lenskit.knn.item.ItemKNNScorer
==============================

.. py:class:: lenskit.knn.item.ItemKNNScorer(config = None, **kwargs)
   

   Bases: :py:obj:`lenskit.pipeline.Component`\ [\ :py:obj:`lenskit.data.ItemList`\ ], :py:obj:`lenskit.training.Trainable`


   Item-item nearest-neighbor collaborative filtering feedback. This item-item
   implementation is based on the description of item-based CF by
   :cite:t:`deshpande:iknn` and hard-codes several design decisions found to
   work well in the previous Java-based LensKit code :cite:p:`lenskit-java`. In
   explicit-feedback mode, its output is equivalent to that of the Java
   version.

   .. note::

       This component must be used with queries containing the user's history,
       either directly in the input or by wiring its query input to the output of a
       user history component (e.g., :class:`~lenskit.basic.UserTrainingHistoryLookup`).

   :Stability: Caller


   .. py:attribute:: config
      :type:  ItemKNNConfig

      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:: items
      :type:  lenskit.data.Vocabulary

      Vocabulary of item IDs.


   .. py:attribute:: item_means
      :type:  numpy.ndarray[tuple[int], numpy.dtype[numpy.float32]] | None

      Mean rating for each known item.


   .. py:attribute:: item_counts
      :type:  numpy.ndarray[tuple[int], numpy.dtype[numpy.int32]]

      Number of saved neighbors for each item.


   .. py:attribute:: sim_matrix
      :type:  lenskit.data.matrix.SparseRowArray

      Similarity matrix (sparse CSR tensor).


   .. py:method:: is_trained()

      Query if this component has already been trained.



   .. py:method:: train(data, options = TrainingOptions())

      Train a model.

      The model-training process depends on ``save_nbrs`` and ``min_sim``, but *not* on other
      algorithm parameters.

      :param ratings: (user,item,rating) data for computing item similarities.



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

      Run the pipeline's operation and produce a result.  This is the key
      method for components to implement.