def find_datasets()

in evals/eval/evaluate.py [0:0]

• 11 lines of code
• 7 McCabe index (conditional complexity)

def find_datasets(pair):
    formatted_pair = f"{pair[0]}-{pair[1]}"
    datasets = []
    datasets += CUSTOM_DATASETS

    for dataset_name, descr in dataset.DATASETS.items():
        is_wmt_official = dataset_name.startswith("wmt") and len(dataset_name) == 5
        is_other_accepted = dataset_name == "iwslt17" or dataset_name == "mtedx/test"

        if not (is_wmt_official or is_other_accepted) or formatted_pair not in descr.langpairs:
            continue

        datasets.append(dataset_name)

    return datasets