형식별 데이터 세트 빌더

import tensorflow as tf
import tensorflow_datasets as tfds

my_ds_train = tf.data.Dataset.from_tensor_slices({"number": [1, 2, 3]})
my_ds_test = tf.data.Dataset.from_tensor_slices({"number": [4, 5]})

# Optionally define a custom `data_dir`.
# If None, then the default data dir is used.
custom_data_dir = "/my/folder"

# Define the builder.
single_number_builder = tfds.dataset_builders.TfDataBuilder(
    name="my_dataset",
    config="single_number",
    version="1.0.0",
    data_dir=custom_data_dir,
    split_datasets={
        "train": my_ds_train,
        "test": my_ds_test,
    },
    features=tfds.features.FeaturesDict({
        "number": tfds.features.Scalar(dtype=tf.int64),
    }),
    description="My dataset with a single number.",
    release_notes={
        "1.0.0": "Initial release with numbers up to 5!",
    }
)

# Make the builder store the data as a TFDS dataset.
single_number_builder.download_and_prepare()

# If no custom data dir was specified:
ds_test = tfds.load("my_dataset/single_number", split="test")

# When there are multiple versions, you can also specify the version.
ds_test = tfds.load("my_dataset/single_number:1.0.0", split="test")

# If the TFDS was stored in a custom folder, then it can be loaded as follows:
custom_data_dir = "/my/folder"
ds_test = tfds.load("my_dataset/single_number:1.0.0", split="test", data_dir=custom_data_dir)

def add_one(example):
  example["number"] = example["number"] + 1
  return example

my_ds_train_v2 = my_ds_train.map(add_one)
my_ds_test_v2 = my_ds_test.map(add_one)

single_number_builder_v2 = tfds.dataset_builders.TfDataBuilder(
    name="my_dataset",
    config="single_number",
    version="1.1.0",
    data_dir=custom_data_dir,
    split_datasets={
        "train": my_ds_train_v2,
        "test": my_ds_test_v2,
    },
    features=tfds.features.FeaturesDict({
        "number": tfds.features.Scalar(dtype=tf.int64, doc="Some number"),
    }),
    description="My dataset with a single number.",
    release_notes={
        "1.1.0": "Initial release with numbers up to 6!",
        "1.0.0": "Initial release with numbers up to 5!",
    }
)

# Make the builder store the data as a TFDS dataset.
single_number_builder_v2.download_and_prepare()

import tensorflow as tf
import tensorflow_datasets as tfds

class MyDatasetBuilder(tfds.dataset_builders.TfDataBuilder):
  def __init__(self):
    ds_train = tf.data.Dataset.from_tensor_slices([1, 2, 3])
    ds_test = tf.data.Dataset.from_tensor_slices([4, 5])
    super().__init__(
        name="my_dataset",
        version="1.0.0",
        split_datasets={
            "train": ds_train,
            "test": ds_test,
        },
        features=tfds.features.FeaturesDict({
            "number": tfds.features.Scalar(dtype=tf.int64),
        }),
        config="single_number",
        description="My dataset with a single number.",
        release_notes={
            "1.0.0": "Initial release with numbers up to 5!",
        })

import tensorflow_datasets as tfds
builder = tfds.dataset_builders.CroissantBuilder(
    jsonld="https://raw.githubusercontent.com/mlcommons/croissant/main/datasets/0.8/huggingface-mnist/metadata.json",
    file_format='array_record',
)
builder.download_and_prepare()
ds = builder.as_data_source()
print(ds['default'][0])

U.N. NNP I-NP I-ORG official
NN I-NP O
Ekeus NNP I-NP I-PER
heads VBZ I-VP O
for IN I-PP O
Baghdad NNP I-NP
I-LOC . . O O

from tensorflow_datasets.core.dataset_builders.conll import conll_dataset_builder_utils as conll_lib
import tensorflow_datasets.public_api as tfds

class MyCoNNLDataset(tfds.dataset_builders.ConllDatasetBuilder):
  VERSION = tfds.core.Version('1.0.0')
  RELEASE_NOTES = {'1.0.0': 'Initial release.'}

  # conllu_lib contains a set of ready-to-use CONLL-specific configs.
  BUILDER_CONFIGS = [conll_lib.CONLL_2003_CONFIG]

  def _info(self) -> tfds.core.DatasetInfo:
    return self.create_dataset_info(
        # ...
    )

  def _split_generators(self, dl_manager):
    path = dl_manager.download_and_extract('https://data-url')

    return {'train': self._generate_examples(path=path / 'train.txt'),
            'test': self._generate_examples(path=path / 'train.txt'),
    }

cd path/to/my/project/datasets/
tfds new my_dataset --format=conll   # Create `my_dataset/my_dataset.py` CoNLL-specific template files

1-2    vámonos   _
1      vamos     ir
2      nos       nosotros
3-4    al        _
3      a         a
4      el        el
5      mar       mar

from tensorflow_datasets.core.dataset_builders.conll import conllu_dataset_builder_utils as conllu_lib
import tensorflow_datasets.public_api as tfds

class MyCoNNLUDataset(tfds.dataset_builders.ConllUDatasetBuilder):
  VERSION = tfds.core.Version('1.0.0')
  RELEASE_NOTES = {'1.0.0': 'Initial release.'}

  # conllu_lib contains a set of ready-to-use features.
  BUILDER_CONFIGS = [
      conllu_lib.get_universal_morphology_config(
          language='en',
          features=conllu_lib.UNIVERSAL_DEPENDENCIES_FEATURES,
      )
  ]

  def _info(self) -> tfds.core.DatasetInfo:
    return self.create_dataset_info(
        # ...
    )

  def _split_generators(self, dl_manager):
    path = dl_manager.download_and_extract('https://data-url')

    return {
        'train':
            self._generate_examples(
                path=path / 'train.txt',
                # If necessary, add optional custom processing (see conllu_lib
                # for examples).
                # process_example_fn=...,
            )
    }

cd path/to/my/project/datasets/
tfds new my_dataset --format=conllu   # Create `my_dataset/my_dataset.py` CoNLL-U specific template files