📄 associationrulesalgorithm.java
字号:
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/**
* Title: XELOPES Data Mining Library
* Description: The XELOPES library is an open platform-independent and data-source-independent library for Embedded Data Mining.
* Copyright: Copyright (c) 2002 Prudential Systems Software GmbH
* Company: ZSoft (www.zsoft.ru), Prudsys (www.prudsys.com)
* @author Valentine Stepanenko (valentine.stepanenko@zsoft.ru)
* @version 1.0
*/
package com.prudsys.pdm.Models.AssociationRules;
import java.util.Date;
import java.util.Enumeration;
import java.util.Hashtable;
import java.util.Vector;
import com.prudsys.pdm.Core.CategoricalAttribute;
import com.prudsys.pdm.Core.Category;
import com.prudsys.pdm.Core.CategoryHierarchy;
import com.prudsys.pdm.Core.MiningAlgorithm;
import com.prudsys.pdm.Core.MiningException;
import com.prudsys.pdm.Core.MiningModel;
import com.prudsys.pdm.Core.MiningSettings;
import com.prudsys.pdm.Utils.IntHashtable;
import com.prudsys.pdm.Utils.IntVector;
/**
* A class representing an Association Rules algorithm. Each implementation
* should to extend this class and override only methods:
* {@link #runAlgorithm() runAlgorithm()},
* {@link #getAssociationRules()() getAssociationRules()} and
* {@link #getLargeItemSets() getLargeItemSets()}
*
* Example (How to use):
* <pre>
* AssociationRulesSettings miningSettings = ...;
* MiningInputStream miningInputStream = ...;
* ApplicationInputSpecification applicationInputSpecification = ...;
* AprioriOptimizedAlgorithm algorithm = new AprioriOptimizedAlgorithm();
* algorithm.setMiningSettings( miningSettings );
* algorithm.setApplicationInputSpecification( applicationInputSpecification );
* algorithm.setMiningInputStream( miningInputStream );
* AssociationRulesMiningModel model = algorithm.buildModel();<br>
* </pre>
* @author <a href="mailto:vlntn@inbox.ru">Valentine Stepanenko</a>
* @version 1.0
* @see com.prudsys.pdm.Core.MiningAlgorithm
* @see com.prudsys.pdm.Models.AssociationRules.Algorithms.Apriori.AprioriOptimizedAlgorithm
* @see com.prudsys.pdm.Models.AssociationRules.Algorithms.Apriori.AprioriHybridAlgorithm
* @see com.prudsys.pdm.Models.AssociationRules.Algorithms.Apriori.AprioriTidAlgorithm
*/
public abstract class AssociationRulesAlgorithm extends MiningAlgorithm
{
// -----------------------------------------------------------------------
// Constants of taxonomy handling
// -----------------------------------------------------------------------
/** If taxonomy: remove nothing from rules. */
public static final int TAX_REMOVE_NOTHING_FROM_RULE = 0;
/** If taxonomy: remove items from conlusion which are parents of premise items. */
public static final int TAX_REMOVE_ANCEST_FROM_RULE = 1;
/** If taxonomy: remove ancestors and all parents within premise and conclusion. */
public static final int TAX_REMOVE_ANCEST_AND_PARENTS_FROM_RULE = 2;
// -----------------------------------------------------------------------
// Variables declarations
// -----------------------------------------------------------------------
/** Item ID attribute. */
protected CategoricalAttribute categoryItemId;
/** Transaction ID attribute. */
protected CategoricalAttribute categoryTransactId;
/** Minimum support. */
protected double minimumSupport;
/** Minimum confidence. */
protected double minimumConfidence;
/** Use taxonomy for creating rules. */
protected boolean useTaxonomy = false;
/** Taxonomy object for item ID attribute. */
protected CategoryHierarchy itemIdTax = null;
/** Defines pruning type of rules when taxonomy is used. */
private int pruneRuleTaxType = TAX_REMOVE_ANCEST_FROM_RULE;
/** Export all transaction IDs into PMML. */
protected boolean exportTransactIds = true;
/** Export names of item ID and transaction ID into PMML. */
private int exportTransactItemNames = AssociationRulesMiningModel.EXPORT_PMML_NAME_TYPE_XELOPES;
// -----------------------------------------------------------------------
// Constructor
// -----------------------------------------------------------------------
/**
* Empty constructor.
*/
public AssociationRulesAlgorithm()
{
}
// -----------------------------------------------------------------------
// Getter and setter methods
// -----------------------------------------------------------------------
/**
* Set use taxonomy of itemId attribute.
*
* @param useTaxonomy true if use, else false
*/
public void setUseTaxonomy(boolean useTaxonomy)
{
this.useTaxonomy = useTaxonomy;
}
/**
* Is taxonomy included?
*
* @return true if taxonomy used, otherwise false
*/
public boolean isUseTaxonomy()
{
return useTaxonomy;
}
/**
* Returns type of how to prune rules if taxonomy is used.
*
* @return type of rule pruning
*/
public int getPruneRuleTaxType() {
return pruneRuleTaxType;
}
/**
* Sets type of how to prune rules if taxonomy is used.
*
* @param pruneRuleTaxType new type of rule pruning
*/
public void setPruneRuleTaxType(int pruneRuleTaxType) {
this.pruneRuleTaxType = pruneRuleTaxType;
}
/**
* Write all transaction IDs into PMML (default: true)?
*
* @return true if write all transaction IDs into PMML, otherwise not
*/
public boolean isExportTransactIds()
{
return exportTransactIds;
}
/**
* Set export all transaction IDs into PMML (default: true).
*
* @param exportTransactIds true if export, otherwise false
*/
public void setExportTransactIds(boolean exportTransactIds)
{
this.exportTransactIds = exportTransactIds;
}
/**
* Returns type how item and transaction IDs are handled in PMML.
*
* @return PMML export type of item and transaction IDs
*/
public int getExportTransactItemNames()
{
return exportTransactItemNames;
}
/**
* Sets type how item and transaction IDs are handled in PMML.
* This is because of an incompleteness in PMML 20: item and
* transaction ID are not specially denoted in the mining schema.
* This makes PMML20 association models not really applicable
* to new data (except you use agreed names for the IDs). <p>
*
* There are three ways to handle this problem:
* 1. Do nothing: conform with PMML 2.0 but lose of functionality,
* 2. Use XELOPES PMML Extension: to AssociationModel two new attributes
* 'itemIdName' (itemId) and 'transactIdName' (transactionId) are added,
* 3. Use PMML 2.1 solution: transaction ID is marked as 'group'
* in mining schema, so the other active attribute is the item ID
* (currently not implemented in XELOPES).
*
* @param exportTransactItemNames PMML export type of item and transaction IDs
*/
public void setExportTransactItemNames(int exportTransactItemNames)
{
this.exportTransactItemNames = exportTransactItemNames;
}
/**
* Creates an instance of the association rules settings class that is required
* to run the algorithm. The mining settings are assigned through the
* setMiningSettings method.
*
* @return new instance of the association rules settings class of the algorithm
*/
public MiningSettings createMiningSettings() {
return new AssociationRulesSettings();
}
/**
* Set association rules settings.
*
* @param miningSettings instance of AssociationRulesSettings
* @exception IllegalArgumentException mining settings not association rules settings
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -