List of usage examples for org.apache.mahout.cf.taste.model DataModel getPreferenceValue
Float getPreferenceValue(long userID, long itemID) 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()); }/* ww w .j a v a2 s .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:com.webir.popcornsaver.cluster.TreeClusteringRecommender.java
License:Apache License
@Override public List<RecommendedItem> recommend(long userID, int howMany, IDRescorer rescorer) throws TasteException { Preconditions.checkArgument(howMany >= 1, "howMany must be at least 1"); buildClusters();/* ww w. j av a 2 s .co m*/ log.debug("Recommending items for user ID '{}'", userID); List<RecommendedItem> recommended = topRecsByUserID.get(userID); if (recommended == null) { return Collections.emptyList(); } DataModel dataModel = getDataModel(); List<RecommendedItem> rescored = new ArrayList<RecommendedItem>(recommended.size()); // Only add items the user doesn't already have a preference for. // And that the rescorer doesn't "reject". for (RecommendedItem recommendedItem : recommended) { long itemID = recommendedItem.getItemID(); if ((rescorer != null) && rescorer.isFiltered(itemID)) { continue; } if ((dataModel.getPreferenceValue(userID, itemID) == null) && ((rescorer == null) || !Double.isNaN(rescorer.rescore(itemID, recommendedItem.getValue())))) { rescored.add(recommendedItem); } } Collections.sort(rescored, new ByRescoreComparator(rescorer)); return rescored; }
From source file:com.webir.popcornsaver.cluster.TreeClusteringRecommender.java
License:Apache License
@Override public float estimatePreference(long userID, long itemID) throws TasteException { DataModel model = getDataModel(); Float actualPref = model.getPreferenceValue(userID, itemID); if (actualPref != null) { return actualPref; }/*from w w w . j a va 2 s .c om*/ buildClusters(); List<RecommendedItem> topRecsForUser = topRecsByUserID.get(userID); if (topRecsForUser != null) { for (RecommendedItem item : topRecsForUser) { if (itemID == item.getItemID()) { return item.getValue(); } } } // Hmm, we have no idea. The item is not in the user's cluster return Float.NaN; }
From source file:de.unima.dws.webmining.rs.recommender.AvgUserPrefAdaptedUserBasedRecommender.java
License:Apache License
public float estimatePreference(long userID, long itemID) throws TasteException { DataModel model = getDataModel(); Float actualPref = model.getPreferenceValue(userID, itemID); if (actualPref != null) { return actualPref; }/*w w w . ja v a 2 s . c om*/ long[] theNeighborhood = neighborhood.getUserNeighborhood(userID); return doEstimatePreference(userID, theNeighborhood, itemID); }
From source file:de.unima.dws.webmining.rs.recommender.AvgUserPrefAdaptedUserBasedRecommender.java
License:Apache License
/** * This estimation is more optimal as it takes into account the avg user * preferences//from ww w . j a v a2 s. co m * * @param theUserID * @param theNeighborhood * @param itemID * @return * @throws TasteException */ protected float doEstimatePreference(long theUserID, long[] theNeighborhood, long itemID) throws TasteException { if (theNeighborhood.length == 0) { return Float.NaN; } DataModel dataModel = getDataModel(); double preference = 0.0; double totalSimilarity = 0.0; int count = 0; for (long userID : theNeighborhood) { if (userID != theUserID) { // See GenericItemBasedRecommender.doEstimatePreference() too Float pref = dataModel.getPreferenceValue(userID, itemID); if (pref != null) { double theSimilarity = similarity.userSimilarity(theUserID, userID); if (!Double.isNaN(theSimilarity)) { float userAvgRating = calculateAverageRating(userID); preference += theSimilarity * (pref - userAvgRating); totalSimilarity += theSimilarity; count++; } } } } // Throw out the estimate if it was based on no data points, of course, // but also if based on // just one. This is a bit of a band-aid on the 'stock' item-based // algorithm for the moment. // The reason is that in this case the estimate is, simply, the user's // rating for one item // that happened to have a defined similarity. The similarity score // doesn't matter, and that // seems like a bad situation. if (count <= 1) { return Float.NaN; } float estimate = (float) (preference / totalSimilarity); float theUserAvgPref = calculateAverageRating(theUserID); estimate += theUserAvgPref; if (capper != null) { estimate = capper.capEstimate(estimate); } return estimate; }
From source file:net.ufida.info.mahout.common.SlopeOneRecommender.java
License:Apache License
@Override public float estimatePreference(long userID, long itemID) throws TasteException { DataModel model = getDataModel(); Float actualPref = model.getPreferenceValue(userID, itemID); if (actualPref != null) { return actualPref; }/*from w ww.ja va 2 s. c om*/ return doEstimatePreference(userID, itemID); }
From source file:net.ufida.info.mahout.common.SlopeOneRecommender.java
License:Apache License
@Override public void setPreference(long userID, long itemID, float value) throws TasteException { DataModel dataModel = getDataModel(); Float oldPref;//from w ww .j a v a 2 s.c o m try { oldPref = dataModel.getPreferenceValue(userID, itemID); } catch (NoSuchUserException nsee) { oldPref = null; } super.setPreference(userID, itemID, value); if (oldPref == null) { // Add new preference diffStorage.addItemPref(userID, itemID, value); } else { // Update preference diffStorage.updateItemPref(itemID, value - oldPref); } }
From source file:net.ufida.info.mahout.common.SlopeOneRecommender.java
License:Apache License
@Override public void removePreference(long userID, long itemID) throws TasteException { DataModel dataModel = getDataModel(); Float oldPref = dataModel.getPreferenceValue(userID, itemID); super.removePreference(userID, itemID); if (oldPref != null) { diffStorage.removeItemPref(userID, itemID, oldPref); }//from w w w . j a va 2 s . c o m }
From source file:org.easyrec.mahout.EasyrecInMemoryDataModelTest.java
License:Open Source License
@Test public void testEasyrecDataModel_getPreferenceValue() throws TasteException { DataModel easyrecDataModel = new EasyrecDataModel(TENANT_ID, RATE_ACTION_TYPE_ID, HAS_RATING_VALUES, mahoutDataModelMappingDAO);//from ww w . j av a 2 s . c om easyrecDataModel = new EasyrecInMemoryDataModel(easyrecDataModel); Float preferenceValue = easyrecDataModel.getPreferenceValue(1, 2); assertEquals(new Float(5), preferenceValue); }
From source file:org.easyrec.mahout.EasyrecInMemoryDataModelTest.java
License:Open Source License
@Test public void testEasyrecDataModel_getBooleanPreferenceValue() throws TasteException { DataModel easyrecDataModel = new EasyrecDataModel(TENANT_ID, BUY_ACTION_TYPE_ID, HAS_NO_RATING_VALUES, mahoutDataModelMappingDAO);//ww w . j ava 2 s . co m easyrecDataModel = new EasyrecInMemoryDataModel(easyrecDataModel); Float preferenceValue = easyrecDataModel.getPreferenceValue(1, 20); assertEquals(new Float(1), preferenceValue); }