Package org.apache.mahout.cf.taste.impl.common

Examples of org.apache.mahout.cf.taste.impl.common.LongPrimitiveIterator

297
298
299
300
301
302
303
304
305
306
307
308
309
    log.info("Building average diffs...");
    try {
      buildAverageDiffsLock.writeLock().lock();
      averageDiffs.clear();
      long averageCount = 0L;
      LongPrimitiveIterator it = dataModel.getUserIDs();
      while (it.hasNext()) {
        averageCount = processOneUser(averageCount, it.nextLong());
      }
     
      pruneInconsequentialDiffs();
      updateAllRecommendableItems();
     
View Full Code Here
336
337
338
339
340
341
342
343
344
345
346
347
348
 
  private void updateAllRecommendableItems() throws TasteException {
    FastIDSet ids = new FastIDSet(dataModel.getNumItems());
    for (Map.Entry<Long,FastByIDMap<RunningAverage>> entry : averageDiffs.entrySet()) {
      ids.add(entry.getKey());
      LongPrimitiveIterator it = entry.getValue().keySetIterator();
      while (it.hasNext()) {
        ids.add(it.next());
      }
    }
    allRecommendableItemIDs.clear();
    allRecommendableItemIDs.addAll(ids);
    allRecommendableItemIDs.rehash();
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
  }

  public void train() throws TasteException {
    for (int i = 0; i < numIterations; i++) {
      if (recomputeUserFeatures) {
        LongPrimitiveIterator userIds = dataModel.getUserIDs();
        /* start with calculating X^TX or Y^TX */
        log.info("Calculating Y^TY");
        reCalculateTrans(recomputeUserFeatures);
        log.info("Building callables for users.");
        while (userIds.hasNext()) {
          long userId = userIds.nextLong();
          int useridx = userIndex(userId);
          buildCallables(buildConfidenceMatrixForUser(userId), buildPreferenceVectorForUser(userId), useridx);
        }
        finishProcessing();
      } else {
        LongPrimitiveIterator itemIds = dataModel.getItemIDs();
        /* start with calculating X^TX or Y^TX */
        log.info("Calculating X^TX");
        reCalculateTrans(recomputeUserFeatures);
        log.info("Building callables for items.");
        while (itemIds.hasNext()) {
          long itemId = itemIds.nextLong();
          int itemidx = itemIndex(itemId);
          buildCallables(buildConfidenceMatrixForItem(itemId), buildPreferenceVectorForItem(itemId), itemidx);
        }
        finishProcessing();
      }
View Full Code Here
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
    return new DiagonalMatrix(vector);
  }

  private double getAveragePreference() throws TasteException {
    RunningAverage average = new FullRunningAverage();
    LongPrimitiveIterator it = dataModel.getUserIDs();
    while (it.hasNext()) {
      int count = 0;
      try {
        PreferenceArray prefs = dataModel.getPreferencesFromUser(it.nextLong());
        for (Preference pref : prefs) {
          average.addDatum(pref.getValue());
          count++;
        }
      } catch (NoSuchUserException ex) {
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
      }
    }

    /* get internal item IDs which we will need several times */
    itemsByUser = Maps.newHashMap();
    LongPrimitiveIterator userIDs = dataModel.getUserIDs();
    while (userIDs.hasNext()) {
      long userId = userIDs.nextLong();
      int userIndex = userIndex(userId);
      FastIDSet itemIDsFromUser = dataModel.getItemIDsFromUser(userId);
      List<Integer> itemIndexes = Lists.newArrayListWithCapacity(itemIDsFromUser.size());
      itemsByUser.put(userIndex, itemIndexes);
      for (long itemID2 : itemIDsFromUser) {
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
    shufflePreferences();
  }

  private int countPreferences() throws TasteException {
    int numPreferences = 0;
    LongPrimitiveIterator userIDs = dataModel.getUserIDs();
    while (userIDs.hasNext()) {
      PreferenceArray preferencesFromUser = dataModel.getPreferencesFromUser(userIDs.nextLong());
      numPreferences += preferencesFromUser.length();
    }
    return numPreferences;
  }
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
  private void cachePreferences() throws TasteException {
    int numPreferences = countPreferences();
    cachedUserIDs = new long[numPreferences];
    cachedItemIDs = new long[numPreferences];

    LongPrimitiveIterator userIDs = dataModel.getUserIDs();
    int index = 0;
    while (userIDs.hasNext()) {
      long userID = userIDs.nextLong();
      PreferenceArray preferencesFromUser = dataModel.getPreferencesFromUser(userID);
      for (Preference preference : preferencesFromUser) {
        cachedUserIDs[index] = userID;
        cachedItemIDs[index] = preference.getItemID();
        index++;
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
181
182
    return createFactorization(userVectors, itemVectors);
  }

  double getAveragePreference() throws TasteException {
    RunningAverage average = new FullRunningAverage();
    LongPrimitiveIterator it = dataModel.getUserIDs();
    while (it.hasNext()) {
      for (Preference pref : dataModel.getPreferencesFromUser(it.nextLong())) {
        average.addDatum(pref.getValue());
      }
    }
    return average.getAverage();
  }
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
    for (int iteration = 0; iteration < numIterations; iteration++) {
      log.info("iteration {}", iteration);

      /* fix M - compute U */
      ExecutorService queue = createQueue();
      LongPrimitiveIterator userIDsIterator = dataModel.getUserIDs();
      try {

        final ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
            ? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, itemY) : null;

        while (userIDsIterator.hasNext()) {
          final long userID = userIDsIterator.nextLong();
          final LongPrimitiveIterator itemIDsFromUser = dataModel.getItemIDsFromUser(userID).iterator();
          final PreferenceArray userPrefs = dataModel.getPreferencesFromUser(userID);
          queue.execute(new Runnable() {
            @Override
            public void run() {
              List<Vector> featureVectors = Lists.newArrayList();
              while (itemIDsFromUser.hasNext()) {
                long itemID = itemIDsFromUser.nextLong();
                featureVectors.add(features.getItemFeatureColumn(itemIndex(itemID)));
              }

              Vector userFeatures = usesImplicitFeedback
                  ? implicitFeedbackSolver.solve(sparseUserRatingVector(userPrefs))
                  : AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(userPrefs), lambda, numFeatures);

              features.setFeatureColumnInU(userIndex(userID), userFeatures);
            }
          });
        }
      } finally {
        queue.shutdown();
        try {
          queue.awaitTermination(dataModel.getNumUsers(), TimeUnit.SECONDS);
        } catch (InterruptedException e) {
          log.warn("Error when computing user features", e);
        }
      }

      /* fix U - compute M */
      queue = createQueue();
      LongPrimitiveIterator itemIDsIterator = dataModel.getItemIDs();
      try {

        final ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
            ? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, userY) : null;

        while (itemIDsIterator.hasNext()) {
          final long itemID = itemIDsIterator.nextLong();
          final PreferenceArray itemPrefs = dataModel.getPreferencesForItem(itemID);
          queue.execute(new Runnable() {
            @Override
            public void run() {
              List<Vector> featureVectors = Lists.newArrayList();
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
    Features(ALSWRFactorizer factorizer) throws TasteException {
      dataModel = factorizer.dataModel;
      numFeatures = factorizer.numFeatures;
      Random random = RandomUtils.getRandom();
      M = new double[dataModel.getNumItems()][numFeatures];
      LongPrimitiveIterator itemIDsIterator = dataModel.getItemIDs();
      while (itemIDsIterator.hasNext()) {
        long itemID = itemIDsIterator.nextLong();
        int itemIDIndex = factorizer.itemIndex(itemID);
        M[itemIDIndex][0] = averateRating(itemID);
        for (int feature = 1; feature < numFeatures; feature++) {
          M[itemIDIndex][feature] = random.nextDouble() * 0.1;
        }
View Full Code Here
TOP

Related Classes of org.apache.mahout.cf.taste.impl.common.LongPrimitiveIterator

  • mia.recommender.ch02.ItemBaseRecommender
  • mia.recommender.ch02.UserBaseRecommender
  • net.myrrix.client.CLI
  • net.myrrix.client.translating.TranslatingClientRecommender
  • net.myrrix.common.collection.FastIDSetTest
  • net.myrrix.common.math.MatrixUtils
  • net.myrrix.common.random.RandomUtils
  • net.myrrix.online.factorizer.als.AlternatingLeastSquares
  • net.myrrix.online.generation.GenerationLoader
  • net.myrrix.online.generation.GenerationSerializer
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.