RunDataset

class lightning_ir.data.dataset.RunDataset(run_path_or_id: Path | str, depth: int = -1, sample_size: int = -1, sampling_strategy: Literal['single_relevant', 'top', 'random', 'log_random', 'top_and_random'] = 'top', targets: Literal['relevance', 'subtopic_relevance', 'rank', 'score'] | None = None, normalize_targets: bool = False, add_non_retrieved_docs: bool = False)

Bases: IRDataset, Dataset

__init__(run_path_or_id: Path | str, depth: int = -1, sample_size: int = -1, sampling_strategy: Literal['single_relevant', 'top', 'random', 'log_random', 'top_and_random'] = 'top', targets: Literal['relevance', 'subtopic_relevance', 'rank', 'score'] | None = None, normalize_targets: bool = False, add_non_retrieved_docs: bool = False) → None

Methods

__init__(run_path_or_id[, depth, ...])
load_csv(path)
load_json(path)
load_parquet(path)
load_run()

Attributes

DASHED_DATASET_MAP
dataset_id
docs
docs_dataset_id
qrels
queries