weka.classifiers.lazy.kstar
Class KStarCache

java.lang.Object
  |
  +--weka.classifiers.lazy.kstar.KStarCache
All Implemented Interfaces:
java.io.Serializable

public class KStarCache
extends java.lang.Object
implements java.io.Serializable

A class representing the caching system used to keep track of each attribute value and its corresponding scale factor or stop parameter.

Version:
$Revision 1.0 $
Author:
Len Trigg (len@reeltwo.com), Abdelaziz Mahoui (am14@cs.waikato.ac.nz)
See Also:
Serialized Form

Nested Class Summary
 class KStarCache.CacheTable
          A custom hashtable class to support the caching system.
 class KStarCache.TableEntry
          Hashtable collision list.
 
Constructor Summary
KStarCache()
           
 
Method Summary
 boolean containsKey(double key)
          Checks if the specified key maps with an entry in the cache table
 KStarCache.TableEntry getCacheValues(double key)
          Returns the values in the cache mapped by the specified key
 void store(double key, double value, double pmiss)
          Stores the specified values in the cahce table for easy retrieval.
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

KStarCache

public KStarCache()
Method Detail

store

public void store(double key,
                  double value,
                  double pmiss)
Stores the specified values in the cahce table for easy retrieval.

Parameters:
key - attribute value used key to lookup the cache table.
value - cache parameter: attribute scale/stop parameter.
pmiss - cache parameter: transformation probability to attribute with missing value.

containsKey

public boolean containsKey(double key)
Checks if the specified key maps with an entry in the cache table

Parameters:
key - the key to map with an entry in the hashtable.

getCacheValues

public KStarCache.TableEntry getCacheValues(double key)
Returns the values in the cache mapped by the specified key

Parameters:
key - the key used to retrieve the table entry.


Copyright (c) 2003 David Lindsay, Computer Learning Research Centre, Dept. Computer Science, Royal Holloway, University of London