TimeSeriesPredictor.refit_full

TimeSeriesPredictor.refit_full(model: str = 'all', set_best_to_refit_full: bool = True) → Dict[str, str][source]

Retrain model on all of the data (training + validation).

This method can only be used if no tuning_data was passed to fit().

Warning

This is experimental functionality, many time series models do not yet support refit_full and will simply be copied.

Parameters:

  • model (str, default = "all") –

    Name of the model to refit. All ancestor models will also be refit in the case that the selected model is a weighted ensemble. Valid models are listed in this predictor by calling model_names().

    • If “all” then all models are refitted.

    • If “best” then the model with the highest validation score is refit.

  • set_best_to_refit_full (bool, default = True) – If True, sets best model to the refit_full version of the prior best model. This means the model used when predictor.predict(data) is called will be the refit_full version instead of the original version of the model. Has no effect if model is not the best model.