Documentation of 'ca.pfv.spmf.algorithms.frequentpatterns.apriori_HT.AlgoAprioriHT' Java class
AlgoAprioriHT
ca.pfv.spmf.algorithms.frequentpatterns.apriori_HT

Class AlgoAprioriHT



  • public class AlgoAprioriHT
    extends java.lang.Object
    This is an implementation of the Apriori algorithm that use an Hash-tree to store candidates, to calculate their support and to generate candidates efficiently. The other version (AlgoApriori) do not use a hash tree.

    The Apriori algorithm is described in :

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

    The Apriori algorithm finds all the frequents itemsets and their support in a transaction database.

    Note that the performance of the Hash-Tree version of Apriori depends on the BRANCH COUNT value in the class ItemsetHashTree. In my test, I have used a value of 30 because it seems to provide the best results. But other values could also be used (see Agrawal & Srikant for details). To change the branch_count variable, see the ItemsetHashTree class (default is 30).
    See Also:
    Itemset, AbstractOrderedItemsetsAdapter, ItemsetHashTree
    • Constructor Summary

      Constructors 
      Constructor and Description
      AlgoAprioriHT()
      Default constructor
    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method and Description
      void printStats()
      Method to print statistics about the execution of the algorithm.
      void runAlgorithm(double minsup, java.lang.String input, java.lang.String output, int hash_tree_branch_count)
      Run the Apriori-HT algorithm
      • Methods inherited from class java.lang.Object

        equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • AlgoAprioriHT

        public AlgoAprioriHT()
        Default constructor
    • Method Detail

      • runAlgorithm

        public void runAlgorithm(double minsup,
                                 java.lang.String input,
                                 java.lang.String output,
                                 int hash_tree_branch_count)
                          throws java.io.IOException
        Run the Apriori-HT algorithm
        Parameters:
        minsup - the minimum support threshold
        input - path to the input file
        output - path to save the result to an output file
        hash_tree_branch_count - the number of child nodes for each node in the hash tree
        Throws:
        java.io.IOException - if an error while reading/writing files
      • printStats

        public void printStats()
        Method to print statistics about the execution of the algorithm.

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.