Package adams.ml.model.regression

Class WekaRegressionModel

java.lang.Object

adams.core.logging.LoggingObject

adams.ml.model.regression.WekaRegressionModel

All Implemented Interfaces:

adams.core.logging.LoggingSupporter, adams.core.SizeOfHandler, adams.ml.model.Model, adams.ml.model.regression.RegressionModel, Serializable

public class WekaRegressionModel
extends adams.core.logging.LoggingObject
implements adams.ml.model.regression.RegressionModel

Regression model for Weka classifiers.

Version:

$Revision$

Author:

FracPete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected adams.ml.data.DatasetInfo	m_DatasetInfo	the dataset info.
protected weka.core.Instances	m_InstancesHeader	the instances used.
protected weka.classifiers.Classifier	m_Model	the underlying model.

Fields inherited from class adams.core.logging.LoggingObject

m_Logger, m_LoggingIsEnabled, m_LoggingLevel

Constructor Summary

Constructors

Constructor	Description
WekaRegressionModel(weka.classifiers.Classifier model, adams.ml.data.Dataset data, weka.core.Instances inst)	Initializes the model.

Method Summary

Modifier and Type	Method	Description
double	classify(adams.data.spreadsheet.Row row)	Returns the regression for the given row.
adams.ml.data.DatasetInfo	getDatasetInfo()	Returns information about the dataset used for building the model.
weka.core.Instances	getInstancesHeader()	Returns the Instances header used for building the model.
String	getModelDescription()	Gets a short string description of the model.
String	isCompatible(adams.ml.data.Dataset data)	Checks whether the dataset is compatible with the model.

Methods inherited from class adams.core.logging.LoggingObject

configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf

Methods inherited from class java.lang.Object

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

Field Detail

m_Model

protected weka.classifiers.Classifier m_Model

the underlying model.

m_DatasetInfo

protected adams.ml.data.DatasetInfo m_DatasetInfo

the dataset info.

m_InstancesHeader

protected weka.core.Instances m_InstancesHeader

the instances used.

Constructor Detail

WekaRegressionModel

public WekaRegressionModel(weka.classifiers.Classifier model,
                           adams.ml.data.Dataset data,
                           weka.core.Instances inst)

Initializes the model.

Parameters:

model - the built Weka classifier

data - the training data

inst - the Weka training data

Method Detail

classify

public double classify(adams.data.spreadsheet.Row row)
                throws Exception

Returns the regression for the given row.

Specified by:

classify in interface adams.ml.model.regression.RegressionModel

Parameters:

row - the row to make predictions for

Returns:

the prediction

Throws:

Exception - if prediction fails

getDatasetInfo

public adams.ml.data.DatasetInfo getDatasetInfo()

Returns information about the dataset used for building the model.

Specified by:

getDatasetInfo in interface adams.ml.model.Model

Returns:

the information

getInstancesHeader

public weka.core.Instances getInstancesHeader()

Returns the Instances header used for building the model.

Returns:

the header

getModelDescription

public String getModelDescription()

Gets a short string description of the model.

Specified by:

getModelDescription in interface adams.ml.model.Model

Returns:

the description, null if none available

isCompatible

public String isCompatible(adams.ml.data.Dataset data)

Checks whether the dataset is compatible with the model.

Specified by:

isCompatible in interface adams.ml.model.Model

Parameters:

data - the dataset to check

Returns:

null if compatible, otherwise error message why not