weka.classifiers.rules
Class FURIA.NumericAntd

java.lang.Object
  extended by weka.classifiers.rules.FURIA.NumericAntd
All Implemented Interfaces:
java.io.Serializable, Copyable, WeightedInstancesHandler
Enclosing class:
FURIA

public class FURIA.NumericAntd
extends java.lang.Object

The antecedent with numeric attribute

See Also:
Serialized Form

Field Summary
 boolean fuzzyYet
          A flag determining whether this antecedent was successfully fuzzified yet
 double splitPoint
          The split point for this numeric antecedent
 double supportBound
          The edge point for the fuzzy set of this numeric antecedent
 
Constructor Summary
FURIA.NumericAntd(Attribute a)
          Constructor
 
Method Summary
 java.lang.Object copy()
          Implements Copyable
 double covers(Instance inst)
          The degree of coverage for the instance given that antecedent
 double getSplitPoint()
          Get split point of this numeric antecedent
 Instances[] splitData(Instances insts, double defAcRt, double cl)
          Implements the splitData function.
 java.lang.String toString()
          Prints this antecedent
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

splitPoint

public double splitPoint
The split point for this numeric antecedent


supportBound

public double supportBound
The edge point for the fuzzy set of this numeric antecedent


fuzzyYet

public boolean fuzzyYet
A flag determining whether this antecedent was successfully fuzzified yet

Constructor Detail

FURIA.NumericAntd

public FURIA.NumericAntd(Attribute a)
Constructor

Method Detail

getSplitPoint

public double getSplitPoint()
Get split point of this numeric antecedent

Returns:
the split point of this numeric antecedent

copy

public java.lang.Object copy()
Implements Copyable

Specified by:
copy in interface Copyable
Returns:
a copy of this object

splitData

public Instances[] splitData(Instances insts,
                             double defAcRt,
                             double cl)
Implements the splitData function. This procedure is to split the data into two bags according to the information gain of the numeric attribute value The maximum infoGain is also calculated.

Parameters:
insts - the data to be split
defAcRt - the default accuracy rate for data
cl - the class label to be predicted
Returns:
the array of data after split

covers

public double covers(Instance inst)
The degree of coverage for the instance given that antecedent

Parameters:
inst - the instance in question
Returns:
the numeric value indicating the membership of the instance for this antecedent

toString

public java.lang.String toString()
Prints this antecedent

Returns:
a textual description of this antecedent