kedro_datasets.huggingface.HFTransformerPipelineDataset

class kedro_datasets.huggingface.HFTransformerPipelineDataset(*, task=None, model_name=None, pipeline_kwargs=None)[source]

HFTransformerPipelineDataset loads pretrained Hugging Face transformers using the transformers library.

Example usage for the YAML API:

summarizer_model:
  type: huggingface.HFTransformerPipelineDataset
  task: summarization

fill_mask_model:
  type: huggingface.HFTransformerPipelineDataset
  task: fill-mask
  model_name: Twitter/twhin-bert-base

Example usage for the Python API:

 from kedro_datasets.huggingface import HFTransformerPipelineDataset
 dataset = HFTransformerPipelineDataset(
...     task="text-classification", model_name="prajjwal1/bert-tiny"
... )
 model = dataset.load()
 assert model("Hello world")[0]["label"].startswith("LABEL_")

Methods

exists()

Checks whether a data set's output already exists by calling the provided _exists() method.

from_config(name, config[, load_version, ...])

Create a data set instance using the configuration provided.

load()

Loads data by delegation to the provided load method.

release()

Release any cached data.

save(data)

Saves data by delegation to the provided save method.
exists()

Checks whether a data set’s output already exists by calling the provided _exists() method.

Return type:

bool

Returns:

Flag indicating whether the output already exists.

Raises:

DatasetError – when underlying exists method raises error.

classmethod from_config(name, config, load_version=None, save_version=None)

Create a data set instance using the configuration provided.

Parameters:

  • name (str) – Data set name.

  • config (dict[str, Any]) – Data set config dictionary.

  • load_version (Optional[str]) – Version string to be used for load operation if the data set is versioned. Has no effect on the data set if versioning was not enabled.

  • save_version (Optional[str]) – Version string to be used for save operation if the data set is versioned. Has no effect on the data set if versioning was not enabled.

Return type:

AbstractDataset

Returns:

An instance of an AbstractDataset subclass.

Raises:

DatasetError – When the function fails to create the data set from its config.

load()

Loads data by delegation to the provided load method.

Return type:

TypeVar(_DO)

Returns:

Data returned by the provided load method.

Raises:

DatasetError – When underlying load method raises error.

release()

Release any cached data.

Raises:

DatasetError – when underlying release method raises error.

Return type:

None

save(data)

Saves data by delegation to the provided save method.

Parameters:

data (TypeVar(_DI)) – the value to be saved by provided save method.

Raises:

  • DatasetError – when underlying save method raises error.

  • FileNotFoundError – when save method got file instead of dir, on Windows.

  • NotADirectoryError – when save method got file instead of dir, on Unix.

Return type:

None