Package org.apache.mahout.math

Examples of org.apache.mahout.math.SparseRowMatrix

205
206
207
208
209
210
211
212
213
214
215
  public void train(Vector document, Vector docTopicCounts, boolean update, int numDocTopicIters) {
    while (true) {
      try {
        workQueue.put(new TrainerRunnable(readModel,
            update ? writeModel : null, document, docTopicCounts, new SparseRowMatrix(
            numTopics, numTerms, true), numDocTopicIters));
        return;
      } catch (InterruptedException e) {
        log.warn("Interrupted waiting to submit document to work queue: " + document, e);
      }
View Full Code Here
217
218
219
220
221
222
223
224
  }

  public void trainSync(Vector document, Vector docTopicCounts, boolean update,
      int numDocTopicIters) {
    new TrainerRunnable(readModel,
            update ? writeModel : null, document, docTopicCounts, new SparseRowMatrix(
            numTopics, numTerms, true), numDocTopicIters).run();
  }
View Full Code Here
223
224
225
226
227
228
229
230
231
            numTopics, numTerms, true), numDocTopicIters).run();
  }

  public double calculatePerplexity(Vector document, Vector docTopicCounts, int numDocTopicIters) {
    TrainerRunnable runner =  new TrainerRunnable(readModel,
            null, document, docTopicCounts, new SparseRowMatrix(
            numTopics, numTerms, true), numDocTopicIters);
    return runner.call();
  }
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
486
487
488
489
490
491
492
493
494
        vectorList.add(record.getSecond().get());
      }
    }
    int numRows = vectorList.size();
    int numCols = vectorList.get(0).size();
    return new SparseRowMatrix(numRows, numCols,
        vectorList.toArray(new Vector[vectorList.size()]), true,
        vectorList.get(0).isSequentialAccess());
  }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
      alphaI = in.readFloat();
      weightsPerFeature = VectorWritable.readVector(in);
      weightsPerLabel = new DenseVector(VectorWritable.readVector(in));
      perLabelThetaNormalizer = new DenseVector(VectorWritable.readVector(in));

      weightsPerLabelAndFeature = new SparseRowMatrix(weightsPerLabel.size(), weightsPerFeature.size() );
      for (int label = 0; label < weightsPerLabelAndFeature.numRows(); label++) {
        weightsPerLabelAndFeature.assignRow(label, VectorWritable.readVector(in));
      }
    } finally {
      Closeables.closeQuietly(in);
View Full Code Here
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
  public static Matrix randomSequentialAccessSparseMatrix(int numRows,
                                                          int nonNullRows,
                                                          int numCols,
                                                          int entriesPerRow,
                                                          double entryMean) {
    Matrix m = new SparseRowMatrix(numRows, numCols);
    //double n = 0;
    Random r = RandomUtils.getRandom();
    for (int i = 0; i < nonNullRows; i++) {
      Vector 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 {
        Vector other = m.viewRow(r.nextInt(numRows));
        if (other != null && other.getLengthSquared() > 0) {
          m.assignRow(c, other.clone());
        }
      }
      //n += m.getRow(c).getLengthSquared();
    }
    return m;
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
116
117
118
119
120
121
122
123
   */
  @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());

    RunningAverage avg = new FullRunningAverage();
    Iterator<MatrixSlice> sliceIterator = preferences.iterateAll();
    while (sliceIterator.hasNext()) {
      MatrixSlice slice = sliceIterator.next();
      Iterator<Vector.Element> elementIterator = slice.vector().iterateNonZero();
      while (elementIterator.hasNext()) {
        Vector.Element e = elementIterator.next();
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
190
191
192
193
194
195
196
197
  }

  @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());

    RunningAverage avg = new FullRunningAverage();
    Iterator<MatrixSlice> sliceIterator = preferences.iterateAll();
    while (sliceIterator.hasNext()) {
      MatrixSlice slice = sliceIterator.next();
      for (Vector.Element e : slice.vector()) {
        if (!Double.isNaN(e.get())) {
          double pref = e.get();
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
      weightsPerFeature = VectorWritable.readVector(in);
      weightsPerLabel = new DenseVector(VectorWritable.readVector(in));
      if (isComplementary){
        perLabelThetaNormalizer = new DenseVector(VectorWritable.readVector(in));
      }
      weightsPerLabelAndFeature = new SparseRowMatrix(weightsPerLabel.size(), weightsPerFeature.size());
      for (int label = 0; label < weightsPerLabelAndFeature.numRows(); label++) {
        weightsPerLabelAndFeature.assignRow(label, VectorWritable.readVector(in));
      }
    } finally {
      Closeables.close(in, true);
View Full Code Here
TOP

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

  • org.apache.mahout.cf.taste.hadoop.als.ParallelALSFactorizationJobTest
  • org.apache.mahout.cf.taste.impl.recommender.svd.ALSWRFactorizerTest
  • org.apache.mahout.classifier.naivebayes.NaiveBayesModel
  • org.apache.mahout.clustering.ClusteringTestUtils
  • org.apache.mahout.clustering.lda.cvb.CVB0DocInferenceMapper
  • org.apache.mahout.clustering.lda.cvb.InMemoryCollapsedVariationalBayes0
  • org.apache.mahout.clustering.lda.cvb.ModelTrainer
  • org.apache.mahout.math.decomposer.lanczos.LanczosSolver
  • org.apache.mahout.math.decomposer.SolverTest
  • org.apache.mahout.math.hadoop.decomposer.EigenVerificationJob
    • 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.