Oracle Data Mining Java API Reference
10g Release 1 (10.1)

B12276-01

oracle.dmt.odm.settings.function
Class FeatureExtractionFunctionSettings

java.lang.Object
  |
  +--oracle.dmt.odm.MiningObject
        |
        +--oracle.dmt.odm.LocatableObject
              |
              +--oracle.dmt.odm.settings.function.MiningFunctionSettings
                    |
                    +--oracle.dmt.odm.settings.function.FeatureExtractionFunctionSettings
All Implemented Interfaces:
java.io.Serializable

public class FeatureExtractionFunctionSettings
extends MiningFunctionSettings

FeatureExtractionFunctionSettings describes settings for Feature Extraction functions. An instance of FeatureExtractionFunctionSettings describes the settings necessary to build a FetaureExtraction model by using a Non Negative Matrix Factorization algorithm. It contains m_numberofFeatures . The specified value of an m_numberofFeatures indicates the number of features resulting from the dimesnionality reduction.

See Also:
Serialized Form

Constructor Summary
FeatureExtractionFunctionSettings(LogicalDataSpecification lds, DataUsageSpecification dus, MiningAlgorithmSettings algorithm)
          Creates an instance of FeatureExtractionFunctionSettings object.

 

Method Summary
static FeatureExtractionFunctionSettings create(Connection dmsConn, MiningAlgorithmSettings algorithm, PhysicalDataSpecification pds, DataPreparationStatus dpStatus, java.lang.Integer numberofFeatures)
          This method is a utility function allowing user to create and populate FeatureExtractionFunctionSettings in one step.
 MiningAttribute[] getActiveAttributes()
          Returns the list of active attributes in this MFS.
 MiningAttribute[] getUnpreparedActiveAttributes()
          Returns the list of unbinned active attributes in this MFS.
 void setNumberOfFeatures(java.lang.Integer numberofFeatures)
          Sets number of features for the NMF model.
 void validate()
          Validates the correctness of these 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

FeatureExtractionFunctionSettings

public FeatureExtractionFunctionSettings(LogicalDataSpecification lds,
DataUsageSpecification dus,
MiningAlgorithmSettings algorithm)
                                  throws InvalidArgumentException
Creates an instance of FeatureExtractionFunctionSettings object.
Parameters:
lds - An instance of LogicalDataSpecification that specifies the logical representation of the input data used for model building
dus - An instance of DataUsageSpecification that defines how the logical data is to be used for model building
algorithm - algorithm settings
Throws:
InvalidArgumentException -
Method Detail

setNumberOfFeatures

public void setNumberOfFeatures(java.lang.Integer numberofFeatures)
                         throws InvalidArgumentException
Sets number of features for the NMF model. This number should not exceed the number of attributs or cases in the dataset.
Parameters:
numberofFeatures - number of features, if it is null then it is ignored
Throws:
InvalidArgumentException - if numberofFeatures < 1
InvalidArgumentException

create

public static FeatureExtractionFunctionSettings create(Connection dmsConn,
MiningAlgorithmSettings algorithm,
PhysicalDataSpecification pds,
DataPreparationStatus dpStatus,
                                                       java.lang.Integer numberofFeatures)
                                                                                 throws java.sql.SQLException,
InvalidArgumentException,
MiningObjectException,
ODMException
This method is a utility function allowing user to create and populate FeatureExtractionFunctionSettings in one step.
Parameters:
dmsConn - server connection
algorithm - mining algorithm settings
pds - PhysicalDataSpecification
dpStatus - DataPreparationStatus, indicates if the data should be binned or not
numberofFeatures - Desired number of features, ignored if it is null
Returns:
FeatureExtractionFunctionSettings created object
Throws:
MiningObjectException - if the settings object cannot be retrieved
SQLException - if the settings meta data cannot be retrieved
InvalidArgumentException -
  • if numberofFeatures < 1
  • if dmsConn is null
  • if algorithm is null
  • if pds is null
  • if dpStatus is null
java.sql.SQLException
InvalidArgumentException
MiningObjectException
ODMException

getActiveAttributes

public MiningAttribute[] getActiveAttributes()
Returns the list of active attributes in this MFS.
Returns:
MiningAttribute[]

getUnpreparedActiveAttributes

public MiningAttribute[] getUnpreparedActiveAttributes()
Returns the list of unbinned active attributes in this MFS.
Returns:
MiningAttribute[]

validate

public void validate()
              throws MiningObjectException
Validates the correctness of these function settings.
Throws:
MiningObjectException -
  • If the algorithm is not nonNegativeMatrixFactorization
  • If number of features was specified incorrectly to be less than 1
MiningObjectException

Copyright © 2003 Oracle Corporation. All Rights Reserved.