weka.classifiers.pmml.consumer

Class NeuralNetwork

java.lang.Object

weka.classifiers.AbstractClassifier

weka.classifiers.pmml.consumer.PMMLClassifier

weka.classifiers.pmml.consumer.NeuralNetwork

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Classifier, BatchPredictor, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, PMMLModel, RevisionHandler

public class NeuralNetwork
extends PMMLClassifier

Class implementing import of PMML Neural Network model. Can be used as a Weka classifier for prediction (buildClassifier() raises an Exception).

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected weka.classifiers.pmml.consumer.NeuralNetwork.ActivationFunction	m_activationFunction The activation function to use
protected double	m_altitude Altitude for radial basis
protected weka.classifiers.pmml.consumer.NeuralNetwork.MiningFunction	m_functionType The mining function
protected java.util.HashMap<java.lang.String,java.lang.Double>	m_inputMap A map for storing network input values (computed from an incoming instance)
protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralInput[]	m_inputs The inputs to the network
protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralLayer[]	m_layers The hidden layers in the network
protected weka.classifiers.pmml.consumer.NeuralNetwork.Normalization	m_normalizationMethod The normalization method
protected int	m_numberOfInputs The number of inputs to the network
protected int	m_numberOfLayers Number of hidden layers in the network
protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralOutputs	m_outputs The outputs of the network
protected double	m_threshold Threshold activation
protected double	m_width Width for radial basis

Fields inherited from class weka.classifiers.pmml.consumer.PMMLClassifier

m_creatorApplication, m_dataDictionary, m_fieldsMap, m_initialized, m_log, m_miningSchema, m_pmmlVersion

Fields inherited from class weka.classifiers.AbstractClassifier

BATCH_SIZE_DEFAULT, m_BatchSize, m_Debug, m_DoNotCheckCapabilities, m_numDecimalPlaces, NUM_DECIMAL_PLACES_DEFAULT

Constructor Summary

Constructors

Constructor and Description
NeuralNetwork(org.w3c.dom.Element model, Instances dataDictionary, MiningSchema miningSchema)

Method Summary

Modifier and Type	Method and Description
double[]	distributionForInstance(Instance inst) Classifies the given test instance.
java.lang.String	getRevision() Returns the revision string.
java.lang.String	toString()

Methods inherited from class weka.classifiers.pmml.consumer.PMMLClassifier

buildClassifier, done, getCreatorApplication, getDataDictionary, getFieldsMappingString, getLog, getMiningSchema, getPMMLVersion, mapToMiningSchema, setCreatorApplication, setLog, setPMMLVersion

Methods inherited from class weka.classifiers.AbstractClassifier

batchSizeTipText, classifyInstance, debugTipText, distributionsForInstances, doNotCheckCapabilitiesTipText, forName, getBatchSize, getCapabilities, getDebug, getDoNotCheckCapabilities, getNumDecimalPlaces, getOptions, implementsMoreEfficientBatchPrediction, listOptions, makeCopies, makeCopy, numDecimalPlacesTipText, postExecution, preExecution, run, runClassifier, setBatchSize, setDebug, setDoNotCheckCapabilities, setNumDecimalPlaces, setOptions

Methods inherited from class java.lang.Object

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

Field Detail

m_functionType

protected weka.classifiers.pmml.consumer.NeuralNetwork.MiningFunction m_functionType

The mining function

m_activationFunction

protected weka.classifiers.pmml.consumer.NeuralNetwork.ActivationFunction m_activationFunction

The activation function to use

m_normalizationMethod

protected weka.classifiers.pmml.consumer.NeuralNetwork.Normalization m_normalizationMethod

The normalization method

m_threshold

protected double m_threshold

Threshold activation

m_width

protected double m_width

Width for radial basis

m_altitude

protected double m_altitude

Altitude for radial basis

m_numberOfInputs

protected int m_numberOfInputs

The number of inputs to the network

m_numberOfLayers

protected int m_numberOfLayers

Number of hidden layers in the network

m_inputs

protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralInput[] m_inputs

The inputs to the network

m_inputMap

protected java.util.HashMap<java.lang.String,java.lang.Double> m_inputMap

A map for storing network input values (computed from an incoming instance)

m_layers

protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralLayer[] m_layers

The hidden layers in the network

m_outputs

protected weka.classifiers.pmml.consumer.NeuralNetwork.NeuralOutputs m_outputs

The outputs of the network

Constructor Detail

NeuralNetwork

public NeuralNetwork(org.w3c.dom.Element model,
                     Instances dataDictionary,
                     MiningSchema miningSchema)
              throws java.lang.Exception

Throws:

java.lang.Exception

Method Detail

getRevision

public java.lang.String getRevision()

Description copied from class: AbstractClassifier

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class AbstractClassifier

Returns:

the revision

distributionForInstance

public double[] distributionForInstance(Instance inst)
                                 throws java.lang.Exception

Classifies the given test instance. The instance has to belong to a dataset when it's being classified.

Specified by:

distributionForInstance in interface Classifier

Overrides:

distributionForInstance in class AbstractClassifier

Parameters:

inst - the instance to be classified

Returns:

the predicted most likely class for the instance or Utils.missingValue() if no prediction is made

Throws:

java.lang.Exception - if an error occurred during the prediction

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object