tabensemb.trainer.Trainer._cal_leaderboard

method

Trainer._cal_leaderboard(programs_predictions: Dict[str, Dict[str, Dict[str, Tuple[ndarray, ndarray]]]], metrics: List[str] | None = None, test_data_only: bool = False, save: bool = True) → DataFrame

Calculate the leaderboard based on results from cross_validation() or tabensemb.model.AbstractModel._predict_all().

Parameters:

programs_predictions

Results from cross_validation(), or assembled results from tabensemb.model.AbstractModel._predict_all(). See the source code of get_leaderboard() for details.

metrics

The metrics that have been implemented in tabensemb.utils.utils.metric_sklearn().

test_data_only

Whether to evaluate models only on testing datasets.

save

Whether to save the leaderboard locally and as an attribute in the Trainer.

Returns:

pd.DataFrame

The leaderboard dataframe.