EvaluationSubsetReport#
- class openstef_beam.evaluation.EvaluationSubsetReport(*, filtering: Filtering, subset: ForecastDataset, metrics: list[SubsetMetric])[source]#
Bases:
BaseModelContainer for evaluation results on a specific data subset.
Bundles filtering criteria, evaluation subset data, and computed metrics for a particular slice of the evaluation dataset. Enables persistence and retrieval of evaluation results for analysis.
- Parameters:
filtering (
AvailableAt|LeadTime)subset (
ForecastDataset)metrics (
list[SubsetMetric])
- filtering: Filtering#
- subset: ForecastDataset#
- metrics: list[SubsetMetric]#
- to_parquet(path: Path)[source]#
Save the subset report to parquet files in the specified directory.
- Parameters:
path (
Path) – Directory where to save the report data.
- classmethod read_parquet(path: Path) Self[source]#
Load a subset report from parquet files in the specified directory.
- get_global_metric() SubsetMetric | None[source]#
Returns the SubsetMetric with window=’global’, or None if not found.
- Return type:
- get_windowed_metrics() list[SubsetMetric][source]#
Returns all SubsetMetrics with window != ‘global’.
- Return type:
- get_measurements() Series[source]#
Extract measurements Series from the report for the given target.
- Return type:
- Returns:
Ground truth measurements as a pandas Series.