simplekmeans.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

			  second.valueSparse(p2));
	p1++; p2++;
      } else if (firstI > secondI) {
	diff = difference(secondI, 
			  0, second.valueSparse(p2));
	p2++;
      } else {
	diff = difference(firstI, 
			  first.valueSparse(p1), 0);
	p1++;
      }
      distance += diff * diff;
    }
    
    //return Math.sqrt(distance / m_ClusterCentroids.numAttributes());
    return distance;
  }

  /**
   * Computes the difference between two given attribute
   * values.
   */
  private double difference(int index, double val1, double val2) {

    switch (m_ClusterCentroids.attribute(index).type()) {
    case Attribute.NOMINAL:
      
      // If attribute is nominal
      if (Instance.isMissingValue(val1) || 
	  Instance.isMissingValue(val2) ||
	  ((int)val1 != (int)val2)) {
	return 1;
      } else {
	return 0;
      }
    case Attribute.NUMERIC:

      // If attribute is numeric
      if (Instance.isMissingValue(val1) || 
	  Instance.isMissingValue(val2)) {
	if (Instance.isMissingValue(val1) && 
	    Instance.isMissingValue(val2)) {
	  return 1;
	} else {
	  double diff;
	  if (Instance.isMissingValue(val2)) {
	    diff = norm(val1, index);
	  } else {
	    diff = norm(val2, index);
	  }
	  if (diff < 0.5) {
	    diff = 1.0 - diff;
	  }
	  return diff;
	}
      } else {
	return norm(val1, index) - norm(val2, index);
      }
    default:
      return 0;
    }
  }

  /**
   * Normalizes a given value of a numeric attribute.
   *
   * @param x the value to be normalized
   * @param i the attribute's index
   */
  private double norm(double x, int i) {

    if (Double.isNaN(m_Min[i]) || Utils.eq(m_Max[i],m_Min[i])) {
      return 0;
    } else {
      return (x - m_Min[i]) / (m_Max[i] - m_Min[i]);
    }
  }

  /**
   * Updates the minimum and maximum values for all the attributes
   * based on a new instance.
   *
   * @param instance the new instance
   */
  private void updateMinMax(Instance instance) {  

    for (int j = 0;j < m_ClusterCentroids.numAttributes(); j++) {
      if (!instance.isMissing(j)) {
	if (Double.isNaN(m_Min[j])) {
	  m_Min[j] = instance.value(j);
	  m_Max[j] = instance.value(j);
	} else {
	  if (instance.value(j) < m_Min[j]) {
	    m_Min[j] = instance.value(j);
	  } else {
	    if (instance.value(j) > m_Max[j]) {
	      m_Max[j] = instance.value(j);
	    }
	  }
	}
      }
    }
  }
  
  /**
   * Returns the number of clusters.
   *
   * @return the number of clusters generated for a training dataset.
   * @exception Exception if number of clusters could not be returned
   * successfully
   */
  public int numberOfClusters() throws Exception {
    return m_NumClusters;
  }

  /**
   * Returns an enumeration describing the available options.. <p>
   *
   * Valid options are:<p>
   *
   * -N <number of clusters> <br>
   * Specify the number of clusters to generate. If omitted,
   * EM will use cross validation to select the number of clusters
   * automatically. <p>
   *
   * -S <seed> <br>
   * Specify random number seed. <p>
   *
   * @return an enumeration of all the available options.
   *
   **/
  public Enumeration listOptions () {
    Vector newVector = new Vector(2);

     newVector.addElement(new Option("\tnumber of clusters. (default = 2)." 
				    , "N", 1, "-N <num>"));
     newVector.addElement(new Option("\trandom number seed.\n (default 10)"
				     , "S", 1, "-S <num>"));

     return  newVector.elements();
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String numClustersTipText() {
    return "set number of clusters";
  }

  /**
   * set the number of clusters to generate
   *
   * @param n the number of clusters to generate
   */
  public void setNumClusters(int n) throws Exception {
    if (n <= 0) {
      throw new Exception("Number of clusters must be > 0");
    }
    m_NumClusters = n;
  }

  /**
   * gets the number of clusters to generate
   *
   * @return the number of clusters to generate
   */
  public int getNumClusters() {
    return m_NumClusters;
  }
    
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String seedTipText() {
    return "random number seed";
  }


  /**
   * Set the random number seed
   *
   * @param s the seed
   */
  public void setSeed (int s) {
    m_Seed = s;
  }


  /**
   * Get the random number seed
   *
   * @return the seed
   */
  public int getSeed () {
    return  m_Seed;
  }

  /**
   * Parses a given list of options.
   * @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 {

    String optionString = Utils.getOption('N', options);

    if (optionString.length() != 0) {
      setNumClusters(Integer.parseInt(optionString));
    }

    optionString = Utils.getOption('S', options);
    
    if (optionString.length() != 0) {
      setSeed(Integer.parseInt(optionString));
    }
  }

  /**
   * Gets the current settings of SimpleKMeans
   *
   * @return an array of strings suitable for passing to setOptions()
   */
  public String[] getOptions () {
    String[] options = new String[4];
    int current = 0;
    
    options[current++] = "-N";
    options[current++] = "" + getNumClusters();
    options[current++] = "-S";
    options[current++] = "" + getSeed();
    
    while (current < options.length) {
      options[current++] = "";
    }

    return  options;
  }

  /**
   * return a string describing this clusterer
   *
   * @return a description of the clusterer as a string
   */
  public String toString() {
    int maxWidth = 0;
    for (int i = 0; i < m_NumClusters; i++) {
      for (int j = 0 ;j < m_ClusterCentroids.numAttributes(); j++) {
	if (m_ClusterCentroids.attribute(j).isNumeric()) {
	  double width = Math.log(Math.abs(m_ClusterCentroids.instance(i).value(j))) /
	    Math.log(10.0);
	  width += 1.0;
	  if ((int)width > maxWidth) {
	    maxWidth = (int)width;
	  }
	}
      }
    }
    StringBuffer temp = new StringBuffer();
    String naString = "N/A";
    for (int i = 0; i < maxWidth+2; i++) {
      naString += " ";
    }
    temp.append("\nkMeans\n======\n");
    temp.append("\nNumber of iterations: " + m_Iterations+"\n");
    temp.append("Within cluster sum of squared errors: " + Utils.sum(m_squaredErrors));

    temp.append("\n\nCluster centroids:\n");
    for (int i = 0; i < m_NumClusters; i++) {
      temp.append("\nCluster "+i+"\n\t");
      temp.append("Mean/Mode: ");
      for (int j = 0; j < m_ClusterCentroids.numAttributes(); j++) {
	if (m_ClusterCentroids.attribute(j).isNominal()) {
	  temp.append(" "+m_ClusterCentroids.attribute(j).
		      value((int)m_ClusterCentroids.instance(i).value(j)));
	} else {
	  temp.append(" "+Utils.doubleToString(m_ClusterCentroids.instance(i).value(j),
					       maxWidth+5, 4));
	}
      }
      temp.append("\n\tStd Devs:  ");
      for (int j = 0; j < m_ClusterStdDevs.numAttributes(); j++) {
	if (m_ClusterStdDevs.attribute(j).isNumeric()) {
	  temp.append(" "+Utils.doubleToString(m_ClusterStdDevs.instance(i).value(j), 
					       maxWidth+5, 4));
	} else {
	  temp.append(" "+naString);
	}
      }
    }
    temp.append("\n\n");
    return temp.toString();
  }

  public Instances getClusterCentroids() {
    return m_ClusterCentroids;
  }

  public Instances getClusterStandardDevs() {
    return m_ClusterStdDevs;
  }

  public int [][][] getClusterNominalCounts() {
    return m_ClusterNominalCounts;
  }

  public double getSquaredError() {
    return Utils.sum(m_squaredErrors);
  }

  public int [] getClusterSizes() {
    return m_ClusterSizes;
  }

  /**
   * Main method for testing this class.
   *
   * @param argv should contain the following arguments: <p>
   * -t training file [-N number of clusters]
   */
  public static void main (String[] argv) {
    try {
      System.out.println(ClusterEvaluation.
			 evaluateClusterer(new SimpleKMeans(), argv));
    }
    catch (Exception e) {
      System.out.println(e.getMessage());
      e.printStackTrace();
    }
  }
}