instances.java

矩阵的QR分解算法

	}
	if ((i == 0) || 
	    (current.value(attIndex) > prev)) {
	  prev = current.value(attIndex);
	  counter++;
	}
      }
      return counter;
    } else {
      return attribute(attIndex).numValues();
    }
  }

  /**
   * Returns the number of distinct values of a given attribute.
   * Returns the number of instances if the attribute is a
   * string attribute. The value 'missing' is not counted.
   *
   * @param att the attribute
   * @return the number of distinct values of a given attribute
   */
  public /*@pure@*/ int numDistinctValues(/*@non_null@*/Attribute att) {

    return numDistinctValues(att.index());
  }
  
  /**
   * Returns the number of instances in the dataset.
   *
   * @return the number of instances in the dataset as an integer
   */
  //@ ensures \result == m_Instances.size();
  public /*@pure@*/ int numInstances() {

    return m_Instances.size();
  }

  /**
   * Shuffles the instances in the set so that they are ordered 
   * randomly.
   *
   * @param random a random number generator
   */
  public void randomize(Random random) {

    for (int j = numInstances() - 1; j > 0; j--)
      swap(j, random.nextInt(j+1));
  }

  /**
   * Reads a single instance from the reader and appends it
   * to the dataset.  Automatically expands the dataset if it
   * is not large enough to hold the instance. This method does
   * not check for carriage return at the end of the line.
   *
   * @param reader the reader 
   * @return false if end of file has been reached
   * @throws IOException if the information is not read 
   * successfully
   * @deprecated instead of using this method in conjunction with the
   * <code>readInstance(Reader)</code> method, one should use the 
   * <code>ArffLoader</code> or <code>DataSource</code> class instead.
   * @see weka.core.converters.ArffLoader
   * @see weka.core.converters.ConverterUtils.DataSource
   */ 
  @Deprecated public boolean readInstance(Reader reader) throws IOException {

    ArffReader arff = new ArffReader(reader, this, m_Lines, 1);
    Instance inst = arff.readInstance(arff.getData(), false);
    m_Lines = arff.getLineNo();
    if (inst != null) {
      add(inst);
      return true;
    }
    else {
      return false;
    }
  }    

  /**
   * Returns the relation's name.
   *
   * @return the relation's name as a string
   */
  //@ ensures \result == m_RelationName;
  public /*@pure@*/ String relationName() {

    return m_RelationName;
  }

  /**
   * Renames an attribute. This change only affects this
   * dataset.
   *
   * @param att the attribute's index (index starts with 0)
   * @param name the new name
   */
  public void renameAttribute(int att, String name) {

    Attribute newAtt = attribute(att).copy(name);
    FastVector newVec = new FastVector(numAttributes());

    for (int i = 0; i < numAttributes(); i++) {
      if (i == att) {
	newVec.addElement(newAtt);
      } else {
	newVec.addElement(attribute(i));
      }
    }
    m_Attributes = newVec;
  }

  /**
   * Renames an attribute. This change only affects this
   * dataset.
   *
   * @param att the attribute
   * @param name the new name
   */
  public void renameAttribute(Attribute att, String name) {

    renameAttribute(att.index(), name);
  }

  /**
   * Renames the value of a nominal (or string) attribute value. This
   * change only affects this dataset.
   *
   * @param att the attribute's index (index starts with 0)
   * @param val the value's index (index starts with 0)
   * @param name the new name 
   */
  public void renameAttributeValue(int att, int val, String name) {

    Attribute newAtt = (Attribute)attribute(att).copy();
    FastVector newVec = new FastVector(numAttributes());

    newAtt.setValue(val, name);
    for (int i = 0; i < numAttributes(); i++) {
      if (i == att) {
	newVec.addElement(newAtt);
      } else {
	newVec.addElement(attribute(i));
      }
    }
    m_Attributes = newVec;
  }

  /**
   * Renames the value of a nominal (or string) attribute value. This
   * change only affects this dataset.
   *
   * @param att the attribute
   * @param val the value
   * @param name the new name
   */
  public void renameAttributeValue(Attribute att, String val, 
                                         String name) {

    int v = att.indexOfValue(val);
    if (v == -1) throw new IllegalArgumentException(val + " not found");
    renameAttributeValue(att.index(), v, name);
  }

  /**
   * Creates a new dataset of the same size using random sampling
   * with replacement.
   *
   * @param random a random number generator
   * @return the new dataset
   */
  public Instances resample(Random random) {

    Instances newData = new Instances(this, numInstances());
    while (newData.numInstances() < numInstances()) {
      newData.add(instance(random.nextInt(numInstances())));
    }
    return newData;
  }

  /**
   * Creates a new dataset of the same size using random sampling
   * with replacement according to the current instance weights. The
   * weights of the instances in the new dataset are set to one.
   *
   * @param random a random number generator
   * @return the new dataset
   */
  public Instances resampleWithWeights(Random random) {

    double [] weights = new double[numInstances()];
    for (int i = 0; i < weights.length; i++) {
      weights[i] = instance(i).weight();
    }
    return resampleWithWeights(random, weights);
  }


  /**
   * Creates a new dataset of the same size using random sampling
   * with replacement according to the given weight vector. The
   * weights of the instances in the new dataset are set to one.
   * The length of the weight vector has to be the same as the
   * number of instances in the dataset, and all weights have to
   * be positive.
   *
   * @param random a random number generator
   * @param weights the weight vector
   * @return the new dataset
   * @throws IllegalArgumentException if the weights array is of the wrong
   * length or contains negative weights.
   */
  public Instances resampleWithWeights(Random random, 
					     double[] weights) {

    if (weights.length != numInstances()) {
      throw new IllegalArgumentException("weights.length != numInstances.");
    }
    Instances newData = new Instances(this, numInstances());
    if (numInstances() == 0) {
      return newData;
    }
    double[] probabilities = new double[numInstances()];
    double sumProbs = 0, sumOfWeights = Utils.sum(weights);
    for (int i = 0; i < numInstances(); i++) {
      sumProbs += random.nextDouble();
      probabilities[i] = sumProbs;
    }
    Utils.normalize(probabilities, sumProbs / sumOfWeights);

    // Make sure that rounding errors don't mess things up
    probabilities[numInstances() - 1] = sumOfWeights;
    int k = 0; int l = 0;
    sumProbs = 0;
    while ((k < numInstances() && (l < numInstances()))) {
      if (weights[l] < 0) {
	throw new IllegalArgumentException("Weights have to be positive.");
      }
      sumProbs += weights[l];
      while ((k < numInstances()) &&
	     (probabilities[k] <= sumProbs)) { 
	newData.add(instance(l));
	newData.instance(k).setWeight(1);
	k++;
      }
      l++;
    }
    return newData;
  }

  /** 
   * Sets the class attribute.
   *
   * @param att attribute to be the class
   */
  public void setClass(Attribute att) {

    m_ClassIndex = att.index();
  }

  /** 
   * Sets the class index of the set.
   * If the class index is negative there is assumed to be no class.
   * (ie. it is undefined)
   *
   * @param classIndex the new class index (index starts with 0)
   * @throws IllegalArgumentException if the class index is too big or < 0
   */
  public void setClassIndex(int classIndex) {

    if (classIndex >= numAttributes()) {
      throw new IllegalArgumentException("Invalid class index: " + classIndex);
    }
    m_ClassIndex = classIndex;
  }

  /**
   * Sets the relation's name.
   *
   * @param newName the new relation name.
   */
  public void setRelationName(/*@non_null@*/String newName) {
    
    m_RelationName = newName;
  }

  /**
   * Sorts the instances based on an attribute. For numeric attributes, 
   * instances are sorted in ascending order. For nominal attributes, 
   * instances are sorted based on the attribute label ordering 
   * specified in the header. Instances with missing values for the 
   * attribute are placed at the end of the dataset.
   *
   * @param attIndex the attribute's index (index starts with 0)
   */
  public void sort(int attIndex) {

    int i,j;

    // move all instances with missing values to end
    j = numInstances() - 1;
    i = 0;
    while (i <= j) {
      if (instance(j).isMissing(attIndex)) {
	j--;
      } else {
	if (instance(i).isMissing(attIndex)) {
	  swap(i,j);
	  j--;
	}
	i++;
      }
    }
    quickSort(attIndex, 0, j);
  }

  /**
   * Sorts the instances based on an attribute. For numeric attributes, 
   * instances are sorted into ascending order. For nominal attributes, 
   * instances are sorted based on the attribute label ordering 
   * specified in the header. Instances with missing values for the 
   * attribute are placed at the end of the dataset.
   *
   * @param att the attribute
   */
  public void sort(Attribute att) {

    sort(att.index());
  }

  /**
   * Stratifies a set of instances according to its class values 
   * if the class attribute is nominal (so that afterwards a 
   * stratified cross-validation can be performed).
   *
   * @param numFolds the number of folds in the cross-validation
   * @throws UnassignedClassException if the class is not set
   */
  public void stratify(int numFolds) {
    
    if (numFolds <= 0) {
      throw new IllegalArgumentException("Number of folds must be greater than 1");
    }
    if (m_ClassIndex < 0) {
      throw new UnassignedClassException("Class index is negative (not set)!");
    }
    if (classAttribute().isNominal()) {

      // sort by class
      int index = 1;
      while (index < numInstances()) {
	Instance instance1 = instance(index - 1);
	for (int j = index; j < numInstances(); j++) {
	  Instance instance2 = instance(j);
	  if ((instance1.classValue() == instance2.classValue()) ||
	      (instance1.classIsMissing() && 
	       instance2.classIsMissing())) {
	    swap(index,j);
	    index++;
	  }
	}
	index++;
      }
      stratStep(numFolds);
    }
  }
 
  /**
   * Computes the sum of all the instances' weights.
   *
   * @return the sum of all the instances' weights as a double
   */
  public /*@pure@*/ double sumOfWeights() {
    
    double sum = 0;

    for (int i = 0; i < numInstances(); i++) {
      sum += instance(i).weight();
    }
    return sum;
  }

  /**
   * Creates the test set for one fold of a cross-validation on 
   * the dataset.
   *
   * @param numFolds the number of folds in the cross-validation. Must
   * be greater than 1.
   * @param numFold 0 for the first fold, 1 for the second, ...
   * @return the test set as a set of weighted instances
   * @throws IllegalArgumentException if the number of folds is less than 2
   * or greater than the number of instances.
   */
  //@ requires 2 <= numFolds && numFolds < numInstances();
  //@ requires 0 <= numFold && numFold < numFolds;
  public Instances testCV(int numFolds, int numFold) {

    int numInstForFold, first, offset;
    Instances test;
    
    if (numFolds < 2) {
      throw new IllegalArgumentException("Number of folds must be at least 2!");
    }
    if (numFolds > numInstances()) {
      throw new IllegalArgumentException("Can't have more folds than instances!");
    }
    numInstForFold = numInstances() / numFolds;
    if (numFold < numInstances() % numFolds){
      numInstForFold++;
      offset = numFold;
    }else