gbnet.models.survival.hazard_integrator
=======================================

.. py:module:: gbnet.models.survival.hazard_integrator


Classes
-------

.. autoapisummary::

   gbnet.models.survival.hazard_integrator.HazardIntegrator


Functions
---------

.. autoapisummary::

   gbnet.models.survival.hazard_integrator.loadModule


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

.. py:function:: loadModule(module)

   Load the appropriate gradient boosting module.


.. py:class:: HazardIntegrator(covariate_cols = [], params = {}, min_hess = 0.0, module_type = 'XGBModule', integration_method = 'trapezoid')

   Bases: :py:obj:`torch.nn.Module`


   .. py:attribute:: params


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



   .. py:attribute:: module_type
      :value: 'XGBModule'



   .. py:attribute:: integration_method
      :value: 'trapezoid'



   .. py:attribute:: covariate_cols
      :value: ['time']



   .. py:attribute:: gb_module
      :type:  Optional[object]
      :value: None



   .. py:attribute:: Module


   .. py:attribute:: static_data
      :type:  Dict[str, torch.Tensor]


   .. py:method:: _integrate_slice(values, dt, same_unit)


   .. py:method:: _prepare_data(df)

      Pre-processes and caches data that is static during training.
      This method performs sorting, tensor conversion, and computes
      time differences and group boundaries once.



   .. py:method:: forward(df, return_survival_estimates = True)


   .. py:method:: gb_step()

      Triggers the gradient boosting model to take a step.