TimeSeriesPredictor.load¶

classmethod TimeSeriesPredictor.load(path: str | Path, require_version_match: bool = True) → TimeSeriesPredictor[source]¶

Load an existing TimeSeriesPredictor from given path.

Parameters:

path (str or pathlib.Path) – Path where the predictor was saved via save().
require_version_match (bool, default = True) – If True, will raise an AssertionError if the autogluon.timeseries version of the loaded predictor does not match the installed version of autogluon.timeseries. If False, will allow loading of models trained on incompatible versions, but is NOT recommended. Users may run into numerous issues if attempting this.

Returns:

predictor

Return type:

TimeSeriesPredictor

Examples

>>> predictor = TimeSeriesPredictor.load(path_to_predictor)