Package weka.classifiers.pmml.producer

Class LogisticProducerHelper

java.lang.Object

weka.classifiers.pmml.producer.AbstractPMMLProducerHelper

weka.classifiers.pmml.producer.LogisticProducerHelper

public class LogisticProducerHelper
extends AbstractPMMLProducerHelper

Helper class for producing PMML for a Logistic classifier. Not designed to be used directly - you should call toPMML() on a trained Logistic classifier.

Version:

$Revision: $

Author:

David Persons, Mark Hall (mhall{[at]}pentaho{[dot]}com)

Field Summary

Fields inherited from class weka.classifiers.pmml.producer.AbstractPMMLProducerHelper

PMML_VERSION

Constructor Summary

Constructors

Constructor	Description
LogisticProducerHelper()

Method Summary

Modifier and Type	Method	Description
static java.lang.String	toPMML(Instances train, Instances structureAfterFiltering, double[][] par, int numClasses)	Produce the PMML for a Logistic classifier

Methods inherited from class weka.classifiers.pmml.producer.AbstractPMMLProducerHelper

addDataDictionary, getNameAndValueFromUnsupervisedNominalToBinaryDerivedAttribute, getOPTYPE, initPMML

Methods inherited from class java.lang.Object

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

Constructor Detail

LogisticProducerHelper

public LogisticProducerHelper()

Method Detail

toPMML

public static java.lang.String toPMML(Instances train,
                                      Instances structureAfterFiltering,
                                      double[][] par,
                                      int numClasses)

Produce the PMML for a Logistic classifier

Parameters:

train - the training data used to build the Logistic model

structureAfterFiltering - the structure of the training data after filtering

par - the parameters of the function(s)

numClasses - the number of classes in the data

Returns:

the PMML for the classifier