multilayerperceptron.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

   */
  private void addNode(NeuralConnection n) {
    
    NeuralConnection[] temp1 = new NeuralConnection[m_neuralNodes.length + 1];
    for (int noa = 0; noa < m_neuralNodes.length; noa++) {
      temp1[noa] = m_neuralNodes[noa];
    }

    temp1[temp1.length-1] = n;
    m_neuralNodes = temp1;
  }

  /** 
   * Call this function to remove the passed node from the list.
   * This will only remove the node if it is in the neuralnodes list.
   * @param n The neuralConnection to remove.
   * @return True if removed false if not (because it wasn't there).
   */
  private boolean removeNode(NeuralConnection n) {
    NeuralConnection[] temp1 = new NeuralConnection[m_neuralNodes.length - 1];
    int skip = 0;
    for (int noa = 0; noa < m_neuralNodes.length; noa++) {
      if (n == m_neuralNodes[noa]) {
	skip++;
      }
      else if (!((noa - skip) >= temp1.length)) {
	temp1[noa - skip] = m_neuralNodes[noa];
      }
      else {
	return false;
      }
    }
    m_neuralNodes = temp1;
    return true;
  }

  /**
   * This function sets what the m_numeric flag to represent the passed class
   * it also performs the normalization of the attributes if applicable
   * and sets up the info to normalize the class. (note that regardless of
   * the options it will fill an array with the range and base, set to 
   * normalize all attributes and the class to be between -1 and 1)
   * @param inst the instances.
   * @return The modified instances. This needs to be done. If the attributes
   * are normalized then deep copies will be made of all the instances which
   * will need to be passed back out.
   */
  private Instances setClassType(Instances inst) throws Exception {
    if (inst != null) {
      // x bounds
      double min=Double.POSITIVE_INFINITY;
      double max=Double.NEGATIVE_INFINITY;
      double value;
      m_attributeRanges = new double[inst.numAttributes()];
      m_attributeBases = new double[inst.numAttributes()];
      for (int noa = 0; noa < inst.numAttributes(); noa++) {
	min = Double.POSITIVE_INFINITY;
	max = Double.NEGATIVE_INFINITY;
	for (int i=0; i < inst.numInstances();i++) {
	  if (!inst.instance(i).isMissing(noa)) {
	    value = inst.instance(i).value(noa);
	    if (value < min) {
	      min = value;
	    }
	    if (value > max) {
	      max = value;
	    }
	  }
	}
	
	m_attributeRanges[noa] = (max - min) / 2;
	m_attributeBases[noa] = (max + min) / 2;
	if (noa != inst.classIndex() && m_normalizeAttributes) {
	  for (int i = 0; i < inst.numInstances(); i++) {
	    if (m_attributeRanges[noa] != 0) {
	      inst.instance(i).setValue(noa, (inst.instance(i).value(noa)  
					      - m_attributeBases[noa]) /
					m_attributeRanges[noa]);
	    }
	    else {
	      inst.instance(i).setValue(noa, inst.instance(i).value(noa) - 
					m_attributeBases[noa]);
	    }
	  }
	}
      }
      if (inst.classAttribute().isNumeric()) {
	m_numeric = true;
      }
      else {
	m_numeric = false;
      }
    }
    return inst;
  }

  /**
   * A function used to stop the code that called buildclassifier
   * from continuing on before the user has finished the decision tree.
   * @param tf True to stop the thread, False to release the thread that is
   * waiting there (if one).
   */
  public synchronized void blocker(boolean tf) {
    if (tf) {
      try {
	wait();
      } catch(InterruptedException e) {
      }
    }
    else {
      notifyAll();
    }
  }

  /**
   * Call this function to update the control panel for the gui.
   */
  private void updateDisplay() {
    
    if (m_gui) {
      m_controlPanel.m_errorLabel.repaint();
      m_controlPanel.m_epochsLabel.repaint();
    }
  }
  

  /**
   * this will reset all the nodes in the network.
   */
  private void resetNetwork() {
    for (int noc = 0; noc < m_numClasses; noc++) {
      m_outputs[noc].reset();
    }
  }
  
  /**
   * This will cause the output values of all the nodes to be calculated.
   * Note that the m_currentInstance is used to calculate these values.
   */
  private void calculateOutputs() {
    for (int noc = 0; noc < m_numClasses; noc++) {	
      //get the values. 
      m_outputs[noc].outputValue(true);
    }
  }

  /**
   * This will cause the error values to be calculated for all nodes.
   * Note that the m_currentInstance is used to calculate these values.
   * Also the output values should have been calculated first.
   * @return The squared error.
   */
  private double calculateErrors() throws Exception {
    double ret = 0, temp = 0; 
    for (int noc = 0; noc < m_numAttributes; noc++) {
      //get the errors.
      m_inputs[noc].errorValue(true);
      
    }
    for (int noc = 0; noc < m_numClasses; noc++) {
      temp = m_outputs[noc].errorValue(false);
      ret += temp * temp;
    }    
    return ret;
    
  }

  /**
   * This will cause the weight values to be updated based on the learning
   * rate, momentum and the errors that have been calculated for each node.
   * @param l The learning rate to update with.
   * @param m The momentum to update with.
   */
  private void updateNetworkWeights(double l, double m) {
    for (int noc = 0; noc < m_numClasses; noc++) {
      //update weights
      m_outputs[noc].updateWeights(l, m);
    }

  }
  
  /**
   * This creates the required input units.
   */
  private void setupInputs() throws Exception {
    m_inputs = new NeuralEnd[m_numAttributes];
    int now = 0;
    for (int noa = 0; noa < m_numAttributes+1; noa++) {
      if (m_instances.classIndex() != noa) {
	m_inputs[noa - now] = new NeuralEnd(m_instances.attribute(noa).name());
	
	m_inputs[noa - now].setX(.1);
	m_inputs[noa - now].setY((noa - now + 1.0) / (m_numAttributes + 1));
	m_inputs[noa - now].setLink(true, noa);
      }    
      else {
	now = 1;
      }
    }

  }

  /**
   * This creates the required output units.
   */
  private void setupOutputs() throws Exception {
  
    m_outputs = new NeuralEnd[m_numClasses];
    for (int noa = 0; noa < m_numClasses; noa++) {
      if (m_numeric) {
	m_outputs[noa] = new NeuralEnd(m_instances.classAttribute().name());
      }
      else {
	m_outputs[noa]= new NeuralEnd(m_instances.classAttribute().value(noa));
      }
      
      m_outputs[noa].setX(.9);
      m_outputs[noa].setY((noa + 1.0) / (m_numClasses + 1));
      m_outputs[noa].setLink(false, noa);
      NeuralNode temp = new NeuralNode(String.valueOf(m_nextId), m_random,
				       m_sigmoidUnit);
      m_nextId++;
      temp.setX(.75);
      temp.setY((noa + 1.0) / (m_numClasses + 1));
      addNode(temp);
      NeuralConnection.connect(temp, m_outputs[noa]);
    }
 
  }
  
  /**
   * Call this function to automatically generate the hidden units
   */
  private void setupHiddenLayer()
  {
    StringTokenizer tok = new StringTokenizer(m_hiddenLayers, ",");
    int val = 0;  //num of nodes in a layer
    int prev = 0; //used to remember the previous layer
    int num = tok.countTokens(); //number of layers
    String c;
    for (int noa = 0; noa < num; noa++) {
      //note that I am using the Double to get the value rather than the
      //Integer class, because for some reason the Double implementation can
      //handle leading white space and the integer version can't!?!
      c = tok.nextToken().trim();
      if (c.equals("a")) {
	val = (m_numAttributes + m_numClasses) / 2;
      }
      else if (c.equals("i")) {
	val = m_numAttributes;
      }
      else if (c.equals("o")) {
	val = m_numClasses;
      }
      else if (c.equals("t")) {
	val = m_numAttributes + m_numClasses;
      }
      else {
	val = Double.valueOf(c).intValue();
      }
      for (int nob = 0; nob < val; nob++) {
	NeuralNode temp = new NeuralNode(String.valueOf(m_nextId), m_random,
					 m_sigmoidUnit);
	m_nextId++;
	temp.setX(.5 / (num) * noa + .25);
	temp.setY((nob + 1.0) / (val + 1));
	addNode(temp);
	if (noa > 0) {
	  //then do connections
	  for (int noc = m_neuralNodes.length - nob - 1 - prev;
	       noc < m_neuralNodes.length - nob - 1; noc++) {
	    NeuralConnection.connect(m_neuralNodes[noc], temp);
	  }
	}
      }      
      prev = val;
    }
    tok = new StringTokenizer(m_hiddenLayers, ",");
    c = tok.nextToken();
    if (c.equals("a")) {
      val = (m_numAttributes + m_numClasses) / 2;
    }
    else if (c.equals("i")) {
      val = m_numAttributes;
    }
    else if (c.equals("o")) {
      val = m_numClasses;
    }
    else if (c.equals("t")) {
      val = m_numAttributes + m_numClasses;
    }
    else {
      val = Double.valueOf(c).intValue();
    }
    
    if (val == 0) {
      for (int noa = 0; noa < m_numAttributes; noa++) {
	for (int nob = 0; nob < m_numClasses; nob++) {
	  NeuralConnection.connect(m_inputs[noa], m_neuralNodes[nob]);
	}
      }
    }
    else {
      for (int noa = 0; noa < m_numAttributes; noa++) {
	for (int nob = m_numClasses; nob < m_numClasses + val; nob++) {
	  NeuralConnection.connect(m_inputs[noa], m_neuralNodes[nob]);
	}
      }
      for (int noa = m_neuralNodes.length - prev; noa < m_neuralNodes.length;
	   noa++) {
	for (int nob = 0; nob < m_numClasses; nob++) {
	  NeuralConnection.connect(m_neuralNodes[noa], m_neuralNodes[nob]);
	}
      }
    }
    
  }
  
  /**
   * This will go through all the nodes and check if they are connected
   * to a pure output unit. If so they will be set to be linear units.
   * If not they will be set to be sigmoid units.
   */
  private void setEndsToLinear() {
    for (int noa = 0; noa < m_neuralNodes.length; noa++) {
      if ((m_neuralNodes[noa].getType() & NeuralConnection.OUTPUT) ==
	  NeuralConnection.OUTPUT) {
	((NeuralNode)m_neuralNodes[noa]).setMethod(m_linearUnit);
      }
      else {
	((NeuralNode)m_neuralNodes[noa]).setMethod(m_sigmoidUnit);
      }
    }
  }

  /**
   * Returns default capabilities of the classifier.
   *
   * @return      the capabilities of this classifier
   */
  public Capabilities getCapabilities() {
    Capabilities result = super.getCapabilities();

    // attributes
    result.enable(Capability.NOMINAL_ATTRIBUTES);
    result.enable(Capability.NUMERIC_ATTRIBUTES);
    result.enable(Capability.DATE_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);

    // class
    result.enable(Capability.NOMINAL_CLASS);
    result.enable(Capability.NUMERIC_CLASS);
    result.enable(Capability.DATE_CLASS);
    result.enable(Capability.MISSING_CLASS_VALUES);
    
    return result;
  }
  
  /**
   * Call this function to build and train a neural network for the training
   * data provided.
   * @param i The training data.
   * @throws Throws exception if can't build classification properly.
   */
  public void buildClassifier(Instances i) throws Exception {

    // can classifier handle the data?
    getCapabilities().testWithFail(i);

    // remove instances with missing class
    i = new Instances(i);
    i.deleteWithMissingClass();
    
    m_epoch = 0;
    m_error = 0;
    m_instances = null;
    m_currentInstance = null;
    m_controlPanel = null;
    m_nodePanel = null;
    
    
    m_outputs = new NeuralEnd[0];
    m_inputs = new NeuralEnd[0];
    m_numAttributes = 0;
    m_numClasses = 0;
    m_neuralNodes = new NeuralConnection[0];
    
    m_selected = new FastVector(4);
    m_graphers = new FastVector(2);
    m_nextId = 0;
    m_stopIt = true;
    m_stopped = true;
    m_accepted = false;    
    m_instances = new Instances(i);
    m_random = new Random(m_randomSeed);
    m_instances.randomize(m_random);

    if (m_useNomToBin) {
      m_nominalToBinaryFilter = new NominalToBinary();
      m_nominalToBinaryFilter.setInputFormat(m_instances);
      m_instances = Filter.useFilter(m_instances,
				     m_nominalToBinaryFilter);
    }
    m_numAttributes = m_instances.numAttributes() - 1;
    m_numClasses = m_instances.numClasses();
 
    
    setClassType(m_instances);
    

   
    //this sets up the validation set.
    Instances valSet = null;
    //numinval is needed later
    int numInVal = (int)(m_valSize / 100.0 * m_instances.numInstances());
    if (m_valSize > 0) {
      if (numInVal == 0) {
	numInVal = 1;
      }
      valSet = new Instances(m_instances, 0, numInVal);
    }
    ///////////

    setupInputs();
      
    setupOutputs();    
    if (m_autoBuild) {
      setupHiddenLayer();
    }
    
    /////////////////////////////
    //this sets up the gui for usage
    if (m_gui) {
      m_win = new JFrame();
      
      m_win.addWindowListener(new WindowAdapter() {
	  public void windowClosing(WindowEvent e) {
	    boolean k = m_stopIt;
	    m_stopIt = true;
	    int well =JOptionPane.showConfirmDialog(m_win, 
						    "Are You Sure...\n"
						    + "Click Yes To Accept"
						    + " The Neural Network" 
						    + "\n Click No To Return",
						    "Accept Neural Network",