lenskit.knn.association.AssociationScorer
=========================================

.. py:class:: lenskit.knn.association.AssociationScorer(config = None, **kwargs)
   

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


   Item scorer using association rules to compute item relatedness.

   This scorer can compute item associations with three formulas:

   - Conditional probability (:math:`P[i|j]`), by setting
     :attr:`~AssociationConfig.method` to ``"probability"``.
   - Lift (:math:`\frac{P[i,j]}{P[i]P[j]}`), by setting
     :attr:`~AssociationConfig.method` to ``"lift"`` and
     :attr:`~AssociationConfig.damping` to 0.
   - `Biased lift`), by setting :attr:`~AssociationConfig.method` to ``"lift"``
     and :attr:`~AssociationConfig.damping` (:math:`\kappa`) to a positive
     value.

   An empty query will recommend no items.

   .. _Biased lift: https://md.ekstrandom.net/blog/2025/01/biased-lift


   .. py:attribute:: config
      :type:  AssociationConfig

      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


   .. py:attribute:: assoc_scores
      :type:  scipy.sparse.csr_array

      Sparse matrix of item association scores, with reference items on rows and
      target items on columns.


   .. py:method:: is_trained()

      Query if this component has already been trained.



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

      Train the model to learn its parameters from a training dataset.

      :param data: The training dataset.
      :param options: The training options.



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

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