de.lmu.ifi.dbs.elki.algorithm.itemsetmining

Class Eclat

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<FrequentItemsetsResult>

de.lmu.ifi.dbs.elki.algorithm.itemsetmining.AbstractFrequentItemsetAlgorithm

de.lmu.ifi.dbs.elki.algorithm.itemsetmining.Eclat

All Implemented Interfaces:

Algorithm

@Reference(authors="M. J. Zaki, S. Parthasarathy, M. Ogihara, W. Li",
           title="New Algorithms for Fast Discovery of Association Rules",
           booktitle="Proc. 3rd ACM SIGKDD \'97 Int. Conf. on Knowledge Discovery and Data Mining",
           url="http://www.aaai.org/Library/KDD/1997/kdd97-060.php",
           bibkey="DBLP:conf/kdd/ZakiPOL97")
public class Eclat
extends AbstractFrequentItemsetAlgorithm

Eclat is a depth-first discovery algorithm for mining frequent itemsets.

Eclat discovers frequent itemsets by first transforming the data into a (sparse) column-oriented form, then performing a depth-first traversal of the prefix lattice, stopping traversal when the minimum support is no longer satisfied.

This implementation is the basic algorithm only, and does not use diffsets. Columns are represented using a sparse representation, which theoretically is beneficial when the density is less than 1/31. This corresponds roughly to a minimum support of 3% for 1-itemsets. When searching for itemsets with a larger minimum support, it may be desirable to use a dense bitset representation instead and/or implement an automatic switching technique!

Performance of this implementation is probably surpassed with a low-level C implementation based on SIMD bitset operations as long as support of an itemset is high, which are not easily accessible in Java.

Reference:

New Algorithms for Fast Discovery of Association Rules
M. J. Zaki, S. Parthasarathy, M. Ogihara, W. Li
Proc. 3rd ACM SIGKDD '97 Int. Conf. on Knowledge Discovery and Data Mining

Since:

0.7.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Eclat.Parameterizer Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
private static Logging	LOG Class logger.
private static java.lang.String	STAT Prefix for statistics.

Fields inherited from class de.lmu.ifi.dbs.elki.algorithm.itemsetmining.AbstractFrequentItemsetAlgorithm

maxlength, minlength

Fields inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

ALGORITHM_ID

Constructor Summary

Constructors

Constructor and Description
Eclat(double minsupp, int minlength, int maxlength) Constructor.

Method Summary

Modifier and Type	Method and Description
private DBIDs[]	buildIndex(Relation<BitVector> relation, int dim, int minsupp)
private void	extractItemsets(DBIDs[] idx, int start, int minsupp, java.util.List<Itemset> solution)
private void	extractItemsets(DBIDs iset, DBIDs[] idx, int[] buf, int depth, int start, int minsupp, java.util.List<Itemset> solution)
TypeInformation[]	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.
protected Logging	getLogger() Get the (STATIC) logger for this class.
private DBIDs	mergeJoin(DBIDs first, DBIDs second)
FrequentItemsetsResult	run(Database db, Relation<BitVector> relation) Run the Eclat algorithm

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.itemsetmining.AbstractFrequentItemsetAlgorithm

getMinimumSupport

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

run

Methods inherited from class java.lang.Object

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

Field Detail

LOG

private static final Logging LOG

Class logger.

STAT

private static final java.lang.String STAT

Prefix for statistics.

Constructor Detail

Eclat

public Eclat(double minsupp,
             int minlength,
             int maxlength)

Constructor.

Parameters:

minsupp - Minimum support

minlength - Minimum length

maxlength - Maximum length

Method Detail

run

public FrequentItemsetsResult run(Database db,
                                  Relation<BitVector> relation)

Run the Eclat algorithm

Parameters:

db - Database to process

relation - Bit vector relation

Returns:

Frequent patterns found

extractItemsets

private void extractItemsets(DBIDs[] idx,
                             int start,
                             int minsupp,
                             java.util.List<Itemset> solution)

extractItemsets

private void extractItemsets(DBIDs iset,
                             DBIDs[] idx,
                             int[] buf,
                             int depth,
                             int start,
                             int minsupp,
                             java.util.List<Itemset> solution)

mergeJoin

private DBIDs mergeJoin(DBIDs first,
                        DBIDs second)

buildIndex

private DBIDs[] buildIndex(Relation<BitVector> relation,
                           int dim,
                           int minsupp)

getInputTypeRestriction

public TypeInformation[] getInputTypeRestriction()

Description copied from class: AbstractAlgorithm

Get the input type restriction used for negotiating the data query.

Specified by:

getInputTypeRestriction in interface Algorithm

Specified by:

getInputTypeRestriction in class AbstractAlgorithm<FrequentItemsetsResult>

Returns:

Type restriction

getLogger

protected Logging getLogger()

Description copied from class: AbstractAlgorithm

Get the (STATIC) logger for this class.

Specified by:

getLogger in class AbstractAlgorithm<FrequentItemsetsResult>

Returns:

the static logger