Examples of OnlineSummarizer

Examples of org.apache.mahout.math.stats.OnlineSummarizer

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
76
  }

  public static void printSummaries(List<OnlineSummarizer> summarizers, String type, PrintWriter fileOut) {
    double maxDistance = 0;
    for (int i = 0; i < summarizers.size(); ++i) {
      OnlineSummarizer summarizer = summarizers.get(i);
      if (summarizer.getCount() == 0) {
        System.out.printf("Cluster %d is empty\n", i);
        continue;
      }
      maxDistance = Math.max(maxDistance, summarizer.getMax());
      System.out.printf("Average distance in cluster %d [%d]: %f\n", i, summarizer.getCount(), summarizer.getMean());
      // If there is just one point in the cluster, quartiles cannot be estimated. We'll just assume all the quartiles
      // equal the only value.
      boolean moreThanOne = summarizer.getCount() > 1;
      if (fileOut != null) {
        fileOut.printf("%d,%f,%f,%f,%f,%f,%f,%f,%d,%s\n", i, summarizer.getMean(),
            summarizer.getSD(),
            summarizer.getQuartile(0),
            moreThanOne ? summarizer.getQuartile(1) : summarizer.getQuartile(0),
            moreThanOne ? summarizer.getQuartile(2) : summarizer.getQuartile(0),
            moreThanOne ? summarizer.getQuartile(3) : summarizer.getQuartile(0),
            summarizer.getQuartile(4), summarizer.getCount(), type);
      }
    }
    System.out.printf("Num clusters: %d; maxDistance: %f\n", summarizers.size(), maxDistance);
  }
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

109
110
111
112
113
114
115
116
117
118
119
    // full distance computations as possible.  Our goal is to only do full distance computations for
    // vectors with hash distance at most as large as the searchSize biggest hash distance seen so far.

    OnlineSummarizer[] distribution = new OnlineSummarizer[BITS + 1];
    for (int i = 0; i < BITS + 1; i++) {
      distribution[i] = new OnlineSummarizer();
    }

    distanceEvaluations = 0;
   
    // We keep the counts of the hash distances here.  This lets us accurately
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
    assertEquals("Total weight not preserved", totalWeight(syntheticData.getFirst()), totalWeight(clusterer), 1.0e-9);

    // Verify that each corner of the cube has a centroid very nearby.
    // This is probably FALSE for large-dimensional spaces!
    OnlineSummarizer summarizer = new OnlineSummarizer();
    for (Vector mean : syntheticData.getSecond()) {
      WeightedThing<Vector> v = searcher.search(mean, 1).get(0);
      summarizer.add(v.getWeight());
    }
    assertTrue(String.format("Median weight [%f] too large [>%f]", summarizer.getMedian(),
        DISTRIBUTION_RADIUS), summarizer.getMedian() < DISTRIBUTION_RADIUS);

    double clusterTime = (endTime - startTime) / 1000.0;
    System.out.printf("%s\n%.2f for clustering\n%.1f us per row\n\n",
        searcher.getClass().getName(), clusterTime,
        clusterTime / syntheticData.getFirst().size() * 1.0e6);
 
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

76
77
78
79
80
81
82
83
84
85
86
      encoder[i] = new ConstantValueEncoder("v" + 1);
    }

    OnlineSummarizer[] s = new OnlineSummarizer[FIELDS];
    for (int i = 0; i < FIELDS; i++) {
      s[i] = new OnlineSummarizer();
    }
    long t0 = System.currentTimeMillis();
    Vector v = new DenseVector(1000);
    if ("--generate".equals(args[0])) {
      PrintWriter out =
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

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
124
125
126
127
      if (lmp.getTargetCategories().size() <= 2) {
        collector = new Auc();
      }

      OnlineSummarizer slh = new OnlineSummarizer();
      ConfusionMatrix cm = new ConfusionMatrix(lmp.getTargetCategories(), defaultCategory);

      State<Wrapper, CrossFoldLearner> best = lr.getBest();
      if (best == null) {
        output.println("AdaptiveLogisticRegression has not be trained probably.");
        return;
      }
      CrossFoldLearner learner = best.getPayload().getLearner();

      BufferedReader in = TrainLogistic.open(inputFile);
      String line = in.readLine();
      csv.firstLine(line);
      line = in.readLine();
      if (showScores) {
        output.println("\"target\", \"model-output\", \"log-likelihood\", \"average-likelihood\"");
      }
      while (line != null) {
        Vector v = new SequentialAccessSparseVector(lmp.getNumFeatures());
        //TODO: How to avoid extra target values not shown in the training process.
        int target = csv.processLine(line, v);
        double likelihood = learner.logLikelihood(target, v);
        double score = learner.classifyFull(v).maxValue();

        slh.add(likelihood);
        cm.addInstance(csv.getTargetString(line), csv.getTargetLabel(target));       

        if (showScores) {
          output.printf(Locale.ENGLISH, "%8d, %.12f, %.13f, %.13f%n", target,
              score, learner.logLikelihood(target, v), slh.getMean());
        }
        if (collector != null) {
          collector.add(target, score);
        }
        line = in.readLine();
      }

      output.printf(Locale.ENGLISH,"\nLog-likelihood:");
      output.printf(Locale.ENGLISH, "Min=%.2f, Max=%.2f, Mean=%.2f, Median=%.2f%n",
          slh.getMin(), slh.getMax(), slh.getMean(), slh.getMedian());

      if (collector != null) {       
        output.printf(Locale.ENGLISH, "%nAUC = %.2f%n", collector.auc());
      }
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

34
35
36
37
38
39
40
41
42
43
44
45
46
    RandomUtils.useTestSeed();
  }

  @Test
  public void testOffset() {
    OnlineSummarizer s = new OnlineSummarizer();
    Sampler<Double> sampler = new Normal(2, 5);
    for (int i = 0; i < 10001; i++) {
      s.add(sampler.sample());
    }
    assertEquals(String.format("m = %.3f, sd = %.3f", s.getMean(), s.getSD()), 2, s.getMean(), 0.04 * s.getSD());
    assertEquals(5, s.getSD(), 0.12);
  }
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
        DenseVector offset = new DenseVector(new double[]{6, 3, 0});
        MultiNormal n = new MultiNormal(
                new DenseVector(new double[]{1, 2, 5}), offset);

        OnlineSummarizer[] s = {
                new OnlineSummarizer(),
                new OnlineSummarizer(),
                new OnlineSummarizer()
        };

        OnlineSummarizer[] cross = {
                new OnlineSummarizer(),
                new OnlineSummarizer(),
                new OnlineSummarizer()
        };

        for (int i = 0; i < 10000; i++) {
            Vector v = n.sample();
            for (int j = 0; j < 3; j++) {
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

68
69
70
71
72
73
74
75
76
77
78
79
80

    @Test
    public void testRadius() {
        MultiNormal gen = new MultiNormal(0.1, new DenseVector(10));
        OnlineSummarizer s = new OnlineSummarizer();
        for (int i = 0; i < 10000; i++) {
            double x = gen.sample().norm(2) / Math.sqrt(10);
            s.add(x);
        }
        assertEquals(0.1, s.getMean(), 0.01);

    }
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
    System.out.printf("speedup,q1,q2,q3\n");

    for (int i = 0; i < 12; i++) {
      double strategy = (i - 1.0) / 10.0;
      cut.setRaiseHashLimitStrategy(strategy);
      OnlineSummarizer t1 = evaluateStrategy(testData, ref, cut);
      int evals = cut.resetEvaluationCount();
      final double speedup = 10.0e6 / evals;
      System.out.printf("%.1f,%.2f,%.2f,%.2f\n", speedup, t1.getQuartile(1),
          t1.getQuartile(2), t1.getQuartile(3));
      assertTrue(t1.getQuartile(2) > 0.45);
      assertTrue(speedup > 4 || t1.getQuartile(2) > 0.9);
      assertTrue(speedup > 15 || t1.getQuartile(2) > 0.8);
    }
  }
View Full Code Here

Examples of org.apache.mahout.math.stats.OnlineSummarizer

66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    }
  }

  private static OnlineSummarizer evaluateStrategy(Matrix testData, BruteSearch ref,
                                                   LocalitySensitiveHashSearch cut) {
    OnlineSummarizer t1 = new OnlineSummarizer();

    for (int i = 0; i < 100; i++) {
      final Vector q = testData.viewRow(i);
      List<WeightedThing<Vector>> v1 = cut.search(q, 150);
      BitSet b1 = new BitSet();
      for (WeightedThing<Vector> v : v1) {
        b1.set(((WeightedVector)v.getValue()).getIndex());
      }

      List<WeightedThing<Vector>> v2 = ref.search(q, 100);
      BitSet b2 = new BitSet();
      for (WeightedThing<Vector> v : v2) {
        b2.set(((WeightedVector)v.getValue()).getIndex());
      }

      b1.and(b2);
      t1.add(b1.cardinality());
    }
    return t1;
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.