DRKG

class DRKG(create_inverse_triples=False, random_state=0, **kwargs)[source]

Bases: pykeen.datasets.base.TarFileSingleDataset

The DRKG dataset.

This is a medium-sized biological knowledge graph including 97,238 entities, 13 entity types, 107 relations, and 5,874,261 triples.

See also

https://github.com/gnn4dr/DRKG

Initialize dataset.

Parameters

  • url – The url where to download the dataset from

  • name – The name of the file. If not given, tries to get the name from the end of the URL

  • cache_root – An optional directory to store the extracted files. Is none is given, the default PyKEEN directory is used. This is defined either by the environment variable PYKEEN_HOME or defaults to ~/.pykeen.

  • relative_path – The path inside the archive to the contained dataset.

  • random_state (Union[None, int, Generator]) – An optional random state to make the training/testing/validation split reproducible.

  • delimiter – The delimiter for the contained dataset.