instances.java

矩阵的QR分解算法

  /**
   * Implements computation of the kth-smallest element according
   * to Manber's "Introduction to Algorithms".
   *
   * @param attIndex the attribute's index (index starts with 0)
   * @param left the first index of the subset (index starts with 0)
   * @param right the last index of the subset (index starts with 0)
   * @param k the value of k
   *
   * @return the index of the kth-smallest element
   */
  //@ requires 0 <= attIndex && attIndex < numAttributes();
  //@ requires 0 <= first && first <= right && right < numInstances();
  protected int select(int attIndex, int left, int right, int k) {
    
    if (left == right) {
      return left;
    } else {
      int middle = partition(attIndex, left, right);
      if ((middle - left + 1) >= k) {
        return select(attIndex, left, middle, k);
      } else {
        return select(attIndex, middle + 1, right, k - (middle - left + 1));
      }
    }
  }

  /**
   * Help function needed for stratification of set.
   *
   * @param numFolds the number of folds for the stratification
   */
  protected 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 (index starts with 0)
   * @param j the second instance's index (index starts with 0)
   */
  //@ requires 0 <= i && i < numInstances();
  //@ requires 0 <= j && j < numInstances();
  public 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
   * @throws 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
   */
  //@ requires argv != null;
  //@ requires argv.length == 1;
  //@ requires argv[0] != null;
  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("\nClasses:\n");
      for (i = 0; i < instances.numClasses(); i++) {
	System.out.println(instances.classAttribute().value(i));
      }
      System.out.println("\nClass values and labels of instances:\n");
      for (i = 0; i < instances.numInstances(); i++) {
	Instance inst = instances.instance(i);
	System.out.print(inst.classValue() + "\t");
	System.out.print(inst.toString(inst.classIndex()));
	if (instances.instance(i).classIsMissing()) {
	  System.out.println("\tis missing");
	} else {
	  System.out.println();
	}
      }
      
      // Create random weights.
      System.out.println("\nCreating random weights for instances.");
      for (i = 0; i < instances.numInstances(); i++) {
	instances.instance(i).setWeight(random.nextDouble()); 
      }
      
      // Print all instances and their weights (and the sum of weights).
      System.out.println("\nInstances and their weights:\n");
      System.out.println(instances.instancesAndWeights());
      System.out.print("\nSum of weights: ");
      System.out.println(instances.sumOfWeights());
      
      // Insert an attribute
      secondInstances = new Instances(instances);
      Attribute testAtt = new Attribute("Inserted");
      secondInstances.insertAttributeAt(testAtt, 0);
      System.out.println("\nSet with inserted attribute:\n");
      System.out.println(secondInstances);
      System.out.println("\nClass name: "
			 + secondInstances.classAttribute().name());
      
      // Delete the attribute
      secondInstances.deleteAttributeAt(0);
      System.out.println("\nSet with attribute deleted:\n");
      System.out.println(secondInstances);
      System.out.println("\nClass name: "
			 + secondInstances.classAttribute().name());
      
      // Test if headers are equal
      System.out.println("\nHeaders equal: "+
			 instances.equalHeaders(secondInstances) + "\n");
      
      // Print data in internal format.
      System.out.println("\nData (internal values):\n");
      for (i = 0; i < instances.numInstances(); i++) {
	for (j = 0; j < instances.numAttributes(); j++) {
	  if (instances.instance(i).isMissing(j)) {
	    System.out.print("? ");
	  } else {
	    System.out.print(instances.instance(i).value(j) + " ");
	  }
	}
	System.out.println();
      }
      
      // Just print header
      System.out.println("\nEmpty dataset:\n");
      empty = new Instances(instances, 0);
      System.out.println(empty);
      System.out.println("\nClass name: "+empty.classAttribute().name());

      // Create copy and rename an attribute and a value (if possible)
      if (empty.classAttribute().isNominal()) {
	Instances copy = new Instances(empty, 0);
	copy.renameAttribute(copy.classAttribute(), "new_name");
	copy.renameAttributeValue(copy.classAttribute(), 
				  copy.classAttribute().value(0), 
				  "new_val_name");
	System.out.println("\nDataset with names changed:\n" + copy);
	System.out.println("\nOriginal dataset:\n" + empty);
      }

      // Create and prints subset of instances.
      start = instances.numInstances() / 4;
      num = instances.numInstances() / 2;
      System.out.print("\nSubset of dataset: ");
      System.out.println(num + " instances from " + (start + 1) 
			 + ". instance");
      secondInstances = new Instances(instances, start, num);
      System.out.println("\nClass name: "
			 + secondInstances.classAttribute().name());

      // Print all instances and their weights (and the sum of weights).
      System.out.println("\nInstances and their weights:\n");
      System.out.println(secondInstances.instancesAndWeights());
      System.out.print("\nSum of weights: ");
      System.out.println(secondInstances.sumOfWeights());
      
      // Create and print training and test sets for 3-fold
      // cross-validation.
      System.out.println("\nTrain and test folds for 3-fold CV:");
      if (instances.classAttribute().isNominal()) {
	instances.stratify(3);
      }
      for (j = 0; j < 3; j++) {
        train = instances.trainCV(3,j, new Random(1));
	test = instances.testCV(3,j);
                      
	// Print all instances and their weights (and the sum of weights).
	System.out.println("\nTrain: ");
	System.out.println("\nInstances and their weights:\n");
	System.out.println(train.instancesAndWeights());
	System.out.print("\nSum of weights: ");
	System.out.println(train.sumOfWeights());
	System.out.println("\nClass name: "+train.classAttribute().name());
	System.out.println("\nTest: ");
	System.out.println("\nInstances and their weights:\n");
	System.out.println(test.instancesAndWeights());
	System.out.print("\nSum of weights: ");
	System.out.println(test.sumOfWeights());
	System.out.println("\nClass name: "+test.classAttribute().name());
      }

      // Randomize instances and print them.
      System.out.println("\nRandomized dataset:");
      instances.randomize(random);
      
      // Print all instances and their weights (and the sum of weights).
      System.out.println("\nInstances and their weights:\n");
      System.out.println(instances.instancesAndWeights());
      System.out.print("\nSum of weights: ");
      System.out.println(instances.sumOfWeights());

      // Sort instances according to first attribute and
      // print them.
      System.out.print("\nInstances sorted according to first attribute:\n ");
      instances.sort(0);
        
      // Print all instances and their weights (and the sum of weights).
      System.out.println("\nInstances and their weights:\n");
      System.out.println(instances.instancesAndWeights());
      System.out.print("\nSum of weights: ");
      System.out.println(instances.sumOfWeights());
    } catch (Exception e) {
      e.printStackTrace(); 
    }
  }

  /**
   * Main method for this class. The following calls are possible:
   * <ul>
   *   <li>
   *     <code>weka.core.Instances</code> help<br/>
   *     prints a short list of possible commands.
   *   </li>
   *   <li>
   *     <code>weka.core.Instances</code> &lt;filename&gt;<br/>
   *     prints a summary of a set of instances.
   *   </li>
   *   <li>
   *     <code>weka.core.Instances</code> merge &lt;filename1&gt; &lt;filename2&gt;<br/>
   *     merges the two datasets (must have same number of instances) and
   *     outputs the results on stdout.
   *   </li>
   *   <li>
   *     <code>weka.core.Instances</code> append &lt;filename1&gt; &lt;filename2&gt;<br/>
   *     appends the second dataset to the first one (must have same headers) and
   *     outputs the results on stdout.
   *   </li>
   *   <li>
   *     <code>weka.core.Instances</code> randomize &lt;seed&gt; &lt;filename&gt;<br/>
   *     randomizes the dataset with the given seed and outputs the result on stdout.
   *   </li>
   * </ul>
   *
   * @param args 	the commandline parameters
   */
  public static void main(String[] args) {

    try {
      Instances i;
      // read from stdin and print statistics
      if (args.length == 0) {
	DataSource source = new DataSource(System.in);
	i = source.getDataSet();
	System.out.println(i.toSummaryString());
      }
      // read file and print statistics
      else if ((args.length == 1) && (!args[0].equals("-h")) && (!args[0].equals("help"))) {
	DataSource source = new DataSource(args[0]);
	i = source.getDataSet();
	System.out.println(i.toSummaryString());
      }
      // read two files, merge them and print result to stdout
      else if ((args.length == 3) && (args[0].toLowerCase().equals("merge"))) {
	DataSource source1 = new DataSource(args[1]);
	DataSource source2 = new DataSource(args[2]);
	i = Instances.mergeInstances(source1.getDataSet(), source2.getDataSet());
	System.out.println(i);
      }
      // read two files, append them and print result to stdout
      else if ((args.length == 3) && (args[0].toLowerCase().equals("append"))) {
	DataSource source1 = new DataSource(args[1]);
	DataSource source2 = new DataSource(args[2]);
	if (!source1.getStructure().equalHeaders(source2.getStructure()))
	  throw new Exception("The two datasets have different headers!");
	Instances structure = source1.getStructure();
	System.out.println(source1.getStructure());
	while (source1.hasMoreElements(structure))
	  System.out.println(source1.nextElement(structure));
	structure = source2.getStructure();
	while (source2.hasMoreElements(structure))
	  System.out.println(source2.nextElement(structure));
      }
      // read file and seed value, randomize data and print result to stdout
      else if ((args.length == 3) && (args[0].toLowerCase().equals("randomize"))) {
	DataSource source = new DataSource(args[2]);
	i = source.getDataSet();
	i.randomize(new Random(Integer.parseInt(args[1])));
	System.out.println(i);
      }
      // wrong parameters
      else {
	System.err.println(
	    "\nUsage:\n"
	    + "\tweka.core.Instances help\n"
	    + "\tweka.core.Instances <filename>\n"
	    + "\tweka.core.Instances merge <filename1> <filename2>\n"
	    + "\tweka.core.Instances append <filename1> <filename2>\n"
	    + "\tweka.core.Instances randomize <seed> <filename>\n"
	);
	System.exit(1);
      }
    }
    catch (Exception ex) {
      ex.printStackTrace();
      System.err.println(ex.getMessage());
    }
  }
}