oracle.dmt.odm.settings.function
Class ClusteringFunctionSettings

java.lang.Object
  |
  +--oracle.dmt.odm.MiningObject
        |
        +--oracle.dmt.odm.LocatableObject
              |
              +--oracle.dmt.odm.settings.function.MiningFunctionSettings
                    |
                    +--oracle.dmt.odm.settings.function.ClusteringFunctionSettings

All Implemented Interfaces:

java.io.Serializable

public class ClusteringFunctionSettings

extends MiningFunctionSettings

An instance of ClusteringFunctionSettings holds metadata for required settings common to all clustering algorithms.

Since:

9.2.0

See Also:

ClusteringAlgorithmSettings, KMeansAlgorithmSettings, OClusterAlgorithmSettings, Serialized Form

Constructor Summary

ClusteringFunctionSettings(int numberOfClusters, LogicalDataSpecification lds, DataUsageSpecification dus)
Creates a ClusteringFunctionSettings object using the default clustering MiningAlgorithmSettings.

ClusteringFunctionSettings(int numberOfClusters, LogicalDataSpecification lds, DataUsageSpecification dus, ClusteringAlgorithmSettings algorithm)
Creates a ClusteringFunctionSettings object using the clustering MiningAlgorithmSettings specified by mas.

Method Summary

static ClusteringFunctionSettings	create(Connection dmsConn, MiningAlgorithmSettings algorithm, PhysicalDataSpecification pds, DataPreparationStatus dpStatus, int numberOfClusters, java.lang.String[] categoricalMiningAttributes, java.lang.String[] numericMiningAttributes, java.lang.String[] intMiningAttributes) This method is a utility function allowing user to create and populate ClusteringFunctionSettings in one step.
MiningAttribute[]	getActiveAttributes() Returns the list of active attributes in this MFS.
int	getMaxNumberOfClusters() Returns the maximum number of clusters a model built with this MFS can have.
MiningAttribute[]	getUnpreparedActiveAttributes() Returns the array of unbinned active attributes in this MFS.
MiningAttribute[]	getUnpreparedActiveNumericAttributes() Returns the list of unbinned active numeric attributes in this MFS.
void	setMaxNumberOfClusters(int maxNum) Sets maximum number of clusters a model built with this MFS can have.
void	validate() Validates the correctness of this function settings.

Methods inherited from class oracle.dmt.odm.settings.function.MiningFunctionSettings

activateAll, adjustAttributesType, adjustAttributeUsage, adjustAttributeUsage, adjustDataPreparationStatus, adjustSparsitySpecification, getDataUsageSpecification, getLogicalDataSpecification, getMiningAlgorithmName, getMiningAlgorithmSettings, getMiningAttributes, getMiningFunction, getName, getSettingsID, getSupplementalAttributes, getValidateBeforeStore, listContents, listContents, listContents, listContents, remove, rename, restore, restore, restorePastVersion, restorePastVersion, setDataUsageSpecification, setLogicalDataSpecification, setMiningAlgorithmName, setMiningAlgorithmSettings, setMiningFunction, setValidateBeforeStore, store

Methods inherited from class java.lang.Object

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

Constructor Detail

ClusteringFunctionSettings

public ClusteringFunctionSettings(int numberOfClusters,
LogicalDataSpecification lds,
DataUsageSpecification dus,
ClusteringAlgorithmSettings algorithm)
                           throws InvalidArgumentException

Creates a ClusteringFunctionSettings object using the clustering MiningAlgorithmSettings specified by mas.

Parameters:

numberOfClusters - Maximum number of clusters the clustering model can have

lds - A LogicalDataSpecification object that specifies the logical data to be used for model building

dus - A DataUsageSpecification object that defines how the logical data is to be used for model building

Throws:

InvalidArgumentException - when numberOfClusters > 1,000,000 or numberOfClusters < 1.

InvalidArgumentException

ClusteringFunctionSettings

public ClusteringFunctionSettings(int numberOfClusters,
LogicalDataSpecification lds,
DataUsageSpecification dus)
                           throws InvalidArgumentException

Creates a ClusteringFunctionSettings object using the default clustering MiningAlgorithmSettings.

Parameters:

numberOfClusters - Maximum number of clusters the clustering model can have

lds - A LogicalDataSpecification object that specifies the logical data to be used for model building

dus - A DataUsageSpecification object that defines how the logical data is to be used for model building

Throws:

InvalidArgumentException - when numberOfClusters > 1,000,000 or numberOfClusters < 1.

InvalidArgumentException

Method Detail

getMaxNumberOfClusters

public int getMaxNumberOfClusters()

Returns the maximum number of clusters a model built with this MFS can have.

Returns:

Maximum number of clusters

setMaxNumberOfClusters

public void setMaxNumberOfClusters(int maxNum)
                            throws InvalidArgumentException

Sets maximum number of clusters a model built with this MFS can have.

Parameters:

maxNum - Maximum number of clusters

Throws:

InvalidArgumentException - when maxNum > 1,000,000 or maxNum < 1.

InvalidArgumentException

getUnpreparedActiveAttributes

public MiningAttribute[] getUnpreparedActiveAttributes()

Returns the array of unbinned active attributes in this MFS.

Returns:

The array of unbinned active attributes.

getUnpreparedActiveNumericAttributes

public MiningAttribute[] getUnpreparedActiveNumericAttributes()

Returns the list of unbinned active numeric attributes in this MFS.

Returns:

The list of unbinned active numeric attributes.

getActiveAttributes

public MiningAttribute[] getActiveAttributes()

Returns the list of active attributes in this MFS.

Returns:

The list of active attributes.

create

public static ClusteringFunctionSettings create(Connection dmsConn,
MiningAlgorithmSettings algorithm,
PhysicalDataSpecification pds,
DataPreparationStatus dpStatus,
                                                int numberOfClusters,
                                                java.lang.String[] categoricalMiningAttributes,
                                                java.lang.String[] numericMiningAttributes,
                                                java.lang.String[] intMiningAttributes)
                                                                          throws java.sql.SQLException,
InvalidArgumentException,
ODMException

This method is a utility function allowing user to create and populate ClusteringFunctionSettings in one step. NOTE: Target attribute data must be integer or string. Method does not validate that the input atTargetAttributeType is correct.

Parameters:

dmsConn - server connection

algorithm - mining algorithm

pds - PhysicalDataSpecification

dpStatus - DataPreparationStatus, indicates if the data should be binned or not

numberOfClusters - Maximum number of clusters

categoricalMiningAttributes - array of names of categorical mining attributes

numericMiningAttributes - array of names of numeric mining attributes

Returns:

ClusteringFunctionSettings created object

Throws:

ODMException - when the settings object cannot be opened

SQLException - when the settings meta data cannot be retrieved

InvalidArgumentException -

• when numberOfClusters > 1,000,000 or numberOfClusters < 1,
• when dmsConn is null,
• when algorithm is null,
• when pds is null,
• when dpStatus is null, or
• when categoricalMiningAttributes is null for KMeans.

java.sql.SQLException

InvalidArgumentException

validate

public void validate()
              throws MiningObjectException

Validates the correctness of this function settings.

Throws:

MiningObjectException - when this function settings is not valid.