aprioriitemset.java

MacroWeka扩展了著名数据挖掘工具weka

	    premise.m_items[i] = -1;
	    consequence.m_items[i] = -1;
	  }
	premise.m_counter = ((Integer)hashtableForPremise.get(premise)).intValue();
	consequenceUnconditionedCounter =
	  ((Integer)hashtableForConsequence.get(consequence)).intValue();

	if (metricType == 0) {
	  contingencyTable[0][0] = (double)(consequence.m_counter);
	  contingencyTable[0][1] = (double)(premise.m_counter - consequence.m_counter);
	  contingencyTable[1][0] = (double)(consequenceUnconditionedCounter -
					    consequence.m_counter);
	  contingencyTable[1][1] = (double)(numTransactions - premise.m_counter -
					    consequenceUnconditionedCounter +
					    consequence.m_counter);
	  chiSquared = ContingencyTables.chiSquared(contingencyTable, false);
	
	  metric = confidenceForRule(premise, consequence);
	
	  if ((!(metric < minMetric)) &&
	      (!(chiSquared > significanceLevel))) {
	    premises.addElement(premise);
	    consequences.addElement(consequence);
	    conf.addElement(new Double(metric));
	    lift.addElement(new Double(liftForRule(premise, consequence, 
				       consequenceUnconditionedCounter)));
	    lev.addElement(new Double(leverageForRule(premise, consequence,
				     premise.m_counter,
				     consequenceUnconditionedCounter)));
	    conv.addElement(new Double(convictionForRule(premise, consequence,
				       premise.m_counter,
				       consequenceUnconditionedCounter)));
	  }
	} else {
	  double tempConf = confidenceForRule(premise, consequence);
	  double tempLift = liftForRule(premise, consequence, 
					consequenceUnconditionedCounter);
	  double tempLev = leverageForRule(premise, consequence,
					   premise.m_counter,
					   consequenceUnconditionedCounter);
	  double tempConv = convictionForRule(premise, consequence,
					      premise.m_counter,
					      consequenceUnconditionedCounter);
	  switch(metricType) {
	  case 1: 
	    metric = tempLift;
	    break;
	  case 2:
	    metric = tempLev;
	    break;
	  case 3: 
	    metric = tempConv;
	    break;
	  default:
	    throw new Exception("ItemSet: Unknown metric type!");
	  }
	  if (!(metric < minMetric)) {
	    premises.addElement(premise);
	    consequences.addElement(consequence);
	    conf.addElement(new Double(tempConf));
	    lift.addElement(new Double(tempLift));
	    lev.addElement(new Double(tempLev));
	    conv.addElement(new Double(tempConv));
	  }
	}
      }
    }
    rules[0] = premises;
    rules[1] = consequences;
    rules[2] = conf;
    rules[3] = lift;
    rules[4] = lev;
    rules[5] = conv;
    return rules;
  }

  /**
   * Subtracts an item set from another one.
   *
   * @param toSubtract the item set to be subtracted from this one.
   * @return an item set that only contains items form this item sets that
   * are not contained by toSubtract
   */
  public final AprioriItemSet subtract(AprioriItemSet toSubtract) {

    AprioriItemSet result = new AprioriItemSet(m_totalTransactions);
    
    result.m_items = new int[m_items.length];
   
    for (int i = 0; i < m_items.length; i++) 
      if (toSubtract.m_items[i] == -1)
	result.m_items[i] = m_items[i];
      else
	result.m_items[i] = -1;
    result.m_counter = 0;
    return result;
  }


  /**
   * Generates rules with more than one item in the consequence.
   *
   * @param rules all the rules having (k-1)-item sets as consequences
   * @param numItemsInSet the size of the item set for which the rules
   * are to be generated
   * @param numItemsInConsequence the value of (k-1)
   * @param minConfidence the minimum confidence a rule has to have
   * @param hashtables the hashtables containing all(!) previously generated
   * item sets
   * @return all the rules having (k)-item sets as consequences
   */
  private final FastVector[] moreComplexRules(FastVector[] rules, 
					      int numItemsInSet, 
					      int numItemsInConsequence,
					      double minConfidence, 
					      FastVector hashtables) {

    AprioriItemSet newPremise;
    FastVector[] result, moreResults;
    FastVector newConsequences, newPremises = new FastVector(), 
      newConf = new FastVector();
    Hashtable hashtable;

    if (numItemsInSet > numItemsInConsequence + 1) {
      hashtable =
	(Hashtable)hashtables.elementAt(numItemsInSet - numItemsInConsequence - 2);
      newConsequences = mergeAllItemSets(rules[1], 
					 numItemsInConsequence - 1,
					 m_totalTransactions);
      Enumeration enu = newConsequences.elements();
      while (enu.hasMoreElements()) {
	AprioriItemSet current = (AprioriItemSet)enu.nextElement();
	current.m_counter = m_counter;
	newPremise = subtract(current);
	newPremise.m_counter = ((Integer)hashtable.get(newPremise)).intValue();
	newPremises.addElement(newPremise);
	newConf.addElement(new Double(confidenceForRule(newPremise, current)));
      }
      result = new FastVector[3];
      result[0] = newPremises;
      result[1] = newConsequences;
      result[2] = newConf;
      pruneRules(result, minConfidence);
      moreResults = moreComplexRules(result,numItemsInSet,numItemsInConsequence+1,
				     minConfidence, hashtables);
      if (moreResults != null) 
	for (int i = 0; i < moreResults[0].size(); i++) {
	  result[0].addElement(moreResults[0].elementAt(i));
	  result[1].addElement(moreResults[1].elementAt(i));
	  result[2].addElement(moreResults[2].elementAt(i));
	}
      return result;
    } else
      return null;
  }
  
  
   /**
   * Returns the contents of an item set as a string.
   *
   * @param instances contains the relevant header information
   * @return string describing the item set
   */
  public final String toString(Instances instances) {
   
      return super.toString(instances);
  }
  
  /**
   * Converts the header info of the given set of instances into a set 
   * of item sets (singletons). The ordering of values in the header file 
   * determines the lexicographic order.
   *
   * @param instances the set of instances whose header info is to be used
   * @return a set of item sets, each containing a single item
   * @exception Exception if singletons can't be generated successfully
   */
  public static FastVector singletons(Instances instances) throws Exception {

    FastVector setOfItemSets = new FastVector();
    ItemSet current;

    for (int i = 0; i < instances.numAttributes(); i++) {
      if (instances.attribute(i).isNumeric())
	throw new Exception("Can't handle numeric attributes!");
      for (int j = 0; j < instances.attribute(i).numValues(); j++) {
	current = new AprioriItemSet(instances.numInstances());
	current.m_items = new int[instances.numAttributes()];
	for (int k = 0; k < instances.numAttributes(); k++)
	  current.m_items[k] = -1;
	current.m_items[i] = j;
	setOfItemSets.addElement(current);
      }
    }
    return setOfItemSets;
  }
  
  /**
   * Merges all item sets in the set of (k-1)-item sets 
   * to create the (k)-item sets and updates the counters.
   *
   * @param itemSets the set of (k-1)-item sets
   * @param size the value of (k-1)
   * @return the generated (k)-item sets
   */
  public static FastVector mergeAllItemSets(FastVector itemSets, int size, 
					    int totalTrans) {

    FastVector newVector = new FastVector();
    ItemSet result;
    int numFound, k;

    for (int i = 0; i < itemSets.size(); i++) {
      ItemSet first = (ItemSet)itemSets.elementAt(i);
    out:
      for (int j = i+1; j < itemSets.size(); j++) {
	ItemSet second = (ItemSet)itemSets.elementAt(j);
	result = new AprioriItemSet(totalTrans);
	result.m_items = new int[first.m_items.length];

	// Find and copy common prefix of size 'size'
	numFound = 0;
	k = 0;
	while (numFound < size) {
	  if (first.m_items[k] == second.m_items[k]) {
	    if (first.m_items[k] != -1) 
	      numFound++;
	    result.m_items[k] = first.m_items[k];
	  } else 
	    break out;
	  k++;
	}
	
	// Check difference
	while (k < first.m_items.length) {
	  if ((first.m_items[k] != -1) && (second.m_items[k] != -1))
	    break;
	  else {
	    if (first.m_items[k] != -1)
	      result.m_items[k] = first.m_items[k];
	    else
	      result.m_items[k] = second.m_items[k];
	  }
	  k++;
	}
	if (k == first.m_items.length) {
	  result.m_counter = 0;
	  newVector.addElement(result);
	}
      }
    }
    return newVector;
  }
 
}