wGmdh.jGmdh.oldskul
Class AttributeNode

java.lang.Object
  extended by wGmdh.jGmdh.oldskul.Node
      extended by wGmdh.jGmdh.oldskul.AttributeNode
All Implemented Interfaces:
java.io.Serializable, java.lang.Comparable<Node>

public class AttributeNode
extends Node

See Also:
Serialized Form

Nested Class Summary
 
Nested classes/interfaces inherited from class wGmdh.jGmdh.oldskul.Node
Node.Visited
 
Field Summary
 weka.core.Attribute attr
           
 int index
           
 
Fields inherited from class wGmdh.jGmdh.oldskul.Node
graphics, trainSetOutput, validationSetOutput, visited
 
Constructor Summary
AttributeNode(DatasetSupervised provider, int attrIndex)
           
AttributeNode(weka.core.Instances instancesTraining, weka.core.Instances instancesValidation, int attrIndex)
          Deprecated. 
AttributeNode(weka.core.Instances dataset, int attrIndex, int nrFolds)
          Deprecated. 
 
Method Summary
 double networkOutput(double[] inputs, int fold)
          Attribute node passes the same output whatever the fold.
 double networkOutputNoFlags(double[] inputs, int fold)
          This one gets invoked by networkOutput.
 
Methods inherited from class wGmdh.jGmdh.oldskul.Node
compareTo, getGlobalIdentifier, getIdentifier, getNrFolds, InitializeGraphics, setGlobalIdentifier
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

attr

public weka.core.Attribute attr

index

public int index
Constructor Detail

AttributeNode

@Deprecated
public AttributeNode(weka.core.Instances instancesTraining,
                                weka.core.Instances instancesValidation,
                                int attrIndex)
Deprecated. 

Appropriate when only two datasets are used: one for building the network structure and one one dataset to approximate how well this structure would generalize

Parameters:
instancesTraining -
instancesValidation -
attrIndex -

AttributeNode

@Deprecated
public AttributeNode(weka.core.Instances dataset,
                                int attrIndex,
                                int nrFolds)
Deprecated. 

Appropriate when n-fold crossvalidation will be used to determine the network structure: one dataset is provided. dataset is randomized at each fold.

Parameters:
dataset -
attrIndex -
nrFolds -

AttributeNode

public AttributeNode(DatasetSupervised provider,
                     int attrIndex)
Parameters:
provider -
attrIndex -
Method Detail

networkOutput

public double networkOutput(double[] inputs,
                            int fold)
Attribute node passes the same output whatever the fold.

Specified by:
networkOutput in class Node
Parameters:
inputs -
fold - doesn't matter
Returns:

networkOutputNoFlags

public double networkOutputNoFlags(double[] inputs,
                                   int fold)
Description copied from class: Node
This one gets invoked by networkOutput. Flags are a must, speed issues otherwise.

Specified by:
networkOutputNoFlags in class Node
Parameters:
inputs -
fold - ...doesn't matter
Returns: