Example usage for org.apache.mahout.math.stats OnlineSummarizer getMean

Introduction

In this page you can find the example usage for org.apache.mahout.math.stats OnlineSummarizer getMean.

Prototype

public double getMean() 

Source Link

Usage

From source file:com.mapr.stats.bandit.BanditTrainer.java

License:Apache License

private static void printRegret(String outputFile, List<OnlineSummarizer> cumulativeRegret, List<Integer> steps)
        throws FileNotFoundException {
    try (PrintWriter out = new PrintWriter(outputFile)) {
        out.printf("n\tmean\n");
        int k = 0;
        for (OnlineSummarizer summary : cumulativeRegret) {
            out.printf("%d\t%.4f\n", steps.get(k++), summary.getMean());
            //        for (int quartile = 0; quartile <= 4; quartile++) {
            //          out.printf("%.3f%s", summary.getQuartile(quartile), quartile < 4 ? "\t" : "\n");
            //        }
        }//from  ww  w  . j av  a  2s .co m
        out.flush();
    }
}

---

From source file:com.mapr.stats.bandit.EpsilonGreedy.java

License:Apache License

/**
 * Samples probability estimates from each bandit and picks the apparent best
 *
 * @return The index of the chosen bandit
 *///from w w  w  .  j a v a  2s. com
@Override
public int sample() {
    if (gen.nextDouble() < epsilon) {
        return gen.nextInt(summaries.size());
    } else {
        double max = summaries.get(0).getMean();
        int i = 0;
        int maxIndex = 0;
        for (OnlineSummarizer summary : summaries) {
            if (summary.getMean() > max) {
                max = summary.getMean();
                maxIndex = i;
            }
            i++;
        }
        return maxIndex;
    }
}

---

From source file:com.mapr.stats.BanditTrainer.java

License:Apache License

private static void printRegret(String outputFile, List<OnlineSummarizer> cumulativeRegret, List<Integer> steps)
        throws FileNotFoundException {
    PrintWriter out = new PrintWriter(outputFile);
    try {//from  w ww. j  av a2  s. c  o  m
        out.printf("n\tmean\n");
        int k = 0;
        for (OnlineSummarizer summary : cumulativeRegret) {
            out.printf("%d\t%.4f\n", steps.get(k++), summary.getMean());
            //        for (int quartile = 0; quartile <= 4; quartile++) {
            //          out.printf("%.3f%s", summary.getQuartile(quartile), quartile < 4 ? "\t" : "\n");
            //        }
        }
        out.flush();
    } finally {
        out.close();
    }

}

---

From source file:com.mapr.synth.SchemaSamplerTest.java

License:Apache License

@Test
public void testSequence() throws IOException {
    SchemaSampler s = new SchemaSampler(
            Resources.asCharSource(Resources.getResource("schema005.json"), Charsets.UTF_8).read());
    OnlineSummarizer s0 = new OnlineSummarizer();
    OnlineSummarizer s1 = new OnlineSummarizer();
    for (int i = 0; i < 10000; i++) {
        JsonNode x = s.sample();//from ww  w .j  a  v  a2  s.  co m
        s0.add(Iterables.size(x.get("c")));
        s1.add(Iterables.size(x.get("d")));

        for (JsonNode n : x.get("d")) {
            int z = n.asInt();
            assertTrue(z >= 3 && z < 9);
        }
    }

    assertEquals(5, s0.getMean(), 1);
    assertEquals(10, s1.getMean(), 2);
}

---

From source file:org.conan.mymahout.clustering.streaming.tools.ClusterQualitySummarizer.java

License:Apache License

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() > 1) {
            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.
            if (fileOut != null) {
                fileOut.printf("%d,%f,%f,%f,%f,%f,%f,%f,%d,%s\n", i, summarizer.getMean(), summarizer.getSD(),
                        summarizer.getQuartile(0), summarizer.getQuartile(1), summarizer.getQuartile(2),
                        summarizer.getQuartile(3), summarizer.getQuartile(4), summarizer.getCount(), type);
            }/* w w w.j a va 2s . c o  m*/
        } else {
            System.out.printf("Cluster %d is has %d data point. Need atleast 2 data points in a cluster for"
                    + " OnlineSummarizer.\n", i, summarizer.getCount());
        }
    }
    System.out.printf("Num clusters: %d; maxDistance: %f\n", summarizers.size(), maxDistance);
}

---