ca.pfv.spmf.algorithms.sequentialpatterns.fournier2008_seqdim.multidimensionalsequentialpatterns
Class AlgoSeqDim
- java.lang.Object
-
- ca.pfv.spmf.algorithms.sequentialpatterns.fournier2008_seqdim.multidimensionalsequentialpatterns.AlgoSeqDim
-
public class AlgoSeqDim extends java.lang.ObjectImplementation of the SeqDim algorithm for multi-dimensional sequential pattern mining proposed by Pinto et al (2001).
SeqDIM is a generic algorithm that can be used in theory with any combination of sequential pattern mining algorithm and MDPattern mining algorithm.
In SPMF, the sequential pattern mining algorithm must be chosen from:
AlgoPrefixspanMDSPM/AlgoBIDEPlus/AlgoFournierViger08 algorithms
In SPMF, the MD-Pattern mining algorithm is AlgoDim and it offers to choose between Charm and AprioriClose (see the AlgoDim class for details).
-
-
Constructor Summary
Constructors Constructor and Description AlgoSeqDim()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method and Description voidprintStatistics(int databaseSize)Print statistics about the algorithm executionMDSequencesrunAlgorithm(MDSequenceDatabase database, AbstractAlgoPrefixSpan algoPrefixSpan, AlgoDim algoDim, boolean mineClosedPatterns, java.lang.String output)Run the algorithm
-
-
-
Method Detail
-
runAlgorithm
public MDSequences runAlgorithm(MDSequenceDatabase database, AbstractAlgoPrefixSpan algoPrefixSpan, AlgoDim algoDim, boolean mineClosedPatterns, java.lang.String output) throws java.io.IOException
Run the algorithm- Parameters:
database- and MDSequence databasealgoPrefixSpan- a prefixpsan based algorithm (BIDE, PrefixSpan or Fournier08)algoDim- an instance of the DIM algorithmmineClosedPatterns- if true, only closed mdsequential pattern will be returnedoutput- a path for writting the result to an output file- Returns:
- the set of MD-sequential patterns found
- Throws:
java.io.IOException- exception if error writing to file
-
printStatistics
public void printStatistics(int databaseSize)
Print statistics about the algorithm execution- Parameters:
databaseSize- the number of MDsequences in the original database.
-
-
DMelt 3.0 © DataMelt by jWork.ORG