databaseTable.h

Go to the documentation of this file.

/****************************************************************************
 *   This file is part of the aGrUM/pyAgrum library.                        *
 *                                                                          *
 *   Copyright (c) 2005-2025 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 2005-2025                            *
 *       - 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_DATABASE_TABLE_H
#define GUM_DATABASE_TABLE_H
 
#include <algorithm>
#include <exception>
#include <functional>
#include <memory>
#include <numeric>
#include <vector>
 
#include <agrum/agrum.h>
 
#include <agrum/base/database/DBTranslatorSet.h>
#include <agrum/base/database/IDatabaseTable.h>
 
#include <agrum/base/core/math/math_utils.h>
 
namespace gum::learning {

  class DatabaseTable final: public IDatabaseTable< DBTranslatedValue > {
    public:
    template < typename TX_DATA >
    using DBVector = std::vector< TX_DATA >;

    template < typename TX_DATA >
    using Row = DBRow< TX_DATA >;

    template < typename TX_DATA >
    using Matrix = std::vector< DBRow< TX_DATA > >;
 
    using MissingValType = std::vector< std::string >;

    using Handler = typename IDatabaseTable< DBTranslatedValue >::Handler;

    using HandlerSafe = typename IDatabaseTable< DBTranslatedValue >::HandlerSafe;
 
    using IsMissing = typename IDatabaseTable< DBTranslatedValue >::IsMissing;

    using value_type      = Row< DBTranslatedValue >;
    using reference       = value_type&;
    using const_reference = const value_type&;
    using pointer         = value_type*;
    using const_pointer   = const value_type*;
    using size_type       = std::size_t;
    using difference_type = std::ptrdiff_t;
    using iterator        = Handler;
    using iterator_safe   = HandlerSafe;
 
 
    // ##########################################################################
    // ##########################################################################

    explicit DatabaseTable(const MissingValType&  missing_symbols,
                           const DBTranslatorSet& translators = DBTranslatorSet());

    explicit DatabaseTable(const DBTranslatorSet& translators = DBTranslatorSet());

    DatabaseTable(const DatabaseTable& from);

    DatabaseTable(DatabaseTable&& from) noexcept;

    DatabaseTable* clone() const override;

    ~DatabaseTable() override;

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

    DatabaseTable& operator=(const DatabaseTable& from);

    DatabaseTable& operator=(DatabaseTable&& from) noexcept;

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


    std::size_t insertTranslator(const DBTranslator& translator,
                                 const std::size_t   input_column,
                                 const bool          unique_column = true);


    std::size_t insertTranslator(const Variable&   var,
                                 const std::size_t input_column,
                                 const bool        unique_column = true);


    std::size_t insertTranslator(const Variable&                   var,
                                 std::size_t                       input_column,
                                 const std::vector< std::string >& missing_symbols,
                                 bool                              unique_column = true);

    void eraseTranslators(std::size_t k, bool k_is_input_col = false);


    void changeTranslator(DBTranslator& new_translator, std::size_t k, bool k_is_input_col = false);


    auto changeTranslator(const Variable&                   var,
                          std::size_t                       k,
                          bool                              k_is_input_col = false,
                          const std::vector< std::string >& missing_symbols
                          = std::vector< std::string >(),
                          bool        editable_dictionary = false,
                          std::size_t max_dico_entries = std::numeric_limits< std::size_t >::max())
        -> void;

    const DBTranslatorSet& translatorSet() const;

    const DBTranslator& translator(const std::size_t k, const bool k_is_input_col = false) const;


    std::vector< std::pair< Idx, std::shared_ptr< DBTranslator > > > betterTranslators() const;

    const Variable& variable(const std::size_t k, const bool k_is_input_col = false) const;

    using IDatabaseTable< DBTranslatedValue >::setVariableNames;


    void setVariableNames(const std::vector< std::string >& names,
                          const bool                        from_external_object = true) override;

    void ignoreColumn(const std::size_t k, const bool from_external_object = true) override;


    const DBVector< std::size_t > ignoredColumns() const override;

    const DBVector< std::size_t > inputColumns() const override;

    std::size_t domainSize(const std::size_t k, const bool k_is_input_col = false) const;

    DBVector< std::size_t > domainSizes() const;

    bool needsReordering(const std::size_t k, const bool k_is_input_col = false) const;

    void reorder(const std::size_t k, const bool k_is_input_col = false);


    void reorder();

    using IDatabaseTable< DBTranslatedValue >::insertRow;


    void insertRow(const std::vector< std::string >& new_row) override;


    void insertRow(Row< DBTranslatedValue >&& new_row,
                   const IsMissing            contains_missing_data) override;


    void insertRow(const Row< DBTranslatedValue >& new_row,
                   const IsMissing                 contains_missing_data) override;


    void insertRow(const Row< DBCell >& new_row) override;


    void insertRow(Row< DBCell >&& new_row) override;


    void insertRows(Matrix< DBTranslatedValue >&& new_rows,
                    const DBVector< IsMissing >&  rows_have_missing_vals) override;


    void insertRows(const Matrix< DBTranslatedValue >& new_rows,
                    const DBVector< IsMissing >&       rows_have_missing_vals) override;


    void insertRows(Matrix< DBCell >&& new_rows) override;


    void insertRows(const Matrix< DBCell >& new_rows) override;

    void clear() override;
 
    // substitutes the kth translator by another one
    /* The method checks that:
     * 1/ it is possible to get back the original values of the database
     *    for the rows already translated.
     * 2/ that the new translator is capable of translating these values.
     *
     * If both checks passed, then it replaces the kth translator
     * by the one passed in arguments and retranslates with it the kth
     * cell of all the rows already contained in the database */

 
 
#ifndef DOXYGEN_SHOULD_SKIP_THIS
 
    private:
    DBTranslatorSet _translators_;

    Set< std::size_t > _ignored_cols_;

    bool _isRowCompatible_(const Row< DBTranslatedValue >& row) const;

    std::size_t _getKthIndex_(const std::size_t k, const bool k_is_input_col) const;

    DBVector< std::size_t > _getKthIndices_(const std::size_t k, const bool k_is_input_col) const;


    template < typename Functor1, typename Functor2 >
    void _threadProcessDatabase_(Functor1& exec_func, Functor2& undo_func);
 
#endif /* DOXYGEN_SHOULD_SKIP_THIS */
  };
 
}   // namespace gum::learning

#include <agrum/base/database/databaseTable_tpl.h>

#ifndef GUM_NO_INLINE
#  include <agrum/base/database/databaseTable_inl.h>
#endif /* GUM_NO_INLINE */
 
 
#endif /* GUM_DATABASE_TABLE_H */