lbr.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

    }
    
    /**
     * 
     * Returns the boolean value at the specified index in the Attribute Indexes array
     *
     * @param index the index of the Instance
     * @return the boolean value
     */
    public boolean getAttIndex(int index) {
      
      if(index < 0 || index >= m_NumAtts)
         throw new IllegalArgumentException("Invalid index value");
      
      return m_AttIndexes[(int)index];
    }
    
    /**
     * 
     * Returns the boolean value at the specified index in the Sequential Attribute Indexes array
     *
     * @param index the index of the Attribute
     * @return the requested value
     */
    public int getSequentialAttIndex(int index) {
      
      if(index < 0 || index >= m_NumAtts)
	throw new IllegalArgumentException("Invalid index value");
      
      return m_SequentialAttIndexes[(int)index];
    }
    
    /**
     * 
     * Returns the number of instances "in use"
     * 
     * @return the number of instances "in use"
     */
    public int getNumInstancesSet() {
      
      return m_NumInstsSet;
   }

    /**
     * 
     * Returns the number of instances in the dataset
     * 
     * @return the number of instances in the dataset
     */
    public int getNumInstances() {
      
      return m_NumInstances;
    }

    /**
     * 
     * Returns the number of instances in the Sequential array
     * 
     * @return the number of instances in the sequential array
     */
    public int getSequentialNumInstances() {
      // will always be the number set as the sequential array is for referencing only
      return m_NumSeqInstsSet;
    }
    
    /**
     * 
     * Returns the number of attributes in the dataset
     * 
     * @return the number of attributes
     */
    public int getNumAttributes() {
      
      return m_NumAtts;
    }
   
    /**
     * 
     * Returns the number of attributes "in use"
     * 
     * @return the number of attributes "in use"
     */
    public int getNumAttributesSet() {
      
      return m_NumAttsSet;
    }
    
    /**
     * 
     * Returns the number of attributes in the Sequential array
     * 
     * @return the number of attributes in the sequentual array
     */
    public int getSequentialNumAttributes() {
      // will always be the number set as the sequential array is for referencing only
      return m_NumSeqAttsSet;
    }
    
    /**
     * 
     * Returns whether or not the Sequential Instance Index requires rebuilding due to a change 
     * 
     * @return true if the sequential instance index needs rebuilding
     */
    public boolean isSequentialInstanceIndexValid() {
      
      return m_SequentialInstanceIndex_valid;
    }
    
    /**
     * 
     * Returns whether or not the Sequential Attribute Index requires rebuilding due to a change 
     * 
     * @return true if the sequential attribute index needs rebuilding
     */
    public boolean isSequentialAttIndexValid() {
      
      return m_SequentialAttIndex_valid;
    }
    
    /**
     * 
     * Sets both the Instance and Attribute indexes to a specified value
     * 
     * @param value the value for the Instance and Attribute indices
     */
    public void setSequentialDataset(boolean value) {
      setSequentialInstanceIndex(value);
      setSequentialAttIndex(value);
    }
    
    /**
     * 
     * A Sequential Instance index is all those Instances that are set to the specified value placed in a sequential array.
     * Each value in the sequential array contains the Instance index within the Indexes.
     *
     * @param value the sequential instance index
     */
    public void setSequentialInstanceIndex(boolean value) {
      
      if(m_SequentialInstanceIndex_valid == true)
	return;
      
      /* needs to be recalculated */
      int size;
      size = m_NumInstsSet;
      
      m_SequentialInstIndexes = new int [(int)size];
      
      int j = 0;
      for(int i = 0; i < m_NumInstances; i++) {
	if(m_InstIndexes[i] == value) {
	  m_SequentialInstIndexes[j] = i;
	  j++;
	}
      }
      
      m_SequentialInstanceIndex_valid = true;
      m_NumSeqInstsSet = j;
    }
    
    /**
     * 
     * A Sequential Attribute index is all those Attributes that are set to the specified value placed in a sequential array.
     * Each value in the sequential array contains the Attribute index within the Indexes
     * 
     * @param value the sequential attribute index
     */
    public void setSequentialAttIndex(boolean value) {
      
      if(m_SequentialAttIndex_valid == true)
	return;
      
      /* needs to be recalculated */
      int size;
      size = m_NumAttsSet;
      
      m_SequentialAttIndexes = new int [(int)size];
      
      int j = 0;
      for(int i = 0; i < m_NumAtts; i++) {
	if(m_AttIndexes[i] == value) {
	  m_SequentialAttIndexes[j] = i;
	  j++;
	 }
      }
      
      m_SequentialAttIndex_valid = true;
      m_NumSeqAttsSet = j;
    }
  } /* end of Indexes inner-class */
  

  /** All the counts for nominal attributes. */
  protected int [][][] m_Counts;
  /** All the counts for nominal attributes. */
  protected int [][][] m_tCounts;
  /** The prior probabilities of the classes. */
  protected int [] m_Priors;
  /** The prior probabilities of the classes. */
  protected int [] m_tPriors;
  
  /** number of attributes for the dataset ***/
  protected int m_numAtts;
  
  /** number of classes for dataset ***/
  protected int m_numClasses;
  
 /** number of instances in dataset ***/
  protected int m_numInsts;
  
  /** The set of instances used for current training. */
  protected Instances m_Instances = null;
  
  /** leave-one-out errors on the training dataset. */
  protected int m_Errors;
  
  /** leave-one-out error flags on the training dataaet. */
  protected boolean [] m_ErrorFlags;
  
  /** best attribute's index list. maybe as output result */
  protected ArrayList leftHand = new ArrayList();
  
  /** significantly lower */
  protected static final double SIGNLOWER = 0.05;
  
  /** following is defined by wangzh, 
   * the number of instances to be classified incorrectly
   * on the subset. */
  protected boolean [] m_subOldErrorFlags;
  
  /** the number of instances to be classified incorrectly
   * besides the subset. */
  protected int m_RemainderErrors = 0;
  
  /** the number of instance to be processed */
  protected int m_Number = 0;
  
  /** the Number of Instances to be used in building a classifiers */
  protected int m_NumberOfInstances = 0;
  
  /** for printing in n-fold cross validation */
  protected boolean m_NCV = false;
  
  /** index of instances and attributes for the given dataset */
  protected Indexes m_subInstances;
  
  /** index of instances and attributes for the given dataset */
  protected Indexes tempSubInstances;
  
  /** probability values array */
  protected double [] posteriorsArray;
  protected int bestCnt;
  protected int tempCnt;
  protected int forCnt;
  protected int whileCnt;

  /**
   * @return a description of the classifier suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {

    return 
        "Lazy Bayesian Rules Classifier. The naive Bayesian classifier "
      + "provides a simple and effective approach to classifier learning, "
      + "but its attribute independence assumption is often violated in the "
      + "real world. Lazy Bayesian Rules selectively relaxes the independence "
      + "assumption, achieving lower error rates over a range of learning "
      + "tasks. LBR defers processing to classification time, making it a "
      + "highly efficient and accurate classification algorithm when small "
      + "numbers of objects are to be classified.\n\n"
      + "For more information, see:\n\n"
      + getTechnicalInformation().toString();
  }

  /**
   * Returns an instance of a TechnicalInformation object, containing 
   * detailed information about the technical background of this class,
   * e.g., paper reference or book this class is based on.
   * 
   * @return the technical information about this class
   */
  public TechnicalInformation getTechnicalInformation() {
    TechnicalInformation 	result;
    
    result = new TechnicalInformation(Type.ARTICLE);
    result.setValue(Field.AUTHOR, "Zijian Zheng and G. Webb");
    result.setValue(Field.YEAR, "2000");
    result.setValue(Field.TITLE, "Lazy Learning of Bayesian Rules");
    result.setValue(Field.JOURNAL, "Machine Learning");
    result.setValue(Field.VOLUME, "4");
    result.setValue(Field.NUMBER, "1");
    result.setValue(Field.PAGES, "53-84");
    
    return result;
  }

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

    // attributes
    result.enable(Capability.NOMINAL_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);

    // class
    result.enable(Capability.NOMINAL_CLASS);
    result.enable(Capability.MISSING_CLASS_VALUES);

    // instances
    result.setMinimumNumberInstances(0);

    return result;
  }

  /**
   * For lazy learning, building classifier is only to prepare their inputs
   * until classification time.
   *
   * @param instances set of instances serving as training data
   * @throws Exception if the preparation has not been generated.
   */
  public void buildClassifier(Instances instances) throws Exception {
    int attIndex, i, j;
    bestCnt = 0;
    tempCnt = 0;
    forCnt = 0;
    whileCnt = 0;
    
    // can classifier handle the data?
    getCapabilities().testWithFail(instances);

    // remove instances with missing class
    instances = new Instances(instances);
    instances.deleteWithMissingClass();
    
    m_numAtts = instances.numAttributes();
    m_numClasses = instances.numClasses();
    m_numInsts = instances.numInstances();

    // Reserve space
    m_Counts = new int[m_numClasses][m_numAtts][0];
    m_Priors = new int[m_numClasses];
    m_tCounts = new int[m_numClasses][m_numAtts][0];
    m_tPriors = new int[m_numClasses];
    m_subOldErrorFlags = new boolean[m_numInsts+1];
    
    m_Instances = instances;
    
    m_subInstances = new Indexes(m_numInsts, m_numAtts, true, m_Instances.classIndex());
    tempSubInstances = new Indexes(m_numInsts, m_numAtts, true, m_Instances.classIndex());
    
    
    posteriorsArray = new double[m_numClasses];
    
    // prepare arrays
    for (attIndex = 0; attIndex < m_numAtts; attIndex++) {
      Attribute attribute = (Attribute) instances.attribute(attIndex);
      for (j = 0; j < m_numClasses; j++) {
        m_Counts[j][attIndex] = new int[attribute.numValues()];
        m_tCounts[j][attIndex] = new int[attribute.numValues()];
      }
    }

    // Compute counts and priors
    for(i = 0; i < m_numInsts; i++) {
      Instance instance = (Instance) instances.instance(i);
      int classValue = (int)instance.classValue();
      // pointer for more efficient access to counts matrix in loop
      int [][] countsPointer = m_tCounts[classValue];
      for(attIndex = 0; attIndex < m_numAtts; attIndex++) {
        countsPointer[attIndex][(int)instance.value(attIndex)]++;
      }
      m_tPriors[classValue]++;
    }
    
    // Step 2: Leave-one-out on the training data set.
    // get m_Errors and its flags array using leave-one-out.
    m_ErrorFlags = new boolean[m_numInsts];
    
    m_Errors = leaveOneOut(m_subInstances, m_tCounts, m_tPriors, m_ErrorFlags);

    if (m_Number == 0) {
      m_NumberOfInstances = m_Instances.numInstances();
    } else {
      System.out.println(" ");
      System.out.println("N-Fold Cross Validation: ");
      m_NCV = true;
    }
  }
  
  /**
   * Calculates the class membership probabilities
   * for the given test instance.
   * This is the most important method for Lazy Bayesian Rule algorithm.
   *
   * @param testInstance the instance to be classified
   * @return predicted class probability distribution
   * @throws Exception if distribution can't be computed
   */