Add support for RTE dataset with unit tests

docs/source/datasets.rst

@@ -72,6 +72,11 @@ QQP
 
 .. autofunction:: QQP
 
+RTE
+~~~~
+
+.. autofunction:: RTE
+
 SogouNews
 ~~~~~~~~~
 

test/datasets/test_rte.py

@@ -0,0 +1,84 @@
+import os
+import zipfile
+from collections import defaultdict
+from unittest.mock import patch
+
+from parameterized import parameterized
+from torchtext.datasets.rte import RTE
+
+from ..common.case_utils import TempDirMixin, zip_equal, get_random_unicode
+from ..common.torchtext_test_case import TorchtextTestCase
+
+
+def _get_mock_dataset(root_dir):
+    """
+    root_dir: directory to the mocked dataset
+    """
+    base_dir = os.path.join(root_dir, "RTE")
+    temp_dataset_dir = os.path.join(base_dir, "temp_dataset_dir")
+    os.makedirs(temp_dataset_dir, exist_ok=True)
+
+    seed = 1
+    mocked_data = defaultdict(list)
+    for file_name in ("train.tsv", "test.tsv", "dev.tsv"):
+        txt_file = os.path.join(temp_dataset_dir, file_name)
+        with open(txt_file, "w", encoding="utf-8") as f:
+            f.write("index\tsentence1\tsentence2\tlabel\n")
+            for i in range(5):
+                label = seed % 2
+                rand_string_1 = get_random_unicode(seed)
+                rand_string_2 = get_random_unicode(seed + 1)
+                if file_name == "test.tsv":
+                    dataset_line = (rand_string_1, rand_string_2)
+                    f.write(f"{i}\t{rand_string_1}\t{rand_string_2}\n")
+                else:
+                    dataset_line = (label, rand_string_1, rand_string_2)
+                    f.write(f"{i}\t{rand_string_1}\t{rand_string_2}\t{label}\n")
+
+                # append line to correct dataset split
+                mocked_data[os.path.splitext(file_name)[0]].append(dataset_line)
+                seed += 1
+
+    compressed_dataset_path = os.path.join(base_dir, "RTE.zip")
+    # create zip file from dataset folder
+    with zipfile.ZipFile(compressed_dataset_path, "w") as zip_file:
+        for file_name in ("train.tsv", "test.tsv", "dev.tsv"):
+            txt_file = os.path.join(temp_dataset_dir, file_name)
+            zip_file.write(txt_file, arcname=os.path.join("RTE", file_name))
+
+    return mocked_data
+
+
+class TestSST2(TempDirMixin, TorchtextTestCase):
+    root_dir = None
+    samples = []
+
+    @classmethod
+    def setUpClass(cls):
+        super().setUpClass()
+        cls.root_dir = cls.get_base_temp_dir()
+        cls.samples = _get_mock_dataset(cls.root_dir)
+        cls.patcher = patch("torchdata.datapipes.iter.util.cacheholder._hash_check", return_value=True)
+        cls.patcher.start()
+
+    @classmethod
+    def tearDownClass(cls):
+        cls.patcher.stop()
+        super().tearDownClass()
+
+    @parameterized.expand(["train", "test", "dev"])
+    def test_rte(self, split):
+        dataset = RTE(root=self.root_dir, split=split)
+
+        samples = list(dataset)
+        expected_samples = self.samples[split]
+        for sample, expected_sample in zip_equal(samples, expected_samples):
+            self.assertEqual(sample, expected_sample)
+
+    @parameterized.expand(["train", "test", "dev"])
+    def test_rte_split_argument(self, split):
+        dataset1 = RTE(root=self.root_dir, split=split)
+        (dataset2,) = RTE(root=self.root_dir, split=(split,))
+
+        for d1, d2 in zip_equal(dataset1, dataset2):
+            self.assertEqual(d1, d2)

torchtext/datasets/__init__.py

@@ -16,6 +16,7 @@
 from .multi30k import Multi30k
 from .penntreebank import PennTreebank
 from .qqp import QQP
+from .rte import RTE
 from .sogounews import SogouNews
 from .squad1 import SQuAD1
 from .squad2 import SQuAD2
@@ -45,6 +46,7 @@
     "Multi30k": Multi30k,
     "PennTreebank": PennTreebank,
     "QQP": QQP,
+    "RTE": RTE,
     "SQuAD1": SQuAD1,
     "SQuAD2": SQuAD2,
     "SogouNews": SogouNews,

torchtext/datasets/rte.py

@@ -0,0 +1,100 @@
+# Copyright (c) Facebook, Inc. and its affiliates.
+import os
+from functools import partial
+
+from torchtext._internal.module_utils import is_module_available
+from torchtext.data.datasets_utils import (
+    _create_dataset_directory,
+    _wrap_split_argument,
+)
+
+if is_module_available("torchdata"):
+    from torchdata.datapipes.iter import FileOpener, IterableWrapper
+
+    # we import HttpReader from _download_hooks so we can swap out public URLs
+    # with interal URLs when the dataset is used within Facebook
+    from torchtext._download_hooks import HttpReader
+
+
+URL = "https://dl.fbaipublicfiles.com/glue/data/RTE.zip"
+
+MD5 = "bef554d0cafd4ab6743488101c638539"
+
+NUM_LINES = {
+    "train": 67349,
+    "dev": 872,
+    "test": 1821,
+}
+
+_PATH = "RTE.zip"
+
+DATASET_NAME = "RTE"
+
+_EXTRACTED_FILES = {
+    "train": os.path.join("RTE", "train.tsv"),
+    "dev": os.path.join("RTE", "dev.tsv"),
+    "test": os.path.join("RTE", "test.tsv"),
+}
+
+
+def _filepath_fn(root, x=None):
+    return os.path.join(root, os.path.basename(x))
+
+
+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]
+
+
+def _modify_res(split, x):
+    if split == "test":
+        return (x[1], x[2])
+    else:
+        return (int(x[3]), x[1], x[2])
+
+
+@_create_dataset_directory(dataset_name=DATASET_NAME)
+@_wrap_split_argument(("train", "dev", "test"))
+def RTE(root, split):
+    """RTE Dataset
+
+    For additional details refer to https://aclweb.org/aclwiki/Recognizing_Textual_Entailment
+
+    Number of lines per split:
+        - train: 67349
+        - dev: 872
+        - test: 1821
+
+    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`, `dev`, `test`)
+
+    :returns: DataPipe that yields tuple of text and/or label (0 and 1). The `test` split only returns text.
+    :rtype: Union[(int, str, str), (str, str)]
+    """
+    # TODO Remove this after removing conditional dependency
+    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, URL): 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")
+    parsed_data = data_dp.parse_csv(skip_lines=1, delimiter="\t").map(partial(_modify_res, split))
+    return parsed_data.shuffle().set_shuffle(False).sharding_filter()