Examples of org.apache.mahout.math.SequentialAccessSparseVector$AbstractElement

org.apache.mahout.math.SequentialAccessSparseVector
Implements vector that only stores non-zero doubles as a pair of parallel arrays (OrderedIntDoubleMapping), one int[], one double[]. If there are k non-zero elements in the vector, this implementation has O(log(k)) random-access read performance, and O(k) random-access write performance, which is far below that of the hashmap based {@link org.apache.mahout.math.RandomAccessSparseVector RandomAccessSparseVector}. This class is primarily used for operations where the all the elements will be accessed in a read-only fashion sequentially: methods which operate not via get() or set(), but via iterateNonZero(), such as (but not limited to) :
- dot(Vector)
- addTo(Vector)
Note that the Vector passed to these above methods may (and currently, are) be used in a random access fashion, so for example, calling SequentialAccessSparseVector.dot(SequentialAccessSparseVector) is slow. TODO: this need not be the case - both are ordered, so this should be very fast if implmented in this class
{@see OrderedIntDoubleMapping}

    }


    private void extendAColIfNeeded(int col, int rowCount) {
      if (aCols[col] == null) {
        aCols[col] =
          new SequentialAccessSparseVector(rowCount < blockHeight ? blockHeight
              : rowCount, 1);
      } else if (aCols[col].size() < rowCount) {
        Vector newVec =
          new SequentialAccessSparseVector(rowCount + blockHeight,
                                           aCols[col].getNumNondefaultElements() << 1);
        newVec.viewPart(0, aCols[col].size()).assign(aCols[col]);
        aCols[col] = newVec;
      }
    }

View Full Code Here

  }


  @Test
  public void testCanopyAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("C-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  }


  @Test
  public void testCanopyAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("C-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  }


  @Test
  public void testClusterAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new org.apache.mahout.clustering.kmeans.Cluster(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("CL-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  }


  @Test
  public void testClusterAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new org.apache.mahout.clustering.kmeans.Cluster(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("CL-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  }


  @Test
  public void testMSCanopyAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new MeanShiftCanopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("MSC-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  }


  @Test
  public void testMSCanopyAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new MeanShiftCanopy(m, 123, measure);
    String[] bindings = { "fee", null, "foo" };
    String formatString = cluster.asFormatString(bindings);
    assertEquals("MSC-123{n=0 c=[fee:1.100, foo:3.300] r=[]}", formatString);
  }

View Full Code Here

    }


    @Override
    protected void map(IntWritable userOrItemID, VectorWritable ratingsWritable, Context ctx)
        throws IOException, InterruptedException {
      Vector ratings = new SequentialAccessSparseVector(ratingsWritable.get());
      List<Vector> featureVectors = Lists.newArrayList();
      Iterator<Vector.Element> interactions = ratings.iterateNonZero();
      while (interactions.hasNext()) {
        int index = interactions.next().index();
        featureVectors.add(UorM.get(index));
      }

View Full Code Here

    }


    @Override
    protected void map(IntWritable userOrItemID, VectorWritable ratingsWritable, Context ctx)
        throws IOException, InterruptedException {
      Vector ratings = new SequentialAccessSparseVector(ratingsWritable.get());


      Vector uiOrmj = solver.solve(ratings);


      ctx.write(userOrItemID, new VectorWritable(uiOrmj));
    }

View Full Code Here

    return sampler.sample(topicTermCounts.viewRow(topic));
  }


  public void reset() {
    for(int x = 0; x < numTopics; x++) {
      topicTermCounts.assignRow(x, new SequentialAccessSparseVector(numTerms));
    }
    topicSums.assign(1.0);
    initializeThreadPool();
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.mahout.math.SequentialAccessSparseVector$AbstractElement

com.fujitsu.ca.fic.dataloaders.bns.corpus.BnsCorpusLineParser

com.fujitsu.ca.fic.dataloaders.bns.corpus.sequence.mapreduce.BnsPigOutputToVectorMapperTest

com.fujitsu.ca.fic.dataloaders.bns.corpus.sequence.mapreduce.VectorToSequenceReducerTest

com.mozilla.grouperfish.transforms.coclustering.pig.storage.MahoutVectorStorage

com.tamingtext.mahout.VectorExamplesTest

com.twitter.elephantbird.pig.mahout.VectorWritableConverter

mia.classifier.ch14.TokenizingAndVectorizingText

mia.clustering.ch12.lastfm.VectorMapper

org.apache.mahout.benchmark.VectorBenchmarks

org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob$MergeUserVectorsReducer

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.