public CachingUserNeighborhood(UserNeighborhood neighborhood, DataModel dataModel)
throws TasteException {
Preconditions.checkArgument(neighborhood != null, "neighborhood is null");
this.neighborhood = neighborhood;
int maxCacheSize = dataModel.getNumUsers(); // just a dumb heuristic for sizing
this.neighborhoodCache =
new Cache<Long, long[]>(new NeighborhoodRetriever(neighborhood), maxCacheSize);
}
/**
* Exports the simple user IDs and associated item IDs in the data model.
*
* @return a {@link FastByIDMap} mapping user IDs to {@link FastIDSet}s representing that user's
* associated items
*/
public static FastByIDMap<FastIDSet> toDataMap(DataModel dataModel) throws TasteException {
FastByIDMap<FastIDSet> data = new FastByIDMap<>(dataModel.getNumUsers());
LongPrimitiveIterator it = dataModel.getUserIDs();
while (it.hasNext()) {
long userID = it.nextLong();
data.put(userID, dataModel.getItemIDsFromUser(userID));
}
return data;
}
@Override
public double itemSimilarity(long itemID1, long itemID2) throws TasteException {
int preferring1and2 = dataModel.getNumUsersWithPreferenceFor(itemID1, itemID2);
if (preferring1and2 == 0) {
return Double.NaN;
}
int preferring1 = dataModel.getNumUsersWithPreferenceFor(itemID1);
int preferring2 = dataModel.getNumUsersWithPreferenceFor(itemID2);
int numUsers = dataModel.getNumUsers();
double logLikelihood =
twoLogLambda(
preferring1and2, preferring1 - preferring1and2, preferring2, numUsers - preferring2);
return 1.0 - 1.0 / (1.0 + logLikelihood);
}
/** Creates a possibly weighted AbstractSimilarity. */
AbstractSimilarity(final DataModel dataModel, Weighting weighting, boolean centerData)
throws TasteException {
if (dataModel == null) {
throw new IllegalArgumentException("dataModel is null");
}
this.dataModel = dataModel;
this.weighted = weighting == Weighting.WEIGHTED;
this.centerData = centerData;
this.cachedNumItems = dataModel.getNumItems();
this.cachedNumUsers = dataModel.getNumUsers();
this.refreshHelper =
new RefreshHelper(
new Callable<Object>() {
@Override
public Object call() throws TasteException {
cachedNumItems = dataModel.getNumItems();
cachedNumUsers = dataModel.getNumUsers();
return null;
}
});
this.refreshHelper.addDependency(this.dataModel);
}
@Override
public double evaluate(
RecommenderBuilder recommenderBuilder,
DataModelBuilder dataModelBuilder,
DataModel dataModel,
double trainingPercentage,
double evaluationPercentage)
throws TasteException {
Preconditions.checkNotNull(recommenderBuilder);
Preconditions.checkNotNull(dataModel);
Preconditions.checkArgument(
trainingPercentage >= 0.0 && trainingPercentage <= 1.0,
"Invalid trainingPercentage: "
+ trainingPercentage
+ ". Must be: 0.0 <= trainingPercentage <= 1.0");
Preconditions.checkArgument(
evaluationPercentage >= 0.0 && evaluationPercentage <= 1.0,
"Invalid evaluationPercentage: "
+ evaluationPercentage
+ ". Must be: 0.0 <= evaluationPercentage <= 1.0");
log.info("Beginning evaluation using {} of {}", trainingPercentage, dataModel);
int numUsers = dataModel.getNumUsers();
FastByIDMap<PreferenceArray> trainingPrefs =
new FastByIDMap<PreferenceArray>(1 + (int) (evaluationPercentage * numUsers));
FastByIDMap<PreferenceArray> testPrefs =
new FastByIDMap<PreferenceArray>(1 + (int) (evaluationPercentage * numUsers));
totalOfTrainingRatingsFromSource = 0;
totalOfTrainingRatingsFromTargetWithContext = 0;
totalOfTrainingRatingsFromTargetWithoutContext = 0;
totalOfTestRatings = 0;
LongPrimitiveIterator it = dataModel.getUserIDs();
while (it.hasNext()) {
long userID = it.nextLong();
if (random.nextDouble() < evaluationPercentage) {
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
// System.out.println("Training (Source, TargetWithoutContext, TargetWithContext):
// "+totalOfTrainingRatingsFromSource+"/"+totalOfTrainingRatingsFromTargetWithoutContext+"/"+totalOfTrainingRatingsFromTargetWithContext);
// int totalTraining =
// (totalOfTrainingRatingsFromSource+totalOfTrainingRatingsFromTargetWithContext+totalOfTrainingRatingsFromTargetWithoutContext);
// System.out.println("Training/Test: "+totalTraining+"/"+totalOfTestRatings);
DataModel newDataModel =
dataModel instanceof ContextualDataModel
? new ContextualDataModel(trainingPrefs)
: new GenericDataModel(trainingPrefs);
DataModel trainingModel =
dataModelBuilder == null ? newDataModel : dataModelBuilder.buildDataModel(trainingPrefs);
Recommender recommender = recommenderBuilder.buildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.info("Evaluation result: {}", result);
return result;
}