addexpression.java

来自「Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等」· Java 代码 · 共 819 行 · 第 1/2 页

    Stack operands = new Stack();

    for (int i=0;i<m_postFixExpVector.size();i++) {
      Object nextob = m_postFixExpVector.elementAt(i);
      if (nextob instanceof NumericOperand) {
	operands.push(new Double(((NumericOperand)nextob).m_numericConst));
      } else if (nextob instanceof AttributeOperand) {
	double value = vals[((AttributeOperand)nextob).m_attributeIndex];
	if (value == Instance.missingValue()) {
	  vals[vals.length-1] = Instance.missingValue();
	  break;
	}
	if (((AttributeOperand)nextob).m_negative) {
	  value = -value;
	}
	operands.push(new Double(value));
      } else if (nextob instanceof Operator) {
	char op = ((Operator)nextob).m_operator;
	if (isUnaryFunction(op)) {
	  double operand = ((Double)operands.pop()).doubleValue();
	  double result = ((Operator)nextob).applyFunction(operand);
	  operands.push(new Double(result));
	} else {
	  double second = ((Double)operands.pop()).doubleValue();
	  double first = ((Double)operands.pop()).doubleValue();
	  double result = ((Operator)nextob).applyOperator(first,second);
	  operands.push(new Double(result));
	}
      } else {
	throw new Exception("Unknown object in postfix vector!");
      }
    }

    if (operands.size() != 1) {
      throw new Exception("Problem applying function");
    }

    Double result = ((Double)operands.pop());
    if (result.isNaN() || result.isInfinite()) {
      vals[vals.length-1] = Instance.missingValue();
    } else {
      vals[vals.length-1] = result.doubleValue();
    }
  }

  /**
   * Returns true if a token is an operator
   * @param tok the token to check
   * @return true if the supplied token is an operator
   */
  private boolean isOperator(char tok) {
    if (OPERATORS.indexOf(tok) == -1) {
      return false;
    }

    return true;
  }

  /**
   * Returns true if a token is a unary function
   * @param tok the token to check
   * @return true if the supplied token is a unary function
   */
  private boolean isUnaryFunction(char tok) {
    if (UNARY_FUNCTIONS.indexOf(tok) == -1) {
      return false;
    }

    return true;
  }

  /**
   * Return the infix priority of an operator
   * @param opp the operator
   * @return the infix priority
   */
  private int infixPriority(char opp) {
    switch (opp) {
      case 'l' : 
      case 'b' :
      case 'c' :
      case 'e' :
      case 's' :
      case 'f' :
      case 'h' :
      case 'r' :
      case 't' :
      case 'n' :
	return 3;
      case '^' :
	return 2;
      case '*' : 
	return 2;
      case '/' : 
	return 2;
      case '+' :
	return 1;
      case '-' :
	return 1;
      case '(' :
	return 4;
      case ')' :
	return 0;
      default :
	throw new IllegalArgumentException("Unrecognized operator:" + opp);
    }
  }

  /**
   * Return the stack priority of an operator
   * @param opp the operator
   * @return the stack priority
   */
  private int stackPriority(char opp) {
     switch (opp) {
       case 'l' :
       case 'b' :
       case 'c' :
       case 'e' :
       case 's' :
       case 'f' :
       case 'h' :
       case 'r' :
       case 't' :
       case 'n' :
	 return 3;
       case '^' :
	 return 2;
       case '*' : 
	 return 2;
       case '/' : 
	 return 2;
       case '+' :
	 return 1;
       case '-' :
	 return 1;
       case '(' :
	 return 0;
       case ')' :
	 return -1;
       default :
	 throw new IllegalArgumentException("Unrecognized operator:" + opp);
    }
  }

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {

    Vector newVector = new Vector(3); 

    newVector.addElement(new Option(
	     "\tSpecify the expression to apply. Eg a1^2*a5/log(a7*4.0)."
	     +"\n\tSupported opperators: ,+, -, *, /, ^, log, abs, cos, "
	     +"\n\texp, sqrt, floor, ceil, rint, tan, sin, (, )",
	     "E",1,"-E <expression>"));

    newVector.addElement(new Option(
	     "\tSpecify the name for the new attribute. (default is the "
	     +"expression provided with -E)",
	     "N",1,"-N <name>"));

    newVector.addElement(new Option(
	     "\tDebug. Names attribute with the postfix parse of the "
	     +"expression.","D",0,"-D"));

    return newVector.elements();
  }

  /**
   * Parses a given list of options. <p/>
   * 
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -E &lt;expression&gt;
   *  Specify the expression to apply. Eg a1^2*a5/log(a7*4.0).
   *  Supported opperators: ,+, -, *, /, ^, log, abs, cos, 
   *  exp, sqrt, floor, ceil, rint, tan, sin, (, )</pre>
   * 
   * <pre> -N &lt;name&gt;
   *  Specify the name for the new attribute. (default is the expression provided with -E)</pre>
   * 
   * <pre> -D
   *  Debug. Names attribute with the postfix parse of the expression.</pre>
   * 
   <!-- options-end -->
   *
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {
    String expString = Utils.getOption('E', options);
    if (expString.length() != 0) {
      setExpression(expString);
    } else {
      throw new Exception("Must specify an expression with the -E option");
    }

    String name = Utils.getOption('N',options);
    if (name.length() != 0) {
      setName(name);
    }

    setDebug(Utils.getFlag('D', options));
  }
  
  /**
   * Gets the current settings of the filter.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] options = new String [5];
    int current = 0;
    
    options[current++] = "-E"; options[current++] = getExpression();
    options[current++] = "-N"; options[current++] = getName();

    if (getDebug()) {
      options[current++] = "-D";
    }
    
    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String nameTipText() {
    return "Set the name of the new attribute.";
  }

  /**
   * Set the name for the new attribute. The string "expression" can
   * be used to make the name of the new attribute equal to the expression
   * provided.
   * @param name the name of the new attribute
   */
  public void setName(String name) {
    m_attributeName = name;
  }

  /**
   * Returns the name of the new attribute
   * @return the name of the new attribute
   */
  public String getName() {
    return m_attributeName;
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String debugTipText() {
    return "Set debug mode. If true then the new attribute will be named with "
      +"the postfix parse of the supplied expression.";
  }
  
  /**
   * Set debug mode. Causes the new attribute to be named with the postfix
   * parse of the expression
   * @param d true if debug mode is to be used
   */
  public void setDebug(boolean d) {
    m_Debug = d;
  }

  /**
   * Gets whether debug is set
   * @return true if debug is set
   */
  public boolean getDebug() {
    return m_Debug;
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String expressionTipText() {
    return "Set the math expression to apply. Eg. a1^2*a5/log(a7*4.0)";
  }

  /**
   * Set the expression to apply
   * @param expr a mathematical expression to apply
   */
  public void setExpression(String expr) {
    m_infixExpression = expr;
  }

  /**
   * Get the expression
   * @return the expression
   */
  public String getExpression() {
    return m_infixExpression;
  }

  /**
   * Sets the format of the input instances.
   *
   * @param instanceInfo an Instances object containing the input instance
   * structure (any instances contained in the object are ignored - only the
   * structure is required).
   * @return true if the outputFormat may be collected immediately
   * @throws Exception if the format couldn't be set successfully
   */
  public boolean setInputFormat(Instances instanceInfo) throws Exception {

    convertInfixToPostfix(new String(m_infixExpression));

    super.setInputFormat(instanceInfo);

    Instances outputFormat = new Instances(instanceInfo, 0);
    Attribute newAttribute;
    if (m_Debug) {
      newAttribute = new Attribute(m_postFixExpVector.toString());
    } else if (m_attributeName.compareTo("expression") != 0) {
      newAttribute = new Attribute(m_attributeName);
    } else {
      newAttribute = new Attribute(m_infixExpression);
    }
    outputFormat.insertAttributeAt(newAttribute, 
				   instanceInfo.numAttributes());
    setOutputFormat(outputFormat);
    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().
   * @throws IllegalStateException if no input format has been defined.
   * @throws Exception if there was a problem during the filtering.
   */
  public boolean input(Instance instance) throws Exception {

    if (getInputFormat() == null) {
      throw new IllegalStateException("No input instance format defined");
    }
    if (m_NewBatch) {
      resetQueue();
      m_NewBatch = false;
    }

    double[] vals = new double[instance.numAttributes()+1];
    for(int i = 0; i < instance.numAttributes(); i++) {
      if (instance.isMissing(i)) {
	vals[i] = Instance.missingValue();
      } else {
	vals[i] = instance.value(i);
      }
    }

    evaluateExpression(vals);

    Instance inst = null;
    if (instance instanceof SparseInstance) {
      inst = new SparseInstance(instance.weight(), vals);
    } else {
      inst = new Instance(instance.weight(), vals);
    }

    inst.setDataset(getOutputFormat());
    copyValues(inst, false, instance.dataset(), getOutputFormat());
    inst.setDataset(getOutputFormat());
    push(inst);
    return true;
  }
  
  /**
   * Main method for testing this class.
   *
   * @param args should contain arguments to the filter: use -h for help
   */
  public static void main(String [] args) {
    try {
      if (Utils.getFlag('b', args)) {
	Filter.batchFilterFile(new AddExpression(), args);
      } else {
	Filter.filterFile(new AddExpression(), args);
      }
    } catch (Exception ex) {
      System.out.println(ex.getMessage());
    }
  }
}