learningrateresultproducer.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

  /**
   * 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 = " ";
    // + "-F " + Utils.quote(getKeyFieldName())
    // + " -X " + getStepSize() + " ";
    if (m_ResultProducer == null) {
      result += "<null ResultProducer>";
    } else {
      result += "-W " + m_ResultProducer.getClass().getName();
    }
    result  += " -- " + m_ResultProducer.getCompatibilityState();
    return result.trim();
  }


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

    Vector newVector = new Vector(2);

    newVector.addElement(new Option(
	     "\tThe number of steps in the learning rate curve.\n"
	      +"\t(default 10)", 
	     "X", 1, 
	     "-X <num steps>"));
    newVector.addElement(new Option(
	     "\tThe full class name of a ResultProducer.\n"
	      +"\teg: weka.experiment.CrossValidationResultProducer", 
	     "W", 1, 
	     "-W <class name>"));

    if ((m_ResultProducer != null) &&
	(m_ResultProducer instanceof OptionHandler)) {
      newVector.addElement(new Option(
	     "",
	     "", 0, "\nOptions specific to result producer "
	     + m_ResultProducer.getClass().getName() + ":"));
      Enumeration enu = ((OptionHandler)m_ResultProducer).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> -X &lt;num steps&gt;
   *  The number of steps in the learning rate curve.
   *  (default 10)</pre>
   * 
   * <pre> -W &lt;class name&gt;
   *  The full class name of a ResultProducer.
   *  eg: weka.experiment.CrossValidationResultProducer</pre>
   * 
   * <pre> 
   * Options specific to result producer weka.experiment.AveragingResultProducer:
   * </pre>
   * 
   * <pre> -F &lt;field name&gt;
   *  The name of the field to average over.
   *  (default "Fold")</pre>
   * 
   * <pre> -X &lt;num results&gt;
   *  The number of results expected per average.
   *  (default 10)</pre>
   * 
   * <pre> -S
   *  Calculate standard deviations.
   *  (default only averages)</pre>
   * 
   * <pre> -W &lt;class name&gt;
   *  The full class name of a ResultProducer.
   *  eg: weka.experiment.CrossValidationResultProducer</pre>
   * 
   * <pre> 
   * Options specific to result producer weka.experiment.CrossValidationResultProducer:
   * </pre>
   * 
   * <pre> -X &lt;number of folds&gt;
   *  The number of folds to use for the cross-validation.
   *  (default 10)</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> 
   * 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 result producer.
   *
   * @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 stepSize = Utils.getOption('S', options);
    if (stepSize.length() != 0) {
      setStepSize(Integer.parseInt(stepSize));
    } else {
      setStepSize(10);
    }

    String lowerSize = Utils.getOption('L', options);
    if (lowerSize.length() != 0) {
      setLowerSize(Integer.parseInt(lowerSize));
    } else {
      setLowerSize(0);
    }
    
    String upperSize = Utils.getOption('U', options);
    if (upperSize.length() != 0) {
      setUpperSize(Integer.parseInt(upperSize));
    } else {
      setUpperSize(-1);
    }

    String rpName = Utils.getOption('W', options);
    if (rpName.length() == 0) {
      throw new Exception("A ResultProducer 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
    // RP.
    setResultProducer((ResultProducer)Utils.forName(
		      ResultProducer.class,
		      rpName,
		      null));
    if (getResultProducer() instanceof OptionHandler) {
      ((OptionHandler) getResultProducer())
	.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_ResultProducer != null) && 
	(m_ResultProducer instanceof OptionHandler)) {
      seOptions = ((OptionHandler)m_ResultProducer).getOptions();
    }
    
    String [] options = new String [seOptions.length + 9];
    int current = 0;

    options[current++] = "-S";
    options[current++] = "" + getStepSize();
    options[current++] = "-L";
    options[current++] = "" + getLowerSize();
    options[current++] = "-U";
    options[current++] = "" + getUpperSize();
    if (getResultProducer() != null) {
      options[current++] = "-W";
      options[current++] = getResultProducer().getClass().getName();
    }
    options[current++] = "--";

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

  /**
   * Set a list of method names for additional measures to look for
   * in SplitEvaluators. This could contain many measures (of which only a
   * subset may be produceable by the current resultProducer) if an experiment
   * is the type that iterates over a set of properties.
   * @param additionalMeasures an array of measure names, null if none
   */
  public void setAdditionalMeasures(String [] additionalMeasures) {
    m_AdditionalMeasures = additionalMeasures;

    if (m_ResultProducer != null) {
      System.err.println("LearningRateResultProducer: setting additional "
			 +"measures for "
			 +"ResultProducer");
      m_ResultProducer.setAdditionalMeasures(m_AdditionalMeasures);
    }
  }

  /**
   * Returns an enumeration of any additional measure names that might be
   * in the result producer
   * @return an enumeration of the measure names
   */
  public Enumeration enumerateMeasures() {
    Vector newVector = new Vector();
    if (m_ResultProducer instanceof AdditionalMeasureProducer) {
      Enumeration en = ((AdditionalMeasureProducer)m_ResultProducer).
	enumerateMeasures();
      while (en.hasMoreElements()) {
	String mname = (String)en.nextElement();
	newVector.addElement(mname);
      }
    }
    return newVector.elements();
  }

  /**
   * Returns the value of the named measure
   * @param additionalMeasureName the name of the measure to query for its value
   * @return the value of the named measure
   * @throws IllegalArgumentException if the named measure is not supported
   */
  public double getMeasure(String additionalMeasureName) {
    if (m_ResultProducer instanceof AdditionalMeasureProducer) {
      return ((AdditionalMeasureProducer)m_ResultProducer).
	getMeasure(additionalMeasureName);
    } else {
      throw new IllegalArgumentException("LearningRateResultProducer: "
			  +"Can't return value for : "+additionalMeasureName
			  +". "+m_ResultProducer.getClass().getName()+" "
			  +"is not an AdditionalMeasureProducer");
    }
  }

  /**
   * Sets the dataset that results will be obtained for.
   *
   * @param instances a value of type 'Instances'.
   */
  public void setInstances(Instances instances) {
    
    m_Instances = instances;
  }


  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String lowerSizeTipText() {
    return "Set the minmum number of instances in a dataset. Setting zero "
      + "here will actually use <stepSize> number of instances at the first "
      + "step (since it makes no sense to use zero instances :-))";
  }

  /**
   * Get the value of LowerSize.
   *
   * @return Value of LowerSize.
   */
  public int getLowerSize() {
    
    return m_LowerSize;
  }
  
  /**
   * Set the value of LowerSize.
   *
   * @param newLowerSize Value to assign to
   * LowerSize.
   */
  public void setLowerSize(int newLowerSize) {
    
    m_LowerSize = newLowerSize;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String upperSizeTipText() {
    return "Set the maximum number of instances in a dataset. Setting -1 "
      + "sets no upper limit (other than the total number of instances "
      + "in the full dataset)";
  }

  /**
   * Get the value of UpperSize.
   *
   * @return Value of UpperSize.
   */
  public int getUpperSize() {
    
    return m_UpperSize;
  }
  
  /**
   * Set the value of UpperSize.
   *
   * @param newUpperSize Value to assign to
   * UpperSize.
   */
  public void setUpperSize(int newUpperSize) {
    
    m_UpperSize = newUpperSize;
  }


  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String stepSizeTipText() {
    return "Set the number of instances to add at each step.";
  }

  /**
   * Get the value of StepSize.
   *
   * @return Value of StepSize.
   */
  public int getStepSize() {
    
    return m_StepSize;
  }
  
  /**
   * Set the value of StepSize.
   *
   * @param newStepSize Value to assign to
   * StepSize.
   */
  public void setStepSize(int newStepSize) {
    
    m_StepSize = newStepSize;
  }

  /**
   * Sets the object to send results of each run to.
   *
   * @param listener a value of type 'ResultListener'
   */
  public void setResultListener(ResultListener listener) {

    m_ResultListener = listener;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String resultProducerTipText() {
    return "Set the resultProducer for which learning rate results should be "
      + "generated.";
  }

  /**
   * Get the ResultProducer.
   *
   * @return the ResultProducer.
   */
  public ResultProducer getResultProducer() {
    
    return m_ResultProducer;
  }
  
  /**
   * Set the ResultProducer.
   *
   * @param newResultProducer new ResultProducer to use.
   */
  public void setResultProducer(ResultProducer newResultProducer) {

    m_ResultProducer = newResultProducer;
    m_ResultProducer.setResultListener(this);
  }

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

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

} // LearningRateResultProducer