ca.pfv.spmf.algorithms.frequentpatterns.apriori_inverse

Class AlgoAprioriInverse

java.lang.Object

ca.pfv.spmf.algorithms.frequentpatterns.apriori_inverse.AlgoAprioriInverse

public class AlgoAprioriInverse
extends java.lang.Object

This is an implementation of the AprioriInverse algorithm as described by :

Yun Sing Koh, Nathan Rountree: Finding Sporadic Rules Using Apriori-Inverse. PAKDD 2005: 97-106

and the original Apriori article:

Agrawal R, Srikant R. "Fast Algorithms for Mining Association Rules", VLDB. Sep 12-15 1994, Chile, 487-99,

The AprioriInverse algorithm finds all perfectly rare itemsets. A perfectly rare itemset is an itemset such that all its subsets are rare. It is very similar to the original Apriori algorithm. The main difference is that it uses a threshold "maxsup" and that frequent items of size 1 need to have a support not higher than maxsup.

This is an optimized version that saves the result to a file or keep it into memory if no output path is provided by the user to the runAlgorithm() method.

See Also:

Itemset, Itemsets

Constructor Summary

Constructors

Constructor and Description
AlgoAprioriInverse() Default constructor

Method Summary

Modifier and Type	Method and Description
int	getDatabaseSize() Return the number of transactions in the last database read by the algorithm.
void	printStats() Print statistics about the algorithm execution to System.out.
Itemsets	runAlgorithm(double minsup, double maxsup, java.lang.String input, java.lang.String output) Method to run the algorithm

Methods inherited from class java.lang.Object

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

Constructor Detail

AlgoAprioriInverse

public AlgoAprioriInverse()

Default constructor

Method Detail

runAlgorithm

public Itemsets runAlgorithm(double minsup,
                             double maxsup,
                             java.lang.String input,
                             java.lang.String output)
                      throws java.io.IOException

Method to run the algorithm

Parameters:

minsup - a minimum support value as a percentage

maxsup - a maximum support value as a percentage

input - the path of an input file

output - the path of an input if the result should be saved to a file. If null, the result will be kept into memory and this method will return the result.

Throws:

java.io.IOException - exception if error while writing or reading the input/output file

getDatabaseSize

public int getDatabaseSize()

Return the number of transactions in the last database read by the algorithm.

Returns:

the number of transactions

printStats

public void printStats()

Print statistics about the algorithm execution to System.out.