All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.attributeSelection.ForwardSelection

java.lang.Object
   |
   +----weka.attributeSelection.ASSearch
           |
           +----weka.attributeSelection.ForwardSelection

public class ForwardSelection

extends ASSearch

implements RankedOutputSearch, StartSetHandler, OptionHandler

Valid options are:

-P
Specify a starting set of attributes. Eg 1,4,7-9.

-R
Produce a ranked list of attributes.

-T
Specify a threshold by which the AttributeSelection module can.
discard attributes. Use in conjunction with -R

Version:

$Revision: 1.6 $

Author:

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

ForwardSelection()

getGenerateRanking()

Gets whether ranking has been requested.

getOptions()

Gets the current settings of ReliefFAttributeEval.

getStartSet()

Returns a list of attributes (and or attribute ranges) as a String

getThreshold()

Returns the threshold so that the AttributeSelection module can discard attributes from the ranking.

listOptions()

Returns an enumeration describing the available options

rankedAttributes()

Produces a ranked list of attributes.

search(ASEvaluation, Instances)

Searches the attribute subset space by forward selection.

setGenerateRanking(boolean)

Records whether the user has requested a ranked list of attributes.

setOptions(String[])

Parses a given list of options.

setStartSet(String)

Sets a starting set of attributes for the search.

setThreshold(double)

Set the threshold by which the AttributeSelection module can discard attributes.

toString()

returns a description of the search.

 public ForwardSelection()

 public void setThreshold(double threshold)

Set the threshold by which the AttributeSelection module can discard attributes.

Parameters:

threshold - the threshold.

 public double getThreshold()

Returns the threshold so that the AttributeSelection module can discard attributes from the ranking.

 public void setGenerateRanking(boolean doRank)

Records whether the user has requested a ranked list of attributes.

Parameters:

doRank - true if ranking is requested

 public boolean getGenerateRanking()

Gets whether ranking has been requested. This is used by the AttributeSelection module to determine if rankedAttributes() should be called.

Returns:

true if ranking has been requested.

 public void setStartSet(String startSet) throws Exception

Sets a starting set of attributes for the search. It is the search method's responsibility to report this start set (if any) in its toString() method.

Parameters:

startSet - a string containing a list of attributes (and or ranges), eg. 1,2,6,10-15.

Throws: Exception

if start set can't be set.

 public String getStartSet()

Returns a list of attributes (and or attribute ranges) as a String

Returns:

a list of attributes (and or attribute ranges)

 public Enumeration listOptions()

Returns an enumeration describing the available options

Returns:

an enumeration of all the available options

 public void setOptions(String options[]) throws Exception

Parses a given list of options. Valid options are:

-P
Specify a starting set of attributes. Eg 1,4,7-9.

-R
Produce a ranked list of attributes.

-T
Specify a threshold by which the AttributeSelection module can.
discard attributes. Use in conjunction with -R

Parameters:

options - the list of options as an array of strings

Throws: Exception

if an option is not supported

 public String[] getOptions()

Gets the current settings of ReliefFAttributeEval.

Returns:

an array of strings suitable for passing to setOptions()

 public String toString()

returns a description of the search.

Returns:

a description of the search as a String.

Overrides:

toString in class Object

 public int[] search(ASEvaluation ASEval,
                     Instances data) throws Exception

Searches the attribute subset space by forward selection.

Parameters:

ASEvaluator - the attribute evaluator to guide the search

data - the training instances.

Returns:

an array (not necessarily ordered) of selected attribute indexes

Throws: Exception

if the search can't be completed

Overrides:

search in class ASSearch

 public double[][] rankedAttributes() throws Exception

Produces a ranked list of attributes. Search must have been performed prior to calling this function. Search is called by this function to complete the traversal of the the search space. A list of attributes and merits are returned. The attributes a ranked by the order they are added to the subset during a forward selection search. Individual merit values reflect the merit associated with adding the corresponding attribute to the subset; because of this, merit values will initially increase but then decrease as the best subset is "passed by" on the way to the far side of the search space.

Returns:

an array of attribute indexes and associated merit values

Throws: Exception

if something goes wrong.

All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home