attributeselectionpanel.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

    m_SeedLab.setEnabled(m_CVBut.isSelected());
    
    if (m_AttributeEvaluatorEditor.getValue() 
	instanceof AttributeTransformer) {
      m_CVBut.setSelected(false);
      m_CVBut.setEnabled(false);
      m_CVText.setEnabled(false);
      m_CVLab.setEnabled(false);
      m_SeedText.setEnabled(false);
      m_SeedLab.setEnabled(false);
      m_TrainBut.setSelected(true);
    }
  }
  
  /**
   * Sets the Logger to receive informational messages
   *
   * @param newLog the Logger that will now get info messages
   */
  public void setLog(Logger newLog) {

    m_Log = newLog;
  }
  
  /**
   * Tells the panel to use a new set of instances.
   *
   * @param inst a set of Instances
   */
  public void setInstances(Instances inst) {
    
    m_Instances = inst;
    String [] attribNames = new String [m_Instances.numAttributes()];
    for (int i = 0; i < attribNames.length; i++) {
      String type = "";
      switch (m_Instances.attribute(i).type()) {
      case Attribute.NOMINAL:
	type = "(Nom) ";
	break;
      case Attribute.NUMERIC:
	type = "(Num) ";
	break;
      case Attribute.STRING:
	type = "(Str) ";
	break;
      default:
	type = "(???) ";
      }
      String attnm = m_Instances.attribute(i).name();
     
      attribNames[i] = type + attnm;
    }
    m_StartBut.setEnabled(m_RunThread == null);
    m_StopBut.setEnabled(m_RunThread != null);
    m_ClassCombo.setModel(new DefaultComboBoxModel(attribNames));
    m_ClassCombo.setSelectedIndex(attribNames.length - 1);
    m_ClassCombo.setEnabled(true);
  }
  
  /**
   * Starts running the currently configured attribute evaluator and
   * search method. This is run in a separate thread, and will only start if
   * there is no attribute selection  already running. The attribute selection
   * output is sent to the results history panel.
   */
  protected void startAttributeSelection() {

    if (m_RunThread == null) {
      m_StartBut.setEnabled(false);
      m_StopBut.setEnabled(true);
      m_RunThread = new Thread() {
	public void run() {
	  // Copy the current state of things
	  m_Log.statusMessage("Setting up...");
	  Instances inst = new Instances(m_Instances);

	  int testMode = 0;
	  int numFolds = 10;
	  int seed = 1;
	  int classIndex = m_ClassCombo.getSelectedIndex();
	  ASEvaluation evaluator = 
	     (ASEvaluation) m_AttributeEvaluatorEditor.getValue();

	  ASSearch search = (ASSearch) m_AttributeSearchEditor.getValue();

	  StringBuffer outBuff = new StringBuffer();
	  String name = (new SimpleDateFormat("HH:mm:ss - "))
	  .format(new Date());
	  String sname = search.getClass().getName();
	  if (sname.startsWith("weka.attributeSelection.")) {
	    name += sname.substring("weka.attributeSelection.".length());
	  } else {
	    name += sname;
	  }
	  String ename = evaluator.getClass().getName();
	  if (ename.startsWith("weka.attributeSelection.")) {
	    name += (" + "
		     +ename.substring("weka.attributeSelection.".length()));
	  } else {
	    name += (" + "+ename);
	  }

	  AttributeSelection eval = null;

	  try {
	    if (m_CVBut.isSelected()) {
	      testMode = 1;
	      numFolds = Integer.parseInt(m_CVText.getText());
	      seed = Integer.parseInt(m_SeedText.getText());
	      if (numFolds <= 1) {
		throw new Exception("Number of folds must be greater than 1");
	      }
	    } 
	    inst.setClassIndex(classIndex);

	    // Output some header information
	    m_Log.logMessage("Started " + ename);
	    if (m_Log instanceof TaskLogger) {
	      ((TaskLogger)m_Log).taskStarted();
	    }
	    outBuff.append("=== Run information ===\n\n");
	    outBuff.append("Evaluator:    " + ename);
	    if (evaluator instanceof OptionHandler) {
	      String [] o = ((OptionHandler) evaluator).getOptions();
	      outBuff.append(" " + Utils.joinOptions(o));
	    }
	    outBuff.append("\nSearch:       " + sname);
	    if (search instanceof OptionHandler) {
	      String [] o = ((OptionHandler) search).getOptions();
	      outBuff.append(" " + Utils.joinOptions(o));
	    }
	    outBuff.append("\n");
	    outBuff.append("Relation:     " + inst.relationName() + '\n');
	    outBuff.append("Instances:    " + inst.numInstances() + '\n');
	    outBuff.append("Attributes:   " + inst.numAttributes() + '\n');
	    if (inst.numAttributes() < 100) {
	      for (int i = 0; i < inst.numAttributes(); i++) {
		outBuff.append("              " + inst.attribute(i).name()
			       + '\n');
	      }
	    } else {
	      outBuff.append("              [list of attributes omitted]\n");
	    }
	    outBuff.append("Evaluation mode:    ");
	    switch (testMode) {
	      case 0: // select using all training
	      outBuff.append("evaluate on all training data\n");
	      break;
	      case 1: // CV mode
	      outBuff.append("" + numFolds + "-fold cross-validation\n");
	      break;
	    }
	    outBuff.append("\n");
	    m_History.addResult(name, outBuff);
	    m_History.setSingle(name);
	    
	    // Do the feature selection and output the results.
	    m_Log.statusMessage("Doing feature selection...");
	    m_History.updateResult(name);
	    
	    eval = new AttributeSelection();
	    eval.setEvaluator(evaluator);
	    eval.setSearch(search);
	    eval.setFolds(numFolds);
	    eval.setSeed(seed);
	    if (testMode == 1) {
	      eval.setXval(true);
	    }
	    	    
	    switch (testMode) {
	      case 0: // select using training
	      m_Log.statusMessage("Evaluating on training data...");
	      eval.SelectAttributes(inst);
	      break;

	      case 1: // CV mode
	      m_Log.statusMessage("Randomizing instances...");
	      Random random = new Random(seed);
	      inst.randomize(random);
	      if (inst.attribute(classIndex).isNominal()) {
		m_Log.statusMessage("Stratifying instances...");
		inst.stratify(numFolds);
	      }
	      for (int fold = 0; fold < numFolds;fold++) {
		m_Log.statusMessage("Creating splits for fold "
				    + (fold + 1) + "...");
		Instances train = inst.trainCV(numFolds, fold, random);
		m_Log.statusMessage("Selecting attributes using all but fold "
				    + (fold + 1) + "...");
		
		eval.selectAttributesCVSplit(train);
	      }
	      break;
	      default:
	      throw new Exception("Test mode not implemented");
	    }

	    if (testMode == 0) {
	      outBuff.append(eval.toResultsString());
	    } else {
	      outBuff.append(eval.CVResultsString());
	    }
	  
	    outBuff.append("\n");
	    m_History.updateResult(name);
	    m_Log.logMessage("Finished " + ename+" "+sname);
	    m_Log.statusMessage("OK");
	  } catch (Exception ex) {
	    m_Log.logMessage(ex.getMessage());
	    m_Log.statusMessage("See error log");
	  } finally {
	    if (evaluator instanceof AttributeTransformer) {
	      try {
		Instances transformed = 
		  ((AttributeTransformer)evaluator).transformedData();
		transformed.
		  setRelationName("AT: "+transformed.relationName());

		FastVector vv = new FastVector();
		vv.addElement(transformed);
		m_History.addObject(name, vv);
	      } catch (Exception ex) {
		System.err.println(ex);
		ex.printStackTrace();
	      }
	    } else if (testMode == 0) {
	      try {
		Instances reducedInst = eval.reduceDimensionality(inst);
		FastVector vv = new FastVector();
		vv.addElement(reducedInst);
		m_History.addObject(name, vv);
	      } catch (Exception ex) {
		ex.printStackTrace();
	      }
	    }
	    if (isInterrupted()) {
	      m_Log.logMessage("Interrupted " + ename+" "+sname);
	      m_Log.statusMessage("See error log");
	    }
	    m_RunThread = null;
	    m_StartBut.setEnabled(true);
	    m_StopBut.setEnabled(false);
	    if (m_Log instanceof TaskLogger) {
	      ((TaskLogger)m_Log).taskFinished();
	    }
	  }
	}
      };
      m_RunThread.setPriority(Thread.MIN_PRIORITY);
      m_RunThread.start();
    }
  }
  
  /**
   * Stops the currently running attribute selection (if any).
   */
  protected void stopAttributeSelection() {

    if (m_RunThread != null) {
      m_RunThread.interrupt();
      
      // This is deprecated (and theoretically the interrupt should do).
      m_RunThread.stop();
      
    }
  }
  
  /**
   * Save the named buffer to a file.
   * @param name the name of the buffer to be saved.
   */
  protected void saveBuffer(String name) {
    StringBuffer sb = m_History.getNamedBuffer(name);
    if (sb != null) {
      if (m_SaveOut.save(sb)) {
	m_Log.logMessage("Save succesful.");
      }
    }
  }

  /**
   * Popup a visualize panel for viewing transformed data
   * @param sp the Instances to display
   */
  protected void visualizeTransformedData(Instances ti) {
    if (ti != null) {
      MatrixPanel mp = new MatrixPanel();
      mp.setInstances(ti);
      String plotName = ti.relationName();
      final javax.swing.JFrame jf = 
	new javax.swing.JFrame("Weka Attribute Selection Visualize: "
			       +plotName);
      jf.setSize(800,600);
      jf.getContentPane().setLayout(new BorderLayout());
      jf.getContentPane().add(mp, BorderLayout.CENTER);
      jf.addWindowListener(new java.awt.event.WindowAdapter() {
	  public void windowClosing(java.awt.event.WindowEvent e) {
	    jf.dispose();
	  }
	});

      jf.setVisible(true);
    }
  }

  /**
   * Handles constructing a popup menu with visualization options
   * @param name the name of the result history list entry clicked on by
   * the user.
   * @param x the x coordinate for popping up the menu
   * @param y the y coordinate for popping up the menu
   */
  protected void visualize(String name, int x, int y) {
    final String selectedName = name;
    JPopupMenu resultListMenu = new JPopupMenu();

    JMenuItem visMainBuffer = new JMenuItem("View in main window");
    if (selectedName != null) {
      visMainBuffer.addActionListener(new ActionListener() {
	  public void actionPerformed(ActionEvent e) {
	    m_History.setSingle(selectedName);
	  }
	});
    } else {
      visMainBuffer.setEnabled(false);
    }
    resultListMenu.add(visMainBuffer);

    JMenuItem visSepBuffer = new JMenuItem("View in separate window");
    if (selectedName != null) {
    visSepBuffer.addActionListener(new ActionListener() {
	public void actionPerformed(ActionEvent e) {
	  m_History.openFrame(selectedName);
	}
      });
    } else {
      visSepBuffer.setEnabled(false);
    }
    resultListMenu.add(visSepBuffer);

    JMenuItem saveOutput = new JMenuItem("Save result buffer");
    if (selectedName != null) {
    saveOutput.addActionListener(new ActionListener() {
	public void actionPerformed(ActionEvent e) {
	  saveBuffer(selectedName);
	}
      });
    } else {
      saveOutput.setEnabled(false);
    }
    resultListMenu.add(saveOutput);
    

    FastVector o = null;
    if (selectedName != null) {
      o = (FastVector)m_History.getNamedObject(selectedName);
    }    

    //    VisualizePanel temp_vp = null;
    Instances tempTransformed = null;

    if (o != null) {
      for (int i = 0; i < o.size(); i++) {
	Object temp = o.elementAt(i);
	//	if (temp instanceof VisualizePanel) {
	if (temp instanceof Instances) {
	  //	  temp_vp = (VisualizePanel)temp;
	  tempTransformed = (Instances) temp;
	} 
      }
    }
    
    //    final VisualizePanel vp = temp_vp;
    final Instances ti = tempTransformed;
    JMenuItem visTrans = null;
    
    if (ti != null) {
      if (ti.relationName().startsWith("AT:")) {
	visTrans = new JMenuItem("Visualize transformed data");
      } else {
	visTrans = new JMenuItem("Visualize reduced data");
      }
      resultListMenu.addSeparator();
    }

    //    JMenuItem visTrans = new JMenuItem("Visualize transformed data");
    if (ti != null && visTrans != null) {
      visTrans.addActionListener(new ActionListener() {
	  public void actionPerformed(ActionEvent e) {
	    visualizeTransformedData(ti);
	  }
	});
    }
     
    if (visTrans != null) {
      resultListMenu.add(visTrans);
    }
    
    resultListMenu.show(m_History.getList(), x, y);
  }

  /**
   * Tests out the attribute selection panel from the command line.
   *
   * @param args may optionally contain the name of a dataset to load.
   */
  public static void main(String [] args) {

    try {
      final javax.swing.JFrame jf =
	new javax.swing.JFrame("Weka Explorer: Select attributes");
      jf.getContentPane().setLayout(new BorderLayout());
      final AttributeSelectionPanel sp = new AttributeSelectionPanel();
      jf.getContentPane().add(sp, BorderLayout.CENTER);
      weka.gui.LogPanel lp = new weka.gui.LogPanel();
      sp.setLog(lp);
      jf.getContentPane().add(lp, BorderLayout.SOUTH);
      jf.addWindowListener(new java.awt.event.WindowAdapter() {
	public void windowClosing(java.awt.event.WindowEvent e) {
	  jf.dispose();
	  System.exit(0);
	}
      });
      jf.pack();
      jf.setVisible(true);
      if (args.length == 1) {
	System.err.println("Loading instances from " + args[0]);
	java.io.Reader r = new java.io.BufferedReader(
			   new java.io.FileReader(args[0]));
	Instances i = new Instances(r);
	sp.setInstances(i);
      }
    } catch (Exception ex) {
      ex.printStackTrace();
      System.err.println(ex.getMessage());
    }
  }
}