lenskit.flexmf.FlexMFScorerBase
===============================

.. py:class:: lenskit.flexmf.FlexMFScorerBase(config = None, **kwargs)
   :canonical: lenskit.flexmf._base.FlexMFScorerBase

   Bases: :py:obj:`lenskit.training.UsesTrainer`, :py:obj:`lenskit.pipeline.Component`


   Base class for the FlexMF scorers, providing common Torch support.

   :Stability: Experimental


   .. py:attribute:: config
      :type:  FlexMFConfigBase

      The component configuration object.  Component classes that support
      configuration **must** redefine this attribute with their specific
      configuration class type, which can be a Python dataclass or a Pydantic
      model class.


   .. py:attribute:: users
      :type:  lenskit.data.Vocabulary


   .. py:attribute:: items
      :type:  lenskit.data.Vocabulary


   .. py:attribute:: model
      :type:  lenskit.flexmf._model.FlexMFModel


   .. py:method:: to(device)

      Move the model to a different device.



   .. py:method:: __call__(query, items)

      Generate item scores for a user.

      Note that user and items are both user and item IDs, not positions.



   .. py:method:: score_items(users, items)

      Score for users and items, after resolivng them and limiting to known
      users and items.