gbnet.base
==========

.. py:module:: gbnet.base


Classes
-------

.. autoapisummary::

   gbnet.base.BaseGBModule


Module Contents
---------------

.. py:class:: BaseGBModule(min_hess=0.0)

   Bases: :py:obj:`torch.nn.Module`, :py:obj:`abc.ABC`


   Base class for gradient boosting modules.

   This abstract base class defines the common interface and functionality that all
   gradient boosting modules should implement.

   :ivar min_hess: minimum hessian value

   :vartype min_hess: float


   .. py:attribute:: min_hess
      :value: 0.0



   .. py:attribute:: grad
      :value: None



   .. py:attribute:: hess
      :value: None



   .. py:method:: _input_checking_setting(input_data)
      :abstractmethod:


      Validate and prepare input data.

      :param input_data: Input data in model-specific format

      :returns: Processed input data ready for model



   .. py:method:: forward(input_data, return_tensor = True)
      :abstractmethod:


      Forward pass through the model.

      :param input_data: Input data in model-specific format
      :param return_tensor: Whether to return predictions as PyTorch tensor

      :returns: Model predictions as tensor or numpy array



   .. py:method:: _get_grad_hess_FX()


   .. py:method:: gb_step()
      :abstractmethod:


      Perform one gradient boosting step.

      This method should implement the logic for:
      1. Getting gradients/hessians
      2. Training one boosting iteration
      3. Updating predictions