/// <p>
/// Creates a possibly weighted {@link AbstractSimilarity}.
/// </p>
public AbstractSimilarity(IDataModel dataModel, Weighting weighting, bool centerData) : base(dataModel) {
this.weighted = weighting == Weighting.WEIGHTED;
this.centerData = centerData;
this.cachedNumItems = dataModel.GetNumItems();
this.cachedNumUsers = dataModel.GetNumUsers();
this.refreshHelper = new RefreshHelper( () => {
cachedNumItems = dataModel.GetNumItems();
cachedNumUsers = dataModel.GetNumUsers();
}
);
}
/// <p>
/// Creates a possibly weighted {@link AbstractSimilarity}.
/// </p>
public AbstractSimilarity(IDataModel dataModel, Weighting weighting, bool centerData) : base(dataModel)
{
this.weighted = weighting == Weighting.WEIGHTED;
this.centerData = centerData;
this.cachedNumItems = dataModel.GetNumItems();
this.cachedNumUsers = dataModel.GetNumUsers();
this.refreshHelper = new RefreshHelper(() => {
cachedNumItems = dataModel.GetNumItems();
cachedNumUsers = dataModel.GetNumUsers();
}
);
}
protected void initialize()
{
RandomWrapper random = RandomUtils.getRandom();
userVectors = new double[dataModel.GetNumUsers()][];
itemVectors = new double[dataModel.GetNumItems()][];
double globalAverage = getAveragePreference();
for (int userIndex = 0; userIndex < userVectors.Length; userIndex++)
{
userVectors[userIndex] = new double[rank];
userVectors[userIndex][0] = globalAverage;
userVectors[userIndex][USER_BIAS_INDEX] = 0; // will store user bias
userVectors[userIndex][ITEM_BIAS_INDEX] = 1; // corresponding item feature contains item bias
for (int feature = FEATURE_OFFSET; feature < rank; feature++)
{
userVectors[userIndex][feature] = random.nextGaussian() * NOISE;
}
}
for (int itemIndex = 0; itemIndex < itemVectors.Length; itemIndex++)
{
itemVectors[itemIndex] = new double[rank];
itemVectors[itemIndex][0] = 1; // corresponding user feature contains global average
itemVectors[itemIndex][USER_BIAS_INDEX] = 1; // corresponding user feature contains user bias
itemVectors[itemIndex][ITEM_BIAS_INDEX] = 0; // will store item bias
for (int feature = FEATURE_OFFSET; feature < rank; feature++)
{
itemVectors[itemIndex][feature] = random.nextGaussian() * NOISE;
}
}
}
public Features(ALSWRFactorizer factorizer)
{
dataModel = factorizer.dataModel;
numFeatures = factorizer.numFeatures;
var random = RandomUtils.getRandom();
M = new double[dataModel.GetNumItems()][]; //numFeatures
var itemIDsIterator = dataModel.GetItemIDs();
while (itemIDsIterator.MoveNext())
{
long itemID = itemIDsIterator.Current;
int itemIDIndex = factorizer.itemIndex(itemID);
M[itemIDIndex] = new double[numFeatures];
M[itemIDIndex][0] = averateRating(itemID);
for (int feature = 1; feature < numFeatures; feature++)
{
M[itemIDIndex][feature] = random.nextDouble() * 0.1;
}
}
U = new double[dataModel.GetNumUsers()][]; //numFeatures
for (int i = 0; i < U.Length; i++)
{
U[i] = new double[numFeatures];
}
}
public AveragingPreferenceInferrer(IDataModel dataModel)
{
this.dataModel = dataModel;
IRetriever <long, float> retriever = new PrefRetriever(this);
averagePreferenceValue = new Cache <long, float>(retriever, dataModel.GetNumUsers());
Refresh(null);
}
public CachingUserNeighborhood(IUserNeighborhood neighborhood, IDataModel dataModel)
{
//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);
}
public override double ItemSimilarity(long itemID1, long itemID2)
{
IDataModel dataModel = getDataModel();
long preferring1 = dataModel.GetNumUsersWithPreferenceFor(itemID1);
long numUsers = dataModel.GetNumUsers();
return(doItemSimilarity(itemID1, itemID2, preferring1, numUsers));
}
/// 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(IDataModel dataModel)
{
FastByIDMap <FastIDSet> data = new FastByIDMap <FastIDSet>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
data.Put(userID, dataModel.GetItemIDsFromUser(userID));
}
return(data);
}
/// <summary>Exports the simple user IDs and preferences in the data model.</summary>
/// <returns>a <see cref="FastByIDMap"/> mapping user IDs to <see cref="IPreferenceArray"/>s representing that user's preferences</returns>
public static FastByIDMap <IPreferenceArray> ToDataMap(IDataModel dataModel)
{
FastByIDMap <IPreferenceArray> data = new FastByIDMap <IPreferenceArray>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
data.Put(userID, dataModel.GetPreferencesFromUser(userID));
}
return(data);
}
/// @param n neighborhood size; capped at the number of users in the data model
/// @param minSimilarity minimal similarity required for neighbors
/// @param samplingRate percentage of users to consider when building neighborhood -- decrease to trade quality for
/// performance
/// @throws IllegalArgumentException
/// if {@code n < 1} or samplingRate is NaN or not in (0,1], or userSimilarity or dataModel are
/// {@code null}
public NearestNUserNeighborhood(int n,
double minSimilarity,
IUserSimilarity userSimilarity,
IDataModel dataModel,
double samplingRate)
: base(userSimilarity, dataModel, samplingRate)
{
//Preconditions.checkArgument(n >= 1, "n must be at least 1");
int numUsers = dataModel.GetNumUsers();
this.n = n > numUsers ? numUsers : n;
this.minSimilarity = minSimilarity;
}
public override double[] ItemSimilarities(long itemID1, long[] itemID2s)
{
IDataModel dataModel = getDataModel();
long preferring1 = dataModel.GetNumUsersWithPreferenceFor(itemID1);
long numUsers = dataModel.GetNumUsers();
int length = itemID2s.Length;
double[] result = new double[length];
for (int i = 0; i < length; i++)
{
result[i] = doItemSimilarity(itemID1, itemID2s[i], preferring1, numUsers);
}
return(result);
}
public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage)
{
//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 <IPreferenceArray> trainingPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
FastByIDMap <IPreferenceArray> testPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage)
{
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return(result);
}
protected virtual void prepareTraining()
{
RandomWrapper random = RandomUtils.getRandom();
userVectors = new double[dataModel.GetNumUsers()][]; //numFeatures
itemVectors = new double[dataModel.GetNumItems()][];
double globalAverage = getAveragePreference();
for (int userIndex = 0; userIndex < userVectors.Length; userIndex++)
{
userVectors[userIndex] = new double[numFeatures];
userVectors[userIndex][0] = globalAverage;
userVectors[userIndex][USER_BIAS_INDEX] = 0; // will store user bias
userVectors[userIndex][ITEM_BIAS_INDEX] = 1; // corresponding item feature contains item bias
for (int feature = FEATURE_OFFSET; feature < numFeatures; feature++)
{
userVectors[userIndex][feature] = random.nextGaussian() * randomNoise;
}
}
for (int itemIndex = 0; itemIndex < itemVectors.Length; itemIndex++)
{
itemVectors[itemIndex] = new double[numFeatures];
itemVectors[itemIndex][0] = 1; // corresponding user feature contains global average
itemVectors[itemIndex][USER_BIAS_INDEX] = 1; // corresponding user feature contains user bias
itemVectors[itemIndex][ITEM_BIAS_INDEX] = 0; // will store item bias
for (int feature = FEATURE_OFFSET; feature < numFeatures; feature++)
{
itemVectors[itemIndex][feature] = random.nextGaussian() * randomNoise;
}
}
cachePreferences();
shufflePreferences();
}
public static LoadStatistics runLoad(IRecommender recommender, int howMany)
{
IDataModel dataModel = recommender.GetDataModel();
int numUsers = dataModel.GetNumUsers();
double sampleRate = 1000.0 / numUsers;
var userSampler =
SamplinglongPrimitiveIterator.MaybeWrapIterator(dataModel.GetUserIDs(), sampleRate);
if (userSampler.MoveNext())
{
recommender.Recommend(userSampler.Current, howMany); // Warm up
}
var callables = new List <Action>();
while (userSampler.MoveNext())
{
callables.Add(new LoadCallable(recommender, userSampler.Current).call);
}
AtomicInteger noEstimateCounter = new AtomicInteger();
IRunningAverageAndStdDev timing = new FullRunningAverageAndStdDev();
AbstractDifferenceRecommenderEvaluator.execute(callables, noEstimateCounter, timing);
return(new LoadStatistics(timing));
}
/// <summary>Exports the simple user IDs and preferences in the data model.</summary>
/// <returns>a <see cref="FastByIDMap"/> mapping user IDs to <see cref="IPreferenceArray"/>s representing that user's preferences</returns>
public static FastByIDMap<IPreferenceArray> ToDataMap(IDataModel dataModel) {
FastByIDMap<IPreferenceArray> data = new FastByIDMap<IPreferenceArray>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
data.Put(userID, dataModel.GetPreferencesFromUser(userID));
}
return data;
}
public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage) {
//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<IPreferenceArray> trainingPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
FastByIDMap<IPreferenceArray> testPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage) {
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return result;
}
/// Creates this on top of the given {@link UserSimilarity}.
/// The cache is sized according to properties of the given {@link DataModel}.
public CachingUserSimilarity(IUserSimilarity similarity, IDataModel dataModel) : this(similarity, dataModel.GetNumUsers())
{
}
public IRStatistics Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
IDRescorer rescorer,
int at,
double relevanceThreshold,
double evaluationPercentage)
{
//Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null");
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(at >= 1, "at must be at least 1");
//Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 < evaluationPercentage <= 1.0");
int numItems = dataModel.GetNumItems();
IRunningAverage precision = new FullRunningAverage();
IRunningAverage recall = new FullRunningAverage();
IRunningAverage fallOut = new FullRunningAverage();
IRunningAverage nDCG = new FullRunningAverage();
int numUsersRecommendedFor = 0;
int numUsersWithRecommendations = 0;
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() >= evaluationPercentage)
{
// Skipped
continue;
}
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
// List some most-preferred items that would count as (most) "relevant" results
double theRelevanceThreshold = Double.IsNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold;
FastIDSet relevantItemIDs = dataSplitter.GetRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel);
int numRelevantItems = relevantItemIDs.Count();
if (numRelevantItems <= 0)
{
continue;
}
FastByIDMap <IPreferenceArray> trainingUsers = new FastByIDMap <IPreferenceArray>(dataModel.GetNumUsers());
var it2 = dataModel.GetUserIDs();
while (it2.MoveNext())
{
dataSplitter.ProcessOtherUser(userID, relevantItemIDs, trainingUsers, it2.Current, dataModel);
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingUsers)
: dataModelBuilder.BuildDataModel(trainingUsers);
try {
trainingModel.GetPreferencesFromUser(userID);
} catch (NoSuchUserException nsee) {
continue; // Oops we excluded all prefs for the user -- just move on
}
int size = numRelevantItems + trainingModel.GetItemIDsFromUser(userID).Count();
if (size < 2 * at)
{
// Really not enough prefs to meaningfully evaluate this user
continue;
}
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
int intersectionSize = 0;
var recommendedItems = recommender.Recommend(userID, at, rescorer);
foreach (IRecommendedItem recommendedItem in recommendedItems)
{
if (relevantItemIDs.Contains(recommendedItem.GetItemID()))
{
intersectionSize++;
}
}
int numRecommendedItems = recommendedItems.Count;
// Precision
if (numRecommendedItems > 0)
{
precision.AddDatum((double)intersectionSize / (double)numRecommendedItems);
}
// Recall
recall.AddDatum((double)intersectionSize / (double)numRelevantItems);
// Fall-out
if (numRelevantItems < size)
{
fallOut.AddDatum((double)(numRecommendedItems - intersectionSize)
/ (double)(numItems - numRelevantItems));
}
// nDCG
// In computing, assume relevant IDs have relevance 1 and others 0
double cumulativeGain = 0.0;
double idealizedGain = 0.0;
for (int i = 0; i < numRecommendedItems; i++)
{
IRecommendedItem item = recommendedItems[i];
double discount = 1.0 / log2(i + 2.0); // Classical formulation says log(i+1), but i is 0-based here
if (relevantItemIDs.Contains(item.GetItemID()))
{
cumulativeGain += discount;
}
// otherwise we're multiplying discount by relevance 0 so it doesn't do anything
// Ideally results would be ordered with all relevant ones first, so this theoretical
// ideal list starts with number of relevant items equal to the total number of relevant items
if (i < numRelevantItems)
{
idealizedGain += discount;
}
}
if (idealizedGain > 0.0)
{
nDCG.AddDatum(cumulativeGain / idealizedGain);
}
// Reach
numUsersRecommendedFor++;
if (numRecommendedItems > 0)
{
numUsersWithRecommendations++;
}
stopWatch.Stop();
log.Info("Evaluated with user {} in {}ms", userID, stopWatch.ElapsedMilliseconds);
log.Info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}",
precision.GetAverage(), recall.GetAverage(), fallOut.GetAverage(), nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor);
}
return(new IRStatisticsImpl(
precision.GetAverage(),
recall.GetAverage(),
fallOut.GetAverage(),
nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor));
}
public Features(ALSWRFactorizer factorizer) {
dataModel = factorizer.dataModel;
numFeatures = factorizer.numFeatures;
var random = RandomUtils.getRandom();
M = new double[dataModel.GetNumItems()][]; //numFeatures
var itemIDsIterator = dataModel.GetItemIDs();
while (itemIDsIterator.MoveNext()) {
long itemID = itemIDsIterator.Current;
int itemIDIndex = factorizer.itemIndex(itemID);
M[itemIDIndex] = new double[numFeatures];
M[itemIDIndex][0] = averateRating(itemID);
for (int feature = 1; feature < numFeatures; feature++) {
M[itemIDIndex][feature] = random.nextDouble() * 0.1;
}
}
U = new double[dataModel.GetNumUsers()][]; //numFeatures
for (int i=0; i<U.Length; i++)
U[i] = new double[numFeatures];
}
public virtual int GetNumUsers()
{
return(_delegate.GetNumUsers() + (tempPrefs == null ? 0 : 1));
}
private void buildMappings()
{
userIDMapping = createIDMapping(dataModel.GetNumUsers(), dataModel.GetUserIDs());
itemIDMapping = createIDMapping(dataModel.GetNumItems(), dataModel.GetItemIDs());
}
/// 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(IDataModel dataModel) {
FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
data.Put(userID, dataModel.GetItemIDsFromUser(userID));
}
return data;
}
public IRStatistics Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
IDRescorer rescorer,
int at,
double relevanceThreshold,
double evaluationPercentage) {
//Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null");
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(at >= 1, "at must be at least 1");
//Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 < evaluationPercentage <= 1.0");
int numItems = dataModel.GetNumItems();
IRunningAverage precision = new FullRunningAverage();
IRunningAverage recall = new FullRunningAverage();
IRunningAverage fallOut = new FullRunningAverage();
IRunningAverage nDCG = new FullRunningAverage();
int numUsersRecommendedFor = 0;
int numUsersWithRecommendations = 0;
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
if (random.nextDouble() >= evaluationPercentage) {
// Skipped
continue;
}
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
// List some most-preferred items that would count as (most) "relevant" results
double theRelevanceThreshold = Double.IsNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold;
FastIDSet relevantItemIDs = dataSplitter.GetRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel);
int numRelevantItems = relevantItemIDs.Count();
if (numRelevantItems <= 0) {
continue;
}
FastByIDMap<IPreferenceArray> trainingUsers = new FastByIDMap<IPreferenceArray>(dataModel.GetNumUsers());
var it2 = dataModel.GetUserIDs();
while (it2.MoveNext()) {
dataSplitter.ProcessOtherUser(userID, relevantItemIDs, trainingUsers, it2.Current, dataModel);
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingUsers)
: dataModelBuilder.BuildDataModel(trainingUsers);
try {
trainingModel.GetPreferencesFromUser(userID);
} catch (NoSuchUserException nsee) {
continue; // Oops we excluded all prefs for the user -- just move on
}
int size = numRelevantItems + trainingModel.GetItemIDsFromUser(userID).Count();
if (size < 2 * at) {
// Really not enough prefs to meaningfully evaluate this user
continue;
}
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
int intersectionSize = 0;
var recommendedItems = recommender.Recommend(userID, at, rescorer);
foreach (IRecommendedItem recommendedItem in recommendedItems) {
if (relevantItemIDs.Contains(recommendedItem.GetItemID())) {
intersectionSize++;
}
}
int numRecommendedItems = recommendedItems.Count;
// Precision
if (numRecommendedItems > 0) {
precision.AddDatum((double) intersectionSize / (double) numRecommendedItems);
}
// Recall
recall.AddDatum((double) intersectionSize / (double) numRelevantItems);
// Fall-out
if (numRelevantItems < size) {
fallOut.AddDatum((double) (numRecommendedItems - intersectionSize)
/ (double) (numItems - numRelevantItems));
}
// nDCG
// In computing, assume relevant IDs have relevance 1 and others 0
double cumulativeGain = 0.0;
double idealizedGain = 0.0;
for (int i = 0; i < numRecommendedItems; i++) {
IRecommendedItem item = recommendedItems[i];
double discount = 1.0 / log2(i + 2.0); // Classical formulation says log(i+1), but i is 0-based here
if (relevantItemIDs.Contains(item.GetItemID())) {
cumulativeGain += discount;
}
// otherwise we're multiplying discount by relevance 0 so it doesn't do anything
// Ideally results would be ordered with all relevant ones first, so this theoretical
// ideal list starts with number of relevant items equal to the total number of relevant items
if (i < numRelevantItems) {
idealizedGain += discount;
}
}
if (idealizedGain > 0.0) {
nDCG.AddDatum(cumulativeGain / idealizedGain);
}
// Reach
numUsersRecommendedFor++;
if (numRecommendedItems > 0) {
numUsersWithRecommendations++;
}
stopWatch.Stop();
log.Info("Evaluated with user {} in {}ms", userID, stopWatch.ElapsedMilliseconds);
log.Info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}",
precision.GetAverage(), recall.GetAverage(), fallOut.GetAverage(), nDCG.GetAverage(),
(double) numUsersWithRecommendations / (double) numUsersRecommendedFor);
}
return new IRStatisticsImpl(
precision.GetAverage(),
recall.GetAverage(),
fallOut.GetAverage(),
nDCG.GetAverage(),
(double) numUsersWithRecommendations / (double) numUsersRecommendedFor);
}
public override Factorization Factorize()
{
log.Info("starting to compute the factorization...");
Features features = new Features(this);
/// feature maps necessary for solving for implicit feedback
IDictionary <int, double[]> userY = null;
IDictionary <int, double[]> itemY = null;
if (usesImplicitFeedback)
{
userY = userFeaturesMapping(dataModel.GetUserIDs(), dataModel.GetNumUsers(), features.getU());
itemY = itemFeaturesMapping(dataModel.GetItemIDs(), dataModel.GetNumItems(), features.getM());
}
IList <Task> tasks;
for (int iteration = 0; iteration < numIterations; iteration++)
{
log.Info("iteration {0}", iteration);
/// fix M - compute U
tasks = new List <Task>();
var userIDsIterator = dataModel.GetUserIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, itemY) : null;
while (userIDsIterator.MoveNext())
{
long userID = userIDsIterator.Current;
var itemIDsFromUser = dataModel.GetItemIDsFromUser(userID).GetEnumerator();
IPreferenceArray userPrefs = dataModel.GetPreferencesFromUser(userID);
tasks.Add(Task.Factory.StartNew(() => {
List <double[]> featureVectors = new List <double[]>();
while (itemIDsFromUser.MoveNext())
{
long itemID = itemIDsFromUser.Current;
featureVectors.Add(features.getItemFeatureColumn(itemIndex(itemID)));
}
var userFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseUserRatingVector(userPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(userPrefs), lambda, numFeatures);
features.setFeatureColumnInU(userIndex(userID), userFeatures);
}
));
}
} finally {
// queue.shutdown();
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumUsers());
} catch (AggregateException e) {
log.Warn("Error when computing user features", e);
throw e;
}
}
/// fix U - compute M
//queue = createQueue();
tasks = new List <Task>();
var itemIDsIterator = dataModel.GetItemIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, userY) : null;
while (itemIDsIterator.MoveNext())
{
long itemID = itemIDsIterator.Current;
IPreferenceArray itemPrefs = dataModel.GetPreferencesForItem(itemID);
tasks.Add(Task.Factory.StartNew(() => {
var featureVectors = new List <double[]>();
foreach (IPreference pref in itemPrefs)
{
long userID = pref.GetUserID();
featureVectors.Add(features.getUserFeatureColumn(userIndex(userID)));
}
var itemFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseItemRatingVector(itemPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(itemPrefs), lambda, numFeatures);
features.setFeatureColumnInM(itemIndex(itemID), itemFeatures);
}));
}
} finally {
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumItems());
//queue.awaitTermination(dataModel.getNumItems(), TimeUnit.SECONDS);
} catch (AggregateException e) {
log.Warn("Error when computing item features", e);
throw e;
}
}
}
log.Info("finished computation of the factorization...");
return(createFactorization(features.getU(), features.getM()));
}
public void testGetNumUsers()
{
Assert.AreEqual(4, model.GetNumUsers());
}
public override int GetNumUsers()
{
return(_delegate.GetNumUsers());
}
