torchtext/datasets/amazonreviewfull.py [43:59]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if not is_module_available("torchdata"):
        raise ModuleNotFoundError("Package `torchdata` not found. Please install following instructions at `https://github.com/pytorch/data`")

    url_dp = IterableWrapper([URL])

    cache_dp = url_dp.on_disk_cache(
        filepath_fn=lambda x: os.path.join(root, _PATH),
        hash_dict={os.path.join(root, _PATH): MD5}, hash_type="md5"
    )
    cache_dp = GDriveReader(cache_dp).end_caching(mode="wb", same_filepath_fn=True)
    cache_dp = FileOpener(cache_dp, mode="b")

    extracted_files = cache_dp.read_from_tar()

    filter_extracted_files = extracted_files.filter(lambda x: _EXTRACTED_FILES[split] in x[0])

    return filter_extracted_files.parse_csv().map(fn=lambda t: (int(t[0]), " ".join(t[1:])))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



torchtext/datasets/dbpedia.py [39:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if not is_module_available("torchdata"):
        raise ModuleNotFoundError("Package `torchdata` not found. Please install following instructions at `https://github.com/pytorch/data`")

    url_dp = IterableWrapper([URL])

    cache_dp = url_dp.on_disk_cache(
        filepath_fn=lambda x: os.path.join(root, _PATH),
        hash_dict={os.path.join(root, _PATH): MD5}, hash_type="md5"
    )
    cache_dp = GDriveReader(cache_dp).end_caching(mode="wb", same_filepath_fn=True)
    cache_dp = FileOpener(cache_dp, mode="b")

    extracted_files = cache_dp.read_from_tar()

    filter_extracted_files = extracted_files.filter(lambda x: _EXTRACTED_FILES[split] in x[0])

    return filter_extracted_files.parse_csv().map(fn=lambda t: (int(t[0]), " ".join(t[1:])))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -