public double UserSimilarity(long userID1, long userID2) { IDataModel dataModel = getDataModel(); FastIDSet xPrefs = dataModel.GetItemIDsFromUser(userID1); FastIDSet yPrefs = dataModel.GetItemIDsFromUser(userID2); int xPrefsSize = xPrefs.Count(); int yPrefsSize = yPrefs.Count(); if (xPrefsSize == 0 && yPrefsSize == 0) { return(Double.NaN); } if (xPrefsSize == 0 || yPrefsSize == 0) { return(0.0); } int intersectionSize = xPrefsSize < yPrefsSize?yPrefs.IntersectionSize(xPrefs) : xPrefs.IntersectionSize(yPrefs); if (intersectionSize == 0) { return(Double.NaN); } int unionSize = xPrefsSize + yPrefsSize - intersectionSize; return((double)intersectionSize / (double)unionSize); }
public double UserSimilarity(long userID1, long userID2) { IDataModel dataModel = getDataModel(); FastIDSet prefs1 = dataModel.GetItemIDsFromUser(userID1); FastIDSet prefs2 = dataModel.GetItemIDsFromUser(userID2); int prefs1Size = prefs1.Count(); int prefs2Size = prefs2.Count(); int intersectionSize = prefs1Size < prefs2Size?prefs2.IntersectionSize(prefs1) : prefs1.IntersectionSize(prefs2); return(doSimilarity(prefs1Size, prefs2Size, intersectionSize)); }
protected FastIDSet getAllOtherItems(long[] theNeighborhood, long theUserID) { IDataModel dataModel = GetDataModel(); FastIDSet possibleItemIDs = new FastIDSet(); foreach (long userID in theNeighborhood) { possibleItemIDs.AddAll(dataModel.GetItemIDsFromUser(userID)); } possibleItemIDs.RemoveAll(dataModel.GetItemIDsFromUser(theUserID)); return(possibleItemIDs); }
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) { FastIDSet possibleItemsIDs = new FastIDSet(); foreach (long itemID in preferredItemIDs) { IPreferenceArray itemPreferences = dataModel.GetPreferencesForItem(itemID); int numUsersPreferringItem = itemPreferences.Length(); for (int index = 0; index < numUsersPreferringItem; index++) { possibleItemsIDs.AddAll(dataModel.GetItemIDsFromUser(itemPreferences.GetUserID(index))); } } possibleItemsIDs.RemoveAll(preferredItemIDs); return possibleItemsIDs; }
/// 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 virtual FastIDSet GetItemIDsFromUser(long userID) { if (userID == TEMP_USER_ID) { if (tempPrefs == null) { throw new NoSuchUserException(TEMP_USER_ID); } return(prefItemIDs); } return(_delegate.GetItemIDsFromUser(userID)); }
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) { var preferredItemIDsIterator = ((IEnumerable <long>)preferredItemIDs).GetEnumerator(); if (preferredItemIDs.Length > maxItems) { double samplingRate = (double)maxItems / preferredItemIDs.Length; log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate); preferredItemIDsIterator = new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate); } FastIDSet possibleItemsIDs = new FastIDSet(); while (preferredItemIDsIterator.MoveNext()) { long itemID = preferredItemIDsIterator.Current; IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID); int prefsLength = prefs.Length(); if (prefsLength > maxUsersPerItem) { var sampledPrefs = new FixedSizeSamplingIterator <IPreference>(maxUsersPerItem, prefs.GetEnumerator()); while (sampledPrefs.MoveNext()) { addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID())); } } else { for (int i = 0; i < prefsLength; i++) { addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i))); } } } possibleItemsIDs.RemoveAll(preferredItemIDs); return(possibleItemsIDs); }
public double UserSimilarity(long userID1, long userID2) { IDataModel dataModel = getDataModel(); FastIDSet prefs1 = dataModel.GetItemIDsFromUser(userID1); FastIDSet prefs2 = dataModel.GetItemIDsFromUser(userID2); long prefs1Size = prefs1.Count(); long prefs2Size = prefs2.Count(); long intersectionSize = prefs1Size < prefs2Size?prefs2.IntersectionSize(prefs1) : prefs1.IntersectionSize(prefs2); if (intersectionSize == 0) { return(Double.NaN); } long numItems = dataModel.GetNumItems(); double logLikelihood = LogLikelihood.logLikelihoodRatio(intersectionSize, prefs2Size - intersectionSize, prefs1Size - intersectionSize, numItems - prefs1Size - prefs2Size + intersectionSize); return(1.0 - 1.0 / (1.0 + logLikelihood)); }
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) { FastIDSet possibleItemsIDs = new FastIDSet(); foreach (long itemID in preferredItemIDs) { IPreferenceArray itemPreferences = dataModel.GetPreferencesForItem(itemID); int numUsersPreferringItem = itemPreferences.Length(); for (int index = 0; index < numUsersPreferringItem; index++) { possibleItemsIDs.AddAll(dataModel.GetItemIDsFromUser(itemPreferences.GetUserID(index))); } } possibleItemsIDs.RemoveAll(preferredItemIDs); return(possibleItemsIDs); }
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) { var preferredItemIDsIterator = ((IEnumerable<long>)preferredItemIDs).GetEnumerator(); if (preferredItemIDs.Length > maxItems) { double samplingRate = (double) maxItems / preferredItemIDs.Length; log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate); preferredItemIDsIterator = new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate); } FastIDSet possibleItemsIDs = new FastIDSet(); while (preferredItemIDsIterator.MoveNext()) { long itemID = preferredItemIDsIterator.Current; IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID); int prefsLength = prefs.Length(); if (prefsLength > maxUsersPerItem) { var sampledPrefs = new FixedSizeSamplingIterator<IPreference>(maxUsersPerItem, prefs.GetEnumerator()); while (sampledPrefs.MoveNext()) { addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID())); } } else { for (int i = 0; i < prefsLength; i++) { addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i))); } } } possibleItemsIDs.RemoveAll(preferredItemIDs); return possibleItemsIDs; }
/// 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 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 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 FastIDSet GetItemIDsFromUser(long userID) { return(_delegate.GetItemIDsFromUser(userID)); }