dctraingen.h

Go to the documentation of this file.

/*

Copyright (c) 2003, Cornell University
All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:

   - Redistributions of source code must retain the above copyright notice,
       this list of conditions and the following disclaimer.
   - Redistributions in binary form must reproduce the above copyright
       notice, this list of conditions and the following disclaimer in the
       documentation and/or other materials provided with the distribution.
   - Neither the name of Cornell University nor the names of its
       contributors may be used to endorse or promote products derived from
       this software without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
THE POSSIBILITY OF SUCH DAMAGE.

*/

// -*- C++ -*-

#ifndef _DCTRAINGEN_H
#define _DCTRAINGEN_H

#include "traingen.h"

namespace CLUS
{

/** Ancestor of all Training Data generators that can manipulate both discrete and continuous
    entries. Used by decision and regression trees. 
  */
class DCTrainingData : public TrainingData
{
protected:

    /// the table with the discrete part of the training data
    Matrix<int> DTable;

    /// list of discrete domain sizes
    Vector<int> dDomainSize;
public:
    DCTrainingData( int M, int Ddims, int Cdims,  Vector<int>& DDomainSize ) :
            TrainingData(M,Cdims), DTable(M,Ddims), dDomainSize(DDomainSize)
    { }

    /** Required for the discrete part. Equivalent to the normalization for continuous variables */
    virtual const Vector<int>& GetDDomainSizes(void)
    {
        return dDomainSize;
    }

    virtual Vector<int> domainSizes()
    {
        return dDomainSize;
    }

    virtual int NumDiscreteCols(void)
    {
        return DTable.num_cols();
    }

    virtual const Matrix<int>& GetDiscreteTrainingData(void)
    {
        return DTable;
    }

};
}

#endif // _DCTRAINGEN_H

---