com.pervasive.datarush.analytics.arm

Class PMMLAssociationModel

java.lang.Object

com.pervasive.datarush.analytics.pmml.PMMLModel

com.pervasive.datarush.analytics.arm.PMMLAssociationModel

public class PMMLAssociationModel
extends PMMLModel

Captures the information required to build a PMML Association model. An association model requires a list of items with mappings to item names from the input. It also contains frequent item sets and association rules.

The frequent item sets contain references to items contained in the item list. The association rules contain references to the defined item sets.

Due to the way the model is defined, the model should be built in this order:

• Item list
• Frequent item sets
• Association rules

Nested Class Summary

Nested classes/interfaces inherited from class com.pervasive.datarush.analytics.pmml.PMMLModel

PMMLModel.MiningFunction

Constructor Summary

Constructors

Constructor and Description
PMMLAssociationModel(Document document) Construct a PMMLAssociationObject from the given PMML represented as an XML DOM.
PMMLAssociationModel(PMMLModelSpec spec) Construct a PMMLAssociationObject from the given specification.

Method Summary

Modifier and Type	Method and Description
void	addAssociationRule(AssociationRule rule) Add an association rule to the model.
void	addItem(Item item) Add an item to the model.
void	addItemSet(ItemSet itemSet) Add an item set to the model.
protected void	buildModelElement(Element modelElem) Subclasses must implement this method to fill-in the contents of the model element.
String	getAlgorithmName() Get the algorithm name.
double	getAvgItemsPerTxn() Get the average items per transaction value.
Map<Integer,String>	getItemLabelMap() Create a mapping from item identifier to item label of the items contained in this model.
Map<Integer,String>	getItemNameMap() Create a mapping from item identifier to item name of the items contained in this model.
List<Item>	getItems() Return the list of items contained in the model.
List<ItemSet>	getItemSets() Return the list of frequent item sets contained in the model.
int	getMaxItemsPerTxn() Get the maximum items per transaction value.
double	getMinConfidence() Get the minimum confidence setting.
double	getMinSupport() Get the minimum support setting.
protected String	getModelElementName() Return the element name of the primary model element associated with this PMML
List<AssociationRule>	getRules() Return the list of association rules contained in the model.
long	getTxnCount() Get the transaction count value.
protected void	parseModelElement(Element modelElem) Parse the given model element into the respective model object.
void	setAlgorithmName(String algorithmName) Set the name of the algorithm used to generate the association model.
void	setAvgItemsPerTxn(double avgItemsPerTxn) Set the average items per transaction value.
void	setMaxItemsPerTxn(int maxItemsPerTxn) Set the maximum items per transaction value.
void	setMinConfidence(double minConfidence) Set the minimum confidence used to generate the rules within this association model.
void	setMinSupport(double minSupport) Set the minimum support setting.
void	setTxnCount(long txnCount) Set the transaction count value.

Methods inherited from class com.pervasive.datarush.analytics.pmml.PMMLModel

findModelElement, getAnnotationText, getModelExplanation, getModelSpec, getVersion, parse, setAnnotationText, setModelExplanation, setVersion, toPMML

Methods inherited from class java.lang.Object

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

Constructor Detail

PMMLAssociationModel

public PMMLAssociationModel(PMMLModelSpec spec)

Construct a PMMLAssociationObject from the given specification.

Parameters:

spec - input specification

PMMLAssociationModel

public PMMLAssociationModel(Document document)

Construct a PMMLAssociationObject from the given PMML represented as an XML DOM.

Parameters:

document - input PMML model

Method Detail

getTxnCount

public long getTxnCount()

Get the transaction count value.

Returns:

transaction count

setTxnCount

public void setTxnCount(long txnCount)

Set the transaction count value.

Parameters:

txnCount - transaction count

getMinSupport

public double getMinSupport()

Get the minimum support setting.

Returns:

minimum support

setMinSupport

public void setMinSupport(double minSupport)

Set the minimum support setting.

Parameters:

minSupport - minimum support

getMaxItemsPerTxn

public int getMaxItemsPerTxn()

Get the maximum items per transaction value.

Returns:

maximum items per transaction

setMaxItemsPerTxn

public void setMaxItemsPerTxn(int maxItemsPerTxn)

Set the maximum items per transaction value.

Parameters:

maxItemsPerTxn - maximum items per transaction

getAvgItemsPerTxn

public double getAvgItemsPerTxn()

Get the average items per transaction value.

Returns:

average items per transaction

setAvgItemsPerTxn

public void setAvgItemsPerTxn(double avgItemsPerTxn)

Set the average items per transaction value.

Parameters:

avgItemsPerTxn - average items per transaction

getAlgorithmName

public String getAlgorithmName()

Get the algorithm name.

Returns:

algorithm name

getMinConfidence

public double getMinConfidence()

Get the minimum confidence setting.

Returns:

minimum confidence

setMinConfidence

public void setMinConfidence(double minConfidence)

Set the minimum confidence used to generate the rules within this association model.

Parameters:

minConfidence - minimum confidence value

setAlgorithmName

public void setAlgorithmName(String algorithmName)

Set the name of the algorithm used to generate the association model. This is an opaque value within the model but useful to help determine how the model was created.

Parameters:

algorithmName - the name of the algorithm used

addItem

public final void addItem(Item item)

Add an item to the model. The given name will be mapped to the given identifier.

Parameters:

item - the item to add to the model

getItems

public List<Item> getItems()

Return the list of items contained in the model.

Returns:

frequent items

getItemNameMap

public Map<Integer,String> getItemNameMap()

Create a mapping from item identifier to item name of the items contained in this model.

Returns:

mapping from item identifier to item name

getItemLabelMap

public Map<Integer,String> getItemLabelMap()

Create a mapping from item identifier to item label of the items contained in this model.

Returns:

mapping from item identifier to item label

getItemSets

public List<ItemSet> getItemSets()

Return the list of frequent item sets contained in the model.

Returns:

frequent item sets

getRules

public List<AssociationRule> getRules()

Return the list of association rules contained in the model.

Returns:

association rules

addItemSet

public void addItemSet(ItemSet itemSet)

Add an item set to the model. Items contained within the set must be contained within the list of items provided. The set includes a support value.

Parameters:

itemSet - the item set to add to the model

addAssociationRule

public void addAssociationRule(AssociationRule rule)

Add an association rule to the model. The antecedent and consequent of the rule are item sets. The item sets must already be contained within the model.

Parameters:

rule - an association rule to add to the model

getModelElementName

protected String getModelElementName()

Description copied from class: PMMLModel

Return the element name of the primary model element associated with this PMML

Specified by:

getModelElementName in class PMMLModel

Returns:

the element name of the primary model element

buildModelElement

protected void buildModelElement(Element modelElem)

Description copied from class: PMMLModel

Subclasses must implement this method to fill-in the contents of the model element. At the time this method is invoked, the element will have its name and MiningSchema sub-element populated.

Specified by:

buildModelElement in class PMMLModel

Parameters:

modelElem - the model element

parseModelElement

protected void parseModelElement(Element modelElem)

Description copied from class: PMMLModel

Parse the given model element into the respective model object.

Specified by:

parseModelElement in class PMMLModel

Parameters:

modelElem - root element of model object