farthestfirst.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

	minDist = dist;
	bestCluster = i;
      }
    }
    return bestCluster;
  }

  /**
   * Classifies a given instance.
   *
   * @param instance the instance to be assigned to a cluster
   * @return the number of the assigned cluster as an integer
   * if the class is enumerated, otherwise the predicted value
   * @throws Exception if instance could not be classified
   * successfully
   */
  public int clusterInstance(Instance instance) throws Exception {
    m_ReplaceMissingFilter.input(instance);
    m_ReplaceMissingFilter.batchFinished();
    Instance inst = m_ReplaceMissingFilter.output();

    return clusterProcessedInstance(inst);
  }

  /**
   * Calculates the distance between two instances
   *
   * @param first the first instance
   * @param second the second instance
   * @return the distance between the two given instances, between 0 and 1
   */          
  protected double distance(Instance first, Instance second) {  

    double distance = 0;
    int firstI, secondI;

    for (int p1 = 0, p2 = 0; 
	 p1 < first.numValues() || p2 < second.numValues();) {
      if (p1 >= first.numValues()) {
	firstI = m_instances.numAttributes();
      } else {
	firstI = first.index(p1); 
      }
      if (p2 >= second.numValues()) {
	secondI = m_instances.numAttributes();
      } else {
	secondI = second.index(p2);
      }
      if (firstI == m_instances.classIndex()) {
	p1++; continue;
      } 
      if (secondI == m_instances.classIndex()) {
	p2++; continue;
      } 
      double diff;
      if (firstI == secondI) {
	diff = difference(firstI, 
			  first.valueSparse(p1),
			  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_instances.numAttributes());
  }

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

    switch (m_instances.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
   * @return the normalized value
   */
  protected 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]);
    }
  }

  /**
   * Returns the number of clusters.
   *
   * @return the number of clusters generated for a training dataset.
   * @throws 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,
   * FarthestFirst 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
   * @throws Exception if number of clusters is negative
   */
  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. <p/>
   * 
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -N &lt;num&gt;
   *  number of clusters. (default = 2).</pre>
   * 
   * <pre> -S &lt;num&gt;
   *  random number seed.
   *  (default 10)</pre>
   * 
   <!-- options-end -->
   *
   * @param options the list of options as an array of strings
   * @throws 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 FarthestFirst
   *
   * @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() {
    StringBuffer temp = new StringBuffer();

    temp.append("\n FarthestFirst\n==============\n");

    temp.append("\nCluster centroids:\n");
    for (int i = 0; i < m_NumClusters; i++) {
      temp.append("\nCluster "+i+"\n\t");
      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(" "+m_ClusterCentroids.instance(i).value(j));
	}
      }
    }
    temp.append("\n\n");
    return temp.toString();
  }

  /**
   * 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 FarthestFirst(), argv));
    }
    catch (Exception e) {
      System.out.println(e.getMessage());
      e.printStackTrace();
    }
  }
}