Source code for pykeen.datasets.openbiolink

# -*- coding: utf-8 -*-

"""The OpenBioLink dataset.

Get a summary with ``python -m pykeen.datasets.openbiolink``

import click
from docdata import parse_docdata
from more_click import verbose_option

from .base import PackedZipRemoteDataset

__all__ = [

HQ_URL = ""
LQ_URL = ""

[docs]@parse_docdata class OpenBioLinkLQ(PackedZipRemoteDataset): """The low-quality variant of the OpenBioLink dataset. --- name: OpenBioLink LQ citation: author: Breit year: 2020 link: github: openbiolink/openbiolink statistics: entities: 480876 relations: 32 training: 25508954 testing: 679934 validation: 1132001 triples: 27320889 """ def __init__(self, **kwargs): """Initialize the OpenBioLink (low quality) dataset. :param kwargs: keyword arguments passed to :class:`pykeen.datasets.base.PackedZipRemoteDataset`. """ super().__init__( url=LQ_URL, name="", relative_training_path="ALL_DIR/train_test_data/train_sample.csv", relative_testing_path="ALL_DIR/train_test_data/test_sample.csv", relative_validation_path="ALL_DIR/train_test_data/val_sample.csv", **kwargs, )
@click.command() @verbose_option def _main(): for cls in [OpenBioLink, OpenBioLinkLQ]: cls().summarize() if __name__ == "__main__": _main()