Examples of org.apache.commons.math3.stat.descriptive.DescriptiveStatistics

Package org.apache.commons.math3.stat.descriptive

Examples of org.apache.commons.math3.stat.descriptive.DescriptiveStatistics

org.apache.commons.math3.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.


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


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


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


            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, format("Expected mean sampling rate to be ~0.5, but was %s", mean));
    }

View Full Code Here


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


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


        for (int i = 0; i < 100; i++) {
            List<MaterializedRow> values = computeActual("SELECT orderkey FROM ORDERS TABLESAMPLE POISSONIZED (50)").getMaterializedRows();
            stats.addValue(values.size() * 1.0 / total);
        }


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

View Full Code Here


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


        long total = (long) computeExpected("SELECT COUNT(*) FROM orders", ImmutableList.of(BIGINT)).getMaterializedRows().get(0).getField(0);


        for (int i = 0; i < 100; i++) {
            long value = (long) computeActual("SELECT COUNT(*) FROM orders TABLESAMPLE POISSONIZED (50) RESCALED").getMaterializedRows().get(0).getField(0);
            stats.addValue(value * 1.0 / total);
        }


        double mean = stats.getGeometricMean();
        assertTrue(mean > 0.90 && mean < 1.1, format("Expected sample to be rescaled to ~1.0, but was %s", mean));
        assertTrue(stats.getVariance() > 0, "Samples all had the exact same size");
    }

View Full Code Here

     * @param sample Sample to normalize.
     * @return normalized (standardized) sample.
     * @since 2.2
     */
    public static double[] normalize(final double[] sample) {
        DescriptiveStatistics stats = new DescriptiveStatistics();


        // Add the data from the series to stats
        for (int i = 0; i < sample.length; i++) {
            stats.addValue(sample[i]);
        }


        // Compute mean and standard deviation
        double mean = stats.getMean();
        double standardDeviation = stats.getStandardDeviation();


        // initialize the standardizedSample, which has the same length as the sample
        double[] standardizedSample = new double[sample.length];


        for (int i = 0; i < sample.length; i++) {

View Full Code Here

        UnivariateFunction f = new QuinticFunction();
        UnivariateOptimizer optimizer = new BrentOptimizer(1e-11, 1e-14);


        final DescriptiveStatistics[] stat = new DescriptiveStatistics[2];
        for (int i = 0; i < stat.length; i++) {
            stat[i] = new DescriptiveStatistics();
        }


        final double min = -0.75;
        final double max = 0.25;
        final int nSamples = 200;

View Full Code Here

     * If alpha = 1, than it must be Cauchy distribution
     */
    @Test
    public void testCauchyCase() {
        StableRandomGenerator generator = new StableRandomGenerator(rg, 1d, 0.0);
        DescriptiveStatistics summary = new DescriptiveStatistics();


        for (int i = 0; i < sampleSize; ++i) {
            double sample = generator.nextNormalizedDouble();
            summary.addValue(sample);
        }


        // Standard Cauchy distribution should have zero median and mode
        double median = summary.getPercentile(50);
        Assert.assertEquals(0.0, median, 0.2);
    }

View Full Code Here

     * values and execute multi-pass algorithms
     */
    @Test
    public void testDescriptiveStatistics() throws Exception {


        DescriptiveStatistics u = new DescriptiveStatistics();


        loadStats("data/PiDigits.txt", u);
        Assert.assertEquals("PiDigits: std", std, u.getStandardDeviation(), 1E-14);
        Assert.assertEquals("PiDigits: mean", mean, u.getMean(), 1E-14);


        loadStats("data/Mavro.txt", u);
        Assert.assertEquals("Mavro: std", std, u.getStandardDeviation(), 1E-14);
        Assert.assertEquals("Mavro: mean", mean, u.getMean(), 1E-14);


        loadStats("data/Michelso.txt", u);
        Assert.assertEquals("Michelso: std", std, u.getStandardDeviation(), 1E-14);
        Assert.assertEquals("Michelso: mean", mean, u.getMean(), 1E-14);


        loadStats("data/NumAcc1.txt", u);
        Assert.assertEquals("NumAcc1: std", std, u.getStandardDeviation(), 1E-14);
        Assert.assertEquals("NumAcc1: mean", mean, u.getMean(), 1E-14);


        loadStats("data/NumAcc2.txt", u);
        Assert.assertEquals("NumAcc2: std", std, u.getStandardDeviation(), 1E-14);
        Assert.assertEquals("NumAcc2: mean", mean, u.getMean(), 1E-14);
    }

View Full Code Here

     * @param file
     * @param statistical summary
     */
    private void loadStats(String resource, Object u) throws Exception {


        DescriptiveStatistics d = null;
        SummaryStatistics s = null;
        if (u instanceof DescriptiveStatistics) {
            d = (DescriptiveStatistics) u;
        } else {
            s = (SummaryStatistics) u;
        }
        u.getClass().getDeclaredMethod(
                "clear", new Class[]{}).invoke(u, new Object[]{});
        mean = Double.NaN;
        std = Double.NaN;


        InputStream resourceAsStream = CertifiedDataTest.class.getResourceAsStream(resource);
        Assert.assertNotNull("Could not find resource "+resource,resourceAsStream);
        BufferedReader in =
            new BufferedReader(
                    new InputStreamReader(
                            resourceAsStream));


        String line = null;


        for (int j = 0; j < 60; j++) {
            line = in.readLine();
            if (j == 40) {
                mean =
                    Double.parseDouble(
                            line.substring(line.lastIndexOf(":") + 1).trim());
            }
            if (j == 41) {
                std =
                    Double.parseDouble(
                            line.substring(line.lastIndexOf(":") + 1).trim());
            }
        }


        line = in.readLine();


        while (line != null) {
            if (d != null) {
                d.addValue(Double.parseDouble(line.trim()));
            }  else {
                s.addValue(Double.parseDouble(line.trim()));
            }
            line = in.readLine();
        }

View Full Code Here

        UnivariateFunction f = new QuinticFunction();
        UnivariateOptimizer optimizer = new BrentOptimizer(1e-11, 1e-14);


        final DescriptiveStatistics[] stat = new DescriptiveStatistics[2];
        for (int i = 0; i < stat.length; i++) {
            stat[i] = new DescriptiveStatistics();
        }


        final double min = -0.75;
        final double max = 0.25;
        final int nSamples = 200;

View Full Code Here


    private Map<String, Double> certifiedValues;


    @Before
    public void setUp() throws IOException {
        descriptives = new DescriptiveStatistics();
        summaries = new SummaryStatistics();
        certifiedValues = new HashMap<String, Double>();


        loadData();
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.commons.math3.stat.descriptive.DescriptiveStatistics

cc.redberry.core.performance.ProductBijectionPerformanceTest

cc.redberry.core.performance.StableSort

com.facebook.presto.AbstractTestQueries

com.facebook.presto.operator.aggregation.AbstractTestApproximateCountDistinct

com.facebook.presto.operator.aggregation.BootstrappedAggregation$BootstrappedAccumulator

com.facebook.presto.operator.aggregation.BootstrappedAggregation$BootstrappedGroupedAccumulator

com.facebook.presto.tests.AbstractTestQueries

org.apache.commons.math3.analysis.differentiation.DerivativeStructure

org.apache.commons.math3.analysis.differentiation.MultivariateDifferentiableVectorFunction

org.apache.commons.math3.analysis.function.HarmonicOscillator

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.