removewithvalues.java

来自「MacroWeka扩展了著名数据挖掘工具weka」· Java 代码 · 共 605 行 · 第 1/2 页

      throw new IllegalStateException("No input instance format defined");
    }
    if (m_NewBatch) {
      resetQueue();
      m_NewBatch = false;
    }
    if (instance.isMissing(m_AttIndex.getIndex())) {
      if (!getMatchMissingValues()) {
        push((Instance)instance.copy());
        return true;
      } else {
        return false;
      }
    }
    if (isNumeric()) {
      if (!m_Values.getInvert()) {
	if (instance.value(m_AttIndex.getIndex()) < m_Value) {
	  push((Instance)instance.copy());
	  return true;
	} 
      } else {
	if (instance.value(m_AttIndex.getIndex()) >= m_Value) {
	  push((Instance)instance.copy());
	  return true;
	} 
      }
    }
    if (isNominal()) {
      if (m_Values.isInRange((int)instance.value(m_AttIndex.getIndex()))) {
	Instance temp = (Instance)instance.copy();
	if (getModifyHeader()) {
	  temp.setValue(m_AttIndex.getIndex(),
			m_NominalMapping[(int)instance.value(m_AttIndex.getIndex())]);
	}
	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_AttIndex.getIndex()).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_AttIndex.getIndex()).isNumeric();
    }
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String modifyHeaderTipText() {
    return "When selecting on nominal attributes, removes header references to "
      + "excluded values.";
  }

  /**
   * 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;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String attributeIndexTipText() {
    return "Choose attribute to be used for selection (default last).";
  }

  /**
   * Get the index of the attribute used.
   *
   * @return the index of the attribute
   */
  public String getAttributeIndex() {

    return m_AttIndex.getSingleIndex();
  }

  /**
   * Sets index of the attribute used.
   *
   * @param index the index of the attribute
   */
  public void setAttributeIndex(String attIndex) {
    
    m_AttIndex.setSingleIndex(attIndex);
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String splitPointTipText() {
    return "Numeric value to be used for selection on numeric attribute. "
     + "Instances with values smaller than given value will be selected.";
  }

  /**
   * 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;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String matchMissingValuesTipText() {
    return "Missing values count as a match. This setting is independent of "
      + "the invertSelection option.";
  }

  /**
   * 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;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String invertSelectionTipText() {
    return "Invert matching sense.";
  }

  /**
   * 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_Values.setInvert(!invert);
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String nominalIndicesTipText() {
    return "Range of label indices to be used for selection on nominal attribute. "
      +"First and last are valid indexes.";
  }

  /**
   * 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 RemoveWithValues(), argv);
      } else {
	Filter.filterFile(new RemoveWithValues(), argv);
      }
    } catch (Exception ex) {
      ex.printStackTrace();
      System.out.println(ex.getMessage());
    }
  }
}