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

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}

    printStats(stats, "Create (incrementally)", "RandSparseVector");


    stats = new TimingStatistics();
    for (int l = 0; l < loop; l++) {
      for (int i = 0; i < numVectors; i++) {
        vectors[2][i] = new SequentialAccessSparseVector(cardinality);
        buildVectorIncrementally(stats, i, vectors[2][i], false);
      }
    }
    printStats(stats, "Create (incrementally)", "SeqSparseVector");
  }

View Full Code Here

                                                          double entryMean) {
    SparseRowMatrix m = new SparseRowMatrix(new int[]{numRows, numCols});
    //double n = 0;
    Random r = new Random(1234L);
    for (int i = 0; i < nonNullRows; i++) {
      SequentialAccessSparseVector v = new SequentialAccessSparseVector(numCols);
      for (int j = 0; j < entriesPerRow; j++) {
        int col = r.nextInt(numCols);
        double val = r.nextGaussian();
        v.set(col, val * entryMean);
      }
      int c = r.nextInt(numRows);
      if (r.nextBoolean() || numRows == nonNullRows) {
        m.assignRow(numRows == nonNullRows ? i : c, v);
      } else {

View Full Code Here

      int prevPercentDone = 1;


      for (Map.Entry<String, List<Integer>> itemFeature : itemFeaturesMap.entrySet()) {
        int numfeatures = itemFeature.getValue().size();
        itemWritable.set(itemFeature.getKey());
        Vector featureVector = new SequentialAccessSparseVector(numfeatures);
        int i = 0;
        for (Integer feature : itemFeature.getValue()) {
          featureVector.setQuick(i++, feature);
        }
        featuresWritable.set(featureVector);
        writer.append(itemWritable, featuresWritable);
        // Update the progress
        double percentDone = ((++doneRecords) * 100.0) / totalRecords;

View Full Code Here

        temporaryVector.setQuick(entry.getCol(), entry.getVal());
        if (++similaritiesSet == maxSimilaritiesPerRow) {
          break;
        }
      }
      SequentialAccessSparseVector vector = new SequentialAccessSparseVector(temporaryVector);
      ctx.write(new IntWritable(key.getRow()), new VectorWritable(vector));
    }

View Full Code Here

  }


  public static List<Vector> getPoints(double[][] raw) {
    List<Vector> points = new ArrayList<Vector>();
    for (double[] fr : raw) {
      Vector vec = new SequentialAccessSparseVector(fr.length);
      vec.assign(fr);
      points.add(vec);
    }
    return points;
  }

View Full Code Here

  }
  
  @Override
  public void write(DataOutput out) throws IOException {
    super.write(out);
    VectorWritable.writeVector(out, new SequentialAccessSparseVector(computeCentroid()));
    out.writeInt(boundPoints.size());
    for (int v : boundPoints.elements()) {
      out.writeInt(v);
    }
  }

View Full Code Here

      Vector accumulator = new RandomAccessSparseVector(it.next().get());
      while (it.hasNext()) {
        Vector row = it.next().get();
        accumulator.assign(row, Functions.PLUS);
      }
      out.collect(rowNum, new VectorWritable(new SequentialAccessSparseVector(accumulator)));
    }

View Full Code Here

    
    // read in the two vectors from the cache
    eigenvalues = VectorCache.load(config);
    diagonal = VectorCache.load(config);
    if (!(eigenvalues instanceof SequentialAccessSparseVector || eigenvalues instanceof DenseVector)) {
      eigenvalues = new SequentialAccessSparseVector(eigenvalues);
    }
    if (!(diagonal instanceof SequentialAccessSparseVector || diagonal instanceof DenseVector)) {
      diagonal = new SequentialAccessSparseVector(diagonal);
    }
  }

View Full Code Here


    return mapping;
  }


  protected Vector sparseItemRatingVector(PreferenceArray prefs) {
    SequentialAccessSparseVector ratings = new SequentialAccessSparseVector(Integer.MAX_VALUE, prefs.length());
    for (Preference preference : prefs) {
      ratings.set((int) preference.getUserID(), preference.getValue());
    }
    return ratings;
  }

View Full Code Here

    }
    return ratings;
  }


  protected Vector sparseUserRatingVector(PreferenceArray prefs) {
    SequentialAccessSparseVector ratings = new SequentialAccessSparseVector(Integer.MAX_VALUE, prefs.length());
    for (Preference preference : prefs) {
      ratings.set((int) preference.getItemID(), preference.getValue());
    }
    return ratings;
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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.