List of usage examples for org.apache.mahout.cf.taste.recommender Recommender recommend
List<RecommendedItem> recommend(long userID, int howMany, IDRescorer rescorer) throws TasteException;
From source file:com.msiiplab.recsys.rwr.GLRecommenderIRStatsEvaluator.java
License:Apache License
public GLIRStatisticsImpl evaluate(RecommenderBuilder recommenderBuilder, List<DataModel> trainingDataModels, List<DataModel> testingDataModels, IDRescorer rescorer, int at, double relevanceThreshold, double evaluationPercentage) throws TasteException { Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null"); Preconditions.checkArgument(trainingDataModels != null, "trainingDataModels is null"); Preconditions.checkArgument(testingDataModels != null, "testingDataModels is null"); Preconditions.checkArgument(testingDataModels.size() == trainingDataModels.size(), "trainingDataModels.size must equals testingDataModels.size"); Preconditions.checkArgument(at >= 1, "at must be at least 1"); Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0, "Invalid evaluationPercentage: %s", evaluationPercentage); // num of train/test pair: num of cross validation folds int numFolds = trainingDataModels.size(); RunningAverage CrossValidationPrecision = new GLRunningAverage(); RunningAverage CrossValidationRPrecision = new GLRunningAverage(); RunningAverage CrossValidationRecall = new GLRunningAverage(); RunningAverage CrossValidationFallOut = new GLRunningAverage(); RunningAverage CrossValidationNDCG = new GLRunningAverage(); RunningAverage CrossValidationRNDCG = new GLRunningAverage();//rating-nDCG RunningAverage CrossValidationReach = new GLRunningAverage(); RunningAverage CrossValidationMacroDOA = new GLRunningAverage(); RunningAverage CrossValidationMicroDOA = new GLRunningAverage(); RunningAverage CrossValidationMacroInnerDOA = new GLRunningAverage(); RunningAverage CrossValidationMicroInnerDOA = new GLRunningAverage(); for (int i_folds = 0; i_folds < numFolds; i_folds++) { log.info("fold {}", i_folds); DataModel trainDataModel = trainingDataModels.get(i_folds); DataModel testDataModel = testingDataModels.get(i_folds); FastIDSet MovieIDs = new FastIDSet(); LongPrimitiveIterator it_train_temp = trainDataModel.getItemIDs(); LongPrimitiveIterator it_test_temp = testDataModel.getItemIDs(); while (it_train_temp.hasNext()) { MovieIDs.add(it_train_temp.nextLong()); }//from ww w. j a va2s . c o m while (it_test_temp.hasNext()) { MovieIDs.add(it_test_temp.nextLong()); } int numTrainItems = trainDataModel.getNumItems(); int numTestItems = testDataModel.getNumItems(); int numItems = numTestItems + numTrainItems; RunningAverage precision = new GLRunningAverage(); RunningAverage rPrecision = new GLRunningAverage(); RunningAverage recall = new GLRunningAverage(); RunningAverage fallOut = new GLRunningAverage(); RunningAverage nDCG = new GLRunningAverage(); RunningAverage rNDCG = new GLRunningAverage(); RunningAverage macroDOA = new GLRunningAverage(); RunningAverage microDOA1 = new GLRunningAverage(); RunningAverage microDOA2 = new GLRunningAverage(); RunningAverage macroInnerDOA = new GLRunningAverage(); RunningAverage microInnerDOA1 = new GLRunningAverage(); RunningAverage microInnerDOA2 = new GLRunningAverage(); int numUsersRecommendedFor = 0; int numUsersWithRecommendations = 0; long start = System.currentTimeMillis(); // Build recommender Recommender recommender = recommenderBuilder.buildRecommender(trainDataModel); LongPrimitiveIterator it_user = testDataModel.getUserIDs(); while (it_user.hasNext()) { long userID = it_user.nextLong(); log.info("user {}", userID); // Use all in testDataModel as relevant FastIDSet learnedItemIDs; FastIDSet relevantItemIDs; try { learnedItemIDs = trainDataModel.getItemIDsFromUser(userID); relevantItemIDs = testDataModel.getItemIDsFromUser(userID); } catch (NoSuchUserException e1) { continue; } // We excluded zero relevant items situation int numRelevantItems = relevantItemIDs.size(); if (numRelevantItems <= 0) { continue; } // We excluded all prefs for the user that has no pref record in // training set try { trainDataModel.getPreferencesFromUser(userID); } catch (NoSuchUserException nsee) { continue; // Oops we excluded all prefs for the user -- just // move on } // Recommend items List<RecommendedItem> recommendedItems = recommender.recommend(userID, at, rescorer); List<RecommendedItem> recommendedItemsAtRelNum = recommender.recommend(userID, numRelevantItems, rescorer); PreferenceArray userPreferences = testDataModel.getPreferencesFromUser(userID); FastByIDMap<Preference> userPreferenceMap = getPrefereceMap(userPreferences); userPreferences.sortByValueReversed(); // relevantItemIDsAtN only consider top N items as relevant items FastIDSet relevantItemIDsAtN = new FastIDSet(); Iterator<Preference> it_pref = userPreferences.iterator(); int num_pref = 0; while (it_pref.hasNext()) { relevantItemIDsAtN.add(it_pref.next().getItemID()); num_pref++; if (num_pref >= at) { break; } } // Compute intersection between recommended items and relevant // items int intersectionSize = 0; int numRecommendedItems = recommendedItems.size(); for (RecommendedItem recommendedItem : recommendedItems) { if (relevantItemIDs.contains(recommendedItem.getItemID())) { intersectionSize++; } } // Precision double prec = 0; if (numRecommendedItems > 0) { prec = (double) intersectionSize / (double) numRecommendedItems; } precision.addDatum(prec); log.info("Precision for user {} is {}", userID, prec); // Recall double rec = (double) intersectionSize / (double) numRelevantItems; recall.addDatum(rec); log.info("Recall for user {} is {}", userID, rec); // R-precision double rprec = 0; int intersectionSizeAtRelNum = 0; int numRecommendedItemsAtRelNum = recommendedItemsAtRelNum.size(); for (RecommendedItem recommendedItem : recommendedItemsAtRelNum) { if (relevantItemIDs.contains(recommendedItem.getItemID())) { intersectionSizeAtRelNum++; } } if (numRecommendedItemsAtRelNum > 0) { rprec = (double) intersectionSizeAtRelNum / (double) numRelevantItems; } rPrecision.addDatum(rprec); log.info("RPrecision for user {} is {}", userID, rprec); double F1 = 0; if (prec + rec > 0) { F1 = 2 * prec * rec / (prec + rec); } log.info("F1 for user {} is {}", userID, F1); // Fall-out double fall = 0; int size = numRelevantItems + trainDataModel.getItemIDsFromUser(userID).size(); if (numRelevantItems < size) { fall = (double) (numRecommendedItems - intersectionSize) / (double) (numItems - numRelevantItems); } fallOut.addDatum(fall); log.info("Fallout for user {} is {}", userID, fall); // nDCG // In computing, assume relevant IDs have relevance ${rating} and others // 0 PreferenceArray userPredictions = getPreferenceArray(recommendedItems, userID); double userNDCG = computeNDCG(userPreferences, userPredictions, relevantItemIDs, userPreferenceMap, at); double userRNDCG = computeRNDCG(userPreferences, userPredictions, relevantItemIDs, userPreferenceMap, at); nDCG.addDatum(userNDCG); rNDCG.addDatum(userRNDCG); log.info("NDCG for user {} is {}", userID, userNDCG); log.info("RNDCG for user {} is {}", userID, userRNDCG); // Reach numUsersRecommendedFor++; if (numRecommendedItems > 0) { numUsersWithRecommendations++; } // DOA // [Siegel and Castellan, 1988] and [Gori and Pucci, 2007] // LongPrimitiveIterator it_movies = MovieIDs.iterator(); LongPrimitiveIterator it_movies = trainDataModel.getItemIDs(); long numNW = 0; long sumCheckOrder = 0; while (it_movies.hasNext()) { long itemID = it_movies.nextLong(); if (!learnedItemIDs.contains(itemID) && !relevantItemIDs.contains(itemID)) { // itemID is in NW_{u_i} numNW++; LongPrimitiveIterator it_test = relevantItemIDs.iterator(); while (it_test.hasNext()) { long testItemID = it_test.nextLong(); float itemPref = 0; float testItemPref = 0; try { itemPref = recommender.estimatePreference(userID, itemID); } catch (NoSuchItemException e) { } try { testItemPref = recommender.estimatePreference(userID, testItemID); } catch (NoSuchItemException e) { } if (itemPref <= testItemPref) { sumCheckOrder++; } } } } if (numNW > 0 && relevantItemIDs.size() > 0) { macroDOA.addDatum((double) sumCheckOrder / (double) (relevantItemIDs.size() * numNW)); microDOA1.addDatum((double) sumCheckOrder); microDOA2.addDatum((double) (relevantItemIDs.size() * numNW)); } // log.info( // "sumCheckOrder / (numNW * numRelevant) = {} / ({} * {})", // sumCheckOrder, numNW, relevantItemIDs.size()); // InnerDOA: only check the agreement of order in test set LongPrimitiveIterator it_test1 = relevantItemIDs.iterator(); long sumCheckInnerOrder = 0; long sumAll = 0; while (it_test1.hasNext()) { long itemID1 = it_test1.nextLong(); LongPrimitiveIterator it_test2 = relevantItemIDs.iterator(); while (it_test2.hasNext()) { long itemID2 = it_test2.nextLong(); if (itemID1 != itemID2) { try { float pref_v1 = testDataModel.getPreferenceValue(userID, itemID1); float pref_v2 = testDataModel.getPreferenceValue(userID, itemID2); float predict_v1 = recommender.estimatePreference(userID, itemID1); float predict_v2 = recommender.estimatePreference(userID, itemID2); if ((pref_v1 >= pref_v2 && predict_v1 >= predict_v2) || (pref_v1 <= pref_v2 && predict_v1 <= predict_v2)) { sumCheckInnerOrder++; } sumAll++; } catch (NoSuchItemException e) { // do nothing, just ignore } } } } if (relevantItemIDs.size() > 1) { macroInnerDOA.addDatum((double) sumCheckInnerOrder / (double) sumAll); microInnerDOA1.addDatum((double) sumCheckInnerOrder); microInnerDOA2.addDatum((double) sumAll); } // log.info( // "sumCheckInnerOrder / (|T| * (|T|-1) ) = {} / ({} * {}) = ", // sumCheckInnerOrder, relevantItemIDs.size(), relevantItemIDs.size()-1); } long end = System.currentTimeMillis(); CrossValidationPrecision.addDatum(precision.getAverage()); CrossValidationRPrecision.addDatum(rPrecision.getAverage()); CrossValidationRecall.addDatum(recall.getAverage()); CrossValidationFallOut.addDatum(fallOut.getAverage()); CrossValidationNDCG.addDatum(nDCG.getAverage()); CrossValidationRNDCG.addDatum(rNDCG.getAverage()); CrossValidationReach.addDatum((double) numUsersWithRecommendations / (double) numUsersRecommendedFor); CrossValidationMacroDOA.addDatum(macroDOA.getAverage()); CrossValidationMicroDOA.addDatum(microDOA1.getAverage() / microDOA2.getAverage()); CrossValidationMacroInnerDOA.addDatum(macroInnerDOA.getAverage()); CrossValidationMicroInnerDOA.addDatum(microInnerDOA1.getAverage() / microInnerDOA2.getAverage()); log.info("Evaluated with training/testing set # {} in {}ms", i_folds, end - start); System.out.printf("Evaluated with training/testing set # %d in %d ms \n", i_folds, end - start); log.info( "Precision/R-Precision/recall/fall-out/nDCG/rNDCG/reach/macroDOA/microDOA/macroInnerDOA/microInnerDOA: {} / {} / {} / {} / {} / {} / {} / {} / {} / {} / {}", precision.getAverage(), rPrecision.getAverage(), recall.getAverage(), fallOut.getAverage(), nDCG.getAverage(), rNDCG.getAverage(), (double) numUsersWithRecommendations / (double) numUsersRecommendedFor, macroDOA.getAverage(), microDOA1.getAverage() / microDOA2.getAverage(), macroInnerDOA.getAverage(), microInnerDOA1.getAverage() / microInnerDOA2.getAverage()); System.out.printf( "Precision/R-Precision/recall/fall-out/nDCG/rNDCG/reach/macroDOA/microDOA/macroInnerDOA/microInnerDOA: %f / %f / %f / %f / %f / %f / %f / %f / %f / %f / %f \n", precision.getAverage(), rPrecision.getAverage(), recall.getAverage(), fallOut.getAverage(), nDCG.getAverage(), rNDCG.getAverage(), (double) numUsersWithRecommendations / (double) numUsersRecommendedFor, macroDOA.getAverage(), microDOA1.getAverage() / microDOA2.getAverage(), macroInnerDOA.getAverage(), microInnerDOA1.getAverage() / microInnerDOA2.getAverage()); } log.info( "Cross Validation Precision/R-Precision/recall/fall-out/nDCG/rNDCG/reach/macroDOA/microDOA: {} / {} / {} / {} / {} / {} / {} / {} / {} / {} / {}", CrossValidationPrecision.getAverage(), CrossValidationRPrecision.getAverage(), CrossValidationRecall.getAverage(), CrossValidationFallOut.getAverage(), CrossValidationNDCG.getAverage(), CrossValidationRNDCG.getAverage(), CrossValidationReach.getAverage(), CrossValidationMacroDOA.getAverage(), CrossValidationMicroDOA.getAverage(), CrossValidationMacroInnerDOA.getAverage(), CrossValidationMicroInnerDOA.getAverage()); System.out.printf( "Cross Validation: \nPrecision/R-Precision/recall/fall-out/nDCG/rNDCG/reach/macroDOA/microDOA: %f / %f / %f / %f / %f / %f / %f / %f / %f / %f / %f\n", CrossValidationPrecision.getAverage(), CrossValidationRPrecision.getAverage(), CrossValidationRecall.getAverage(), CrossValidationFallOut.getAverage(), CrossValidationNDCG.getAverage(), CrossValidationRNDCG.getAverage(), CrossValidationReach.getAverage(), CrossValidationMacroDOA.getAverage(), CrossValidationMicroDOA.getAverage(), CrossValidationMacroInnerDOA.getAverage(), CrossValidationMicroInnerDOA.getAverage()); return new GLIRStatisticsImpl(CrossValidationPrecision.getAverage(), CrossValidationRPrecision.getAverage(), CrossValidationRecall.getAverage(), CrossValidationFallOut.getAverage(), CrossValidationNDCG.getAverage(), CrossValidationRNDCG.getAverage(), CrossValidationReach.getAverage(), CrossValidationMacroDOA.getAverage(), CrossValidationMicroDOA.getAverage(), CrossValidationMacroInnerDOA.getAverage(), CrossValidationMicroInnerDOA.getAverage()); }
From source file:recommender.GenericRecommenderIRStatsEvaluatorCustom.java
License:Apache License
@Override public IRStatistics evaluate(RecommenderBuilder recommenderBuilder, DataModelBuilder dataModelBuilder, DataModel dataModel, IDRescorer rescorer, int at, double relevanceThreshold, double evaluationPercentage) throws TasteException { prop = new Properties(); try {//w w w . j av a 2s .c o m prop.load(GenericRecommenderIRStatsEvaluatorCustom.class.getResourceAsStream("settings.properties")); } catch (IOException ex) { java.util.logging.Logger.getLogger(GenericRecommenderIRStatsEvaluatorCustom.class.getName()) .log(Level.SEVERE, null, ex); } // load settings from MySQL database loadSettings(); 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(); System.out.println("Data model numItems: " + numItems); RunningAverage precision = new FullRunningAverage(); RunningAverage recall = new FullRunningAverage(); RunningAverage fallOut = new FullRunningAverage(); RunningAverage nDCG = new FullRunningAverage(); int numUsersRecommendedFor = 0; int numUsersWithRecommendations = 0; // map to store diversity ranges => number of users HashMap<String, String> map = new HashMap<>(); LongPrimitiveIterator it = dataModel.getUserIDs(); while (it.hasNext()) { long userID = it.nextLong(); if (userID == 0) { continue; } // get the top users if (!list.contains(userID + "")) { continue; } if (random.nextDouble() >= evaluationPercentage) { // Skipped continue; } long start = System.currentTimeMillis(); PreferenceArray prefs = dataModel.getPreferencesFromUser(userID); System.out.println("User preferences: " + prefs); // List some most-preferred items that would count as (most) "relevant" results double theRelevanceThreshold = 0;//Double.isNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold; FastIDSet relevantItemIDs = dataSplitter.getRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel); System.out.println("Relevant items: " + relevantItemIDs); System.out.println("Relevance threshold: " + theRelevanceThreshold); int numRelevantItems = relevantItemIDs.size(); if (numRelevantItems <= 0) { continue; } FastByIDMap<PreferenceArray> trainingUsers = new FastByIDMap<>(dataModel.getNumUsers()); LongPrimitiveIterator it2 = dataModel.getUserIDs(); while (it2.hasNext()) { dataSplitter.processOtherUser(userID, relevantItemIDs, trainingUsers, it2.nextLong(), dataModel); } DataModel 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).size(); if (size < 2 * at) { // Really not enough prefs to meaningfully evaluate this user System.out .println("Really not enough prefs (" + size + ") to meaningfully evaluate user: " + userID); continue; } Recommender recommender = recommenderBuilder.buildRecommender(trainingModel); int intersectionSize = 0; List<RecommendedItem> recommendedItems = recommender.recommend(userID, at, rescorer); HashMap<Long, Double> user_preferences = getUserPreferencesList(userID); for (RecommendedItem recommendedItem : recommendedItems) { double preference = isRelevant(user_preferences, recommendedItem); System.out.println("Preference: " + preference); if (relevantItemIDs.contains(recommendedItem.getItemID()) || preference != 0) { intersectionSize++; } } int numRecommendedItems = recommendedItems.size(); // Precision if (numRecommendedItems > 0) { precision.addDatum((double) intersectionSize / (double) numRecommendedItems); System.out.println( "intersectionSize: " + intersectionSize + " numRecommendedItems: " + 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++) { RecommendedItem item = recommendedItems.get(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++; } long end = System.currentTimeMillis(); log.info("Evaluated with user {} in {}ms", userID, end - start); log.info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}", precision.getAverage(), recall.getAverage(), fallOut.getAverage(), nDCG.getAverage(), (double) numUsersWithRecommendations / (double) numUsersRecommendedFor); System.out.println("Relevant items: " + numRelevantItems); System.out.println("Precision: " + precision.getAverage()); System.out.println("Recall: " + recall.getAverage()); System.out.println("Fall-out: " + fallOut.getAverage()); System.out.println("nDCG: " + nDCG.getAverage()); System.out.println("Reach: " + (double) numUsersWithRecommendations / (double) numUsersRecommendedFor); double diversity = getDiversity(recommendedItems); System.out.println("Diversity: " + diversity); if (diversity >= 0 && diversity < 0.1) { int count = map.get("0-0.1") != null ? Integer.parseInt(map.get("0-0.1")) + 1 : 1; map.put("0-0.1", count + ""); } else if (diversity >= 0.1 && diversity < 0.2) { int count = map.get("0.1-0.2") != null ? Integer.parseInt(map.get("0.1-0.2")) + 1 : 1; map.put("0.1-0.2", count + ""); } else if (diversity >= 0.2 && diversity < 0.3) { int count = map.get("0.2-0.3") != null ? Integer.parseInt(map.get("0.2-0.3")) + 1 : 1; map.put("0.2-0.3", count + ""); } else if (diversity >= 0.3 && diversity < 0.4) { int count = map.get("0.3-0.4") != null ? Integer.parseInt(map.get("0.3-0.4")) + 1 : 1; map.put("0.3-0.4", count + ""); } else if (diversity >= 0.4 && diversity < 0.5) { int count = map.get("0.4-0.5") != null ? Integer.parseInt(map.get("0.4-0.5")) + 1 : 1; map.put("0.4-0.5", count + ""); } else if (diversity >= 0.5 && diversity < 0.6) { int count = map.get("0.5-0.6") != null ? Integer.parseInt(map.get("0.5-0.6")) + 1 : 1; map.put("0.5-0.6", count + ""); } else if (diversity >= 0.6 && diversity < 0.7) { int count = map.get("0.6-0.7") != null ? Integer.parseInt(map.get("0.6-0.7")) + 1 : 1; map.put("0.6-0.7", count + ""); } else if (diversity >= 0.7 && diversity < 0.8) { int count = map.get("0.7-0.8") != null ? Integer.parseInt(map.get("0.7-0.8")) + 1 : 1; map.put("0.7-0.8", count + ""); } else if (diversity >= 0.8 && diversity < 0.9) { int count = map.get("0.8-0.9") != null ? Integer.parseInt(map.get("0.8-0.9")) + 1 : 1; map.put("0.8-0.9", count + ""); } else if (diversity >= 0.9) { int count = map.get("0.9-1") != null ? Integer.parseInt(map.get("0.9-1")) + 1 : 1; map.put("0.9-1", count + ""); } } JSONObject json = new JSONObject(map); writeFile(prop.getProperty("metrics_file"), json.toJSONString()); return new IRStatisticsImplCustom(precision.getAverage(), recall.getAverage(), fallOut.getAverage(), nDCG.getAverage(), (double) numUsersWithRecommendations / (double) numUsersRecommendedFor); }