pykeen Logo
v1.5.0

Getting Started

  • Installation
  • First Steps
  • Tracking Results during Training
  • Saving Checkpoints during Training
  • A Toy Example with Translational Distance Models
  • Understanding the Evaluation
  • Optimizing a Model’s Hyper-parameters
  • Novel Link Prediction
  • Running an Ablation Study
  • Performance Tricks

Bring Your Own

  • Bring Your Own Data
  • Bring Your Own Interaction

Extending PyKEEN

  • Extending the Datasets
  • Extending the Models
  • Extending the Interaction Models (Old-Style)

Reference

  • Pipeline
  • Models
  • Datasets
    • pykeen.datasets Package
      • Functions
      • Classes
        • Hetionet
        • Kinships
        • Nations
        • OpenBioLink
        • OpenBioLinkLQ
        • CoDExSmall
        • CoDExMedium
        • CoDExLarge
        • OGBBioKG
        • OGBWikiKG
        • UMLS
        • FB15k
        • FB15k237
        • WK3l15k
        • WN18
        • WN18RR
        • YAGO310
        • DRKG
        • ConceptNet
        • CKG
        • CSKG
        • DBpedia50
        • DB100K
        • Countries
      • Class Inheritance Diagram
    • pykeen.datasets.base Module
    • pykeen.datasets.analysis Module
  • Triples
  • Training
  • Stoppers
  • Loss Functions
  • Regularizers
  • Result Trackers
  • Negative Sampling
  • Filtering
  • Evaluation
  • Hyper-parameter Optimization
  • Ablation
  • Lookup
  • Prediction
  • Sealant
  • Constants
  • pykeen.nn
  • Utilities

Appendix

  • References
pykeen
  • »
  • Datasets »
  • OpenBioLink
  • Edit on GitHub

OpenBioLink¶

class OpenBioLink(create_inverse_triples=False, **kwargs)[source]¶

Bases: pykeen.datasets.base.PackedZipRemoteDataset

The OpenBioLink dataset.

OpenBioLink is an open-source, reproducible framework for generating biological knowledge graphs for benchmarking link prediction. It is available on GitHub at https://github.com/openbiolink/openbiolink and published in [breit2020]. There are four available datasets - this class represents the high quality, directed set.

Initialize the OpenBioLink dataset.

Parameters
  • create_inverse_triples (bool) – Should inverse triples be created? Defaults to false.

  • kwargs – keyword arguments passed to pykeen.datasets.base.PackedZipRemoteDataset.

Next Previous

© Copyright 2019-2021, PyKEEN Project Team. Revision 87e6c28f.

Built with Sphinx using a theme provided by Read the Docs.