instancefilter.java

一个数据挖掘系统的源码

      instanceInfo.insertAttributeAt(new Attribute(oldAtt.name(), newVals),
				      m_Attribute);
      m_NominalMapping = new int [oldAtt.numValues()];
      for (int i = 0; i < m_NominalMapping.length; i++) {
	boolean found = false;
	for (int j = 0; j < selection.length; j++) {
	  if (selection[j] == i) {
	    m_NominalMapping[i] = j;
	    found = true;
	    break;
	  }
	}
	if (!found) {
	  m_NominalMapping[i] = -1;
	}
      }
    }
    setOutputFormat(instanceInfo);
    return true;
  }

  /**
   * Input an instance for filtering. Ordinarily the instance is processed
   * and made available for output immediately. Some filters require all
   * instances be read before producing output.
   *
   * @param instance the input instance
   * @return true if the filtered instance may now be
   * collected with output().
   * @exception IllegalStateException if no input format has been set.
   */
  public boolean input(Instance instance) {

    if (getInputFormat() == null) {
      throw new IllegalStateException("No input instance format defined");
    }
    if (m_NewBatch) {
      resetQueue();
      m_NewBatch = false;
    }
    if (instance.isMissing(m_Attribute)) {
      if (getMatchMissingValues()) {
        push((Instance)instance.copy());
        return true;
      } else {
        return false;
      }
    }
    if (isNumeric()) {
      if (!m_Inverse) {
	if (Utils.sm(instance.value(m_Attribute), m_Value)) {
	  push((Instance)instance.copy());
	  return true;
	}
      } else {
	if (Utils.grOrEq(instance.value(m_Attribute), m_Value)) {
	  push((Instance)instance.copy());
	  return true;
	}
      }
    }
    if (isNominal()) {
      if (m_Values.isInRange((int)instance.value(m_Attribute))) {
	Instance temp = (Instance)instance.copy();
	if (getModifyHeader()) {
	  temp.setValue(m_Attribute,
			m_NominalMapping[(int)instance.value(m_Attribute)]);
	}
	push(temp);
	return true;
      }
    }
    return false;
  }

  /**
   * Returns true if selection attribute is nominal.
   *
   * @return true if selection attribute is nominal
   */
  public boolean isNominal() {

    if (getInputFormat() == null) {
      return false;
    } else {
      return getInputFormat().attribute(m_Attribute).isNominal();
    }
  }

  /**
   * Returns true if selection attribute is numeric.
   *
   * @return true if selection attribute is numeric
   */
  public boolean isNumeric() {

    if (getInputFormat() == null) {
      return false;
    } else {
      return getInputFormat().attribute(m_Attribute).isNumeric();
    }
  }

  /**
   * Gets whether the header will be modified when selecting on nominal
   * attributes.
   *
   * @return true if so.
   */
  public boolean getModifyHeader() {

    return m_ModifyHeader;
  }

  /**
   * Sets whether the header will be modified when selecting on nominal
   * attributes.
   *
   * @param newModifyHeader true if so.
   */
  public void setModifyHeader(boolean newModifyHeader) {

    m_ModifyHeader = newModifyHeader;
  }

  /**
   * Get the attribute to be used for selection (-1 for last)
   *
   * @return the attribute index
   */
  public int getAttributeIndex() {

    return m_AttributeSet;
  }

  /**
   * Sets attribute to be used for selection
   *
   * @param attribute the attribute's index (-1 for last);
   */
  public void setAttributeIndex(int attribute) {

    m_AttributeSet = attribute;
  }

  /**
   * Get the split point used for numeric selection
   *
   * @return the numeric split point
   */
  public double getSplitPoint() {

    return m_Value;
  }

  /**
   * Split point to be used for selection on numeric attribute.
   *
   * @param value the split point
   */
  public void setSplitPoint(double value) {

    m_Value = value;
  }

  /**
   * Gets whether missing values are counted as a match.
   *
   * @return true if missing values are counted as a match.
   */
  public boolean getMatchMissingValues() {

    return m_MatchMissingValues;
  }

  /**
   * Sets whether missing values are counted as a match.
   *
   * @param newMatchMissingValues true if missing values are counted as a match.
   */
  public void setMatchMissingValues(boolean newMatchMissingValues) {

    m_MatchMissingValues = newMatchMissingValues;
  }

  /**
   * Get whether the supplied columns are to be removed or kept
   *
   * @return true if the supplied columns will be kept
   */
  public boolean getInvertSelection() {

    return m_Values.getInvert();
  }

  /**
   * Set whether selected values should be removed or kept. If true the
   * selected values are kept and unselected values are deleted.
   *
   * @param invert the new invert setting
   */
  public void setInvertSelection(boolean invert) {

    m_Inverse = invert;
    m_Values.setInvert(invert);
  }

  /**
   * Get the set of nominal value indices that will be used for selection
   *
   * @return rangeList a string representing the list of nominal indices.
   */
  public String getNominalIndices() {

    return m_Values.getRanges();
  }

  /**
   * Set which nominal labels are to be included in the selection.
   *
   * @param rangeList a string representing the list of nominal indices.
   * eg: first-3,5,6-last
   * @exception InvalidArgumentException if an invalid range list is supplied
   */
  public void setNominalIndices(String rangeList) {

    m_Values.setRanges(rangeList);
  }

  /**
   * Set which values of a nominal attribute are to be used for
   * selection.
   *
   * @param values an array containing indexes of values to be
   * used for selection
   * @exception InvalidArgumentException if an invalid set of ranges is supplied
   */
  public void setNominalIndicesArr(int [] values) {

    String rangeList = "";
    for(int i = 0; i < values.length; i++) {
      if (i == 0) {
	rangeList = "" + (values[i] + 1);
      } else {
	rangeList += "," + (values[i] + 1);
      }
    }
    setNominalIndices(rangeList);
  }

  /**
   * Main method for testing this class.
   *
   * @param argv should contain arguments to the filter:
   * use -h for help
   */
  public static void main(String [] argv) {

    try {
      if (Utils.getFlag('b', argv)) {
 	Filter.batchFilterFile(new InstanceFilter(), argv);
      } else {
	Filter.filterFile(new InstanceFilter(), argv);
      }
    } catch (Exception ex) {
      log.error(ex.getMessage());
    }
  }
}