Package org.apache.mahout.math.set

Examples of org.apache.mahout.math.set.OpenIntHashSet

60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    protected void map(LongWritable offset, Text input, Context context)
    throws IOException, InterruptedException {

    String[] items = splitter.split(input.toString());

    OpenIntHashSet itemSet = new OpenIntHashSet();

    for (String item : items) {
      if (fMap.containsKey(item) && !item.trim().isEmpty()) {
        itemSet.add(fMap.get(item));
      }
    }

    IntArrayList itemArr = new IntArrayList(itemSet.size());
    itemSet.keys(itemArr);
    itemArr.sort();

    OpenIntHashSet groups = new OpenIntHashSet();
    for (int j = itemArr.size() - 1; j >= 0; j--) {
      // generate group dependent shards
      int item = itemArr.get(j);
      int groupID = PFPGrowth.getGroup(item, maxPerGroup);
       
      if (!groups.contains(groupID)) {
        IntArrayList tempItems = new IntArrayList(j + 1);
        tempItems.addAllOfFromTo(itemArr, 0, j);
        context.setStatus("Parallel FPGrowth: Generating Group Dependent transactions for: " + item);
        wGroupID.set(groupID);
        context.write(wGroupID, new TransactionTree(tempItems, 1L));
      }
      groups.add(groupID);
    }
   
  }
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
    protected void map(IntWritable userIDWritable, VectorWritable ratingsWritable, Context ctx)
        throws IOException, InterruptedException {

      Vector ratings = ratingsWritable.get();
      final int userID = userIDWritable.get();
      final OpenIntHashSet alreadyRatedItems = new OpenIntHashSet(ratings.getNumNondefaultElements());
      final TopK<RecommendedItem> topKItems = new TopK<RecommendedItem>(recommendationsPerUser, BY_PREFERENCE_VALUE);

      Iterator<Vector.Element> ratingsIterator = ratings.iterateNonZero();
      while (ratingsIterator.hasNext()) {
        alreadyRatedItems.add(ratingsIterator.next().index());
      }

      M.forEachPair(new IntObjectProcedure<Vector>() {
        @Override
        public boolean apply(int itemID, Vector itemFeatures) {
          if (!alreadyRatedItems.contains(itemID)) {
            double predictedRating = U.get(userID).dot(itemFeatures);
            topKItems.offer(new GenericRecommendedItem(itemID, (float) predictedRating));
          }
          return true;
        }
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
      }
    }

    log.info("Number of unique items {}", attributeFrequency.size());

    OpenIntHashSet returnFeatures = new OpenIntHashSet();
    if (returnableFeatures == null || returnableFeatures.isEmpty()) {
      returnableFeatures = new IntArrayList();
      for (int j = 0; j < attributeFrequency.size(); j++) {
        returnableFeatures.add(j);
      }
View Full Code Here
303
304
305
306
307
308
309
310
311
312
313
314
315
316
  /**
   * @see "https://issues.apache.org/jira/browse/MAHOUT-1225"
   */
  @Test
  public void testMahout1225() {
    AbstractIntSet s = new OpenIntHashSet();
    s.clear();
    s.add(23);
    s.add(46);
    s.clear();
    s.add(70);
    s.add(93);
    s.contains(100);
  }
View Full Code Here
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
          y.getNumNondefaultElements() * y.getIteratorAdvanceCost() * x.getLookupCost());
    }

    @Override
    public double aggregate(Vector x, Vector y, DoubleDoubleFunction fa, DoubleDoubleFunction fc) {
      OpenIntHashSet visited = new OpenIntHashSet();
      Iterator<Vector.Element> xi = x.nonZeroes().iterator();
      boolean validResult = false;
      double result = 0;
      double thisResult;
      while (xi.hasNext()) {
        Vector.Element xe = xi.next();
        thisResult = fc.apply(xe.get(), y.getQuick(xe.index()));
        if (validResult) {
          result = fa.apply(result, thisResult);
        } else {
          result = thisResult;
          validResult = true;
        }
        visited.add(xe.index());
      }
      Iterator<Vector.Element> yi = y.nonZeroes().iterator();
      while (yi.hasNext()) {
        Vector.Element ye = yi.next();
        if (!visited.contains(ye.index())) {
          thisResult = fc.apply(x.getQuick(ye.index()), ye.get());
          if (validResult) {
            result = fa.apply(result, thisResult);
          } else {
            result = thisResult;
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
  protected void map(LongWritable offset, Text input, Context context)
    throws IOException, InterruptedException {

    String[] items = splitter.split(input.toString());

    OpenIntHashSet itemSet = new OpenIntHashSet();

    for (String item : items) {
      if (fMap.containsKey(item) && !item.trim().isEmpty()) {
        itemSet.add(fMap.get(item));
      }
    }

    IntArrayList itemArr = new IntArrayList(itemSet.size());
    itemSet.keys(itemArr);
    itemArr.sort();

    OpenIntHashSet groups = new OpenIntHashSet();
    for (int j = itemArr.size() - 1; j >= 0; j--) {
      // generate group dependent shards
      int item = itemArr.get(j);
      int groupID = PFPGrowth.getGroup(item, maxPerGroup);
       
      if (!groups.contains(groupID)) {
        IntArrayList tempItems = new IntArrayList(j + 1);
        tempItems.addAllOfFromTo(itemArr, 0, j);
        context.setStatus("Parallel FPGrowth: Generating Group Dependent transactions for: " + item);
        wGroupID.set(groupID);
        context.write(wGroupID, new TransactionTree(tempItems, 1L));
      }
      groups.add(groupID);
    }
   
  }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
    OpenIntObjectHashMap<Vector> U = uAndM.getFirst();
    OpenIntObjectHashMap<Vector> M = uAndM.getSecond();

    Vector ratings = ratingsWritable.get();
    int userIndex = userIndexWritable.get();
    final OpenIntHashSet alreadyRatedItems = new OpenIntHashSet(ratings.getNumNondefaultElements());

    for (Vector.Element e : ratings.nonZeroes()) {
      alreadyRatedItems.add(e.index());
    }

    final TopItemsQueue topItemsQueue = new TopItemsQueue(recommendationsPerUser);
    final Vector userFeatures = U.get(userIndex);

    M.forEachPair(new IntObjectProcedure<Vector>() {
      @Override
      public boolean apply(int itemID, Vector itemFeatures) {
        if (!alreadyRatedItems.contains(itemID)) {
          double predictedRating = userFeatures.dot(itemFeatures);

          MutableRecommendedItem top = topItemsQueue.top();
          if (predictedRating > top.getValue()) {
            top.set(itemID, (float) predictedRating);
View Full Code Here
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
          y.getNumNondefaultElements() * y.getIteratorAdvanceCost() * x.getLookupCost());
    }

    @Override
    public Vector assign(Vector x, Vector y, DoubleDoubleFunction f) {
      OpenIntHashSet visited = new OpenIntHashSet();
      for (Element xe : x.nonZeroes()) {
        xe.set(f.apply(xe.get(), y.getQuick(xe.index())));
        visited.add(xe.index());
      }
      OrderedIntDoubleMapping updates = new OrderedIntDoubleMapping(false);
      for (Element ye : y.nonZeroes()) {
        if (!visited.contains(ye.index())) {
          updates.set(ye.index(), f.apply(x.getQuick(ye.index()), ye.get()));
        }
      }
      x.mergeUpdates(updates);
      return x;
View Full Code Here
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
      return Math.max(x.getNumNondefaultElements() * x.getIteratorAdvanceCost() * y.getLookupCost(),
          y.getNumNondefaultElements() * y.getIteratorAdvanceCost() * x.getLookupCost());
    }
    @Override
    public Vector assign(Vector x, Vector y, DoubleDoubleFunction f) {
      OpenIntHashSet visited = new OpenIntHashSet();
      for (Element xe : x.nonZeroes()) {
        xe.set(f.apply(xe.get(), y.getQuick(xe.index())));
        visited.add(xe.index());
      }
      for (Element ye : y.nonZeroes()) {
        if (!visited.contains(ye.index())) {
          x.setQuick(ye.index(), f.apply(x.getQuick(ye.index()), ye.get()));
        }
      }
      return x;
    }
View Full Code Here
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
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
  }

  @Test
  @Repeat(iterations = 20)
  public void testAgainstReferenceOpenIntHashSet() {
    AbstractIntSet base = new OpenIntHashSet();
    HashSet<Integer> reference = Sets.newHashSet();

    List<Operation> ops = Lists.newArrayList();
    addOp(ops, Operation.ADD, 60);
    addOp(ops, Operation.REMOVE, 30);
    addOp(ops, Operation.INDEXOF, 30);
    addOp(ops, Operation.CLEAR, 5);
    addOp(ops, Operation.ISEMPTY, 2);
    addOp(ops, Operation.SIZE, 2);

    int max = randomIntBetween(1000, 20000);
    for (int reps = 0; reps < max; reps++) {
      // Ensure some collisions among keys.
      int k = randomIntBetween(0, max / 4);
      switch (randomFrom(ops)) {
        case ADD:
          assertEquals(reference.add(k), base.add(k));
          break;

        case REMOVE:
          assertEquals(reference.remove(k), base.remove(k));
          break;

        case INDEXOF:
          assertEquals(reference.contains(k), base.contains(k));
          break;

        case CLEAR:
          reference.clear();
          base.clear();
          break;

        case ISEMPTY:
          assertEquals(reference.isEmpty(), base.isEmpty());
          break;

        case SIZE:
          assertEquals(reference.size(), base.size());
          break;

        default:
          throw new RuntimeException();
      }
View Full Code Here
TOP

Related Classes of org.apache.mahout.math.set.OpenIntHashSet

  • org.apache.mahout.cf.taste.hadoop.als.PredictionMapper
  • org.apache.mahout.cf.taste.hadoop.als.RecommenderJob$PredictionMapper
  • org.apache.mahout.fpm.pfpgrowth.fpgrowth2.FPGrowthIds
  • org.apache.mahout.fpm.pfpgrowth.ParallelFPGrowthMapper
  • org.apache.mahout.math.randomized.RandomBlasting
  • org.apache.mahout.math.VectorBinaryAggregate$AggregateIterateUnionRandom
  • org.apache.mahout.math.VectorBinaryAssign$AssignIterateUnionRandomInplaceUpdates
  • org.apache.mahout.math.VectorBinaryAssign$AssignIterateUnionRandomMergeUpdates
  • resys.impl.datamodel.MovieLensDataModel
    • 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.