Pipeline

The PyKEEN pipeline and related wrapper functions.

Functions

build_representation_getter([relation, index])	Build a representation getter.
pipeline(*[, dataset, dataset_kwargs, ...])	Train and evaluate a model.
pipeline_from_config(config[, discard_seed])	Run the pipeline with a configuration dictionary.
pipeline_from_path(path, **kwargs)	Run the pipeline with configuration in a JSON/YAML file at the given path.
plot(pipeline_result[, er_kwargs, figsize])	Plot all plots.
plot_early_stopping(pipeline_result, *[, ...])	Plot the evaluations during early stopping.
plot_er(pipeline_result, *[, model, ...])	Plot the reduced entities and relation vectors in 2D.
plot_losses(pipeline_result, *[, ax])	Plot the losses per epoch.
replicate_pipeline_from_config(config, ...)	Run the same pipeline several times from a configuration dictionary.
replicate_pipeline_from_path(path, **kwargs)	Run the same pipeline several times from a configuration file by path.
resolve_pipeline(*[, dataset, ...])	Resolve all pipeline components into a ResolutionResult without running training.

Classes

PipelineResult(random_seed, model, training, ...)	A dataclass containing the results of running pipeline().
ResolutionResult(random_seed, model, ...)	Result of resolve_pipeline(), containing all resolved pipeline components before training.
TrainResult(random_seed, model, training, ...)	Result of training, containing a trained model without post-training evaluation.