Examples of org.apache.commons.math.stat.descriptive.DescriptiveStatistics

Package org.apache.commons.math.stat.descriptive

Examples of org.apache.commons.math.stat.descriptive.DescriptiveStatistics

org.apache.commons.math.stat.descriptive.DescriptiveStatistics
Maintains a dataset of values of a single variable and computes descriptive statistics based on stored data. The {@link #getWindowSize() windowSize}property sets a limit on the number of values that can be stored in the dataset. The default value, INFINITE_WINDOW, puts no limit on the size of the dataset. This value should be used with caution, as the backing store will grow without bound in this case. For very large datasets, {@link SummaryStatistics}, which does not store the dataset, should be used instead of this class. If windowSize is not INFINITE_WINDOW and more values are added than can be stored in the dataset, new values are added in a "rolling" manner, with new values replacing the "oldest" values in the dataset.
Note: this class is not threadsafe. Use {@link SynchronizedDescriptiveStatistics} if concurrent access from multiplethreads is required.
@version $Revision: 1054186 $ $Date: 2011-01-01 03:28:46 +0100 (sam. 01 janv. 2011) $


    @Test
    public void testTableSampleBernoulli()
            throws Exception
    {
        DescriptiveStatistics stats = new DescriptiveStatistics();


        int total = computeExpected("SELECT orderkey FROM orders", ImmutableList.of(SINGLE_LONG)).getMaterializedTuples().size();


        for (int i = 0; i < 100; i++) {
            List<MaterializedTuple> values = computeActual("SELECT orderkey FROM ORDERS TABLESAMPLE BERNOULLI (50)").getMaterializedTuples();


            assertEquals(values.size(), ImmutableSet.copyOf(values).size(), "TABLESAMPLE produced duplicate rows");
            stats.addValue(values.size() * 1.0 / total);
        }


        double mean = stats.getGeometricMean();
        assertTrue(mean > 0.45 && mean < 0.55, String.format("Expected mean sampling rate to be ~0.5, but was %s", mean));
    }

View Full Code Here


    @Test
    public void testTableSampleBernoulli()
            throws Exception
    {
        DescriptiveStatistics stats = new DescriptiveStatistics();


        int total = computeExpected("SELECT orderkey FROM orders", TupleInfo.SINGLE_LONG).getMaterializedTuples().size();


        for (int i = 0; i < 100; i++) {
            List<MaterializedTuple> values = computeActual("SELECT orderkey FROM ORDERS TABLESAMPLE BERNOULLI (50)").getMaterializedTuples();


            assertEquals(values.size(), ImmutableSet.copyOf(values).size(), "TABLESAMPLE produced duplicate rows");
            stats.addValue(values.size() * 1.0 / total);
        }


        double mean = stats.getGeometricMean();
        assertTrue(mean > 0.45 && mean < 0.55, String.format("Expected mean sampling rate to be ~0.5, but was %s", mean));
    }

View Full Code Here

      if (!warmup)
         System.out.printf("%s %s %s %s%n", padString("Function Impl", 25), padString("String keys", 18), padString("Byte array keys", 18), padString("Object keys", 18));


      for (HashFunction f : functions) {
         long oRes = 0, sRes = 0, bRes = 0;
         DescriptiveStatistics oStats = new DescriptiveStatistics();
         DescriptiveStatistics sStats = new DescriptiveStatistics();
         DescriptiveStatistics bStats = new DescriptiveStatistics();


         long st = System.currentTimeMillis();
         for (Object o : objectKeys) captureStats(f.hash(o.hashCode()), oStats);
         oRes = System.currentTimeMillis() - st;


         st = System.currentTimeMillis();
         for (String s : stringKeys) captureStats(f.hash(s), sStats);
         sRes = System.currentTimeMillis() - st;


         st = System.currentTimeMillis();
         for (byte[] b : byteArrayKeys) captureStats(f.hash(b), bStats);
         bRes = System.currentTimeMillis() - st;


         if (!warmup) {
            System.out.printf("%s %s %s %s%n",
                    padString(f.functionName(), 25),
                    padString(prettyPrintTime(sRes), 18),
                    padString(prettyPrintTime(bRes), 18),
                    padString(prettyPrintTime(oRes), 18)
            );
            System.out.printf("%s %s %s %s%n",
                    padString("  mean", 25),
                    padDouble(sStats.getMean()),
                    padDouble(bStats.getMean()),
                    padDouble(oStats.getMean())
            );
            System.out.printf("%s %s %s %s%n",
                    padString("  median", 25),
                    padDouble(sStats.getPercentile(50.0)),
                    padDouble(bStats.getPercentile(50.0)),
                    padDouble(oStats.getPercentile(50.0))
            );
            System.out.printf("%s %s %s %s%n",
                    padString("  deviation", 25),
                    padDouble(sStats.getStandardDeviation()),
                    padDouble(bStats.getStandardDeviation()),
                    padDouble(oStats.getStandardDeviation())
            );


            System.out.printf("%s %s %s %s%n",
                    padString("  variance", 25),
                    padDouble(sStats.getVariance()),
                    padDouble(bStats.getVariance()),
                    padDouble(oStats.getVariance())
            );
         }
      }
   }

View Full Code Here

        for (RepositoryFixture fixture : fixtures) {
            try {
                Repository[] cluster = fixture.setUpCluster(1);
                try {
                    // Run the test
                    DescriptiveStatistics statistics = runTest(cluster[0]);
                    if (statistics.getN() > 0) {
                        System.out.format(
                                "%-28.28s  %6.0f  %6.0f  %6.0f  %6.0f  %6.0f  %6d%n",
                                fixture.toString(),
                                statistics.getMin(),
                                statistics.getPercentile(10.0),
                                statistics.getPercentile(50.0),
                                statistics.getPercentile(90.0),
                                statistics.getMax(),
                                statistics.getN());
                    }
                } finally {
                    fixture.tearDownCluster();
                }
            } catch (Exception e) {

View Full Code Here

            }
        }
    }


    private DescriptiveStatistics runTest(Repository repository) throws Exception {
        DescriptiveStatistics statistics = new DescriptiveStatistics();


        setUp(repository, CREDENTIALS);
        try {
            // Run a few iterations to warm up the system
            for (int i = 0; i < WARMUP; i++) {
                execute();
            }


            // Run test iterations, and capture the execution times
            int iterations = 0;
            long runtimeEnd = System.currentTimeMillis() + RUNTIME;
            while (iterations++ < 10
                    || System.currentTimeMillis() < runtimeEnd) {
                statistics.addValue(execute());
            }
        } finally {
            tearDown();
        }

View Full Code Here

            MicroKernel mk = createMicroKernel(microKernel);
            try {
                Repository repository= createRepository(mk);


                // Run the test
                DescriptiveStatistics statistics = runTest(test, repository);
                if (statistics.getN() > 0) {
                    writeReport(test.toString(), name, microKernel, statistics);
                }
            } catch (RepositoryException re) {
                re.printStackTrace();
            } catch (Exception e) {

View Full Code Here

        }
    }


    private DescriptiveStatistics runTest(AbstractTest test,
            Repository repository) throws Exception {
        DescriptiveStatistics statistics = new DescriptiveStatistics();


        test.setUp(repository, credentials);
        try {
            // Run a few iterations to warm up the system
            if (warmup > 0) {
                long warmupEnd = System.currentTimeMillis() + warmup;
                while (System.currentTimeMillis() < warmupEnd) {
                    test.execute();
                }
            }


            // Run test iterations, and capture the execution times
            long runtimeEnd = System.currentTimeMillis() + runtime;
            while (System.currentTimeMillis() < runtimeEnd) {
                statistics.addValue(test.execute());
            }
        } finally {
            test.tearDown();
        }

View Full Code Here

    public void beforeIteration(ResultNode node) {
    }


    public void beforeNode(ResultNode node) {
        for(Alternative a : alternatives) {
            statisticsMap.put(a.getName(), new DescriptiveStatistics());
        }


    }

View Full Code Here


    QChart createCoverageAcrossReferenceChart() throws IOException {
        BamQCChart baseChart = new BamQCChart("Coverage Across Reference",
                            "Multi-sample BAM QC", "Position in reference (relative)", "Coverage");


        DescriptiveStatistics stats = new DescriptiveStatistics();
        int k = 0;
        for (SampleInfo bamQcResult : bamQCResults) {
            String path = rawDataDirs.get(bamQcResult) + File.separator + "coverage_across_reference.txt";
            XYVector rawData = loadColumnData(new File(path), 0, Double.MAX_VALUE, 1);
            XYVector scaledData = scaleXAxis(rawData);
            for (int i = 0; i < scaledData.getSize(); ++i) {
                stats.addValue( scaledData.get(i).getY() );
            }


            baseChart.addSeries(bamQcResult.name, scaledData, getSampleColor(k) );
            ++k;
        }
        baseChart.setDomainAxisIntegerTicks(false);


        baseChart.render();
        double p75 = stats.getPercentile(75);
        if (p75 > 0) {
            baseChart.getChart().getXYPlot().getRangeAxis().setRange(0, 2*p75);
        }
        stats.clear();


        return new QChart("Coverage across reference", baseChart.getChart());
    }

View Full Code Here


    @Test
    public void testTableSampleBernoulli()
            throws Exception
    {
        DescriptiveStatistics stats = new DescriptiveStatistics();


        int total = computeExpected("SELECT orderkey FROM orders", TupleInfo.SINGLE_LONG).getMaterializedTuples().size();


        for (int i = 0; i < 100; i++) {
            List<MaterializedTuple> values = computeActual("SELECT orderkey FROM ORDERS TABLESAMPLE BERNOULLI (50)").getMaterializedTuples();


            assertEquals(values.size(), ImmutableSet.copyOf(values).size(), "TABLESAMPLE produced duplicate rows");
            stats.addValue(values.size() * 1.0 / total);
        }


        double mean = stats.getGeometricMean();
        assertTrue(mean > 0.45 && mean < 0.55, String.format("Expected mean sampling rate to be ~0.5, but was %s", mean));
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.commons.math.stat.descriptive.DescriptiveStatistics

cc.redberry.performance.PairECBenchmark0

cc.redberry.performance.ProductBijectionMappingPerformanceHugeTensorTest

cc.redberry.performance.ProductBijectionMappingPerformanceTest

cc.redberry.performance.ProductBijectionPerformanceHugeTest

cc.redberry.performance.ProductBijectionPerformanceTest

com.dsi.parallax.ml.vector.util.Benchmarks

com.facebook.presto.AbstractTestQueries

com.facebook.presto.operator.aggregation.AbstractTestApproximateCountDistinct

com.google.caliper.runner.ConsoleResultProcessor

eas.plugins.standard.eaPlugin.evolvableTranslators.ChartCreator

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.