calc_auc_metrics

rectools.metrics.auc.calc_auc_metrics(metrics: Dict[str, Union[PartialAUC, PAP]], reco: DataFrame, interactions: DataFrame) → Dict[str, float][source]

Calculate any ROC AUC based ranking metric.

Works with pre-prepared data.

Warning: It is not recommended to use this function directly. Use calc_metrics instead.

Parameters

  • metrics (dict(str -> AucMetric)) – Dict of metric objects to calculate, where key is metric name and value is metric object.

  • reco (pd.DataFrame) – Recommendations table with columns Columns.User, Columns.Item, Columns.Rank.

  • interactions (pd.DataFrame, optional) – Interactions table with columns Columns.User, Columns.Item. Obligatory only for some types of metrics.

Returns

Dictionary where keys are the same with keys in metrics and values are metric calculation results.

Return type

dict(str->float)