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

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

280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
 
  private void findClusters(List<FastIDSet> newClusters) throws TasteException {
    if (clusteringByThreshold) {
      Pair<FastIDSet,FastIDSet> nearestPair = findNearestClusters(newClusters);
      if (nearestPair != null) {
        FastIDSet cluster1 = nearestPair.getFirst();
        FastIDSet cluster2 = nearestPair.getSecond();
        while (clusterSimilarity.getSimilarity(cluster1, cluster2) >= clusteringThreshold) {
          newClusters.remove(cluster1);
          newClusters.remove(cluster2);
          FastIDSet merged = new FastIDSet(cluster1.size() + cluster2.size());
          merged.addAll(cluster1);
          merged.addAll(cluster2);
          newClusters.add(merged);
          nearestPair = findNearestClusters(newClusters);
          if (nearestPair == null) {
            break;
          }
          cluster1 = nearestPair.getFirst();
          cluster2 = nearestPair.getSecond();
        }
      }
    } else {
      while (newClusters.size() > numClusters) {
        Pair<FastIDSet,FastIDSet> nearestPair = findNearestClusters(newClusters);
        if (nearestPair == null) {
          break;
        }
        FastIDSet cluster1 = nearestPair.getFirst();
        FastIDSet cluster2 = nearestPair.getSecond();
        newClusters.remove(cluster1);
        newClusters.remove(cluster2);
        FastIDSet merged = new FastIDSet(cluster1.size() + cluster2.size());
        merged.addAll(cluster1);
        merged.addAll(cluster2);
        newClusters.add(merged);
      }
    }
  }
View Full Code Here
320
321
322
323
324
325
326
327
328
329
330
331
332
333
  private Pair<FastIDSet,FastIDSet> findNearestClusters(List<FastIDSet> clusters) throws TasteException {
    int size = clusters.size();
    Pair<FastIDSet,FastIDSet> nearestPair = null;
    double bestSimilarity = Double.NEGATIVE_INFINITY;
    for (int i = 0; i < size; i++) {
      FastIDSet cluster1 = clusters.get(i);
      for (int j = i + 1; j < size; j++) {
        if ((samplingRate >= 1.0) || (RANDOM.nextDouble() < samplingRate)) {
          FastIDSet cluster2 = clusters.get(j);
          double similarity = clusterSimilarity.getSimilarity(cluster1, cluster2);
          if (!Double.isNaN(similarity) && (similarity > bestSimilarity)) {
            bestSimilarity = similarity;
            nearestPair = new Pair<FastIDSet,FastIDSet>(cluster1, cluster2);
          }
View Full Code Here
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
    return recsPerUser;
  }
 
  private List<RecommendedItem> computeTopRecsForCluster(FastIDSet cluster) throws TasteException {
    DataModel dataModel = getDataModel();
    FastIDSet possibleItemIDs = new FastIDSet();
    LongPrimitiveIterator it = cluster.iterator();
    while (it.hasNext()) {
      possibleItemIDs.addAll(dataModel.getItemIDsFromUser(it.next()));
    }
   
    TopItems.Estimator<Long> estimator = new Estimator(cluster);
   
    List<RecommendedItem> topItems =
        TopItems.getTopItems(possibleItemIDs.size(), possibleItemIDs.iterator(), null, estimator);
   
    log.debug("Recommendations are: {}", topItems);
    return Collections.unmodifiableList(topItems);
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
  @Override
  public List<RecommendedItem> recommend(long userID, int howMany, IDRescorer rescorer) throws TasteException {
    Preconditions.checkArgument(howMany >= 1, "howMany must be at least 1");
    log.debug("Recommending items for user ID '{}'", userID);

    FastIDSet possibleItemIDs = getAllOtherItems(userID);

    TopItems.Estimator<Long> estimator = new Estimator();

    List<RecommendedItem> topItems = TopItems.getTopItems(howMany, possibleItemIDs.iterator(), rescorer,
      estimator);

    log.debug("Recommendations are: {}", topItems);
    return topItems;
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
  @Override
  public FastIDSet getCandidateItems(long userID, DataModel dataModel) throws TasteException {
    int maxPrefsPerItemConsidered = (int) Math.max(defaultMaxPrefsPerItemConsidered,
        userItemCountMultiplier * Math.log(Math.max(dataModel.getNumUsers(), dataModel.getNumItems())));
    FastIDSet possibleItemsIDs = new FastIDSet();
    FastIDSet itemIDs = dataModel.getItemIDsFromUser(userID);
    LongPrimitiveIterator itemIDIterator = itemIDs.iterator();
    while (itemIDIterator.hasNext()) {
      long itemID = itemIDIterator.next();
      PreferenceArray prefs = dataModel.getPreferencesForItem(itemID);
      int prefsConsidered = Math.min(prefs.length(), maxPrefsPerItemConsidered);
      Iterator<Preference> sampledPrefs = new FixedSizeSamplingIterator(prefsConsidered, prefs.iterator());
View Full Code Here
58
59
60
61
62
63
64
65
66
67
    DataModel dataModel = new GenericDataModel(userData);

    CandidateItemsStrategy strategy = new SamplingCandidateItemsStrategy(1, 1);

    FastIDSet candidateItems = strategy.getCandidateItems(123L, dataModel);
    /* result can be either item2 or item3 or empty */
    assertTrue(candidateItems.size() <= 1);
    assertFalse(candidateItems.contains(1L));
  }
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
*/
public final class AllUnknownItemsCandidateItemsStrategyTest extends TasteTestCase {

  @Test 
  public void testStrategy() throws TasteException {
    FastIDSet allItemIDs = new FastIDSet();
    allItemIDs.addAll(new long[] { 1L, 2L, 3L });

    FastIDSet preferredItemIDs = new FastIDSet(1);
    preferredItemIDs.add(2L);
   
    DataModel dataModel = EasyMock.createMock(DataModel.class);
    EasyMock.expect(dataModel.getNumItems()).andReturn(3);
    EasyMock.expect(dataModel.getItemIDs()).andReturn(allItemIDs.iterator());
    EasyMock.expect(dataModel.getItemIDsFromUser(123L)).andReturn(preferredItemIDs);

    CandidateItemsStrategy strategy = new AllUnknownItemsCandidateItemsStrategy();

    EasyMock.replay(dataModel);

    FastIDSet candidateItems = strategy.getCandidateItems(123L, dataModel);
    assertEquals(2, candidateItems.size());
    assertTrue(candidateItems.contains(1L));
    assertTrue(candidateItems.contains(3L));

    EasyMock.verify(dataModel);
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
 
  @Override
  public long[] getUserNeighborhood(long userID) throws TasteException {
   
    DataModel dataModel = getDataModel();
    FastIDSet neighborhood = new FastIDSet();
    LongPrimitiveIterator usersIterable = SamplingLongPrimitiveIterator.maybeWrapIterator(dataModel
        .getUserIDs(), getSamplingRate());
    UserSimilarity userSimilarityImpl = getUserSimilarity();
   
    while (usersIterable.hasNext()) {
      long otherUserID = usersIterable.next();
      if (userID != otherUserID) {
        double theSimilarity = userSimilarityImpl.userSimilarity(userID, otherUserID);
        if (!Double.isNaN(theSimilarity) && (theSimilarity >= threshold)) {
          neighborhood.add(otherUserID);
        }
      }
    }
   
    return neighborhood.toArray();
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
    if (usersFilePathString != null) {
      FSDataInputStream in = null;
      try {
        Path unqualifiedUsersFilePath = new Path(usersFilePathString);
        FileSystem fs = FileSystem.get(unqualifiedUsersFilePath.toUri(), jobConf);
        usersToRecommendFor = new FastIDSet();
        Path usersFilePath = unqualifiedUsersFilePath.makeQualified(fs);
        in = fs.open(usersFilePath);
        for (String line : new FileLineIterable(in)) {
          usersToRecommendFor.add(Long.parseLong(line));
        }    
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
  public GenericBooleanPrefDataModel(FastByIDMap<FastIDSet> userData, FastByIDMap<FastByIDMap<Long>> timestamps) {
    Preconditions.checkArgument(userData != null, "userData is null");

    this.preferenceFromUsers = userData;
    this.preferenceForItems = new FastByIDMap<FastIDSet>();
    FastIDSet itemIDSet = new FastIDSet();
    for (Map.Entry<Long, FastIDSet> entry : preferenceFromUsers.entrySet()) {
      long userID = entry.getKey();
      FastIDSet itemIDs = entry.getValue();
      itemIDSet.addAll(itemIDs);
      LongPrimitiveIterator it = itemIDs.iterator();
      while (it.hasNext()) {
        long itemID = it.next();
        FastIDSet userIDs = preferenceForItems.get(itemID);
        if (userIDs == null) {
          userIDs = new FastIDSet(2);
          preferenceForItems.put(itemID, userIDs);
        }
        userIDs.add(userID);
      }
    }

    this.itemIDs = itemIDSet.toArray();
    itemIDSet = null; // Might help GC -- this is big
View Full Code Here
TOP

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

  • io.prediction.engines.base.mahout.AllValidItemsCandidateItemsStrategy
  • mia.recommender.ch05.GenderRescorer
  • mia.recommender.ch05.LibimsetiRecommender
  • org.apache.mahout.cf.taste.example.kddcup.track1.svd.DataModelFactorizablePreferences
  • org.apache.mahout.cf.taste.example.kddcup.track2.TrackData
  • org.apache.mahout.cf.taste.example.kddcup.track2.TrackItemSimilarity
  • org.apache.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer
  • org.apache.mahout.cf.taste.hadoop.item.IDReader
  • org.apache.mahout.cf.taste.hadoop.item.IDReaderTest
  • org.apache.mahout.cf.taste.hadoop.item.RecommenderJobTest
    • 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.