c45saver.java

矩阵的QR分解算法

              }
              setFileExtension(".names");
              m_incrementalCounter = 0;
              resetStructure();
              outW = null;
              resetWriter();
          }
      }
  }

  
  /** 
   * Writes a Batch of instances
   * @throws IOException throws IOException if saving in batch mode is not possible
   */
  public void writeBatch() throws IOException {
      
      Instances instances = getInstances();
      
      if(instances == null)
          throw new IOException("No instances to save");
      if(instances.classIndex() == -1){
          instances.setClassIndex(instances.numAttributes()-1);
          System.err.println("No class specified. Last attribute is used as class attribute.");
      }
      if(instances.attribute(instances.classIndex()).isNumeric())
          throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
      if(getRetrieval() == INCREMENTAL)
          throw new IOException("Batch and incremental saving cannot be mixed.");
      
      setRetrieval(BATCH);
      if(retrieveFile() == null || getWriter() == null){
          throw new IOException("C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
      }
      setWriteMode(WRITE);
      //print names file
      setFileExtension(".names");
      PrintWriter outW = new PrintWriter(getWriter());
      for (int i = 0; i < instances.attribute(instances.classIndex()).numValues(); i++) {
        outW.write(instances.attribute(instances.classIndex()).value(i));
        if (i < instances.attribute(instances.classIndex()).numValues()-1) {
            outW.write(",");
        } else {
            outW.write(".\n");
	}
      }
      for (int i = 0; i < instances.numAttributes(); i++) {
        if (i != instances.classIndex()) {
            outW.write(instances.attribute(i).name()+": ");
            if (instances.attribute(i).isNumeric() || instances.attribute(i).isDate()) {
                outW.write("continuous.\n");
            } else {
                Attribute temp = instances.attribute(i);
		for (int j = 0; j < temp.numValues(); j++) {
                    outW.write(temp.value(j));
		    if (j < temp.numValues()-1) {
			outW.write(",");
		    } else {
			outW.write(".\n");
		    }
		 }
             }
        }
      }
      outW.flush();
      outW.close();
      
      //print data file
      String out = retrieveFile().getAbsolutePath();
      setFileExtension(".data");
      out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
      File namesFile = new File(out);
      try{
        setFile(namesFile);
      } catch(Exception ex){
          throw new IOException("Cannot create data file, only names file created (Reason: " + ex.toString() + ").");
      }
      if(retrieveFile() == null || getWriter() == null){
          throw new IOException("Cannot create data file, only names file created.");
      }
      outW = new PrintWriter(getWriter());
      // print data file
      for (int i = 0; i < instances.numInstances(); i++) {
	Instance temp = instances.instance(i);
        for(int j = 0; j < temp.numAttributes(); j++){
            if(j != instances.classIndex()){
                if (temp.isMissing(j)) {
		      outW.write("?,");
		    } else if (instances.attribute(j).isNominal() || 
			       instances.attribute(j).isString()) {
		      outW.write(instances.attribute(j).value((int)temp.value(j))+",");
		    } else {
		      outW.write(""+temp.value(j)+",");
		    }
            }
        }
        // write the class value
        if (temp.isMissing(instances.classIndex())) {
            outW.write("?");
        } 
        else {
            outW.write(instances.attribute(instances.classIndex()).value((int)temp.value(instances.classIndex())));
        }
        outW.write("\n");
      }
      outW.flush();
      outW.close();
      setFileExtension(".names");
      setWriteMode(WAIT);
      outW = null;
      resetWriter();
      setWriteMode(CANCEL);
  }
  
  
  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {
    FastVector result = new FastVector();

    Enumeration en = super.listOptions();
    while (en.hasMoreElements())
      result.addElement(en.nextElement());

    result.addElement(new Option(
	"The class index", 
	"c", 1, "-c <the class index>"));
    
    return result.elements();
  }

 
  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -i &lt;the input file&gt;
   * The input file</pre>
   * 
   * <pre> -o &lt;the output file&gt;
   * The output file</pre>
   * 
   * <pre> -c &lt;the class index&gt;
   * The class index</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 outputString = Utils.getOption('o', options);
    String inputString = Utils.getOption('i', options);
    String indexString = Utils.getOption('c', options);
    
    ArffLoader loader = new ArffLoader();
    
    resetOptions();

    // parse index
    int index = -1;
    if (indexString.length() != 0){
      if(indexString.equals("first"))
	index = 0;
      else {
	if (indexString.equals("last"))
	  index = -1;
	else
	  index = Integer.parseInt(indexString);
      }
    }
    
    if (inputString.length() != 0){
      try {
	File input = new File(inputString);
	loader.setFile(input);
	Instances inst = loader.getDataSet();
	if (index == -1)
	  inst.setClassIndex(inst.numAttributes() - 1);
	else
	  inst.setClassIndex(index);
	setInstances(inst);
      } catch(Exception ex){
	throw new IOException("No data set loaded. Data set has to be arff format (Reason: " + ex.toString() + ").");
      }
    }
    else
      throw new IOException("No data set to save.");

    if (outputString.length() != 0){ 
      //add appropriate file extension
      if (!outputString.endsWith(getFileExtension())){
	if (outputString.lastIndexOf('.') != -1)
	  outputString = (outputString.substring(0,outputString.lastIndexOf('.'))) + getFileExtension();
	else
	  outputString = outputString + getFileExtension();
      }
      try {
	File output = new File(outputString);
	setFile(output);
      } catch(Exception ex){
	throw new IOException("Cannot create output file.");
      }
    }

    if (index == -1)
      index = getInstances().numAttributes() - 1;
    getInstances().setClassIndex(index);
  }

  /**
   * Gets the current settings of the C45Saver object.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] options = new String [10];
    int current = 0;
    if(retrieveFile() != null){
        options[current++] = "-o"; options[current++] = "" + retrieveFile();
    }
    else{
        options[current++] = "-o"; options[current++] = "";
    }
    if(getInstances() != null){
        options[current++] = "-i"; options[current++] = "" + getInstances().relationName();
        options[current++] = "-c"; options[current++] = "" + getInstances().classIndex();
    }
    else{
        options[current++] = "-i"; options[current++] = "";
        options[current++] = "-c"; options[current++] = "";
    }
    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }



  /**
   * Main method.
   *
   * @param args should contain the options of a Saver.
   */
  public static void main(String[] args) {
    runFileSaver(new C45Saver(), args);
  }
}