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

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}

    }
    String artist = fields[1];
    String tag = fields[2];
    double weight = Double.parseDouble(fields[3]);
    NamedVector vector = new NamedVector(
        new SequentialAccessSparseVector(dictionary.size()), tag);
    vector.set(dictionary.get(artist), weight);
    writer.set(vector);
    context.write(new Text(tag), writer);
  }

View Full Code Here

      char[] termBuffer = termAtt.termBuffer();
      int termLen = termAtt.termLength();
      String w = new String(termBuffer, 0, termLen);                 
      encoder.addToVector(w, 1, v1);                                 
    }
    System.out.printf("%s\n", new SequentialAccessSparseVector(v1));
  }

View Full Code Here

  public void testProgrammatic() throws Exception {
    //<start id="vec.examples.programmatic"/>
    double[] vals = new double[]{0.3, 1.8, 200.228};
    Vector dense = new DenseVector(vals);//<co id="vec.exam.dense"/>
    assertTrue(dense.size() == 3);
    Vector sparseSame = new SequentialAccessSparseVector(3);//<co id="vec.exam.sparse.same"/>
    Vector sparse = new SequentialAccessSparseVector(3000);//<co id="vec.exam.sparse"/>
    for (int i = 0; i < vals.length; i++) {//<co id="vec.exam.assign.sparse"/>
      sparseSame.set(i, vals[i]);
      sparse.set(i, vals[i]);
    }
    assertFalse(dense.equals(sparse));//<co id="vec.exam.notequals.d.s"/>
    assertEquals(dense, sparseSame);//<co id="vec.exam.equals.d.s"/>
    assertFalse(sparse.equals(sparseSame));
    /*
<calloutlist>
    <callout arearefs="vec.exam.dense"><para>Create a <classname>DenseVector</classname> with a label of "my-dense" and 3 values.  The cardinality of this vector is 3 </para></callout>
    <callout arearefs="vec.exam.sparse.same"><para>Create a <classname>SparseVector</classname> with a label of my-sparse-same that has cardinality of 3</para></callout>

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

      RandomAccessSparseVector tmp = new RandomAccessSparseVector(newNumCols, 100);
      while(it.hasNext()) {
        DistributedRowMatrix.MatrixEntryWritable e = it.next();
        tmp.setQuick(e.getCol(), e.getVal());
      }
      SequentialAccessSparseVector outVector = new SequentialAccessSparseVector(tmp);
      out.collect(outRow, new VectorWritable(outVector));
    }

View Full Code Here

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


  public void testCanopyAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new Canopy(m, 123);
    String formatString = cluster.asFormatString(null);
    System.out.println(formatString);
    assertEquals("format", "C123: [0:1.100, 2:3.300]", formatString);
  }

View Full Code Here

    assertEquals("format", "C123: [fee:1.100, 1:2.200, 2:3.300]", formatString);
  }


  public void testCanopyAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new Canopy(m, 123);
    String formatString = cluster.asFormatString(null);
    System.out.println(formatString);
    assertEquals("format", "C123: [0:1.100, 2:3.300]", formatString);
  }

View Full Code Here

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


  public void testClusterAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new Cluster(m, 123);
    String formatString = cluster.asFormatString(null);
    System.out.println(formatString);
    assertEquals("format", "C123: [0:1.100, 2:3.300]", formatString);
  }

View Full Code Here

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


  public void testClusterAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new Cluster(m, 123);
    String formatString = cluster.asFormatString(null);
    System.out.println(formatString);
    assertEquals("format", "C123: [0:1.100, 2:3.300]", formatString);
  }

View Full Code Here

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


  public void testMSCanopyAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Printable cluster = new MeanShiftCanopy(m, 123);
    String formatString = cluster.asFormatString(null);
    System.out.println(formatString);
    assertEquals("format", "C123: [0:1.100, 2:3.300]", formatString);
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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.