randomsplitresultproducer.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

    String [] keyNames = m_SplitEvaluator.getKeyNames();
    // Add in the names of our extra key fields
    String [] newKeyNames = new String [keyNames.length + 2];
    newKeyNames[0] = DATASET_FIELD_NAME;
    newKeyNames[1] = RUN_FIELD_NAME;
    System.arraycopy(keyNames, 0, newKeyNames, 2, keyNames.length);
    return newKeyNames;
  }

  /**
   * Gets the data types of each of the columns produced for a single run.
   * This method should really be static.
   *
   * @return an array containing objects of the type of each column. The 
   * objects should be Strings, or Doubles.
   */
  public Object [] getKeyTypes() {

    Object [] keyTypes = m_SplitEvaluator.getKeyTypes();
    // Add in the types of our extra fields
    Object [] newKeyTypes = new String [keyTypes.length + 2];
    newKeyTypes[0] = new String();
    newKeyTypes[1] = new String();
    System.arraycopy(keyTypes, 0, newKeyTypes, 2, keyTypes.length);
    return newKeyTypes;
  }

  /**
   * Gets the names of each of the columns produced for a single run.
   * This method should really be static.
   *
   * @return an array containing the name of each column
   */
  public String [] getResultNames() {

    String [] resultNames = m_SplitEvaluator.getResultNames();
    // Add in the names of our extra Result fields
    String [] newResultNames = new String [resultNames.length + 1];
    newResultNames[0] = TIMESTAMP_FIELD_NAME;
    System.arraycopy(resultNames, 0, newResultNames, 1, resultNames.length);
    return newResultNames;
  }

  /**
   * Gets the data types of each of the columns produced for a single run.
   * This method should really be static.
   *
   * @return an array containing objects of the type of each column. The 
   * objects should be Strings, or Doubles.
   */
  public Object [] getResultTypes() {

    Object [] resultTypes = m_SplitEvaluator.getResultTypes();
    // Add in the types of our extra Result fields
    Object [] newResultTypes = new Object [resultTypes.length + 1];
    newResultTypes[0] = new Double(0);
    System.arraycopy(resultTypes, 0, newResultTypes, 1, resultTypes.length);
    return newResultTypes;
  }

  /**
   * Gets a description of the internal settings of the result
   * producer, sufficient for distinguishing a ResultProducer
   * instance from another with different settings (ignoring
   * those settings set through this interface). For example,
   * a cross-validation ResultProducer may have a setting for the
   * number of folds. For a given state, the results produced should
   * be compatible. Typically if a ResultProducer is an OptionHandler,
   * this string will represent the command line arguments required
   * to set the ResultProducer to that state.
   *
   * @return the description of the ResultProducer state, or null
   * if no state is defined
   */
  public String getCompatibilityState() {

    String result = "-P " + m_TrainPercent;
    if (!getRandomizeData()) {
      result += " -R";
    }
    if (m_SplitEvaluator == null) {
      result += " <null SplitEvaluator>";
    } else {
      result += " -W " + m_SplitEvaluator.getClass().getName();
    }
    return result + " --";
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String outputFileTipText() {
    return "Set the destination for saving raw output. If the rawOutput "
      +"option is selected, then output from the splitEvaluator for "
      +"individual train-test splits is saved. If the destination is a "
      +"directory, "
      +"then each output is saved to an individual gzip file; if the "
      +"destination is a file, then each output is saved as an entry "
      +"in a zip file.";
  }

  /**
   * Get the value of OutputFile.
   *
   * @return Value of OutputFile.
   */
  public File getOutputFile() {
    
    return m_OutputFile;
  }
  
  /**
   * Set the value of OutputFile.
   *
   * @param newOutputFile Value to assign to OutputFile.
   */
  public void setOutputFile(File newOutputFile) {
    
    m_OutputFile = newOutputFile;
  }  

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String randomizeDataTipText() {
    return "Do not randomize dataset and do not perform probabilistic rounding " +
      "if true";
  }

  /**
   * Get if dataset is to be randomized
   * @return true if dataset is to be randomized
   */
  public boolean getRandomizeData() {
    return m_randomize;
  }
  
  /**
   * Set to true if dataset is to be randomized
   * @param d true if dataset is to be randomized
   */
  public void setRandomizeData(boolean d) {
    m_randomize = d;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String rawOutputTipText() {
    return "Save raw output (useful for debugging). If set, then output is "
      +"sent to the destination specified by outputFile";
  }

  /**
   * Get if raw split evaluator output is to be saved
   * @return true if raw split evalutor output is to be saved
   */
  public boolean getRawOutput() {
    return m_debugOutput;
  }
  
  /**
   * Set to true if raw split evaluator output is to be saved
   * @param d true if output is to be saved
   */
  public void setRawOutput(boolean d) {
    m_debugOutput = d;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String trainPercentTipText() {
    return "Set the percentage of data to use for training.";
  }

  /**
   * Get the value of TrainPercent.
   *
   * @return Value of TrainPercent.
   */
  public double getTrainPercent() {
    
    return m_TrainPercent;
  }
  
  /**
   * Set the value of TrainPercent.
   *
   * @param newTrainPercent Value to assign to TrainPercent.
   */
  public void setTrainPercent(double newTrainPercent) {
    
    m_TrainPercent = newTrainPercent;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String splitEvaluatorTipText() {
    return "The evaluator to apply to the test data. "
      +"This may be a classifier, regression scheme etc.";
  }

  /**
   * Get the SplitEvaluator.
   *
   * @return the SplitEvaluator.
   */
  public SplitEvaluator getSplitEvaluator() {
    
    return m_SplitEvaluator;
  }
  
  /**
   * Set the SplitEvaluator.
   *
   * @param newSplitEvaluator new SplitEvaluator to use.
   */
  public void setSplitEvaluator(SplitEvaluator newSplitEvaluator) {
    
    m_SplitEvaluator = newSplitEvaluator;
    m_SplitEvaluator.setAdditionalMeasures(m_AdditionalMeasures);
  }

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

    Vector newVector = new Vector(5);

    newVector.addElement(new Option(
	     "\tThe percentage of instances to use for training.\n"
	      +"\t(default 66)", 
	     "P", 1, 
	     "-P <percent>"));

    newVector.addElement(new Option(
	     "Save raw split evaluator output.",
	     "D",0,"-D"));

    newVector.addElement(new Option(
	     "\tThe filename where raw output will be stored.\n"
	     +"\tIf a directory name is specified then then individual\n"
	     +"\toutputs will be gzipped, otherwise all output will be\n"
	     +"\tzipped to the named file. Use in conjuction with -D."
	     +"\t(default splitEvalutorOut.zip)", 
	     "O", 1, 
	     "-O <file/directory name/path>"));

    newVector.addElement(new Option(
	     "\tThe full class name of a SplitEvaluator.\n"
	      +"\teg: weka.experiment.ClassifierSplitEvaluator", 
	     "W", 1, 
	     "-W <class name>"));

    newVector.addElement(new Option(
	     "\tSet when data is not to be randomized and the data sets' size.\n"
	     + "\tIs not to be determined via probabilistic rounding.",
	     "R",0,"-R"));

 
    if ((m_SplitEvaluator != null) &&
	(m_SplitEvaluator instanceof OptionHandler)) {
      newVector.addElement(new Option(
	     "",
	     "", 0, "\nOptions specific to split evaluator "
	     + m_SplitEvaluator.getClass().getName() + ":"));
      Enumeration enu = ((OptionHandler)m_SplitEvaluator).listOptions();
      while (enu.hasMoreElements()) {
	newVector.addElement(enu.nextElement());
      }
    }
    return newVector.elements();
  }

  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -P &lt;percent&gt;
   *  The percentage of instances to use for training.
   *  (default 66)</pre>
   * 
   * <pre> -D
   * Save raw split evaluator output.</pre>
   * 
   * <pre> -O &lt;file/directory name/path&gt;
   *  The filename where raw output will be stored.
   *  If a directory name is specified then then individual
   *  outputs will be gzipped, otherwise all output will be
   *  zipped to the named file. Use in conjuction with -D. (default splitEvalutorOut.zip)</pre>
   * 
   * <pre> -W &lt;class name&gt;
   *  The full class name of a SplitEvaluator.
   *  eg: weka.experiment.ClassifierSplitEvaluator</pre>
   * 
   * <pre> -R
   *  Set when data is not to be randomized and the data sets' size.
   *  Is not to be determined via probabilistic rounding.</pre>
   * 
   * <pre> 
   * Options specific to split evaluator weka.experiment.ClassifierSplitEvaluator:
   * </pre>
   * 
   * <pre> -W &lt;class name&gt;
   *  The full class name of the classifier.
   *  eg: weka.classifiers.bayes.NaiveBayes</pre>
   * 
   * <pre> -C &lt;index&gt;
   *  The index of the class for which IR statistics
   *  are to be output. (default 1)</pre>
   * 
   * <pre> -I &lt;index&gt;
   *  The index of an attribute to output in the
   *  results. This attribute should identify an
   *  instance in order to know which instances are
   *  in the test set of a cross validation. if 0
   *  no output (default 0).</pre>
   * 
   * <pre> -P
   *  Add target and prediction columns to the result
   *  for each fold.</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.rules.ZeroR:
   * </pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   <!-- options-end -->
   *
   * All options after -- will be passed to the split evaluator.
   *
   * @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 {
    
    setRawOutput(Utils.getFlag('D', options));
    setRandomizeData(!Utils.getFlag('R', options));

    String fName = Utils.getOption('O', options);
    if (fName.length() != 0) {
      setOutputFile(new File(fName));
    }

    String trainPct = Utils.getOption('P', options);
    if (trainPct.length() != 0) {
      setTrainPercent((new Double(trainPct)).doubleValue());
    } else {
      setTrainPercent(66);
    }

    String seName = Utils.getOption('W', options);
    if (seName.length() == 0) {
      throw new Exception("A SplitEvaluator must be specified with"
			  + " the -W option.");
    }
    // Do it first without options, so if an exception is thrown during
    // the option setting, listOptions will contain options for the actual
    // SE.
    setSplitEvaluator((SplitEvaluator)Utils.forName(
		      SplitEvaluator.class,
		      seName,
		      null));
    if (getSplitEvaluator() instanceof OptionHandler) {
      ((OptionHandler) getSplitEvaluator())
	.setOptions(Utils.partitionOptions(options));
    }
  }

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

    String [] seOptions = new String [0];
    if ((m_SplitEvaluator != null) && 
	(m_SplitEvaluator instanceof OptionHandler)) {
      seOptions = ((OptionHandler)m_SplitEvaluator).getOptions();
    }
    
    String [] options = new String [seOptions.length + 9];
    int current = 0;

    options[current++] = "-P"; options[current++] = "" + getTrainPercent();
    
    if (getRawOutput()) {
      options[current++] = "-D";
    }
    
    if (!getRandomizeData()) {
      options[current++] = "-R";
    }

    options[current++] = "-O"; 
    options[current++] = getOutputFile().getName();

    if (getSplitEvaluator() != null) {
      options[current++] = "-W";
      options[current++] = getSplitEvaluator().getClass().getName();
    }
    options[current++] = "--";

    System.arraycopy(seOptions, 0, options, current, 
		     seOptions.length);
    current += seOptions.length;
    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Gets a text descrption of the result producer.
   *
   * @return a text description of the result producer.
   */
  public String toString() {

    String result = "RandomSplitResultProducer: ";
    result += getCompatibilityState();
    if (m_Instances == null) {
      result += ": <null Instances>";
    } else {
      result += ": " + Utils.backQuoteChars(m_Instances.relationName());
    }
    return result;
  }

} // RandomSplitResultProducer