/** initializes the attribute indices. */
 protected void initializeAttributeIndices() {
   m_AttributeIndices.setUpper(m_Data.numAttributes() - 1);
   m_ActiveIndices = new boolean[m_Data.numAttributes()];
   for (int i = 0; i < m_ActiveIndices.length; i++) {
     m_ActiveIndices[i] = m_AttributeIndices.isInRange(i);
   }
 }
Пример #2
0
  /**
   * 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 {

    Instances data;
    Instances result;
    FastVector atts;
    FastVector values;
    HashSet hash;
    int i;
    int n;
    boolean isDate;
    Instance inst;
    Vector sorted;

    m_Cols.setUpper(inputFormat.numAttributes() - 1);
    data = new Instances(inputFormat);
    atts = new FastVector();
    for (i = 0; i < data.numAttributes(); i++) {
      if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
        atts.addElement(data.attribute(i));
        continue;
      }

      // date attribute?
      isDate = (data.attribute(i).type() == Attribute.DATE);

      // determine all available attribtues in dataset
      hash = new HashSet();
      for (n = 0; n < data.numInstances(); n++) {
        inst = data.instance(n);
        if (inst.isMissing(i)) continue;

        if (isDate) hash.add(inst.stringValue(i));
        else hash.add(new Double(inst.value(i)));
      }

      // sort values
      sorted = new Vector();
      for (Object o : hash) sorted.add(o);
      Collections.sort(sorted);

      // create attribute from sorted values
      values = new FastVector();
      for (Object o : sorted) {
        if (isDate) values.addElement(o.toString());
        else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
      }
      atts.addElement(new Attribute(data.attribute(i).name(), values));
    }

    result = new Instances(inputFormat.relationName(), atts, 0);
    result.setClassIndex(inputFormat.classIndex());

    return result;
  }
Пример #3
0
  /**
   * 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 {
    Instances result;
    int i;
    int n;
    double[] values;
    String value;
    Instance inst;
    Instance newInst;

    // we need the complete input data!
    if (!isFirstBatchDone()) setOutputFormat(determineOutputFormat(getInputFormat()));

    result = new Instances(getOutputFormat());

    for (i = 0; i < instances.numInstances(); i++) {
      inst = instances.instance(i);
      values = inst.toDoubleArray();

      for (n = 0; n < values.length; n++) {
        if (!m_Cols.isInRange(n) || !instances.attribute(n).isNumeric() || inst.isMissing(n))
          continue;

        // get index of value
        if (instances.attribute(n).type() == Attribute.DATE) value = inst.stringValue(n);
        else value = Utils.doubleToString(inst.value(n), MAX_DECIMALS);

        values[n] = result.attribute(n).indexOfValue(value);
      }

      // generate new instance
      if (inst instanceof SparseInstance) newInst = new SparseInstance(inst.weight(), values);
      else newInst = new DenseInstance(inst.weight(), values);

      // copy possible string, relational values
      newInst.setDataset(getOutputFormat());
      copyValues(newInst, false, inst.dataset(), getOutputFormat());

      result.add(newInst);
    }

    return result;
  }