TimeSeriesPredictor.load

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

Load an existing TimeSeriesPredictor from given path.

Warning

autogluon.timeseries.TimeSeriesPredictor.load() uses pickle module implicitly, which is known to be insecure. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling. Never load data that could have come from an untrusted source, or that could have been tampered with. Only load data you trust.

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)