leastmedsq.java

MacroWeka扩展了著名数据挖掘工具weka

   */
  private void buildRLSRegression()throws Exception{

    buildWeight();
    m_RLSData = new Instances(m_Data);
    int x = 0;
    int y = 0;
    int n = m_RLSData.numInstances();
    while(y < n){
      if (m_weight[x] == 0){
	m_RLSData.delete(y);
	n = m_RLSData.numInstances();
	y--;
      }
      x++;
      y++;
    }
    if ( m_RLSData.numInstances() == 0){
      System.err.println("rls regression unbuilt");
      m_ls = m_currentRegression;
    }else{
      m_ls = new LinearRegression();
      m_ls.setOptions(new String[]{"-S", "1"});
      m_ls.buildClassifier(m_RLSData);
      m_currentRegression = m_ls;
    }

  }

  /**
   * Finds the kth number in an array
   *
   * @param a an array of numbers
   * @param l left pointer
   * @param r right pointer
   * @param k position of number to be found
   */
  private static void select( double [] a, int l, int r, int k){

    if (r <=l) return;
    int i = partition( a, l, r);
    if (i > k) select(a, l, i-1, k);
    if (i < k) select(a, i+1, r, k);
  }

  /**
   * Partitions an array of numbers such that all numbers
   * less than that at index r, between indexes l and r
   * will have a smaller index and all numbers greater than
   * will have a larger index
   *
   * @param a an array of numbers
   * @param l left pointer
   * @param r right pointer
   * @return final index of number originally at r
   */
  private static int partition( double [] a, int l, int r ){

    int i = l-1, j = r;
    double v = a[r], temp;
    while(true){
      while(a[++i] < v);
      while(v < a[--j]) if(j == l) break;
      if(i >= j) break;
      temp = a[i];
      a[i] = a[j];
      a[j] = temp;
    }
    temp = a[i];
    a[i] = a[r];
    a[r] = temp;
    return i;
  }

  /**
   * Produces a random sample from m_Data
   * in m_SubSample
   *
   * @param data data from which to take sample
   * @exception Exception if an error occurs
   */
  private void selectSubSample(Instances data)throws Exception{

    m_SplitFilter = new RemoveRange();
    m_SplitFilter.setInvertSelection(true);
    m_SubSample = data;
    m_SplitFilter.setInputFormat(m_SubSample);
    m_SplitFilter.setInstancesIndices(selectIndices(m_SubSample));
    m_SubSample = Filter.useFilter(m_SubSample, m_SplitFilter);
  }

  /**
   * Returns a string suitable for passing to RemoveRange consisting
   * of m_samplesize indices.
   *
   * @param data dataset from which to take indicese
   * @return string of indices suitable for passing to RemoveRange 
   */
  private String selectIndices(Instances data){

    StringBuffer text = new StringBuffer();
    for(int i = 0, x = 0; i < m_samplesize; i++){
      do{x = (int) (m_random.nextDouble() * data.numInstances());}
      while(x==0);
      text.append(Integer.toString(x));
      if(i < m_samplesize - 1)
	text.append(",");
      else
	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 sampleSizeTipText() {
    return "Set the size of the random samples used to generate the least sqaured "
      +"regression functions.";
  }

  /**
   * sets number of samples
   *
   * @param samplesize value
   */
  public void setSampleSize(int samplesize){

    m_samplesize = samplesize;
  }

  /**
   * gets number of samples
   *
   * @return value
   */
  public int getSampleSize(){

    return m_samplesize;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String randomSeedTipText() {
    return "Set the seed for selecting random subsamples of the training data.";
  }

  /**
   * Set the seed for the random number generator
   *
   * @param randomseed the seed
   */
  public void setRandomSeed(long randomseed){

    m_randomseed = randomseed;
  }

  /**
   * get the seed for the random number generator
   *
   * @return the seed value
   */
  public long getRandomSeed(){

    return m_randomseed;
  }

  /**
   * sets  whether or not debugging output shouild be printed
   *
   * @param debug true if debugging output selected
   */
  public void setDebug(boolean debug){

    m_debug = debug;
  }

  /**
   * Returns whether or not debugging output shouild be printed
   *
   * @return true if debuging output selected
   */
  public boolean getDebug(){

    return m_debug;
  }

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

    Vector newVector = new Vector(1);
    newVector.addElement(new Option("\tSet sample size\n"
				    + "\t(default: 4)\n",
				    "S", 4, "-S <sample size>"));
    newVector.addElement(new Option("\tSet the seed used to generate samples\n"
				    + "\t(default: 0)\n",
				    "G", 0, "-G <seed>"));
    newVector.addElement(new Option("\tProduce debugging output\n"
				    + "\t(default no debugging output)\n",
				    "D", 0, "-D"));

    return newVector.elements();
  }

  /**
   * Sets the OptionHandler's options using the given list. All options
   * will be set (or reset) during this call (i.e. incremental setting
   * of options is not possible).
   *
   * @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 curropt = Utils.getOption('S', options);
    if ( curropt.length() != 0){
      setSampleSize(Integer.parseInt(curropt));
    } else
      setSampleSize(4);

    curropt = Utils.getOption('G', options);
    if ( curropt.length() != 0){
      setRandomSeed(Long.parseLong(curropt));
    } else {
      setRandomSeed(0);
    }

    setDebug(Utils.getFlag('D', options));
  }

  /**
   * Gets the current option settings for the OptionHandler.
   *
   * @return the list of current option settings as an array of strings
   */
  public String[] getOptions(){

    String options[] = new String[9];
    int current = 0;

    options[current++] = "-S";
    options[current++] = "" + getSampleSize();

    options[current++] = "-G";
    options[current++] = "" + getRandomSeed();

    if (getDebug()) {
      options[current++] = "-D";
    }

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

    return options;
  }

  /**
   * Produces the combination nCr
   *
   * @param n
   * @param n
   * @return the combination
   * @exception Exception if r is greater than n
   */
  public static int combinations (int n, int r)throws Exception {

    int c = 1, denom = 1, num = 1, i,orig=r;
    if (r > n) throw new Exception("r must be less that or equal to n.");
    r = Math.min( r , n - r);

    for (i = 1 ; i <= r; i++){

      num *= n-i+1;
      denom *= i;
    }

    c = num / denom;
    if(false)
      System.out.println( "n: "+n+" r: "+orig+" num: "+num+
			  " denom: "+denom+" c: "+c);
    return c;
  }

  /**
   * generate a Linear regression predictor for testing
   *
   * @param argv options
   */
  public static void main(String [] argv){

    try{
      System.out.println(Evaluation.evaluateModel(new LeastMedSq(), argv));
    } catch (Exception e) {
      System.out.println(e.getMessage());
      e.printStackTrace();
    }
  } // main
} // lmr