manager.trainer.get_path_model

manager.trainer.get_path_model(name, iteration, model_dir=None)

Yield the path to a model file for a given iteration and model name.

Parameters

Name	Type	Description	Default
name	str	Model name (e.g. `"lgbm"`, `"xgb"`).	required
iteration	int	Iteration of the model.	required
model_dir	Optional[Union[str, Path]]	Directory where models are stored. If None, defaults to `get_cache_home()`.	`None`

Returns

Name	Type	Description
Path	Path	Full path where the model file should be stored.

Examples

import tempfile
from pathlib import Path
from spotforecast2_safe.manager.trainer import get_path_model

with tempfile.TemporaryDirectory() as tmpdir:
    p = get_path_model("lgbm", 3, model_dir=tmpdir)
    print(p.name)
    assert p.name == "lgbm_forecaster_3.joblib"

lgbm_forecaster_3.joblib