Package org.apache.mahout.math

Examples of org.apache.mahout.math.Matrix

96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
        desiredRank, corpus.numRows());
    int i = state.getIterationNumber();
    Vector currentVector = state.getBasisVector(i - 1);
    Vector previousVector = state.getBasisVector(i - 2);
    double beta = 0;
    Matrix triDiag = state.getDiagonalMatrix();
    while (i < desiredRank) {
      startTime(TimingSection.ITERATE);
      Vector nextVector = isSymmetric ? corpus.times(currentVector) : corpus.timesSquared(currentVector);
      log.info("{} passes through the corpus so far...", i);
      if(state.getScaleFactor() <= 0) {
        state.setScaleFactor(calculateScaleFactor(nextVector));
      }
      nextVector.assign(new Scale(1.0 / state.getScaleFactor()));
      if(previousVector != null) {
        nextVector.assign(previousVector, new PlusMult(-beta));
      }
      // now orthogonalize
      double alpha = currentVector.dot(nextVector);
      nextVector.assign(currentVector, new PlusMult(-alpha));
      endTime(TimingSection.ITERATE);
      startTime(TimingSection.ORTHOGANLIZE);
      orthoganalizeAgainstAllButLast(nextVector, state);
      endTime(TimingSection.ORTHOGANLIZE);
      // and normalize
      beta = nextVector.norm(2);
      if (outOfRange(beta) || outOfRange(alpha)) {
        log.warn("Lanczos parameters out of range: alpha = {}, beta = {}.  Bailing out early!",
            alpha, beta);
        break;
      }
      nextVector.assign(new Scale(1 / beta));
      state.setBasisVector(i, nextVector);
      previousVector = currentVector;
      currentVector = nextVector;
      // save the projections and norms!
      triDiag.set(i - 1, i - 1, alpha);
      if (i < desiredRank - 1) {
        triDiag.set(i - 1, i, beta);
        triDiag.set(i, i - 1, beta);
      }
      state.setIterationNumber(++i);
    }
    startTime(TimingSection.TRIDIAG_DECOMP);
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
   */
  @Test
  public void completeJobToyExample() throws Exception {

    Double na = Double.NaN;
    Matrix preferences = new SparseRowMatrix(4, 4, new Vector[] {
        new DenseVector(new double[] { 5.0, 5.0, 2.0, na }),
        new DenseVector(new double[] { 2.0, na,  3.0, 5.0 }),
        new DenseVector(new double[] { na,  5.0, na,  3.0 }),
        new DenseVector(new double[] { 3.0, na,  na,  5.0 }) });

    writeLines(inputFile, preferencesAsText(preferences));

    ParallelALSFactorizationJob alsFactorization = new ParallelALSFactorizationJob();
    alsFactorization.setConf(conf);

    int numFeatures = 3;
    int numIterations = 5;
    double lambda = 0.065;

    alsFactorization.run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(),
        "--tempDir", tmpDir.getAbsolutePath(), "--lambda", String.valueOf(lambda),
        "--numFeatures", String.valueOf(numFeatures), "--numIterations", String.valueOf(numIterations) });

    Matrix u = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "U/part-m-00000"),
        preferences.numRows(), numFeatures);
    Matrix m = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "M/part-m-00000"),
        preferences.numCols(), numFeatures);

    StringBuilder info = new StringBuilder();
    info.append("\nA - users x items\n\n");
    info.append(MathHelper.nice(preferences));
    info.append("\nU - users x features\n\n");
    info.append(MathHelper.nice(u));
    info.append("\nM - items x features\n\n");
    info.append(MathHelper.nice(m));
    Matrix Ak = u.times(m.transpose());
    info.append("\nAk - users x items\n\n");
    info.append(MathHelper.nice(Ak));
    info.append('\n');

    log.info(info.toString());
View Full Code Here
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
  }

  @Test
  public void completeJobImplicitToyExample() throws Exception {

    Matrix observations = new SparseRowMatrix(4, 4, new Vector[] {
        new DenseVector(new double[] { 5.0, 5.0, 2.0, 0 }),
        new DenseVector(new double[] { 2.0, 0,   3.0, 5.0 }),
        new DenseVector(new double[] { 0,   5.0, 0,   3.0 }),
        new DenseVector(new double[] { 3.0, 0,   0,   5.0 }) });

    Matrix preferences = new SparseRowMatrix(4, 4, new Vector[] {
        new DenseVector(new double[] { 1.0, 1.0, 1.0, 0 }),
        new DenseVector(new double[] { 1.0, 0,   1.0, 1.0 }),
        new DenseVector(new double[] { 0,   1.0, 0,   1.0 }),
        new DenseVector(new double[] { 1.0, 0,   0,   1.0 }) });

    writeLines(inputFile, preferencesAsText(observations));

    ParallelALSFactorizationJob alsFactorization = new ParallelALSFactorizationJob();
    alsFactorization.setConf(conf);

    int numFeatures = 3;
    int numIterations = 5;
    double lambda = 0.065;
    double alpha = 20;

    alsFactorization.run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(),
        "--tempDir", tmpDir.getAbsolutePath(), "--lambda", String.valueOf(lambda),
        "--implicitFeedback", String.valueOf(true), "--alpha", String.valueOf(alpha),
        "--numFeatures", String.valueOf(numFeatures), "--numIterations", String.valueOf(numIterations) });

    Matrix u = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "U/part-m-00000"),
        observations.numRows(), numFeatures);
    Matrix m = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(), "M/part-m-00000"),
        observations.numCols(), numFeatures);

    StringBuilder info = new StringBuilder();
    info.append("\nObservations - users x items\n");
    info.append(MathHelper.nice(observations));
    info.append("\nA - users x items\n\n");
    info.append(MathHelper.nice(preferences));
    info.append("\nU - users x features\n\n");
    info.append(MathHelper.nice(u));
    info.append("\nM - items x features\n\n");
    info.append(MathHelper.nice(m));
    Matrix Ak = u.times(m.transpose());
    info.append("\nAk - users x items\n\n");
    info.append(MathHelper.nice(Ak));
    info.append('\n');

    log.info(info.toString());
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
  @Override
  public void map(IntWritable docId, VectorWritable doc, Context context)
      throws IOException, InterruptedException {
    int numTopics = getNumTopics();
    Vector docTopics = new DenseVector(new double[numTopics]).assign(1.0 /numTopics);
    Matrix docModel = new SparseRowMatrix(numTopics, doc.get().size());
    int maxIters = getMaxIters();
    ModelTrainer modelTrainer = getModelTrainer();
    for(int i = 0; i < maxIters; i++) {
      modelTrainer.getReadModel().trainDocTopicModel(doc.get(), docTopics, docModel);
    }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
                                 int startRowKey) throws IOException {

    Random rnd = RandomUtils.getRandom();

    int svCnt = svalues.size();
    Matrix v = generateDenseOrthonormalRandom(n, svCnt, rnd);
    Matrix u = generateDenseOrthonormalRandom(m, svCnt, rnd);

    // apply singular values
    Matrix mx = m > n ? v : u;
    for (int i = 0; i < svCnt; i++) {
      mx.assignColumn(i, mx.viewColumn(i).times(svalues.getQuick(i)));
    }

    SequenceFile.Writer w =
      SequenceFile.createWriter(dfs,
                                dfs.getConf(),
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
    }

  }

  static Matrix generateDenseOrthonormalRandom(int m, int n, Random rnd) {
    Matrix result = new DenseMatrix(m, n);
    for (int j = 0; j < n; j++) {
      for (int i = 0; i < m; i++) {
        result.setQuick(i, j, rnd.nextDouble() - 0.5);
      }
    }
    GramSchmidt.orthonormalizeColumns(result);
    SSVDPrototypeTest.assertOrthonormality(result, false, 1.0e-10);
    return result;
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
        "56,34",
        "56,56",
        "56,78",
        "78,34");

    Matrix expectedAdjacencyMatrix = new DenseMatrix(new double[][] {
        { 0, 1, 1, 0 },
        { 0, 1, 0, 1 },
        { 1, 1, 1, 1 },
        { 0, 1, 0, 0 } });

    AdjacencyMatrixJob createAdjacencyMatrix = new AdjacencyMatrixJob();
    createAdjacencyMatrix.setConf(conf);
    createAdjacencyMatrix.run(new String[] { "--vertices", verticesFile.getAbsolutePath(),
        "--edges", edgesFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath() });

    int numVertices = HadoopUtil.readInt(new Path(outputDir.getAbsolutePath(), AdjacencyMatrixJob.NUM_VERTICES), conf);
    Matrix actualAdjacencyMatrix = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(),
        AdjacencyMatrixJob.ADJACENCY_MATRIX + "/part-r-00000"), numVertices, numVertices);

    StringBuilder info = new StringBuilder();
    info.append("expected adjacency matrix:\n");
    info.append(MathHelper.nice(expectedAdjacencyMatrix));
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
        "34,78",
        "56,34",
        "56,56",
        "56,78");

    Matrix expectedAdjacencyMatrix = new DenseMatrix(new double[][] {
        { 0, 1, 1, 0 },
        { 1, 1, 1, 1 },
        { 1, 1, 1, 1 },
        { 0, 1, 1, 0 } });

    AdjacencyMatrixJob createAdjacencyMatrix = new AdjacencyMatrixJob();
    createAdjacencyMatrix.setConf(conf);
    createAdjacencyMatrix.run(new String[] { "--vertices", verticesFile.getAbsolutePath(),
        "--edges", edgesFile.getAbsolutePath(), "--symmetric", String.valueOf(true),
        "--output", outputDir.getAbsolutePath() });

    int numVertices = HadoopUtil.readInt(new Path(outputDir.getAbsolutePath(), AdjacencyMatrixJob.NUM_VERTICES), conf);
    Matrix actualAdjacencyMatrix = MathHelper.readMatrix(conf, new Path(outputDir.getAbsolutePath(),
        AdjacencyMatrixJob.ADJACENCY_MATRIX + "/part-r-00000"), numVertices, numVertices);

    StringBuilder info = new StringBuilder();
    info.append("expected adjacency matrix:\n");
    info.append(MathHelper.nice(expectedAdjacencyMatrix));
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
    for(int i=0; i<terms.length; i++) {
      terms[i] = String.valueOf((char) (i + 'a'));
    }
    int numGeneratingTopics = 3;
    int numTerms = 26;
    Matrix matrix = ClusteringTestUtils.randomStructuredModel(numGeneratingTopics, numTerms, new DoubleFunction() {
      @Override public double apply(double d) {
        return 1.0 / Math.pow(d + 1.0, 2);
      }
    });

    int numDocs = 100;
    int numSamples = 20;
    int numTopicsPerDoc = 1;

    Matrix sampledCorpus = ClusteringTestUtils.sampledCorpus(matrix, RandomUtils.getRandom(),
                                                             numDocs, numSamples, numTopicsPerDoc);

    List<Double> perplexities = Lists.newArrayList();
    int numTrials = 1;
    for (int numTestTopics = 1; numTestTopics < 2 * numGeneratingTopics; numTestTopics++) {
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
  @Test
  public void testRandomStructuredModelViaMR() throws Exception {
    int numGeneratingTopics = 3;
    int numTerms = 9;
    Matrix matrix = ClusteringTestUtils.randomStructuredModel(numGeneratingTopics, numTerms, new DoubleFunction() {
      @Override
      public double apply(double d) {
        return 1.0 / Math.pow(d + 1.0, 3);
      }
    });

    int numDocs = 500;
    int numSamples = 10;
    int numTopicsPerDoc = 1;

    Matrix sampledCorpus = ClusteringTestUtils.sampledCorpus(matrix, RandomUtils.getRandom(1234),
                                                             numDocs, numSamples, numTopicsPerDoc);

    Path sampleCorpusPath = getTestTempDirPath("corpus");
    MatrixUtils.write(sampleCorpusPath, new Configuration(), sampledCorpus);
    int numIterations = 5;
View Full Code Here
TOP

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

  • com.mapr.stats.bandit.ContextualBayesBanditTest
  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJobTest
  • org.apache.mahout.cf.taste.impl.recommender.svd.ImplicitLinearRegressionFactorizer
  • org.apache.mahout.classifier.AbstractVectorClassifier
  • org.apache.mahout.classifier.ConfusionMatrix
  • org.apache.mahout.classifier.ConfusionMatrixDumper
  • org.apache.mahout.classifier.ConfusionMatrixTest
  • org.apache.mahout.classifier.discriminative.PerceptronTrainerTest
  • org.apache.mahout.classifier.discriminative.WinnowTrainerTest
  • org.apache.mahout.classifier.evaluation.AucTest
    • 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.