError("Specify only one of `direction` and `directions`.")
elif direction is not None:
directions = [direction]
elif directions is not None:
directions = list(directions)
else:
assert False
if len(directions) < 1:
raise ValueError("The number of objectives must be greater than 0.")
elif any(d != "minimize" and d != "maximize" for d in directions):
raise ValueError("Please set either 'minimize' or 'maximize' to direction.")
direction_objects = [
StudyDirection.MINIMIZE if d == "minimize" else StudyDirection.MAXIMIZE for d in directions
]
storage = storages.get_storage(storage)
try:
study_id = storage.create_new_study(study_name)
except exceptions.DuplicatedStudyError:
if load_if_exists:
assert study_name is not None
_logger.info(
"Using an existing study with name '{}' instead of "
"creating a new one.".format(study_name)
)
study_id = storage.get_study_id_from_name(study_name)
else:
raise
# TODO(imamura): Change the default sampler for MO as NSGAII after MO sampler refactoring.
if sampler is None and len(direction_objects) > 1:
_logger.info(
"Multi-objective optimization is set, but no sampler is specified. "
"The sampler is set to `optuna.samplers.RandomSampler`."
)
sampler = samplers.RandomSampler()
study_name = storage.get_study_name_from_id(study_id)
study = Study(study_name=study_name, storage=storage, sampler=sampler, pruner=pruner)
study._storage.set_study_directions(study_id, direction_objects)
return study