def test_handling_alias_metrics() -> None:
for alias in [
"lambdarank",
"rank_xendcg",
"xendcg",
"xe_ndcg",
"xe_ndcg_mart",
"xendcg_mart",
"ndcg",
]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "ndcg"
for alias in ["mean_average_precision", "map"]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "map"
lgbm_params = {}
_handling_alias_metrics(lgbm_params)
assert lgbm_params == {}
lgbm_params = {"metric": "auc"}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "auc"
lgbm_params = {"metric": "rmse"}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "rmse"
def __init__(self, lgbm_params=None, lgbm_kwargs=None):
# type: (Dict[str, Any], Dict[str,Any]) -> None
# Handling alias metrics.
if lgbm_params is not None:
_handling_alias_metrics(lgbm_params)
self.lgbm_params = lgbm_params or {}
self.lgbm_kwargs = lgbm_kwargs or {}
def test_handling_alias_metrics(aliases: List[str], expect: str) -> None:
if len(aliases) > 0:
for alias in aliases:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == expect
else:
lgbm_params = {}
_handling_alias_metrics(lgbm_params)
assert lgbm_params == {}
def __init__(
self,
lgbm_params: Optional[Dict[str, Any]] = None,
lgbm_kwargs: Optional[Dict[str, Any]] = None,
) -> None:
# Handling alias metrics.
if lgbm_params is not None:
_handling_alias_metrics(lgbm_params)
self.lgbm_params = lgbm_params or {}
self.lgbm_kwargs = lgbm_kwargs or {}
def __init__(
self,
params: Dict[str, Any],
train_set: "lgb.Dataset",
num_boost_round: int = 1000,
fobj: Optional[Callable[..., Any]] = None,
feval: Optional[Callable[..., Any]] = None,
feature_name: str = "auto",
categorical_feature: str = "auto",
early_stopping_rounds: Optional[int] = None,
verbose_eval: Optional[Union[bool, int]] = True,
callbacks: Optional[List[Callable[..., Any]]] = None,
time_budget: Optional[int] = None,
sample_size: Optional[int] = None,
study: Optional[optuna.study.Study] = None,
optuna_callbacks: Optional[List[Callable[[Study, FrozenTrial],
None]]] = None,
verbosity: Optional[int] = None,
show_progress_bar: bool = True,
) -> None:
_imports.check()
params = copy.deepcopy(params)
# Handling alias metrics.
_handling_alias_metrics(params)
args = [params, train_set]
kwargs = dict(
num_boost_round=num_boost_round,
fobj=fobj,
feval=feval,
feature_name=feature_name,
categorical_feature=categorical_feature,
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
callbacks=callbacks,
time_budget=time_budget,
sample_size=sample_size,
verbosity=verbosity,
show_progress_bar=show_progress_bar,
) # type: Dict[str, Any]
self._parse_args(*args, **kwargs)
self._start_time = None # type: Optional[float]
self._optuna_callbacks = optuna_callbacks
self._best_params = {}
# Set default parameters as best.
self._best_params.update(_DEFAULT_LIGHTGBM_PARAMETERS)
if study is None:
self.study = optuna.create_study(
direction="maximize" if self.higher_is_better(
) else "minimize")
else:
self.study = study
if self.higher_is_better():
if self.study.direction != optuna.study.StudyDirection.MAXIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'maximize' as the direction.".format(
metric_name))
else:
if self.study.direction != optuna.study.StudyDirection.MINIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'minimize' as the direction.".format(
metric_name))
if verbosity is not None:
warnings.warn(
"`verbosity` argument is deprecated and will be removed in the future. "
"The removal of this feature is currently scheduled for v4.0.0, "
"but this schedule is subject to change. Please use optuna.logging.set_verbosity()"
" instead.",
FutureWarning,
)
def __init__(
self,
params: Dict[str, Any],
train_set: "lgb.Dataset",
num_boost_round: int = 1000,
fobj: Optional[Callable[..., Any]] = None,
feval: Optional[Callable[..., Any]] = None,
feature_name: str = "auto",
categorical_feature: str = "auto",
early_stopping_rounds: Optional[int] = None,
verbose_eval: Optional[Union[bool, int]] = True,
callbacks: Optional[List[Callable[..., Any]]] = None,
time_budget: Optional[int] = None,
sample_size: Optional[int] = None,
study: Optional[optuna.study.Study] = None,
optuna_callbacks: Optional[List[Callable[[Study, FrozenTrial], None]]] = None,
verbosity: Optional[int] = None,
show_progress_bar: bool = True,
model_dir: Optional[str] = None,
) -> None:
_imports.check()
params = copy.deepcopy(params)
# Handling alias metrics.
_handling_alias_metrics(params)
args = [params, train_set]
kwargs: Dict[str, Any] = dict(
num_boost_round=num_boost_round,
fobj=fobj,
feval=feval,
feature_name=feature_name,
categorical_feature=categorical_feature,
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
callbacks=callbacks,
time_budget=time_budget,
sample_size=sample_size,
verbosity=verbosity,
show_progress_bar=show_progress_bar,
)
self._parse_args(*args, **kwargs)
self._start_time: Optional[float] = None
self._optuna_callbacks = optuna_callbacks
self._best_booster_with_trial_number: Optional[
Tuple[Union[lgb.Booster, lgb.CVBooster], int]
] = None
self._model_dir = model_dir
# Should not alter data since `min_data_in_leaf` is tuned.
# https://lightgbm.readthedocs.io/en/latest/Parameters.html#feature_pre_filter
if self.lgbm_params.get("feature_pre_filter", False):
warnings.warn(
"feature_pre_filter is given as True but will be set to False. This is required "
"for the tuner to tune min_data_in_leaf."
)
self.lgbm_params["feature_pre_filter"] = False
if study is None:
self.study = optuna.create_study(
direction="maximize" if self.higher_is_better() else "minimize"
)
else:
self.study = study
if self.higher_is_better():
if self.study.direction != optuna.study.StudyDirection.MAXIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'maximize' as the direction.".format(metric_name)
)
else:
if self.study.direction != optuna.study.StudyDirection.MINIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'minimize' as the direction.".format(metric_name)
)
if verbosity is not None:
warnings.warn(
"`verbosity` argument is deprecated and will be removed in the future. "
"The removal of this feature is currently scheduled for v4.0.0, "
"but this schedule is subject to change. Please use optuna.logging.set_verbosity()"
" instead.",
FutureWarning,
)
def __init__(
self,
params: Dict[str, Any],
train_set: "lgb.Dataset",
num_boost_round: int = 1000,
fobj: Optional[Callable[..., Any]] = None,
feval: Optional[Callable[..., Any]] = None,
feature_name: str = "auto",
categorical_feature: str = "auto",
early_stopping_rounds: Optional[int] = None,
verbose_eval: Optional[Union[bool, int]] = True,
callbacks: Optional[List[Callable[..., Any]]] = None,
time_budget: Optional[int] = None,
sample_size: Optional[int] = None,
study: Optional[optuna.study.Study] = None,
optuna_callbacks: Optional[List[Callable[[Study, FrozenTrial],
None]]] = None,
verbosity: Optional[int] = 1,
) -> None:
_imports.check()
params = copy.deepcopy(params)
# Handling alias metrics.
_handling_alias_metrics(params)
args = [params, train_set]
kwargs = dict(
num_boost_round=num_boost_round,
fobj=fobj,
feval=feval,
feature_name=feature_name,
categorical_feature=categorical_feature,
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
callbacks=callbacks,
time_budget=time_budget,
sample_size=sample_size,
verbosity=verbosity,
) # type: Dict[str, Any]
self._parse_args(*args, **kwargs)
self._start_time = None # type: Optional[float]
self._use_pbar = True
self._optuna_callbacks = optuna_callbacks
self._best_params = {}
# Set default parameters as best.
self._best_params.update(_DEFAULT_LIGHTGBM_PARAMETERS)
if study is None:
self.study = optuna.create_study(
direction="maximize" if self.higher_is_better(
) else "minimize")
else:
self.study = study
if self.higher_is_better():
if self.study.direction != optuna.study.StudyDirection.MAXIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'maximize' as the direction.".format(
metric_name))
else:
if self.study.direction != optuna.study.StudyDirection.MINIMIZE:
metric_name = self.lgbm_params.get("metric", "binary_logloss")
raise ValueError(
"Study direction is inconsistent with the metric {}. "
"Please set 'minimize' as the direction.".format(
metric_name))
def test_handling_alias_metrics() -> None:
for alias in [
"lambdarank",
"rank_xendcg",
"xendcg",
"xe_ndcg",
"xe_ndcg_mart",
"xendcg_mart",
"ndcg",
]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "ndcg"
for alias in ["mean_average_precision", "map"]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "map"
for alias in [
"regression", "regression_l2", "l2", "mean_squared_error", "mse"
]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "l2"
lgbm_params = {}
_handling_alias_metrics(lgbm_params)
assert lgbm_params == {}
lgbm_params = {"metric": "auc"}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "auc"
for alias in ["l2_root", "root_mean_squared_error", "rmse"]:
lgbm_params = {"metric": alias}
_handling_alias_metrics(lgbm_params)
assert lgbm_params["metric"] == "rmse"