lenskit.testing.ScorerTests
===========================

.. py:class:: lenskit.testing.ScorerTests
   :canonical: lenskit.testing._components.ScorerTests

   Bases: :py:obj:`TrainingTests`


   Common tests for scorer components.  Many of these just test that the component
   runs, not that it produces correct output.


   .. py:attribute:: component
      :type:  ClassVar[type[lenskit.pipeline.Component]]


   .. py:attribute:: can_score
      :type:  ClassVar[Literal['some', 'known', 'all']]
      :value: 'known'


      What can this scorer score?


   .. py:attribute:: expected_rmse
      :type:  ClassVar[float | tuple[float, float] | object | None]
      :value: None


      Asserts RMSE either less than the provided expected value or between two values as tuple.


   .. py:attribute:: expected_ndcg
      :type:  ClassVar[float | tuple[float, float] | object | None]
      :value: None


      Asserts nDCG either greater than the provided expected value or between two values as tuple.


   .. py:method:: invoke_scorer(pipe, **kwargs)


   .. py:method:: verify_models_equivalent(orig, copy)

      Verify that two models are equivalent.



   .. py:method:: test_score_known(rng, ml_ds, trained_pipeline)


   .. py:method:: test_pickle_roundrip(rng, ml_ds, trained_pipeline, trained_model)


   .. py:method:: test_score_unknown_user(rng, ml_ds, trained_pipeline)

      score with an unknown user ID



   .. py:method:: test_score_unknown_item(rng, ml_ds, trained_pipeline)

      score with one target item unknown



   .. py:method:: test_score_empty_query(rng, ml_ds, trained_pipeline)

      score with an empty query



   .. py:method:: test_score_query_history(rng, ml_ds, trained_pipeline)

      score when query has user ID and history



   .. py:method:: test_score_query_history_only(rng, ml_ds, trained_pipeline)

      score when query only has history



   .. py:method:: test_score_empty_items(rng, ml_ds, trained_pipeline)

      score an empty list of items



   .. py:method:: test_train_score_items_missing_data(rng, ml_ds)

      train and score when some entities are missing data



   .. py:method:: test_train_recommend(rng, ml_ds, trained_topn_pipeline)

      Test that a full train-recommend pipeline works.



   .. py:method:: test_ray_recommend(rng, ml_ds, trained_topn_pipeline)

      Ensure pipeline can be used via Ray.



   .. py:method:: test_run_with_doubles(ml_ratings)


   .. py:method:: test_batch_prediction_accuracy(rng, ml_100k)


   .. py:method:: test_batch_top_n_accuracy(rng, ml_100k)