org.apache.mahout.cf.taste.impl.recommender
Class TreeClusteringRecommender2

java.lang.Object
  org.apache.mahout.cf.taste.impl.recommender.AbstractRecommender
      org.apache.mahout.cf.taste.impl.recommender.TreeClusteringRecommender2

All Implemented Interfaces:

Refreshable, ClusteringRecommender, Recommender

public final class TreeClusteringRecommender2
extends AbstractRecommender
implements ClusteringRecommender

A Recommender that clusters users, then determines the clusters' top recommendations. This implementation builds clusters by repeatedly merging clusters until only a certain number remain, meaning that each cluster is sort of a tree of other clusters.

This Recommender therefore has a few properties to note:

• For all users in a cluster, recommendations will be the same
• estimatePreference(long, long) may well return Double.NaN; it does so when asked to estimate preference for an item for which no preference is expressed in the users in the cluster.

This is an experimental implementation which tries to gain a lot of speed at the cost of accuracy in building clusters, compared to TreeClusteringRecommender. It will sometimes cluster two other clusters together that may not be the exact closest two clusters in existence. This may not affect the recommendation quality much, but it potentially speeds up the clustering process dramatically.

Constructor Summary

TreeClusteringRecommender2(DataModel dataModel, ClusterSimilarity clusterSimilarity, double clusteringThreshold)

TreeClusteringRecommender2(DataModel dataModel, ClusterSimilarity clusterSimilarity, int numClusters)

Method Summary

float	estimatePreference(long userID, long itemID)
FastIDSet	getCluster(long userID) Returns the cluster of users to which the given user, denoted by user ID, belongs.
FastIDSet[]	getClusters() Returns all clusters of users.
List<RecommendedItem>	recommend(long userID, int howMany, IDRescorer rescorer)
void	refresh(Collection<Refreshable> alreadyRefreshed) Triggers "refresh" -- whatever that means -- of the implementation.
String	toString()

Methods inherited from class org.apache.mahout.cf.taste.impl.recommender.AbstractRecommender

getAllOtherItems, getDataModel, getDefaultCandidateItemsStrategy, recommend, removePreference, setPreference

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.mahout.cf.taste.recommender.Recommender

getDataModel, recommend, removePreference, setPreference

Constructor Detail

TreeClusteringRecommender2

public TreeClusteringRecommender2(DataModel dataModel,
                                  ClusterSimilarity clusterSimilarity,
                                  int numClusters)
                           throws TasteException

Parameters:

dataModel - DataModel which provides users

clusterSimilarity - ClusterSimilarity used to compute cluster similarity

numClusters - desired number of clusters to create

Throws:

IllegalArgumentException - if arguments are null, or numClusters is less than 2

TasteException

TreeClusteringRecommender2

public TreeClusteringRecommender2(DataModel dataModel,
                                  ClusterSimilarity clusterSimilarity,
                                  double clusteringThreshold)
                           throws TasteException

Parameters:

dataModel - DataModel which provides users

clusterSimilarity - ClusterSimilarity used to compute cluster similarity

clusteringThreshold - clustering similarity threshold; clusters will be aggregated into larger clusters until the next two nearest clusters' similarity drops below this threshold

Throws:

IllegalArgumentException - if arguments are null, or clusteringThreshold is Double.NaN

TasteException

Method Detail

recommend

public List<RecommendedItem> recommend(long userID,
                                       int howMany,
                                       IDRescorer rescorer)
                                throws TasteException

Specified by:

recommend in interface Recommender

Parameters:

userID - user for which recommendations are to be computed

howMany - desired number of recommendations

rescorer - rescoring function to apply before final list of recommendations is determined

Returns:

List of recommended RecommendedItems, ordered from most strongly recommend to least

Throws:

TasteException - if an error occurs while accessing the DataModel

estimatePreference

public float estimatePreference(long userID,
                                long itemID)
                         throws TasteException

Specified by:

estimatePreference in interface Recommender

Parameters:

userID - user ID whose preference is to be estimated

itemID - item ID to estimate preference for

Returns:

an estimated preference if the user has not expressed a preference for the item, or else the user's actual preference for the item. If a preference cannot be estimated, returns Double.NaN

Throws:

TasteException - if an error occurs while accessing the DataModel

getCluster

public FastIDSet getCluster(long userID)
                     throws TasteException

Description copied from interface: ClusteringRecommender

Returns the cluster of users to which the given user, denoted by user ID, belongs.

Specified by:

getCluster in interface ClusteringRecommender

Parameters:

userID - user ID for which to find a cluster

Returns:

FastIDSet of IDs of users in the requested user's cluster

Throws:

TasteException - if an error occurs while accessing the DataModel

getClusters

public FastIDSet[] getClusters()
                        throws TasteException

Description copied from interface: ClusteringRecommender

Returns all clusters of users.

Specified by:

getClusters in interface ClusteringRecommender

Returns:

array of FastIDSets of user IDs

Throws:

TasteException - if an error occurs while accessing the DataModel

refresh

public void refresh(Collection<Refreshable> alreadyRefreshed)

Description copied from interface: Refreshable

Triggers "refresh" -- whatever that means -- of the implementation. The general contract is that any should always leave itself in a consistent, operational state, and that the refresh atomically updates internal state from old to new.

Specified by:

refresh in interface Refreshable

Parameters:

alreadyRefreshed - s that are known to have already been refreshed as a result of an initial call to a method on some object. This ensure that objects in a refresh dependency graph aren't refreshed twice needlessly.

toString

public String toString()

Overrides:

toString in class Object