manager.trainer.load_iteration

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

Load a saved model at a given iteration.

Parameters

Name	Type	Description	Default
name	str	Model name (e.g. `"lgbm"`).	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
	Optional[Any]	The loaded model instance, or None if the file does not exist.

Raises

Name	Type	Description
	OSError	If the model file exists on disk but cannot be deserialised (corrupt joblib, version mismatch, etc.). A missing file returns `None` instead — that’s a legitimate “no model yet” state.

Examples

import tempfile
from spotforecast2_safe.manager.trainer import load_iteration

with tempfile.TemporaryDirectory() as tmpdir:
    result = load_iteration("lgbm", 99, model_dir=tmpdir)
    print(result)
    assert result is None

Iteration 99 does not exist at /tmp/tmpnc9ppka3/lgbm_forecaster_99.joblib!

None