c45saver.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

      
      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);
        setDestination(retrieveFile());
      } catch(Exception ex){
          throw new IOException("Cannot create data file, only names file created.");
      }
      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 newVector = new FastVector(3);

    newVector.addElement(new Option("The input file", "i", 1, 
				    "-i <the input file>"));
    
    newVector.addElement(new Option("The output file", "o", 1, 
				    "-o <the output file>"));
    
    newVector.addElement(new Option("The class index", "c", 1, 
				    "-c <the class index>"));
    
    return newVector.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();
    
    if(inputString.length() != 0){
        try{
            File input = new File(inputString);
            loader.setFile(input);
            setInstances(loader.getDataSet());
        } catch(Exception ex){
            throw new IOException("No data set loaded. Data set has to be arff format.");
        }
    }
    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.");
        } finally{
            setDestination(retrieveFile());
        }
    }
    if(indexString.length() != 0){
        if(indexString.equals("first"))
            getInstances().setClassIndex(0);
        else{
            if(indexString.equals("last"))
                getInstances().setClassIndex(getInstances().numAttributes()-1);
            else{
                int classIndex = Integer.parseInt(indexString);
                if(classIndex >=0 && classIndex < getInstances().numAttributes())
                    getInstances().setClassIndex(classIndex);
                else
                    throw new IOException("Invalid class index");
            }
        }
    }
    else
        getInstances().setClassIndex(getInstances().numAttributes()-1);

  }

  /**
   * 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 options should contain the options of a Saver.
   */
  public static void main(String [] options) {
      
      StringBuffer text = new StringBuffer();
      try {
	C45Saver csv = new C45Saver();
        text.append("\n\nC45Saver options:\n\n");
        Enumeration enumi = csv.listOptions();
        while (enumi.hasMoreElements()) {
            Option option = (Option)enumi.nextElement();
            text.append(option.synopsis()+'\n');
            text.append(option.description()+'\n');
        }
        try {
          csv.setOptions(options);  
        } catch (Exception ex) {
            System.out.println("\n"+text);
            System.exit(1);
	}
        //incremental
        /*
        csv.setRetrieval(INCREMENTAL);
        Instances instances = csv.getInstances();
        csv.setStructure(instances);
        for(int i = 0; i < instances.numInstances(); i++){ //last instance is null and finishes incremental saving
            csv.writeIncremental(instances.instance(i));
        }
        csv.writeIncremental(null);
        */
        
        //batch
        csv.writeBatch();
      } catch (Exception ex) {
	ex.printStackTrace();
	}
      
    }
}