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

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 {@link OrderedIntDoubleMapping}

  }


  @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);
    System.out.println(formatString);
    assertEquals("format", "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);
    System.out.println(formatString);
    assertEquals("format", "MSC-123{n=0 c=[fee:1.100, foo:3.300] r=[]}", formatString);

View Full Code Here

        df = minDf;
      }
      vector.setQuick(e.index(), tfidf.calculate((int) e.get(), (int) df, (int) featureCount, (int) vectorCount));
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    
    if (namedVector) {
      vector = new NamedVector(vector, key.toString());
    }

View Full Code Here

          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      }
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    
    if (namedVector) {
      vector = new NamedVector(vector, key.toString());
    }

View Full Code Here

      line = in.readLine();
      if (showScores) {
        System.out.printf("\"%s\",\"%s\",\"%s\"\n", "target", "model-output", "log-likelihood");
      }
      while (line != null) {
        Vector v = new SequentialAccessSparseVector(lmp.getNumFeatures());
        int target = csv.processLine(line, v);
        double score = lr.classifyScalar(v);
        if (showScores) {
          System.out.printf("%d,%.3f,%.6f\n", target, score, lr.logLikelihood(target, v));
        }

View Full Code Here


    @Override
    public void reduce(WritableComparable<?> key, Iterator<VectorWritable> vectors,
                       OutputCollector<WritableComparable<?>, VectorWritable> out, Reporter reporter) throws IOException {
      Vector merged = VectorWritable.merge(vectors).get();
      out.collect(key, new VectorWritable(new SequentialAccessSparseVector(merged)));
    }

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


  @Override
  protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
    Vector vector;
    if (sequentialVecs) {
      vector = new SequentialAccessSparseVector(cardinality);
    } else {
      vector = new RandomAccessSparseVector(cardinality);
    }
    if (namedVectors){
      vector = new NamedVector(vector, key.toString());

View Full Code Here

        df = minDf;
      }
      vector.setQuick(e.index(), tfidf.calculate((int) e.get(), (int) df, (int) featureCount, (int) vectorCount));
    }
    if (sequentialAccess) {
      vector = new SequentialAccessSparseVector(vector);
    }
    
    if (namedVector) {
      vector = new NamedVector(vector, key.toString());
    }

View Full Code Here

    VectorWritable vw = new VectorWritable();
    IntWritable roww = new IntWritable();


    double muAmplitude = 50.0;
    for (int i = 0; i < m; i++) {
      Vector dv = new SequentialAccessSparseVector(n);
      for (int j = 0; j < n * percent / 100; j++) {
        dv.setQuick(rnd.nextInt(n), muAmplitude * (rnd.nextDouble() - 0.5));
      }
      roww.set(i);
      vw.set(dv);
      w.append(roww, vw);
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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.