lenskit.knn.slim.SLIMConfig
===========================

.. py:class:: lenskit.knn.slim.SLIMConfig
   

   Bases: :py:obj:`pydantic.BaseModel`


   Hyperparameters for SLIM/fsSLIM (:class:`SlimScorer`).


   .. py:attribute:: l1_reg
      :type:  pydantic.PositiveFloat
      :value: 1.0


      L₁ regularization strength for SLIM.


   .. py:attribute:: l2_reg
      :type:  pydantic.PositiveFloat
      :value: 1.0


      L₂ regularization strength for SLIM.


   .. py:attribute:: max_iters
      :type:  pydantic.PositiveInt
      :value: 100


      Maximum coordinate descent iterations per column.


   .. py:attribute:: max_nbrs
      :type:  pydantic.PositiveInt | None
      :value: None


      Maximum neighbors (features) for each item.  Setting this to a positive
      integer enables fsSLIM (with item cosine selection).