gfn.gym.helpers.bayesian_structure.priors
=========================================

.. py:module:: gfn.gym.helpers.bayesian_structure.priors


Classes
-------

.. autoapisummary::

   gfn.gym.helpers.bayesian_structure.priors.BasePrior
   gfn.gym.helpers.bayesian_structure.priors.EdgePrior
   gfn.gym.helpers.bayesian_structure.priors.ErdosRenyiPrior
   gfn.gym.helpers.bayesian_structure.priors.FairPrior
   gfn.gym.helpers.bayesian_structure.priors.UniformPrior


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

.. py:class:: BasePrior(num_variables=None)

   Bases: :py:obj:`abc.ABC`


   Base class for the prior over graphs p(G).

   Any subclass of `BasePrior` must return the contribution of log p(G) for a
   given variable with `num_parents` parents. We assume that the prior is modular.

   :param num_variables: The number of variables in the graph. If not specified, this gets
                         populated inside the scorer class.
   :type num_variables: int (optional)


   .. py:method:: __call__(num_parents)


   .. py:attribute:: _log_prior
      :value: None



   .. py:attribute:: _num_variables
      :value: None



   .. py:property:: log_prior
      :abstractmethod:



   .. py:property:: num_variables


.. py:class:: EdgePrior(num_variables=None, beta=1.0)

   Bases: :py:obj:`BasePrior`


   Base class for the prior over graphs p(G).

   Any subclass of `BasePrior` must return the contribution of log p(G) for a
   given variable with `num_parents` parents. We assume that the prior is modular.

   :param num_variables: The number of variables in the graph. If not specified, this gets
                         populated inside the scorer class.
   :type num_variables: int (optional)


   .. py:attribute:: beta
      :value: 1.0



   .. py:property:: log_prior


.. py:class:: ErdosRenyiPrior(num_variables=None, num_edges_per_node=1.0)

   Bases: :py:obj:`BasePrior`


   Base class for the prior over graphs p(G).

   Any subclass of `BasePrior` must return the contribution of log p(G) for a
   given variable with `num_parents` parents. We assume that the prior is modular.

   :param num_variables: The number of variables in the graph. If not specified, this gets
                         populated inside the scorer class.
   :type num_variables: int (optional)


   .. py:property:: log_prior


   .. py:attribute:: num_edges_per_node
      :value: 1.0



.. py:class:: FairPrior(num_variables=None)

   Bases: :py:obj:`BasePrior`


   Base class for the prior over graphs p(G).

   Any subclass of `BasePrior` must return the contribution of log p(G) for a
   given variable with `num_parents` parents. We assume that the prior is modular.

   :param num_variables: The number of variables in the graph. If not specified, this gets
                         populated inside the scorer class.
   :type num_variables: int (optional)


   .. py:property:: log_prior


.. py:class:: UniformPrior(num_variables=None)

   Bases: :py:obj:`BasePrior`


   Base class for the prior over graphs p(G).

   Any subclass of `BasePrior` must return the contribution of log p(G) for a
   given variable with `num_parents` parents. We assume that the prior is modular.

   :param num_variables: The number of variables in the graph. If not specified, this gets
                         populated inside the scorer class.
   :type num_variables: int (optional)


   .. py:property:: log_prior