TreeMiner.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 TREEMINER_H
#define TREEMINER_H

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

#include "ItemSetTree.h"
#include "LevelwiseMiner.h"

// ------------------------------- Definitions ------------------------------ //

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

class TreeMiner: public LevelwiseMiner
{
    typedef ItemSetTree<struct assoc> atree;

    protected:
        // 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
        atree tree;

        // The current status
        unsigned int current;

        // The current level
        unsigned int level;

        // The level 1 position
        unsigned int level1pos;

        // Helper methods
        void analyzeHelper();
        virtual bool analyzeLevel(unsigned int level);
        virtual void countTable(unsigned int length);
        virtual void pruneItemSets(const vector<unsigned int>& tallies,
            unsigned int length);
        virtual unsigned int handlePrinting();
        virtual unsigned int generateCandidates(atree::ConstIterator& iter,
            atree::ConstIterator& jter);
        virtual bool hasMatches(const ItemSet& i, const ItemSet& j) const;
        virtual struct assoc getval(const ItemSet& is) const;
        virtual void setcode(const ItemSet& is, int code);
        virtual void setcode(int code);
        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;

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

#endif