def get_best_booster(self) -> "lgb.CVBooster":
"""Return the best cvbooster.
If the best booster cannot be found, :class:`ValueError` will be raised.
To prevent the errors, please save boosters by specifying
both of the ``model_dir`` and the ``return_cvbooster`` arguments of
:meth:`~optuna.integration.lightgbm.LightGBMTunerCV.__init__`,
when you resume tuning or you run tuning in parallel.
"""
if self.lgbm_kwargs.get("return_cvbooster") is not True:
raise ValueError(
"LightGBMTunerCV requires `return_cvbooster=True` for method `get_best_booster()`."
)
if self._best_booster_with_trial_number is not None:
if self._best_booster_with_trial_number[
1] == self.study.best_trial.number:
return self._best_booster_with_trial_number[0]
if len(self.study.trials) == 0:
raise ValueError(
"The best booster is not available because no trials completed."
)
# The best booster exists, but this instance does not have it.
# This may be due to resuming or parallelization.
if self._model_dir is None:
raise ValueError(
"The best booster cannot be found. It may be found in the other processes due to "
"resuming or distributed computing. Please set the `model_dir` argument of "
"`LightGBMTunerCV.__init__` and make sure that boosters are shared with all "
"processes.")
best_trial = self.study.best_trial
path = os.path.join(self._model_dir,
"{}.pkl".format(best_trial.number))
if not os.path.exists(path):
raise ValueError(
"The best booster cannot be found in {}. If you execute `LightGBMTunerCV` in "
"distributed environment, please use network file system (e.g., NFS) to share "
"models with multiple workers.".format(self._model_dir))
with open(path, "rb") as fin:
boosters, best_iteration = pickle.load(fin)
# At version `lightgbm==3.0.0`, :class:`lightgbm.CVBooster` does not
# have `__getstate__` which is required for pickle serialization.
cvbooster = lgb.CVBooster()
cvbooster.boosters = boosters
cvbooster.best_iteration = best_iteration
return cvbooster
# ベースモデル読み込み
with open(f"./pkl/lr_{hash_lr}.pkl", "rb") as f:
clf_lr = pickle.load(f)
with open(f"./pkl/rf_{hash_rf}.pkl", "rb") as f:
clf_rf = pickle.load(f)
with open(f"./pkl/knn_{hash_knn}.pkl", "rb") as f:
clf_knn = pickle.load(f)
# with open(f"./pkl/lgbm_{hash_lgbm}.pkl", "rb") as f:
# clf_lgbm = pickle.load(f)
with open(f"./pkl/catb_{hash_catb}.pkl", "rb") as f:
clf_catb = pickle.load(f)
with open(f"./pkl/svc_{hash_svc}.pkl", "rb") as f:
clf_svc = pickle.load(f)
cvbooster = lgb.CVBooster()
for i in range(5):
booster_file = f"./pkl/lgbm_cv_{hash_lgbm}_{i}.txt"
tmp = lgb.Booster(model_file=booster_file)
cvbooster._append(booster=tmp)
with open(f"./pkl/lgbm_cv_{hash_lgbm}_best_iter.txt") as f:
cvbooster.best_iteration = int(f.read())
net = mlp_net.net()
net.load_state_dict(torch.load(f"./pkl/mlp_{hash_mlp}.net"))
# データ読み込み
df_test_tree = pd.read_csv("./data/test_prep_tree.csv")
df_test_nontree = pd.read_csv("./data/test_prep_nontree.csv")
df_lr = pd.read_csv(f"./output/base_pred_proba_lr_{hash_lr}.csv")
