Examples of org.apache.mahout.math.SequentialAccessSparseVector

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}

    assertEquals("format", "C123: [fee:1.100, 1:2.200, foo:3.300]", formatString);
  }


  public void testMSCanopyAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new MeanShiftCanopy(m, 123);
    String[] bindings = { "fee", null, "foo" };
    String formatString = cluster.asFormatString(bindings);
    System.out.println(formatString);
    assertEquals("format", "C123: [fee:1.100, foo:3.300]", formatString);

View Full Code Here

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

View Full Code Here

        NullWritable nw = NullWritable.get();
        reader.next(nw, val);
        reader.close();
        inputVector = val.get();
        if(!(inputVector instanceof SequentialAccessSparseVector || inputVector instanceof DenseVector)) {
          inputVector = new SequentialAccessSparseVector(inputVector);
        }
        int outDim = conf.getInt(OUTPUT_VECTOR_DIMENSION, Integer.MAX_VALUE);
        outputVector = conf.getBoolean(IS_SPARSE_OUTPUT, false)
                     ? new RandomAccessSparseVector(outDim, 10)
                     : new DenseVector(outDim);

View Full Code Here

  
  public static List<Vector> getPoints(double[][] raw) {
    List<Vector> points = new ArrayList<Vector>();
    for (int i = 0; i < raw.length; i++) {
      double[] fr = raw[i];
      Vector vec = new SequentialAccessSparseVector(String.valueOf(i), fr.length);
      vec.assign(fr);
      points.add(vec);
    }
    return points;
  }

View Full Code Here

          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      }
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    // if the vector has no nonZero entries (nothing in the dictionary), let's not waste space sending it to disk.
    if(vector.getNumNondefaultElements() > 0) {
      vectorWritable.set(vector);
      output.collect(key, vectorWritable);

View Full Code Here

    }
    if (normPower != PartialVectorMerger.NO_NORMALIZING) {
      vector = vector.normalize(normPower);
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    vectorWritable.set(vector);
    output.collect(key, vectorWritable);
  }

View Full Code Here

    this.sparsity = sparsity;
    this.numVectors = numVectors;
    this.loop = loop;
    this.opsPerUnit = opsPerUnit;
    for (int i = 0; i < numVectors; i++) {
      Vector v = new SequentialAccessSparseVector(cardinality, sparsity); // sparsity!
      BitSet featureSpace = new BitSet(cardinality);
      int[] indexes = new int[sparsity];
      double[] values = new double[sparsity];
      int j = 0;
      while (j < sparsity) {
        double value = r.nextGaussian();
        int index = r.nextInt(cardinality);
        if (featureSpace.get(index) == false) {
          featureSpace.set(index);
          indexes[j] = index;
          values[j++] = value;
          v.set(index, value);
        }
      }
      randomVectorIndices.add(indexes);
      randomVectorValues.add(values);
      randomVectors.add(v);

View Full Code Here

    
    stats = new TimingStatistics();
    for (int l = 0; l < loop; l++) {
      for (int i = 0; i < numVectors; i++) {
        TimingStatistics.Call call = stats.newCall();
        vectors[2][i] = new SequentialAccessSparseVector(randomVectors.get(i));
        call.end();
      }
    }
    printStats(stats, "Create (copy)", "SeqSparseVector");

View Full Code Here

    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

      }
      vector.setQuick(e.index(), tfidf.calculate((int) e.get(), (int) df, (int) featureCount,
        (int) vectorCount));
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    vectorWritable.set(vector);
    output.collect(key, vectorWritable);
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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.