apriori.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

/*
 *    This program 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 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program 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 this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/**
 * Title:        prudsys basket analysis
 * Description:  Basket analysis algorithms
 * Copyright:    Copyright (c) 2001
 * Company:      PRUDENTIAL SYSTEMS SOFTWARE GmbH
 * @author Stefan Ludwig
 * @author Michael Thess
 * @version 1.0
 */
package com.prudsys.pdm.Models.Sequential.Algorithms.SeqSimple;


/**
 * Apriori - Data Mining Algorithm. Old implementation of 1999
 * by Stefan Ludwig. New implementation in AprioriOptimized
 * by Alexej Grinyuk is magnitudes faster.
 *
 * @author Stefan Ludwig
 * @author Michael Thess
 * @version 1.3, 2002/08/12
 */
public class Apriori {

  static boolean dbg = false;


  /**
   * Implements the part of finding large itemsets of
   * Algorithm Apriori (by Rakesh Agrawal).
   *
   * @param transSet transaction set
   * @param minsupp minimal support
   * @return result as list of large itemsets
   */
  protected static ItemSetList AprioriAlgLITS(TransactionSet transSet,
                                           double minsupp) {

    return AprioriAlgLITS(transSet, 0, minsupp, 1, -1);
  }

  /**
   * Implements the part of finding large itemsets of
   * Algorithm Apriori (by Rakesh Agrawal).
   *
   * @param transSet transaction set
   * @param minsuppcount minimum support count, ignore if <=0
   * @param minsupp minimal support
   * @param minItemSize minimum size of rules
   * @param maxItemSize maximum size of rules, -1 for unbounded
   * @return result as list of large itemsets
   */
  protected static ItemSetList AprioriAlgLITS(TransactionSet transSet,
                                           int minsuppcount, double minsupp,
                                           int minItemSize, int maxItemSize) {

    // Create list of large itemsets:
    ItemSetList largeItemSetList = new ItemSetList();

    // Determine minimal support:
    if (minsuppcount <= 0)
      transSet.setMinSuppCount(minsupp);
    else
      transSet.setMinSuppCount(minsuppcount);
    int minSuppCount = transSet.getMinSuppCount();
    if (dbg) System.out.println("minSuppCount = " + minSuppCount);

    // Find large 1-itemsets:
    int itemSetSize = 1;
    ItemSetList itemSetList = new ItemSetList(); //contains "ItemSet"s
    largeItemSetList        = transSet.buildHashTable();
    if (dbg) System.out.println("Large 1-Itemsets w/ minSuppCount:");
    if (dbg) largeItemSetList.print();

    // Convert the large 1-itemsets to a tree
    ItemTree itree = new ItemTree(largeItemSetList);
    itree.setTransactionSet(transSet);

    // Find remaining large itemsets:
    int depth = 1000;
    if (maxItemSize > -1)
      depth = maxItemSize;
    for (int i = 1; i < depth; i++) {
      if (! itree.filltree(i) )
        break;
    };
    if (dbg) itree.printtree(itree.tree);

    // Copy large itemsets:
    largeItemSetList = itree.getLargeItemSetList(itree.tree);
    if (dbg) System.out.println("L A R G E  Itemset list:");
    if (dbg) largeItemSetList.print();

    return largeItemSetList;
 }
}