Package org.apache.mahout.math

Examples of org.apache.mahout.math.Vector

74
75
76
77
78
79
80
81
82
83
84
    Path path = new Path("testdata/clusters/part-00000");
    SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
        path, Text.class, Cluster.class);
   
    for (int i = 0; i < k; i++) {
      Vector vec = vectors.get(i);
      Cluster cluster = new Cluster(vec, i, new EuclideanDistanceMeasure());
      writer.append(new Text(cluster.getIdentifier()), cluster);
    }
    writer.close();
   
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
    FeatureVectorEncoder[] encoder = new FeatureVectorEncoder[FIELDS];
    for (int i = 0; i < FIELDS; i++) {
      encoder[i] = new ConstantValueEncoder("v" + i);
    }
    long t0 = System.currentTimeMillis();
    Vector v = new DenseVector(1000);
    ByteBuffer buf = ByteBuffer.wrap(FileUtils
        .readFileToByteArray(new File(args[1])));
    FastLine line = FastLine.read(buf);
    while (line != null) {
      v.assign(0);
      for (int i = 0; i < FIELDS; i++) {
        encoder[i].addToVector((byte[]) null, line.getDouble(i), v);
      }
      line = FastLine.read(buf);
    }
View Full Code Here
26
27
28
29
30
31
32
33
34
35
36
    StringReader in = new StringReader("text to magically vectorize");
    TokenStream ts = analyzer.tokenStream("body", in);
    TermAttribute termAtt = ts.addAttribute(TermAttribute.class);

    Vector v1 = new RandomAccessSparseVector(100);                  
    while (ts.incrementToken()) {
      char[] termBuffer = termAtt.termBuffer();
      int termLen = termAtt.termLength();
      String w = new String(termBuffer, 0, termLen);                
      encoder.addToVector(w, 1, v1);                                
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
    int[] bumps = {1, 2, 5};
    for (File file : files) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

      Vector v = encodeFeatureVector(file);
      learningAlgorithm.train(actual, v);

      k++;

      int bump = bumps[(int) Math.floor(step) % bumps.length];
View Full Code Here
243
244
245
246
247
248
249
250
251
252
253
    encoder.setTraceDictionary(traceDictionary);
    bias.setTraceDictionary(traceDictionary);

    for (File file : permute(files, rand).subList(0, 500)) {
      traceDictionary.clear();
      Vector v = encodeFeatureVector(file);
      md.update(v, traceDictionary, model);
    }

    List<String> ngNames = Lists.newArrayList(newsGroups.values());
    List<ModelDissector.Weight> weights = md.summary(100);
View Full Code Here
285
286
287
288
289
290
291
292
293
294
      }
    } finally {
      reader.close();
    }

    Vector v = new RandomAccessSparseVector(FEATURES);
    bias.addToVector((byte[]) null, 1, v);
    encoder.flush(1, v);
    return v;
  }
View Full Code Here
15
16
17
18
19
20
21
22
23
24
25
  @Override
  protected void reduce(Text tag,
                        Iterable<VectorWritable> values,
                        Context context) throws IOException,
                                        InterruptedException {
    Vector vector = null;
    for (VectorWritable partialVector : values) {
      if (vector == null) {
        vector = partialVector.get().like();
      }
      partialVector.get().addTo(vector);
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
  private Map<Long, Double> interactionCache = Maps.newHashMap();

  private FeatureEncoder encoder = new FeatureEncoder();

  public List<ScoredItem> topItems(User u, int limit) {
    Vector userVector = new RandomAccessSparseVector(model.numFeatures());
    encoder.addUserFeatures(u, userVector);
    double userScore = model.classifyScalarNoLink(userVector);

    PriorityQueue<ScoredItem> r = new PriorityQueue<ScoredItem>();
    for (Item item : items) {
      Double itemScore = itemCache.get(item);
      if (itemScore == null) {
        Vector v = new RandomAccessSparseVector(model.numFeatures());
        encoder.addItemFeatures(item, v);
        itemScore = model.classifyScalarNoLink(v);
        itemCache.put(item, itemScore);
      }

      long code = encoder.interactionHash(u, item);
      Double interactionScore = interactionCache.get(code);
      if (interactionScore == null) {
        Vector v = new RandomAccessSparseVector(model.numFeatures());
        encoder.addInteractions(u, item, v);
        interactionScore = model.classifyScalarNoLink(v);
        interactionCache.put(code, interactionScore);
      }
      double score = userScore + itemScore + interactionScore;
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
    FeatureVectorEncoder[] encoder = new FeatureVectorEncoder[FIELDS];
    for (int i = 0; i < FIELDS; i++) {
      encoder[i] = new ConstantValueEncoder("v" + i);
    }
    long t0 = System.currentTimeMillis();
    Vector v = new DenseVector(1000);
    BufferedReader in = new BufferedReader(new FileReader(args[1]));
    String line = in.readLine();
    while (line != null) {
      v.assign(0);
      Line x = new Line(line);
      for (int i = 0; i < FIELDS; i++) {
        encoder[i].addToVector((byte[]) null, x.getDouble(i), v);
      }
      line = in.readLine();
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
public class VectorExamplesTest extends TamingTextTestJ4 {
  @Test
  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
TOP

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

  • com.fujitsu.ca.fic.dataloaders.bns.corpus.BnsCorpusLineParserTest
  • mia.classifier.ch16.train.TrainNewsGroups
  • mia.clustering.ch07.SimpleKMeansClustering
  • org.apache.mahout.cf.taste.hadoop.als.ALS
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJob
  • org.apache.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer
  • org.apache.mahout.cf.taste.hadoop.item.RecommenderJobTest
  • org.apache.mahout.cf.taste.hadoop.item.UserVectorSplitterMapper
  • org.apache.mahout.cf.taste.impl.recommender.svd.ALSWRFactorizerTest
  • org.apache.mahout.cf.taste.impl.recommender.svd.ParallelSGDFactorizerTest
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.