apriori.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

	m_allTheRules[0].addElement(sortedRuleSet[0].elementAt(indices[i]));
	m_allTheRules[1].addElement(sortedRuleSet[1].elementAt(indices[i]));
	m_allTheRules[2].addElement(sortedRuleSet[2].elementAt(indices[i]));
	if (m_metricType != CONFIDENCE || m_significanceLevel != -1) {
	  m_allTheRules[3].addElement(sortedRuleSet[3].elementAt(indices[i]));
	  m_allTheRules[4].addElement(sortedRuleSet[4].elementAt(indices[i]));
	  m_allTheRules[5].addElement(sortedRuleSet[5].elementAt(indices[i]));
	}
      }

      if (m_verbose) {
	if (m_Ls.size() > 1) {
	  System.out.println(toString());
	}
      }
      m_minSupport -= m_delta;
      /*      m_minSupport = (m_minSupport < m_lowerBoundMinSupport) 
	? 0 
	: m_minSupport; */

      necSupport = (int)(m_minSupport * 
			 (double)instances.numInstances()+0.5);

      m_cycles++;
    } while ((m_allTheRules[0].size() < m_numRules) &&
	     (Utils.grOrEq(m_minSupport, m_lowerBoundMinSupport))
	     /*	     (necSupport >= lowerBoundNumInstancesSupport)*/
	     /*	     (Utils.grOrEq(m_minSupport, m_lowerBoundMinSupport)) */ &&     
	     (necSupport >= 1));
    m_minSupport += m_delta;
  }

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {

    String string1 = "\tThe required number of rules. (default = " + m_numRules + ")",
      string2 = 
      "\tThe minimum confidence of a rule. (default = " + m_minMetric + ")",
      string3 = "\tThe delta by which the minimum support is decreased in\n",
      string4 = "\teach iteration. (default = " + m_delta + ")",
      string5 = 
      "\tThe lower bound for the minimum support. (default = " + 
      m_lowerBoundMinSupport + ")",
      string6 = "\tIf used, rules are tested for significance at\n",
      string7 = "\tthe given level. Slower. (default = no significance testing)",
      string8 = "\tIf set the itemsets found are also output. (default = no)",
      stringType = "\tThe metric type by which to rank rules. (default = "
      +"confidence)";
    

    FastVector newVector = new FastVector(9);

    newVector.addElement(new Option(string1, "N", 1, 
				    "-N <required number of rules output>"));
    newVector.addElement(new Option(stringType, "T", 1,
				    "-T <0=confidence | 1=lift | "
				    +"2=leverage | 3=Conviction>"));
    newVector.addElement(new Option(string2, "C", 1, 
				    "-C <minimum metric score of a rule>"));
    newVector.addElement(new Option(string3 + string4, "D", 1,
				    "-D <delta for minimum support>"));
    newVector.addElement(new Option("\tUpper bound for minimum support. "
				    +"(default = 1.0)", "U", 1,
				     "-U <upper bound for minimum support>"));
    newVector.addElement(new Option(string5, "M", 1,
				    "-M <lower bound for minimum support>"));
    newVector.addElement(new Option(string6 + string7, "S", 1,
				    "-S <significance level>"));
    newVector.addElement(new Option(string8, "S", 0,
				    "-I"));
    newVector.addElement(new Option("\tRemove columns that contain "
				    +"all missing values (default = no)"
				    , "R", 0,
				    "-R"));
    newVector.addElement(new Option("\tReport progress iteratively. (default "
				    +"= no)", "V", 0,
				    "-V"));
    
    return newVector.elements();
  }

  /**
   * Parses a given list of options. Valid options are:<p>
   *   
   * -N required number of rules <br>
   * The required number of rules (default: 10). <p>
   *
   * -T type of metric by which to sort rules <br>
   * 0 = confidence | 1 = lift | 2 = leverage | 3 = Conviction. <p>
   *
   * -C minimum metric score of a rule <br>
   * The minimum confidence of a rule (default: 0.9). <p>
   *
   * -D delta for minimum support <br>
   * The delta by which the minimum support is decreased in
   * each iteration (default: 0.05).
   *
   * -U upper bound for minimum support <br>
   * The upper bound for minimum support. Don't explicitly look for 
   * rules with more than this level of support. <p>
   *
   * -M lower bound for minimum support <br>
   * The lower bound for the minimum support (default = 0.1). <p>
   *
   * -S significance level <br>
   * If used, rules are tested for significance at
   * the given level. Slower (default = no significance testing). <p>
   *
   * -I <br>
   * If set the itemsets found are also output (default = no). <p>
   *
   * -V <br>
   * If set then progress is reported iteratively during execution. <p>
   *
   * -R <br>
   * If set then columns that contain all missing values are removed from
   * the data. <p>
   *
   * @param options the list of options as an array of strings
   * @exception Exception if an option is not supported 
   */
  public void setOptions(String[] options) throws Exception {
    
    resetOptions();
    String numRulesString = Utils.getOption('N', options),
      minConfidenceString = Utils.getOption('C', options),
      deltaString = Utils.getOption('D', options),
      maxSupportString = Utils.getOption('U', options),
      minSupportString = Utils.getOption('M', options),
      significanceLevelString = Utils.getOption('S', options);
    String metricTypeString = Utils.getOption('T', options);
    if (metricTypeString.length() != 0) {
      setMetricType(new SelectedTag(Integer.parseInt(metricTypeString),
				    TAGS_SELECTION));
    }
    
    if (numRulesString.length() != 0) {
      m_numRules = Integer.parseInt(numRulesString);
    }
    if (minConfidenceString.length() != 0) {
      m_minMetric = (new Double(minConfidenceString)).doubleValue();
    }
    if (deltaString.length() != 0) {
      m_delta = (new Double(deltaString)).doubleValue();
    }
    if (maxSupportString.length() != 0) {
      setUpperBoundMinSupport((new Double(maxSupportString)).doubleValue());
    }
    if (minSupportString.length() != 0) {
      m_lowerBoundMinSupport = (new Double(minSupportString)).doubleValue();
    }
    if (significanceLevelString.length() != 0) {
      m_significanceLevel = (new Double(significanceLevelString)).doubleValue();
    }
    m_outputItemSets = Utils.getFlag('I', options);
    m_verbose = Utils.getFlag('V', options);
    setRemoveAllMissingCols(Utils.getFlag('R', options));
  }

  /**
   * Gets the current settings of the Apriori object.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] options = new String [16];
    int current = 0;

    if (m_outputItemSets) {
      options[current++] = "-I";
    }

    if (getRemoveAllMissingCols()) {
      options[current++] = "-R";
    }

    options[current++] = "-N"; options[current++] = "" + m_numRules;
    options[current++] = "-T"; options[current++] = "" + m_metricType;
    options[current++] = "-C"; options[current++] = "" + m_minMetric;
    options[current++] = "-D"; options[current++] = "" + m_delta;
    options[current++] = "-U"; options[current++] = ""+m_upperBoundMinSupport;
    options[current++] = "-M"; options[current++] = ""+m_lowerBoundMinSupport;
    options[current++] = "-S"; options[current++] = "" + m_significanceLevel;

    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Outputs the size of all the generated sets of itemsets and the rules.
   */
  public String toString() {

    StringBuffer text = new StringBuffer();

    if (m_Ls.size() <= 1)
      return "\nNo large itemsets and rules found!\n";
    text.append("\nApriori\n=======\n\n");
    text.append("Minimum support: " 
		+ Utils.doubleToString(m_minSupport,2) + '\n');
    text.append("Minimum metric <");
    switch(m_metricType) {
    case CONFIDENCE:
      text.append("confidence>: ");
      break;
    case LIFT:
      text.append("lift>: ");
      break;
    case LEVERAGE:
      text.append("leverage>: ");
      break;
    case CONVICTION:
      text.append("conviction>: ");
      break;
    }
    text.append(Utils.doubleToString(m_minMetric,2)+'\n');
   
    if (m_significanceLevel != -1)
      text.append("Significance level: "+
		  Utils.doubleToString(m_significanceLevel,2)+'\n');
    text.append("Number of cycles performed: " + m_cycles+'\n');
    text.append("\nGenerated sets of large itemsets:\n");
    for (int i = 0; i < m_Ls.size(); i++) {
      text.append("\nSize of set of large itemsets L("+(i+1)+"): "+
		  ((FastVector)m_Ls.elementAt(i)).size()+'\n');
      if (m_outputItemSets) {
	text.append("\nLarge Itemsets L("+(i+1)+"):\n");
	for (int j = 0; j < ((FastVector)m_Ls.elementAt(i)).size(); j++)
	  text.append(((ItemSet)((FastVector)m_Ls.elementAt(i)).elementAt(j)).
		      toString(m_instances)+"\n");
      }
    }
    text.append("\nBest rules found:\n\n");
    for (int i = 0; i < m_allTheRules[0].size(); i++) {
      text.append(Utils.doubleToString((double)i+1, 
		  (int)(Math.log(m_numRules)/Math.log(10)+1),0)+
		  ". " + ((ItemSet)m_allTheRules[0].elementAt(i)).
		  toString(m_instances) 
		  + " ==> " + ((ItemSet)m_allTheRules[1].elementAt(i)).
		  toString(m_instances) +"    conf:("+  
		  Utils.doubleToString(((Double)m_allTheRules[2].
					elementAt(i)).doubleValue(),2)+")");
      if (m_metricType != CONFIDENCE || m_significanceLevel != -1) {
	text.append((m_metricType == LIFT ? " <" : "")+" lift:("+  
		    Utils.doubleToString(((Double)m_allTheRules[3].
					  elementAt(i)).doubleValue(),2)
		    +")"+(m_metricType == LIFT ? ">" : ""));
	text.append((m_metricType == LEVERAGE ? " <" : "")+" lev:("+  
		    Utils.doubleToString(((Double)m_allTheRules[4].
					  elementAt(i)).doubleValue(),2)
		    +")");
	text.append(" ["+
		    (int)(((Double)m_allTheRules[4].elementAt(i))
			  .doubleValue() * (double)m_instances.numInstances())
		    +"]"+(m_metricType == LEVERAGE ? ">" : ""));
	text.append((m_metricType == CONVICTION ? " <" : "")+" conv:("+  
		    Utils.doubleToString(((Double)m_allTheRules[5].
					  elementAt(i)).doubleValue(),2)
		    +")"+(m_metricType == CONVICTION ? ">" : ""));
      }
      text.append('\n');
    }
    return text.toString();
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String removeAllMissingColsTipText() {
    return "Remove columns with all missing values.";
  }

  /**
   * Remove columns containing all missing values.
   * @param r true if cols are to be removed.
   */
  public void setRemoveAllMissingCols(boolean r) {
    m_removeMissingCols = r;
  }

  /**
   * Returns whether columns containing all missing values are to be removed
   * @return true if columns are to be removed.
   */
  public boolean getRemoveAllMissingCols() {
    return m_removeMissingCols;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String upperBoundMinSupportTipText() {
    return "Upper bound for minimum support. Start iteratively decreasing "
      +"minimum support from this value.";
  }

  /**
   * Get the value of upperBoundMinSupport.
   *
   * @return Value of upperBoundMinSupport.
   */
  public double getUpperBoundMinSupport() {
    
    return m_upperBoundMinSupport;
  }
  
  /**
   * Set the value of upperBoundMinSupport.
   *
   * @param v  Value to assign to upperBoundMinSupport.
   */
  public void setUpperBoundMinSupport(double v) {
    
    m_upperBoundMinSupport = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String lowerBoundMinSupportTipText() {