PosMiner.h

/**************************************************************************
 * Copyright (c) 2007 Clifford Conley Owens III                           *
 *                                                                        *
 * This file is part of Biorithm.                                         *
 *                                                                        *
 * Biorithm is free software: you can redistribute it and/or modify       *
 * it under the terms of the GNU General Public License as published by   *
 * the Free Software Foundation, either version 3 of the License, or      *
 * (at your option) any later version.                                    *
 *                                                                        *
 * Biorithm is distributed in the hope that it will be useful,            *
 * but WITHOUT ANY WARRANTY; without even the implied warranty of         *
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the          *
 * GNU General Public License for more details.                           *
 *                                                                        *
 * You should have received a copy of the GNU General Public License      *
 * along with Biorithm.  If not, see <http://www.gnu.org/licenses/>.      *
 *                                                                        *
 **************************************************************************/

#ifndef POSMINER_H
#define POSMINER_H

// ---------------------------- Internal Headers ---------------------------- //

#include "LevItemSetMap.h"
#include "LevelwiseMiner.h"

struct passoc
{
    int code;
    unsigned int count;
};

typedef map<ItemSet, struct passoc> i_map;
typedef i_map::iterator m_iter;
typedef i_map::const_iterator m_citer;

class PosMiner: public LevelwiseMiner
{
    protected:
        // Used for giving status messages
        unsigned int current;

        // The fraction of the rows that must comprise each bitpattern
        float balance;

        // The required number of occurances for each bitpattern
        unsigned int bpreq;

        // This is twice the required number of occurances for each bitpattern
        // it may seems redundant, but it is nice to not have to compute this
        // value, as it is useful in early termination
        unsigned int bpreq2;

        // The fraction of bitpatterns that must succeed
        float support;

        // The buffer of combinations.  Prevents using too much memory.
        vector<ItemSet> buffer;

        // The buffer size
        unsigned int buffer_size;

        // The previously mined item sets
        LevItemSetMap<struct passoc> keepSets;

        // Helper methods
        void analyzeHelper();
        virtual bool analyzeLevel(unsigned int level);
        virtual void analyzeFirstLevel();
        virtual void analyzeNewLevel(unsigned int level);
        virtual void countTable(unsigned int level, unsigned int length);
        virtual bool hasMatches(m_citer i, m_citer j, unsigned int level);
        virtual void pruneItemSets(const vector<unsigned int>& tallies,
            unsigned int level);
        virtual unsigned int handlePrinting(unsigned int level);
        virtual void analyzeItemSet(const ItemSet& is,
            const ItemSet& ispos, const ItemSet& isneg, unsigned int& penalty,
            unsigned int& success) const;
        virtual void analyzeItemSet(const ItemSet& is, unsigned int& penalty,
            unsigned int& success) const;
        int gensupp(const ItemSet& ispos, const ItemSet& isneg,
            unsigned int start) const;
        void setcode(const ItemSet& is, unsigned int code);
        void setcode(unsigned int code);

    public:
        PosMiner(float balance = 0.5, float support = 1.0,
            unsigned int buffer_size = 1000);
        PosMiner(const PosMiner& src);
        virtual ~PosMiner();
        virtual PosMiner& operator =(const PosMiner& rhs);
};

#endif