weka.filters.unsupervised.attribute
Class AddExpression

java.lang.Object
  weka.filters.Filter
      weka.filters.unsupervised.attribute.AddExpression

All Implemented Interfaces:

OptionHandler, java.io.Serializable, StreamableFilter, UnsupervisedFilter

public class AddExpression

extends Filter

implements UnsupervisedFilter, StreamableFilter, OptionHandler

Applys a mathematical expression involving attributes and numeric constants to a dataset. A new attribute is appended after the last attribute that contains the result of applying the expression. Supported operators are: +, -, *, /, ^, log, abs, cos, exp, sqrt, floor, ceil, rint, tan, sin, (, ). Attributes are specified by prefixing with 'a', eg. a7 is attribute number 7 (starting from 1).

Valid filter-specific options are:

-E expression
Specify the expression to apply. Eg. a1^2*a5/log(a7*4.0).

-N name
Specify a name for the new attribute. Default is to name it with the expression provided with the -E option.

-D
Debug. Names the attribute with the postfix parse of the expression.

Version:

$Revision: 1.2 $

Author:

Mark Hall (mhall@cs.waikato.ac.nz)

See Also:

Serialized Form

Nested Class Summary

private class	AddExpression.AttributeOperand Inner class handling an attribute index as an operand
private class	AddExpression.NumericOperand Inner class for storing numeric constant opperands
private class	AddExpression.Operator Inner class for storing operators

Field Summary

private java.lang.String	m_attributeName Name of the new attribute.
private boolean	m_Debug If true, makes the attribute name equal to the postfix parse of the expression
private java.lang.String	m_infixExpression The infix expression
private java.util.Stack	m_operatorStack Operator stack
private java.util.Vector	m_postFixExpVector Holds the expression in postfix form
private java.lang.String	m_previousTok Holds the previous token
private boolean	m_signMod True if the next numeric constant or attribute index is negative
private static java.lang.String	OPERATORS Supported operators. l = log, b = abs, c = cos, e = exp, s = sqrt, f = floor, h = ceil, r = rint, t = tan, n = sin
private static java.lang.String	UNARY_FUNCTIONS

Fields inherited from class weka.filters.Filter

m_NewBatch

Constructor Summary

AddExpression()

Method Summary

private void	convertInfixToPostfix(java.lang.String infixExp) Converts a string containing a mathematical expression in infix form to postfix form.
java.lang.String	debugTipText() Returns the tip text for this property
private void	evaluateExpression(double[] vals) Evaluate the expression using the supplied array of attribute values.
java.lang.String	expressionTipText() Returns the tip text for this property
boolean	getDebug() Gets whether debug is set
java.lang.String	getExpression() Get the expression
java.lang.String	getName() Returns the name of the new attribute
java.lang.String[]	getOptions() Gets the current settings of the filter.
java.lang.String	globalInfo() Returns a string describing this filter
private void	handleOperand(java.lang.String tok) Handles the processing of an infix operand to postfix
private void	handleOperator(java.lang.String tok) Handles the processing of an infix operator to postfix
private int	infixPriority(char opp) Return the infix priority of an operator
boolean	input(Instance instance) Input an instance for filtering.
private boolean	isOperator(char tok) Returns true if a token is an operator
private boolean	isUnaryFunction(char tok) Returns true if a token is a unary function
java.util.Enumeration	listOptions() Returns an enumeration describing the available options.
static void	main(java.lang.String[] args) Main method for testing this class.
java.lang.String	nameTipText() Returns the tip text for this property
void	setDebug(boolean d) Set debug mode.
void	setExpression(java.lang.String expr) Set the expression to apply
boolean	setInputFormat(Instances instanceInfo) Sets the format of the input instances.
void	setName(java.lang.String name) Set the name for the new attribute.
void	setOptions(java.lang.String[] options) Parses a list of options for this object.
private int	stackPriority(char opp) Return the stack priority of an operator

Methods inherited from class weka.filters.Filter

batchFilterFile, batchFinished, bufferInput, copyStringValues, copyStringValues, filterFile, flushInput, getInputFormat, getInputStringIndex, getOutputFormat, getOutputStringIndex, getStringIndices, inputFormat, inputFormatPeek, isOutputFormatDefined, numPendingOutput, output, outputFormat, outputFormatPeek, outputPeek, push, resetQueue, setOutputFormat, useFilter

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

m_infixExpression

private java.lang.String m_infixExpression

The infix expression

m_operatorStack

private java.util.Stack m_operatorStack

Operator stack

OPERATORS

private static final java.lang.String OPERATORS

Supported operators. l = log, b = abs, c = cos, e = exp, s = sqrt, f = floor, h = ceil, r = rint, t = tan, n = sin

See Also:

Constant Field Values

UNARY_FUNCTIONS

private static final java.lang.String UNARY_FUNCTIONS

See Also:

Constant Field Values

m_postFixExpVector

private java.util.Vector m_postFixExpVector

Holds the expression in postfix form

m_signMod

private boolean m_signMod

True if the next numeric constant or attribute index is negative

m_previousTok

private java.lang.String m_previousTok

Holds the previous token

m_attributeName

private java.lang.String m_attributeName

Name of the new attribute. "expression" length string will use the provided expression as the new attribute name

m_Debug

private boolean m_Debug

If true, makes the attribute name equal to the postfix parse of the expression

Constructor Detail

AddExpression

public AddExpression()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this filter

Returns:

a description of the filter suitable for displaying in the explorer/experimenter gui

handleOperand

private void handleOperand(java.lang.String tok)
                    throws java.lang.Exception

Handles the processing of an infix operand to postfix

Parameters:

tok - the infix operand

Throws:

java.lang.Exception - if there is difficulty parsing the operand

handleOperator

private void handleOperator(java.lang.String tok)
                     throws java.lang.Exception

Handles the processing of an infix operator to postfix

Parameters:

tok - the infix operator

Throws:

java.lang.Exception - if there is difficulty parsing the operator

convertInfixToPostfix

private void convertInfixToPostfix(java.lang.String infixExp)
                            throws java.lang.Exception

Converts a string containing a mathematical expression in infix form to postfix form. The result is stored in the vector m_postfixExpVector

Parameters:

infixExp - the infix expression to convert

Throws:

java.lang.Exception - if something goes wrong during the conversion

evaluateExpression

private void evaluateExpression(double[] vals)
                         throws java.lang.Exception

Evaluate the expression using the supplied array of attribute values. The result is stored in the last element of the array. Assumes that the infix expression has been converted to postfix and stored in m_postFixExpVector

Parameters:

vals - the values to apply the expression to

Throws:

java.lang.Exception - if something goes wrong

isOperator

private boolean isOperator(char tok)

Returns true if a token is an operator

Parameters:

tok - the token to check

Returns:

true if the supplied token is an operator

isUnaryFunction

private boolean isUnaryFunction(char tok)

Returns true if a token is a unary function

Parameters:

tok - the token to check

Returns:

true if the supplied token is a unary function

infixPriority

private int infixPriority(char opp)

Return the infix priority of an operator

Returns:

the infix priority

stackPriority

private int stackPriority(char opp)

Return the stack priority of an operator

Returns:

the stack priority

listOptions

public java.util.Enumeration listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Returns:

an enumeration of all the available options.

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a list of options for this object. Valid options are:

-E expression
Specify the expression to apply. Eg. a1^2*a5/log(a7*4.0).

-N name
Specify a name for the new attribute. Default is to name it with the expression provided with the -E option.

-D
Debug. Names the attribute with the postfix parse of the expression.

Specified by:

setOptions in interface OptionHandler

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the filter.

Specified by:

getOptions in interface OptionHandler

Returns:

an array of strings suitable for passing to setOptions

nameTipText

public java.lang.String nameTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setName

public void setName(java.lang.String name)

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.

Parameters:

name - the name of the new attribute

getName

public java.lang.String getName()

Returns the name of the new attribute

Returns:

the name of the new attribute

debugTipText

public java.lang.String debugTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setDebug

public void setDebug(boolean d)

Set debug mode. Causes the new attribute to be named with the postfix parse of the expression

Parameters:

d - true if debug mode is to be used

getDebug

public boolean getDebug()

Gets whether debug is set

Returns:

true if debug is set

expressionTipText

public java.lang.String expressionTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setExpression

public void setExpression(java.lang.String expr)

Set the expression to apply

Parameters:

expr - a mathematical expression to apply

getExpression

public java.lang.String getExpression()

Get the expression

Returns:

the expression

setInputFormat

public boolean setInputFormat(Instances instanceInfo)
                       throws java.lang.Exception

Sets the format of the input instances.

Overrides:

setInputFormat in class Filter

Parameters:

instanceInfo - an Instances object containing the input instance structure (any instances contained in the object are ignored - only the structure is required).

Returns:

true if the outputFormat may be collected immediately

Throws:

java.lang.Exception - if the format couldn't be set successfully

input

public boolean input(Instance instance)
              throws java.lang.Exception

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.

Overrides:

input in class Filter

Parameters:

instance - the input instance

Returns:

true if the filtered instance may now be collected with output().

Throws:

java.lang.IllegalStateException - if no input format has been defined.

java.lang.Exception - if there was a problem during the filtering.

main

public static void main(java.lang.String[] args)

Main method for testing this class.

Parameters:

args - should contain arguments to the filter: use -h for help