skills/pytdc/scripts/benchmark_evaluation.py

• benchmark_names · function · L37-L42 — def benchmark_names(metadata: Any, group: str) -> list[str]
• validate_seeds · function · L45-L54 — def validate_seeds(seeds: list[int]) -> list[int]
• _validate_values · function · L57-L68 — def _validate_values(values: Any, dataset: str) -> list[float]
• normalize_prediction_mapping · function · L71-L95 — def normalize_prediction_mapping( value: Any, *, available: list[str], selected_dataset: str | None, ) -> tuple[dict[str, list[float]], int]
• normalize_predictions · function · L98-L158 — def normalize_predictions( payload: Any, *, mode: str, available: list[str], selected_dataset: str | None, ) -> tuple[dict[str, list[float]] | list[dict[str, list[float]]], list[int | None]]
• build_plan · function · L161-L191 — def build_plan( *, group: str, dataset: str | None, seeds: list[int], data_dir: Path, package_version: str, metric: str | None, prediction_summary: dict[str, Any] | None, ) -> dict[str, Any]
• execute_evaluation · function · L194-L227 — def execute_evaluation( *, group: str, dataset: str | None, mode: str, predictions: dict[str, list[float]] | list[dict[str, list[float]]], run_seeds: list[int | None], data_dir: Path, package_version: str, ) -> dict[str, Any]
• build_parser · function · L230-L279 — def build_parser() -> argparse.ArgumentParser
• main · function · L282-L363 — def main(argv: list[str] | None = None) -> int