/**
* @param dataModel
* {@link DataModel} which provides users
* @param clusterSimilarity
* {@link ClusterSimilarity} used to compute cluster similarity
* @param numClusters
* desired number of clusters to create
* @throws IllegalArgumentException
* if arguments are {@code null}, or {@code numClusters} is less than 2
*/
public TreeClusteringRecommender2(DataModel dataModel, ClusterSimilarity clusterSimilarity, int numClusters)
: base(dataModel)
{
if (numClusters < 2)
{
throw new Exception("numClusters must be at least 2");
}
//Preconditions.checkArgument(numClusters >= 2, "numClusters must be at least 2");
this.clusterSimilarity = clusterSimilarity;//Preconditions.checkNotNull(clusterSimilarity);
this.numClusters = numClusters;
this.clusteringThreshold = Double.NaN;
this.clusteringByThreshold = false;
this.refreshHelper = new RefreshHelper(buildClusters);
refreshHelper.addDependency(dataModel);
refreshHelper.addDependency(clusterSimilarity);
buildClusters();
}
/**
* @param dataModel
* {@link DataModel} which provides users
* @param clusterSimilarity
* {@link ClusterSimilarity} used to compute cluster
* similarity
* @param 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 {@code null}, or {@code clusteringThreshold} is {@link Double#NaN}
*/
public TreeClusteringRecommender2(DataModel dataModel,
ClusterSimilarity clusterSimilarity,
double clusteringThreshold)
: base(dataModel)
{
// Preconditions.checkArgument(!Double.isNaN(clusteringThreshold), "clusteringThreshold must not be NaN");
if (Double.IsNaN(clusteringThreshold))
{
throw new Exception("clusteringThreshold must not be NaN");
}
this.clusterSimilarity = clusterSimilarity; //Preconditions.checkNotNull(clusterSimilarity);
this.numClusters = int.MinValue; // Integer.MIN_VALUE;
this.clusteringThreshold = clusteringThreshold;
this.clusteringByThreshold = true;
this.refreshHelper = new RefreshHelper(buildClusters);
refreshHelper.addDependency(dataModel);
refreshHelper.addDependency(clusterSimilarity);
buildClusters();
}
/**
* @param dataModel
* {@link DataModel} which provides users
* @param clusterSimilarity
* {@link ClusterSimilarity} used to compute cluster similarity
* @param clusteringThreshold
* clustering similarity threshold; clusters will be aggregated into larger clusters until the next
* two nearest clusters' similarity drops below this threshold
* @param samplingRate
* percentage of all cluster-cluster pairs to consider when finding next-most-similar clusters.
* Decreasing this value from 1.0 can increase performance at the cost of accuracy
* @throws IllegalArgumentException
* if arguments are {@code null}, or {@code clusteringThreshold} is {@link Double#NaN},
* or samplingRate is {@link Double#NaN} or nonpositive or greater than 1.0
*/
public TreeClusteringRecommender(DataModel dataModel,
ClusterSimilarity clusterSimilarity,
double clusteringThreshold,
double samplingRate)
: base(dataModel)
{
//Preconditions.checkArgument(!Double.IsNaN(clusteringThreshold), "clusteringThreshold must not be NaN");
//Preconditions.checkArgument(samplingRate > 0.0 && samplingRate <= 1.0, "samplingRate is invalid: %f", samplingRate);
random = RandomUtils.getRandom();
this.clusterSimilarity = clusterSimilarity; //Preconditions.checkNotNull(clusterSimilarity);
this.numClusters = int.MinValue; //Integer.MIN_VALUE;
this.clusteringThreshold = clusteringThreshold;
this.clusteringByThreshold = true;
this.samplingRate = samplingRate;
this.refreshHelper = new RefreshHelper(buildClusters);
refreshHelper.addDependency(dataModel);
refreshHelper.addDependency(clusterSimilarity);
buildClusters();
}
/**
* @param dataModel
* {@link DataModel} which provdes users
* @param clusterSimilarity
* {@link ClusterSimilarity} used to compute cluster similarity
* @param numClusters
* desired number of clusters to create
* @param samplingRate
* percentage of all cluster-cluster pairs to consider when finding next-most-similar clusters.
* Decreasing this value from 1.0 can increase performance at the cost of accuracy
* @throws IllegalArgumentException
* if arguments are {@code null}, or {@code numClusters} is less than 2, or samplingRate
* is {@link Double#NaN} or nonpositive or greater than 1.0
*/
public TreeClusteringRecommender(DataModel dataModel,
ClusterSimilarity clusterSimilarity,
int numClusters,
double samplingRate)
: base(dataModel)
{
//Preconditions.checkArgument(numClusters >= 2, "numClusters must be at least 2");
//Preconditions.checkArgument(samplingRate > 0.0 && samplingRate <= 1.0,
// "samplingRate is invalid: %f", samplingRate);
random = RandomUtils.getRandom();
this.clusterSimilarity = clusterSimilarity;//Preconditions.checkNotNull(clusterSimilarity);
this.numClusters = numClusters;
this.clusteringThreshold = Double.NaN;
this.clusteringByThreshold = false;
this.samplingRate = samplingRate;
this.refreshHelper = new RefreshHelper(buildClusters);
refreshHelper.addDependency(dataModel);
refreshHelper.addDependency(clusterSimilarity);
buildClusters();
}
public MemoryDiffStorage(DataModel dataModel,
Weighting stdDevWeighted,
long maxEntries)
{
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(dataModel.getNumItems() >= 1, "dataModel has no items");
//Preconditions.checkArgument(maxEntries > 0L, "maxEntries must be positive");
this.dataModel = dataModel;
this.stdDevWeighted = stdDevWeighted == Weighting.WEIGHTED;
this.maxEntries = maxEntries;
this.averageDiffs = new FastByIDMap <FastByIDMap <RunningAverage> >();
this.averageItemPref = new FastByIDMap <RunningAverage>();
this.buildAverageDiffsLock = new ReaderWriterLockSlim();
this.allRecommendableItemIDs = new FastIDSet(dataModel.getNumItems());
this.refreshHelper = new RefreshHelper(buildAverageDiffs);
refreshHelper.addDependency(dataModel);
buildAverageDiffs();
}