Shortcuts

Source code for torchtext.datasets.udpos

import os
from functools import partial
from typing import Union, Tuple

from torchtext._internal.module_utils import is_module_available
from torchtext.data.datasets_utils import (
    _wrap_split_argument,
    _create_dataset_directory,
)

if is_module_available("torchdata"):
    from torchdata.datapipes.iter import FileOpener, IterableWrapper
    from torchtext._download_hooks import HttpReader

URL = "https://bitbucket.org/sivareddyg/public/downloads/en-ud-v2.zip"

MD5 = "bdcac7c52d934656bae1699541424545"

NUM_LINES = {
    "train": 12543,
    "valid": 2002,
    "test": 2077,
}

_EXTRACTED_FILES = {"train": "train.txt", "valid": "dev.txt", "test": "test.txt"}


DATASET_NAME = "UDPOS"


def _filepath_fn(root, _=None):
    return os.path.join(root, os.path.basename(URL))


def _extracted_filepath_fn(root, split, _=None):
    return os.path.join(root, _EXTRACTED_FILES[split])


def _filter_fn(split, x):
    return _EXTRACTED_FILES[split] in x[0]


[docs]@_create_dataset_directory(dataset_name=DATASET_NAME) @_wrap_split_argument(("train", "valid", "test")) def UDPOS(root: str, split: Union[Tuple[str], str]): """UDPOS Dataset .. warning:: using datapipes is still currently subject to a few caveats. if you wish to use this dataset with shuffling, multi-processing, or distributed learning, please see :ref:`this note <datapipes_warnings>` for further instructions. Number of lines per split: - train: 12543 - valid: 2002 - test: 2077 Args: root: Directory where the datasets are saved. Default: os.path.expanduser('~/.torchtext/cache') split: split or splits to be returned. Can be a string or tuple of strings. Default: (`train`, `valid`, `test`) :returns: DataPipe that yields list of words along with corresponding parts-of-speech tags :rtype: [list(str), list(str)] """ 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_compressed_dp = url_dp.on_disk_cache( filepath_fn=partial(_filepath_fn, root), hash_dict={_filepath_fn(root): MD5}, hash_type="md5", ) cache_compressed_dp = HttpReader(cache_compressed_dp).end_caching(mode="wb", same_filepath_fn=True) cache_decompressed_dp = cache_compressed_dp.on_disk_cache(filepath_fn=partial(_extracted_filepath_fn, root, split)) cache_decompressed_dp = ( FileOpener(cache_decompressed_dp, mode="b").load_from_zip().filter(partial(_filter_fn, split)) ) cache_decompressed_dp = cache_decompressed_dp.end_caching(mode="wb", same_filepath_fn=True) data_dp = FileOpener(cache_decompressed_dp, encoding="utf-8") return data_dp.readlines().read_iob().shuffle().set_shuffle(False).sharding_filter()

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources