paramEstimator.h

Go to the documentation of this file.

/****************************************************************************
 *   This file is part of the aGrUM/pyAgrum library.                        *
 *                                                                          *
 *   Copyright (c) 2005-2026 by                                             *
 *       - Pierre-Henri WUILLEMIN(_at_LIP6)                                 *
 *       - Christophe GONZALES(_at_AMU)                                     *
 *                                                                          *
 *   The aGrUM/pyAgrum library is free software; you can redistribute it    *
 *   and/or modify it under the terms of either :                           *
 *                                                                          *
 *    - the GNU Lesser General Public License as published by               *
 *      the Free Software Foundation, either version 3 of the License,      *
 *      or (at your option) any later version,                              *
 *    - the MIT license (MIT),                                              *
 *    - or both in dual license, as here.                                   *
 *                                                                          *
 *   (see https://agrum.gitlab.io/articles/dual-licenses-lgplv3mit.html)    *
 *                                                                          *
 *   This aGrUM/pyAgrum library is distributed in the hope that it will be  *
 *   useful, but WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,          *
 *   INCLUDING BUT NOT LIMITED TO THE WARRANTIES MERCHANTABILITY or FITNESS *
 *   FOR A PARTICULAR PURPOSE  AND NONINFRINGEMENT. IN NO EVENT SHALL THE   *
 *   AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER *
 *   LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,        *
 *   ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR  *
 *   OTHER DEALINGS IN THE SOFTWARE.                                        *
 *                                                                          *
 *   See LICENCES for more details.                                         *
 *                                                                          *
 *   SPDX-FileCopyrightText: Copyright 2005-2026                            *
 *       - Pierre-Henri WUILLEMIN(_at_LIP6)                                 *
 *       - Christophe GONZALES(_at_AMU)                                     *
 *   SPDX-License-Identifier: LGPL-3.0-or-later OR MIT                      *
 *                                                                          *
 *   Contact  : info_at_agrum_dot_org                                       *
 *   homepage : http://agrum.gitlab.io                                      *
 *   gitlab   : https://gitlab.com/agrumery/agrum                           *
 *                                                                          *
 ****************************************************************************/
 

#ifndef GUM_LEARNING_PARAM_ESTIMATOR_H
#define GUM_LEARNING_PARAM_ESTIMATOR_H
 
#include <agrum/agrum.h>
 
#include <agrum/base/stattests/recordCounter.h>
#include <agrum/BN/learning/priors/prior.h>
 
#include <type_traits>
 
namespace gum {
 
  namespace learning {
 

    class ParamEstimator: public IThreadNumberManager {
      public:
      // ##########################################################################
      // ##########################################################################


      ParamEstimator(const DBRowGeneratorParser& parser,
                     const Prior&                external_prior,
                     const Prior&                _score_internal_prior,
                     const std::vector< std::pair< std::size_t, std::size_t > >& ranges,
                     const Bijection< NodeId, std::size_t >&                     nodeId2columns
                     = Bijection< NodeId, std::size_t >());


      ParamEstimator(const DBRowGeneratorParser&             parser,
                     const Prior&                            external_prior,
                     const Prior&                            _score_internal_prior,
                     const Bijection< NodeId, std::size_t >& nodeId2columns
                     = Bijection< NodeId, std::size_t >());

      ParamEstimator(const ParamEstimator& from);

      ParamEstimator(ParamEstimator&& from) noexcept;

      [[nodiscard]] virtual ParamEstimator* clone() const = 0;

      virtual ~ParamEstimator();

 
 
      // ##########################################################################
      // ##########################################################################

      virtual void clear();


      void setNumberOfThreads(Size nb) override;

      Size getNumberOfThreads() const override;

      bool isGumNumberOfThreadsOverriden() const override;

      virtual void setMinNbRowsPerThread(const std::size_t nb) const;

      virtual std::size_t minNbRowsPerThread() const;


      void setRanges(const std::vector< std::pair< std::size_t, std::size_t > >& new_ranges);

      void clearRanges();

      const std::vector< std::pair< std::size_t, std::size_t > >& ranges() const;

      std::vector< double > parameters(const NodeId target_node);

      std::pair< std::vector< double >, double >
          parametersAndLogLikelihood(const NodeId target_node);


      virtual std::vector< double > parameters(const NodeId                 target_node,
                                               const std::vector< NodeId >& conditioning_nodes) = 0;

      virtual std::pair< std::vector< double >, double >
          parametersAndLogLikelihood(const NodeId                 target_node,
                                     const std::vector< NodeId >& conditioning_nodes) = 0;

      template < GUM_Numeric GUM_SCALAR >
      double setParameters(const NodeId                 target_node,
                           const std::vector< NodeId >& conditioning_nodes,
                           Tensor< GUM_SCALAR >&        pot,
                           const bool                   compute_log_likelihood = false);


      const Bijection< NodeId, std::size_t >& nodeId2Columns() const;

      const DatabaseTable& database() const;


      template < GUM_Numeric GUM_SCALAR >
      void setBayesNet(const BayesNet< GUM_SCALAR >& new_bn);

 
      protected:
      Prior* external_prior_{nullptr};

      Prior* score_internal_prior_{nullptr};

      RecordCounter counter_;

      const std::vector< NodeId > empty_nodevect_;
 

      ParamEstimator& operator=(const ParamEstimator& from);

      ParamEstimator& operator=(ParamEstimator&& from);
 
      private:
#ifndef DOXYGEN_SHOULD_SKIP_THIS

      template < GUM_Numeric GUM_SCALAR >
      void _checkParameters_(const NodeId                 target_node,
                             const std::vector< NodeId >& conditioning_nodes,
                             Tensor< GUM_SCALAR >&        pot);
 
      // sets the CPT's parameters corresponding to a given Tensor
      // when the tensor belongs to a BayesNet<GUM_SCALAR> when
      // GUM_SCALAR is different from a double
      template < GUM_Numeric GUM_SCALAR >
      typename std::enable_if< !std::is_same< GUM_SCALAR, double >::value, double >::type
          _setParameters_(const NodeId                 target_node,
                          const std::vector< NodeId >& conditioning_nodes,
                          Tensor< GUM_SCALAR >&        pot,
                          const bool                   compute_log_likelihood);
 
      // sets the CPT's parameters corresponding to a given Tensor
      // when the tensor belongs to a BayesNet<GUM_SCALAR> when
      // GUM_SCALAR is equal to double (the code is optimized for doubles)
      template < GUM_Numeric GUM_SCALAR >
      typename std::enable_if< std::is_same< GUM_SCALAR, double >::value, double >::type
          _setParameters_(const NodeId                 target_node,
                          const std::vector< NodeId >& conditioning_nodes,
                          Tensor< GUM_SCALAR >&        pot,
                          const bool                   compute_log_likelihood);
 
      friend class DAG2BNLearner;
 
#endif /* DOXYGEN_SHOULD_SKIP_THIS */
    };
 
  } /* namespace learning */
 
} /* namespace gum */

#include <agrum/BN/learning/paramUtils/paramEstimator_tpl.h>
 
// include the inlined functions if necessary
#ifndef GUM_NO_INLINE
#  include <agrum/BN/learning/paramUtils/paramEstimator_inl.h>
#endif /* GUM_NO_INLINE */
 
#endif /* GUM_LEARNING_PARAM_ESTIMATOR_H */