instances.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

	} else if (tokenizer.sval.equalsIgnoreCase(Attribute.ARFF_ATTRIBUTE_DATE)) {
          String format = null;
          if (tokenizer.nextToken() != StreamTokenizer.TT_EOL) {
            if ((tokenizer.ttype != StreamTokenizer.TT_WORD) &&
                (tokenizer.ttype != '\'') &&
                (tokenizer.ttype != '\"')) {
              errms(tokenizer,"not a valid date format");
            }
            format = tokenizer.sval;
            readTillEOL(tokenizer);
          } else {
            tokenizer.pushBack();
          }
	  m_Attributes.addElement(new Attribute(attributeName, format,
                                                numAttributes()));

	} else {
	  errms(tokenizer,"no valid attribute type or invalid "+
		"enumeration");
	}
      } else {

	// Attribute is nominal.
	attributeValues = new FastVector();
	tokenizer.pushBack();
	
	// Get values for nominal attribute.
	if (tokenizer.nextToken() != '{') {
	  errms(tokenizer,"{ expected at beginning of enumeration");
	}
	while (tokenizer.nextToken() != '}') {
	  if (tokenizer.ttype == StreamTokenizer.TT_EOL) {
	    errms(tokenizer,"} expected at end of enumeration");
	  } else {
	    attributeValues.addElement(tokenizer.sval);
	  }
	}
	if (attributeValues.size() == 0) {
	  errms(tokenizer,"no nominal values found");
	}
	m_Attributes.
	  addElement(new Attribute(attributeName, attributeValues,
				   numAttributes()));
      }
      getLastToken(tokenizer,false);
      getFirstToken(tokenizer);
      if (tokenizer.ttype == StreamTokenizer.TT_EOF)
	errms(tokenizer,"premature end of file");
    }

    // Check if data part follows. We can't easily check for EOL.
    if (!ARFF_DATA.equalsIgnoreCase(tokenizer.sval)) {
      errms(tokenizer,"keyword " + ARFF_DATA + " expected");
    }
    
    // Check if any attributes have been declared.
    if (m_Attributes.size() == 0) {
      errms(tokenizer,"no attributes declared");
    }

    // Allocate buffers in case sparse instances have to be read
    m_ValueBuffer = new double[numAttributes()];
    m_IndicesBuffer = new int[numAttributes()];
  }

  /**
   * Copies instances from one set to the end of another 
   * one.
   *
   * @param source the source of the instances
   * @param from the position of the first instance to be copied
   * @param dest the destination for the instances
   * @param num the number of instances to be copied
   */
  private void copyInstances(int from, Instances dest, int num) {
    
    for (int i = 0; i < num; i++) {
      dest.add(instance(from + i));
    }
  }
  
  /**
   * Throws error message with line number and last token read.
   *
   * @param theMsg the error message to be thrown
   * @param tokenizer the stream tokenizer
   * @throws IOExcpetion containing the error message
   */
  private void errms(StreamTokenizer tokenizer, String theMsg) 
       throws IOException {
    
    throw new IOException(theMsg + ", read " + tokenizer.toString());
  }
  
  /**
   * Replaces the attribute information by a clone of
   * itself.
   */
  private void freshAttributeInfo() {

    m_Attributes = (FastVector) m_Attributes.copyElements();
  }

  /**
   * Gets next token, skipping empty lines.
   *
   * @param tokenizer the stream tokenizer
   * @exception IOException if reading the next token fails
   */
  private void getFirstToken(StreamTokenizer tokenizer) 
    throws IOException {
    
    while (tokenizer.nextToken() == StreamTokenizer.TT_EOL){};
    if ((tokenizer.ttype == '\'') ||
	(tokenizer.ttype == '"')) {
      tokenizer.ttype = StreamTokenizer.TT_WORD;
    } else if ((tokenizer.ttype == StreamTokenizer.TT_WORD) &&
	       (tokenizer.sval.equals("?"))){
      tokenizer.ttype = '?';
    }
  }

  /**
   * Gets index, checking for a premature and of line.
   *
   * @param tokenizer the stream tokenizer
   * @exception IOException if it finds a premature end of line
   */
  private void getIndex(StreamTokenizer tokenizer) throws IOException {
    
    if (tokenizer.nextToken() == StreamTokenizer.TT_EOL) {
      errms(tokenizer,"premature end of line");
    }
    if (tokenizer.ttype == StreamTokenizer.TT_EOF) {
      errms(tokenizer,"premature end of file");
    }
  }
  
  /**
   * Gets token and checks if its end of line.
   *
   * @param tokenizer the stream tokenizer
   * @exception IOException if it doesn't find an end of line
   */
  private void getLastToken(StreamTokenizer tokenizer, boolean endOfFileOk) 
       throws IOException {

    if ((tokenizer.nextToken() != StreamTokenizer.TT_EOL) &&
	((tokenizer.ttype != StreamTokenizer.TT_EOF) || !endOfFileOk)) {
      errms(tokenizer,"end of line expected");
    }
  }

  /**
   * Gets next token, checking for a premature and of line.
   *
   * @param tokenizer the stream tokenizer
   * @exception IOException if it finds a premature end of line
   */
  private void getNextToken(StreamTokenizer tokenizer) 
       throws IOException {
    
    if (tokenizer.nextToken() == StreamTokenizer.TT_EOL) {
      errms(tokenizer,"premature end of line");
    }
    if (tokenizer.ttype == StreamTokenizer.TT_EOF) {
      errms(tokenizer,"premature end of file");
    } else if ((tokenizer.ttype == '\'') ||
	       (tokenizer.ttype == '"')) {
      tokenizer.ttype = StreamTokenizer.TT_WORD;
    } else if ((tokenizer.ttype == StreamTokenizer.TT_WORD) &&
	       (tokenizer.sval.equals("?"))){
      tokenizer.ttype = '?';
    }
  }
	
  /**
   * Initializes the StreamTokenizer used for reading the ARFF file.
   *
   * @param tokenizer the stream tokenizer
   */
  private void initTokenizer(StreamTokenizer tokenizer){

    tokenizer.resetSyntax();         
    tokenizer.whitespaceChars(0, ' ');    
    tokenizer.wordChars(' '+1,'\u00FF');
    tokenizer.whitespaceChars(',',',');
    tokenizer.commentChar('%');
    tokenizer.quoteChar('"');
    tokenizer.quoteChar('\'');
    tokenizer.ordinaryChar('{');
    tokenizer.ordinaryChar('}');
    tokenizer.eolIsSignificant(true);
  }
 
  /**
   * Returns string including all instances, their weights and
   * their indices in the original dataset.
   *
   * @return description of instance and its weight as a string
   */
  private String instancesAndWeights(){

    StringBuffer text = new StringBuffer();

    for (int i = 0; i < numInstances(); i++) {
      text.append(instance(i) + " " + instance(i).weight());
      if (i < numInstances() - 1) {
	text.append("\n");
      }
    }
    return text.toString();
  }
  
  /**
   * Implements quicksort.
   *
   * @param attIndex the attribute's index
   * @param lo0 the first index of the subset to be sorted
   * @param hi0 the last index of the subset to be sorted
   */
  private void quickSort(int attIndex, int lo0, int hi0) {
    
    int lo = lo0, hi = hi0;
    double mid;
    
    if (hi0 > lo0) {
      
      // Arbitrarily establishing partition element as the 
      // midpoint of the array.
      mid = instance((lo0 + hi0) / 2).value(attIndex);

      // loop through the array until indices cross
      while(lo <= hi) {
	
	// find the first element that is greater than or equal to 
	// the partition element starting from the left Index.
	while ((instance(lo).value(attIndex) < 
		mid) && (lo < hi0)) {
	  ++lo;
	}
	
	// find an element that is smaller than or equal to
	// the partition element starting from the right Index.
	while ((instance(hi).value(attIndex)  > 
		mid) && (hi > lo0)) {
	  --hi;
	}
	
	// if the indexes have not crossed, swap
	if(lo <= hi) {
	  swap(lo,hi);
	  ++lo;
	  --hi;
	}
      }
      
      // If the right index has not reached the left side of array
      // must now sort the left partition.
      if(lo0 < hi) {
	quickSort(attIndex,lo0,hi);
      }
      
      // If the left index has not reached the right side of array
      // must now sort the right partition.
      if(lo < hi0) {
	quickSort(attIndex,lo,hi0);
      }
    }
  }

  /**
   * Reads and skips all tokens before next end of line token.
   *
   * @param tokenizer the stream tokenizer
   */
  private void readTillEOL(StreamTokenizer tokenizer) 
       throws IOException {
    
    while (tokenizer.nextToken() != StreamTokenizer.TT_EOL) {};
    tokenizer.pushBack();
  }

  /**
   * Help function needed for stratification of set.
   *
   * @param numFolds the number of folds for the stratification
   */
  private void stratStep (int numFolds){
    
    FastVector newVec = new FastVector(m_Instances.capacity());
    int start = 0, j;

    // create stratified batch
    while (newVec.size() < numInstances()) {
      j = start;
      while (j < numInstances()) {
	newVec.addElement(instance(j));
	j = j + numFolds;
      }
      start++;
    }
    m_Instances = newVec;
  }
  
  /**
   * Swaps two instances in the set.
   *
   * @param i the first instance's index
   * @param j the second instance's index
   */
  private void swap(int i, int j){
    
    m_Instances.swap(i, j);
  }

  /**
   * Merges two sets of Instances together. The resulting set will have
   * all the attributes of the first set plus all the attributes of the 
   * second set. The number of instances in both sets must be the same.
   *
   * @param first the first set of Instances
   * @param second the second set of Instances
   * @return the merged set of Instances
   * @exception IllegalArgumentException if the datasets are not the same size
   */
  public static Instances mergeInstances(Instances first, Instances second) {

    if (first.numInstances() != second.numInstances()) {
      throw new IllegalArgumentException("Instance sets must be of the same size");
    }

    // Create the vector of merged attributes
    FastVector newAttributes = new FastVector();
    for (int i = 0; i < first.numAttributes(); i++) {
      newAttributes.addElement(first.attribute(i));
    }
    for (int i = 0; i < second.numAttributes(); i++) {
      newAttributes.addElement(second.attribute(i));
    }
    
    // Create the set of Instances
    Instances merged = new Instances(first.relationName() + '_'
				     + second.relationName(), 
				     newAttributes, 
				     first.numInstances());
    // Merge each instance
    for (int i = 0; i < first.numInstances(); i++) {
      merged.add(first.instance(i).mergeInstance(second.instance(i)));
    }
    return merged;
  }

  /**
   * Method for testing this class.
   *
   * @param argv should contain one element: the name of an ARFF file
   */
  public static void test(String [] argv) {

    Instances instances, secondInstances, train, test, empty;
    Random random = new Random(2);
    Reader reader;
    int start, num;
    FastVector testAtts, testVals;
    int i,j;
    
    try{
      if (argv.length > 1) {
	throw (new Exception("Usage: Instances [<filename>]"));
      }
      
      // Creating set of instances from scratch
      testVals = new FastVector(2);
      testVals.addElement("first_value");
      testVals.addElement("second_value");
      testAtts = new FastVector(2);
      testAtts.addElement(new Attribute("nominal_attribute", testVals));
      testAtts.addElement(new Attribute("numeric_attribute"));
      instances = new Instances("test_set", testAtts, 10);
      instances.add(new Instance(instances.numAttributes()));
      instances.add(new Instance(instances.numAttributes()));
      instances.add(new Instance(instances.numAttributes()));
      instances.setClassIndex(0);
      System.out.println("\nSet of instances created from scratch:\n");
      System.out.println(instances);
      
      if (argv.length == 1) {
	String filename = argv[0];
	reader = new FileReader(filename);
	
	// Read first five instances and print them
	System.out.println("\nFirst five instances from file:\n");
	instances = new Instances(reader, 1);
	instances.setClassIndex(instances.numAttributes() - 1);
	i = 0;
	while ((i < 5) && (instances.readInstance(reader))) {
	  i++;
	}
	System.out.println(instances);

	// Read all the instances in the file
	reader = new FileReader(filename);
	instances = new Instances(reader);

	// Make the last attribute be the class 
	instances.setClassIndex(instances.numAttributes() - 1);
	
	// Print header and instances.
	System.out.println("\nDataset:\n");
	System.out.println(instances);
	System.out.println("\nClass index: "+instances.classIndex());
      }
      
      // Test basic methods based on class index.
      System.out.println("\nClass name: "+instances.classAttribute().name());
      System.out.println("\nClass index: "+instances.classIndex());
      System.out.println("\nClass is nominal: " +
			 instances.classAttribute().isNominal());
      System.out.println("\nClass is numeric: " +
			 instances.classAttribute().isNumeric());
      System.out.println("\nClasse