data_loader#

class FlagEmbedding.evaluation.miracl.MIRACLEvalDataLoader(eval_name: str, dataset_dir: str | None = None, cache_dir: str | None = None, token: str | None = None, force_redownload: bool = False)[source]#

Data loader class for MIRACL.

Methods#

MIRACLEvalDataLoader.available_dataset_names() → List[str][source]#

Get the available dataset names.

Returns:

All the available dataset names.

Return type:

List[str]

MIRACLEvalDataLoader.available_splits(dataset_name: str) → List[str][source]#

Get the avaialble splits.

Parameters:

dataset_name (str) – Dataset name.

Returns:

All the available splits for the dataset.

Return type:

List[str]

MIRACLEvalDataLoader._load_remote_corpus(dataset_name: str, save_dir: str | None = None) → DatasetDict[source]#

Load the corpus dataset from HF.

Parameters:

  • dataset_name (str) – Name of the dataset.

  • save_dir (Optional[str], optional) – Directory to save the dataset. Defaults to None.

Returns:

Loaded datasets instance of corpus.

Return type:

datasets.DatasetDict

MIRACLEvalDataLoader._load_remote_qrels(dataset_name: str, split: str = 'dev', save_dir: str | None = None) → DatasetDict[source]#

Load the qrels from HF.

Parameters:

  • dataset_name (str) – Name of the dataset.

  • split (str, optional) – Split of the dataset. Defaults to 'dev'.

  • save_dir (Optional[str], optional) – Directory to save the dataset. Defaults to None.

Returns:

Loaded datasets instance of qrel.

Return type:

datasets.DatasetDict

MIRACLEvalDataLoader._load_remote_queries(dataset_name: str, split: str = 'dev', save_dir: str | None = None) → DatasetDict[source]#

Load the queries from HF.

Parameters:

  • dataset_name (str) – Name of the dataset.

  • split (str, optional) – Split of the dataset. Defaults to 'dev'.

  • save_dir (Optional[str], optional) – Directory to save the dataset. Defaults to None.

Returns:

Loaded datasets instance of queries.

Return type:

datasets.DatasetDict