הוסף אוסף מערכי נתונים חדש

my_collection/
  __init__.py
  my_collection.py # Dataset collection definition
  my_collection_test.py # (Optional) test
  description.md # (Optional) collection description (if not included in my_collection.py)
  citations.md # (Optional) collection citations (if not included in my_collection.py)

import collections
from typing import Mapping
from tensorflow_datasets.core import dataset_collection_builder
from tensorflow_datasets.core import naming

class MyCollection(dataset_collection_builder.DatasetCollection):
  """Dataset collection builder my_dataset_collection."""

  @property
  def info(self) -> dataset_collection_builder.DatasetCollectionInfo:
    return dataset_collection_builder.DatasetCollectionInfo.from_cls(
        dataset_collection_class=self.__class__,
        description="my_dataset_collection description.",
        release_notes={
            "1.0.0": "Initial release",
        },
    )

  @property
  def datasets(
      self,
  ) -> Mapping[str, Mapping[str, naming.DatasetReference]]:
    return collections.OrderedDict({
        "1.0.0":
            naming.references_for({
                "dataset_1": "natural_questions/default:0.0.2",
                "dataset_2": "media_sum:1.0.0",
            }),
        "1.1.0":
            naming.references_for({
                "dataset_1": "natural_questions/longt5:0.1.0",
                "dataset_2": "media_sum:1.0.0",
                "dataset_3": "squad:3.0.0"
            })
    })

class MyCollection(dataset_collection_builder.DatasetCollection):
  ...
  @property
  def datasets(self):
    return {
        "1.0.0": {
            "yes_no":
                naming.DatasetReference(
                    dataset_name="yes_no", version="1.0.0"),
            "sst2":
                naming.DatasetReference(
                    dataset_name="glue", config="sst2", version="2.0.0"),
            "assin2":
                naming.DatasetReference(
                    dataset_name="assin2", version="1.0.0"),
        },
        ...
    }

class MyCollection(dataset_collection_builder.DatasetCollection):
  ...
  @property
  def datasets(self):
    return {
        "1.0.0":
            naming.references_for({
                "yes_no": "yes_no:1.0.0",
                "sst2": "glue/sst:2.0.0",
                "assin2": "assin2:1.0.0",
            }),
        ...
    }

from tensorflow_datasets.testing.dataset_collection_builder_testing import DatasetCollectionTestBase
from . import my_collection

class TestMyCollection(DatasetCollectionTestBase):
  DATASET_COLLECTION_CLASS = my_collection.MyCollection

python my_dataset_test.py