apriori.java

wekaUT是 university texas austin 开发的基于weka的半指导学习(semi supervised learning)的分类器

   * Get the value of lowerBoundMinSupport.
   *
   * @return Value of lowerBoundMinSupport.
   */
  public double getLowerBoundMinSupport() {
    
    return m_lowerBoundMinSupport;
  }
  
  /**
   * Set the value of lowerBoundMinSupport.
   *
   * @param v  Value to assign to lowerBoundMinSupport.
   */
  public void setLowerBoundMinSupport(double v) {
    
    m_lowerBoundMinSupport = v;
  }
  
  /**
   * Get the metric type
   *
   * @return the type of metric to use for ranking rules
   */
  public SelectedTag getMetricType() {
    return new SelectedTag(m_metricType, TAGS_SELECTION);
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String metricTypeTipText() {
    return "Set the type of metric by which to rank rules. Confidence is "
      +"the proportion of the examples covered by the premise that are also "
      +"covered by the consequence. Lift is confidence divided by the "
      +"proportion of all examples that are covered by the consequence. This "
      +"is a measure of the importance of the association that is independent "
      +"of support. Leverage is the proportion of additional examples covered "
      +"by both the premise and consequence above those expected if the "
      +"premise and consequence were independent of each other. The total "
      +"number of examples that this represents is presented in brackets "
      +"following the leverage. Conviction is "
      +"another measure of departure from independence. Conviction is given "
      +"by ";
  }

  /**
   * Set the metric type for ranking rules
   *
   * @param d the type of metric
   */
  public void setMetricType (SelectedTag d) {
    
    if (d.getTags() == TAGS_SELECTION) {
      m_metricType = d.getSelectedTag().getID();
    }

    if (m_significanceLevel != -1 && m_metricType != CONFIDENCE) {
      m_metricType = CONFIDENCE;
    }

    if (m_metricType == CONFIDENCE) {
      setMinMetric(0.9);
    }

    if (m_metricType == LIFT || m_metricType == CONVICTION) {
      setMinMetric(1.1);
    }
  
    if (m_metricType == LEVERAGE) {
      setMinMetric(0.1);
    }
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String minMetricTipText() {
    return "Minimum metric score. Consider only rules with scores higher than "
      +"this value.";
  }

  /**
   * Get the value of minConfidence.
   *
   * @return Value of minConfidence.
   */
  public double getMinMetric() {
    
    return m_minMetric;
  }
  
  /**
   * Set the value of minConfidence.
   *
   * @param v  Value to assign to minConfidence.
   */
  public void setMinMetric(double v) {
    
    m_minMetric = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String numRulesTipText() {
    return "Number of rules to find.";
  }

  /**
   * Get the value of numRules.
   *
   * @return Value of numRules.
   */
  public int getNumRules() {
    
    return m_numRules;
  }
  
  /**
   * Set the value of numRules.
   *
   * @param v  Value to assign to numRules.
   */
  public void setNumRules(int v) {
    
    m_numRules = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String deltaTipText() {
    return "Iteratively decrease support by this factor. Reduces support "
      +"until min support is reached or required number of rules has been "
      +"generated.";
  }
    
  /**
   * Get the value of delta.
   *
   * @return Value of delta.
   */
  public double getDelta() {
    
    return m_delta;
  }
  
  /**
   * Set the value of delta.
   *
   * @param v  Value to assign to delta.
   */
  public void setDelta(double v) {
    
    m_delta = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String significanceLevelTipText() {
    return "Significance level. Significance test (confidence metric only).";
  }

  /**
   * Get the value of significanceLevel.
   *
   * @return Value of significanceLevel.
   */
  public double getSignificanceLevel() {
    
    return m_significanceLevel;
  }
  
  /**
   * Set the value of significanceLevel.
   *
   * @param v  Value to assign to significanceLevel.
   */
  public void setSignificanceLevel(double v) {
    
    m_significanceLevel = v;
  }

  /** 
   * Method that finds all large itemsets for the given set of instances.
   *
   * @param the instances to be used
   * @exception Exception if an attribute is numeric
   */
  private void findLargeItemSets(Instances instances) throws Exception {
    
    FastVector kMinusOneSets, kSets;
    Hashtable hashtable;
    int necSupport, necMaxSupport,i = 0;
    
    m_instances = instances;
    
    // Find large itemsets

    // minimum support
    necSupport = (int)(m_minSupport * (double)instances.numInstances()+0.5);
    necMaxSupport = (int)(m_upperBoundMinSupport * (double)instances.numInstances()+0.5);
   
    kSets = ItemSet.singletons(instances);
    ItemSet.upDateCounters(kSets, instances);
    kSets = ItemSet.deleteItemSets(kSets, necSupport, necMaxSupport);
    if (kSets.size() == 0)
      return;
    do {
      m_Ls.addElement(kSets);
      kMinusOneSets = kSets;
      kSets = ItemSet.mergeAllItemSets(kMinusOneSets, i, instances.numInstances());
      hashtable = ItemSet.getHashtable(kMinusOneSets, kMinusOneSets.size());
      m_hashtables.addElement(hashtable);
      kSets = ItemSet.pruneItemSets(kSets, hashtable);
      ItemSet.upDateCounters(kSets, instances);
      kSets = ItemSet.deleteItemSets(kSets, necSupport, necMaxSupport);
      i++;
    } while (kSets.size() > 0);
  }  

  /** 
   * Method that finds all association rules and performs significance test.
   *
   * @exception Exception if an attribute is numeric
   */
  private void findRulesBruteForce() throws Exception {

    FastVector[] rules;

    // Build rules
    for (int j = 1; j < m_Ls.size(); j++) {
      FastVector currentItemSets = (FastVector)m_Ls.elementAt(j);
      Enumeration enumItemSets = currentItemSets.elements();
      while (enumItemSets.hasMoreElements()) {
	ItemSet currentItemSet = (ItemSet)enumItemSets.nextElement();
	rules=currentItemSet.
	  generateRulesBruteForce(m_minMetric,m_metricType,
				  m_hashtables,j+1,
				  m_instances.numInstances(),
				  m_significanceLevel);
	for (int k = 0; k < rules[0].size(); k++) {
	  m_allTheRules[0].addElement(rules[0].elementAt(k));
	  m_allTheRules[1].addElement(rules[1].elementAt(k));
	  m_allTheRules[2].addElement(rules[2].elementAt(k));

	  m_allTheRules[3].addElement(rules[3].elementAt(k));
	  m_allTheRules[4].addElement(rules[4].elementAt(k));
	  m_allTheRules[5].addElement(rules[5].elementAt(k));
	}
      }
    }
  }

  /** 
   * Method that finds all association rules.
   *
   * @exception Exception if an attribute is numeric
   */
  private void findRulesQuickly() throws Exception {

    FastVector[] rules;

    // Build rules
    for (int j = 1; j < m_Ls.size(); j++) {
      FastVector currentItemSets = (FastVector)m_Ls.elementAt(j);
      Enumeration enumItemSets = currentItemSets.elements();
      while (enumItemSets.hasMoreElements()) {
	ItemSet currentItemSet = (ItemSet)enumItemSets.nextElement();
	rules = currentItemSet.generateRules(m_minMetric, m_hashtables, j + 1);
	for (int k = 0; k < rules[0].size(); k++) {
	  m_allTheRules[0].addElement(rules[0].elementAt(k));
	  m_allTheRules[1].addElement(rules[1].elementAt(k));
	  m_allTheRules[2].addElement(rules[2].elementAt(k));
	}
      }
    }
  }

  /**
   * Main method for testing this class.
   */
  public static void main(String[] options) {

    String trainFileString;
    StringBuffer text = new StringBuffer();
    Apriori apriori = new Apriori();
    Reader reader;

    try {
      text.append("\n\nApriori options:\n\n");
      text.append("-t <training file>\n");
      text.append("\tThe name of the training file.\n");
      Enumeration enum = apriori.listOptions();
      while (enum.hasMoreElements()) {
	Option option = (Option)enum.nextElement();
	text.append(option.synopsis()+'\n');
	text.append(option.description()+'\n');
      }
      trainFileString = Utils.getOption('t', options);
      if (trainFileString.length() == 0) 
	throw new Exception("No training file given!");
      apriori.setOptions(options);
      reader = new BufferedReader(new FileReader(trainFileString));
      apriori.buildAssociations(new Instances(reader));
      System.out.println(apriori);
    } catch(Exception e) {
      e.printStackTrace();
      System.out.println("\n"+e.getMessage()+text);
    }
  }
}