wavelet.java

代码是一个分类器的实现,其中使用了部分weka的源代码。可以将项目导入eclipse运行

    if (tmpOptions.length != 0) {
      tmpStr        = tmpOptions[0];
      tmpOptions[0] = "";
      setFilter((Filter) Utils.forName(Filter.class, tmpStr, tmpOptions));
    }
    else {
      filter = new MultiFilter();
      ((MultiFilter) filter).setFilters(
	  new Filter[]{
	      new weka.filters.unsupervised.attribute.ReplaceMissingValues(),
	      new weka.filters.unsupervised.attribute.Normalize()
	      });
      setFilter(filter);
    }
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String filterTipText() {
    return "The preprocessing filter to use.";
  }

  /**
   * Set the preprocessing filter (only used for setup).
   *
   * @param value	the preprocessing filter.
   */
  public void setFilter(Filter value) {
    m_Filter = value;
  }

  /**
   * Get the preprocessing filter.
   *
   * @return 		the preprocessing filter
   */
  public Filter getFilter() {
    return m_Filter;
  }

  /**
   * Returns the tip text for this property
   * 
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String algorithmTipText() {
    return "Sets the type of algorithm to use.";
  }

  /**
   * Sets the type of algorithm to use 
   *
   * @param value 	the algorithm type
   */
  public void setAlgorithm(SelectedTag value) {
    if (value.getTags() == TAGS_ALGORITHM) {
      m_Algorithm = value.getSelectedTag().getID();
    }
  }

  /**
   * Gets the type of algorithm to use 
   *
   * @return 		the current algorithm type.
   */
  public SelectedTag getAlgorithm() {
    return new SelectedTag(m_Algorithm, TAGS_ALGORITHM);
  }

  /**
   * Returns the tip text for this property
   * 
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String paddingTipText() {
    return "Sets the type of padding to use.";
  }

  /**
   * Sets the type of Padding to use 
   *
   * @param value 	the Padding type
   */
  public void setPadding(SelectedTag value) {
    if (value.getTags() == TAGS_PADDING) {
      m_Padding = value.getSelectedTag().getID();
    }
  }

  /**
   * Gets the type of Padding to use 
   *
   * @return 		the current Padding type.
   */
  public SelectedTag getPadding() {
    return new SelectedTag(m_Padding, TAGS_PADDING);
  }

  /**
   * returns the next bigger number that's a power of 2. If the number is 
   * already a power of 2 then this will be returned. The number will be at
   * least 2^2..
   * 
   * @param n		the number to start from
   * @return		the next bigger number
   */
  protected static int nextPowerOf2(int n) {
    int		exp;
    
    exp = (int) StrictMath.ceil(StrictMath.log(n) / StrictMath.log(2.0));
    exp = StrictMath.max(2, exp);
    
    return (int) StrictMath.pow(2, exp);
  }
  
  /**
   * pads the data to conform to the necessary number of attributes
   * 
   * @param data	the data to pad
   * @return		the padded data
   */
  protected Instances pad(Instances data) {
    Instances 		result;
    int 		i;
    int			n;
    String 		prefix;
    int			numAtts;
    boolean		isLast;
    int			index;
    Vector<Integer>	padded;
    int[]		indices;
    FastVector		atts;

    // determine number of padding attributes
    switch (m_Padding) {
      case PADDING_ZERO:
	if (data.classIndex() > -1)
	  numAtts = (nextPowerOf2(data.numAttributes() - 1) + 1) - data.numAttributes();
	else
	  numAtts = nextPowerOf2(data.numAttributes()) - data.numAttributes();
	break;
	
      default:
	throw new IllegalStateException(
	    "Padding " + new SelectedTag(m_Algorithm, TAGS_PADDING) 
	    + " not implemented!");
    }

    result = new Instances(data);
    prefix = getAlgorithm().getSelectedTag().getReadable();

    // any padding necessary?
    if (numAtts > 0) {
      // add padding attributes
      isLast = (data.classIndex() == data.numAttributes() - 1);
      padded = new Vector<Integer>();
      for (i = 0; i < numAtts; i++) {
	if (isLast)
	  index = result.numAttributes() - 1;
	else
	  index = result.numAttributes();
	
	result.insertAttributeAt(
	    new Attribute(prefix + "_padding_" + (i+1)),
	    index);
	
	// record index
	padded.add(new Integer(index));
      }
      
      // get padded indices
      indices = new int[padded.size()];
      for (i = 0; i < padded.size(); i++)
	indices[i] = padded.get(i);
      
      // determine number of padding attributes
      switch (m_Padding) {
	case PADDING_ZERO:
	  for (i = 0; i < result.numInstances(); i++) {
	    for (n = 0; n < indices.length; n++)
	      result.instance(i).setValue(indices[n], 0);
	  }
	  break;
      }
    }

    // rename all attributes apart from class
    data = result;
    atts = new FastVector();
    n = 0;
    for (i = 0; i < data.numAttributes(); i++) {
      n++;
      if (i == data.classIndex())
	atts.addElement(new Attribute(data.attribute(i).name()));
      else
	atts.addElement(new Attribute(prefix + "_" + n));
    }

    // create new dataset
    result = new Instances(data.relationName(), atts, data.numInstances());
    result.setClassIndex(data.classIndex());
    for (i = 0; i < data.numInstances(); i++)
      result.add(new Instance(1.0, data.instance(i).toDoubleArray()));
    
    return result;
  }
  
  /**
   * Determines the output format based on the input format and returns 
   * this. In case the output format cannot be returned immediately, i.e.,
   * immediateOutputFormat() returns false, then this method will be called
   * from batchFinished().
   *
   * @param inputFormat     the input format to base the output format on
   * @return                the output format
   * @throws Exception      in case the determination goes wrong
   * @see   #hasImmediateOutputFormat()
   * @see   #batchFinished()
   */
  protected Instances determineOutputFormat(Instances inputFormat) 
    throws Exception {

    return pad(new Instances(inputFormat, 0));
  }
  
  /**
   * processes the instances using the HAAR algorithm
   *
   * @param instances   the data to process
   * @return            the modified data
   * @throws Exception  in case the processing goes wrong
   */
  protected Instances processHAAR(Instances instances) throws Exception {
    Instances	result;
    int		i;
    int		n;
    int		j;
    int		clsIdx;
    double[]	oldVal;
    double[]	newVal;
    int		level;
    int		length;
    double[]	clsVal;
    String	clsName;

    clsIdx  = instances.classIndex();
    clsVal  = null;
    clsName = "<noname>";
    if (clsIdx > -1) {
      clsVal  = instances.attributeToDoubleArray(clsIdx);
      clsName = instances.classAttribute().name();
      instances.setClassIndex(-1);
      instances.deleteAttributeAt(clsIdx);
    }
    result = new Instances(instances, 0);
    level  = (int) StrictMath.ceil(
			StrictMath.log(instances.numAttributes())
			/ StrictMath.log(2.0));
    
    for (i = 0; i < instances.numInstances(); i++) {
      oldVal = instances.instance(i).toDoubleArray();
      newVal = new double[oldVal.length];
      
      for (n = level; n > 0; n--) {
	length = (int) StrictMath.pow(2, n - 1);
	
	for (j = 0; j < length; j++) {
	  newVal[j]          = (oldVal[j*2] + oldVal[j*2 + 1]) / StrictMath.sqrt(2);
	  newVal[j + length] = (oldVal[j*2] - oldVal[j*2 + 1]) / StrictMath.sqrt(2);
	}
	
	System.arraycopy(newVal, 0, oldVal, 0, newVal.length);
      }
      
      // add new transformed instance
      result.add(new Instance(1, newVal));
    }

    // add class again
    if (clsIdx > -1) {
      result.insertAttributeAt(new Attribute(clsName), clsIdx);
      result.setClassIndex(clsIdx);
      for (i = 0; i < clsVal.length; i++)
	result.instance(i).setClassValue(clsVal[i]);
    }
    
    return result;
  }

  /** 
   * Returns the Capabilities of this filter.
   *
   * @return            the capabilities of this object
   * @see               Capabilities
   */
  public Capabilities getCapabilities() {
    Capabilities result = super.getCapabilities();

    // attribute
    result.enable(Capability.NUMERIC_ATTRIBUTES);
    result.enable(Capability.DATE_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);
    
    // class
    result.enable(Capability.NUMERIC_CLASS);
    result.enable(Capability.DATE_CLASS);
    result.enable(Capability.NO_CLASS);
    
    return result;
  }
  
  /**
   * Processes the given data (may change the provided dataset) and returns
   * the modified version. This method is called in batchFinished().
   *
   * @param instances   the data to process
   * @return            the modified data
   * @throws Exception  in case the processing goes wrong
   * @see               #batchFinished()
   */
  protected Instances process(Instances instances) throws Exception {
    if (!isFirstBatchDone())
      m_Filter.setInputFormat(instances);
    instances = Filter.useFilter(instances, m_Filter);
    
    switch (m_Algorithm) {
      case ALGORITHM_HAAR:
	return processHAAR(pad(instances));
      default:
	throw new IllegalStateException(
	    "Algorithm type '" + m_Algorithm + "' is not recognized!");
    }
  }

  /**
   * runs the filter with the given arguments
   *
   * @param args      the commandline arguments
   */
  public static void main(String[] args) {
    runFilter(new Wavelet(), args);
  }
}