def cv(self, dataset: tk.data.Dataset,
folds: tk.validation.FoldsType) -> Model:
"""CVして保存。
Args:
dataset: 入力データ
folds: CVのindex
Returns:
self
"""
dataset = dataset.copy()
if self.preprocessors is not None:
dataset.data = self.preprocessors.fit_transform(
dataset.data, dataset.labels)
if self.postprocessors is not None:
dataset.labels = np.squeeze(
self.postprocessors.fit_transform(
np.expand_dims(dataset.labels, axis=-1)),
axis=-1,
)
self._cv(dataset, folds)
if self.save_on_cv:
self.save()
return self
def cv(
self,
dataset: tk.data.Dataset,
folds: tk.validation.FoldsType,
models_dir: pathlib.Path,
) -> dict:
"""CVして保存。
Args:
dataset: 入力データ
folds: CVのindex
models_dir: 保存先ディレクトリ (Noneなら保存しない)
Returns:
metrics名と値
"""
if models_dir is not None:
models_dir = pathlib.Path(models_dir)
models_dir.mkdir(parents=True, exist_ok=True)
dataset = dataset.copy()
if self.preprocessors is not None:
dataset.data = self.preprocessors.fit_transform(
dataset.data, dataset.labels)
if self.postprocessors is not None:
dataset.labels = np.squeeze(
self.postprocessors.fit_transform(
np.expand_dims(dataset.labels, axis=-1)),
axis=-1,
)
scores = self._cv(dataset, folds)
if models_dir is not None:
if self.preprocessors is not None:
tk.utils.dump(self.preprocessors,
models_dir / "preprocessors.pkl")
if self.postprocessors is not None:
tk.utils.dump(self.postprocessors,
models_dir / "postprocessors.pkl")
self._save(models_dir)
return scores