List of usage examples for org.apache.commons.math3.stat.descriptive DescriptiveStatistics getKurtosis
public double getKurtosis()
From source file:com.itemanalysis.jmetrik.stats.descriptives.DescriptiveAnalysis.java
public void publishTable(VariableAttributes v) { TextTable table = null;// w w w .j a va2 s . c o m TextTableColumnFormat[] cformats = new TextTableColumnFormat[2]; cformats[0] = new TextTableColumnFormat(); cformats[0].setStringFormat(15, TextTableColumnFormat.OutputAlignment.LEFT); cformats[1] = new TextTableColumnFormat(); cformats[1].setDoubleFormat(10, 4, TextTableColumnFormat.OutputAlignment.RIGHT); DescriptiveStatistics temp = data.get(v); table = new TextTable(); table.addAllColumnFormats(cformats, 17); table.getRowAt(0).addHeader(0, 2, v.getName().toString(), TextTablePosition.CENTER); table.getRowAt(1).addHorizontalRule(0, 2, "="); table.getRowAt(2).addHeader(0, 1, "Statistic", TextTablePosition.CENTER); table.getRowAt(2).addHeader(1, 1, "Value", TextTablePosition.CENTER); table.getRowAt(3).addHorizontalRule(0, 2, "-"); table.addStringAt(4, 0, "N"); table.addDoubleAt(4, 1, maxProgress); table.addStringAt(5, 0, "Valid N"); table.addDoubleAt(5, 1, temp.getN()); table.addStringAt(6, 0, "Min"); table.addDoubleAt(6, 1, temp.getMin()); table.addStringAt(7, 0, "Max"); table.addDoubleAt(7, 1, temp.getMax()); table.addStringAt(8, 0, "Mean"); table.addDoubleAt(8, 1, temp.getMean()); table.addStringAt(9, 0, "Std. Dev."); table.addDoubleAt(9, 1, temp.getStandardDeviation()); table.addStringAt(10, 0, "Skewness"); table.addDoubleAt(10, 1, temp.getSkewness()); table.addStringAt(11, 0, "Kurtosis"); table.addDoubleAt(11, 1, temp.getKurtosis()); table.addStringAt(12, 0, "First Quartile"); table.addDoubleAt(12, 1, temp.getPercentile(25)); table.addStringAt(13, 0, "Median"); table.addDoubleAt(13, 1, temp.getPercentile(50)); table.addStringAt(14, 0, "Third Quartile"); table.addDoubleAt(14, 1, temp.getPercentile(75)); table.addStringAt(15, 0, "IQR"); table.addDoubleAt(15, 1, temp.getPercentile(75) - temp.getPercentile(25)); table.getRowAt(16).addHorizontalRule(0, 2, "="); publish(table.toString() + "\n"); }
From source file:info.financialecology.finance.utilities.datastruct.VersatileTimeSeries.java
/** * Computes the unbiased excess kurtosis of the data points in this time series. * /*from w w w.j a v a 2s .co m*/ * @return the unbiased excess kurtosis of this time series * @see <a href=http://tinyurl.com/d4cajfw>Unbiased excess kurtosis</a> */ public double operatorUnbiasedExcessKurtosis() { DescriptiveStatistics stats = new DescriptiveStatistics(); for (int i = 0; i < this.getItemCount(); i++) stats.addValue(getValue(i).doubleValue()); return stats.getKurtosis(); }
From source file:org.apache.metron.common.math.stats.OnlineStatisticsProviderTest.java
public static void validateStatisticsProvider(StatisticsProvider statsProvider, SummaryStatistics summaryStats, DescriptiveStatistics stats) { //N/*from w w w .ja v a2 s .c om*/ Assert.assertEquals(statsProvider.getCount(), stats.getN()); //sum Assert.assertEquals(statsProvider.getSum(), stats.getSum(), 1e-3); //sum of squares Assert.assertEquals(statsProvider.getSumSquares(), stats.getSumsq(), 1e-3); //sum of squares Assert.assertEquals(statsProvider.getSumLogs(), summaryStats.getSumOfLogs(), 1e-3); //Mean Assert.assertEquals(statsProvider.getMean(), stats.getMean(), 1e-3); //Quadratic Mean Assert.assertEquals(statsProvider.getQuadraticMean(), summaryStats.getQuadraticMean(), 1e-3); //SD Assert.assertEquals(statsProvider.getStandardDeviation(), stats.getStandardDeviation(), 1e-3); //Variance Assert.assertEquals(statsProvider.getVariance(), stats.getVariance(), 1e-3); //Min Assert.assertEquals(statsProvider.getMin(), stats.getMin(), 1e-3); //Max Assert.assertEquals(statsProvider.getMax(), stats.getMax(), 1e-3); //Kurtosis Assert.assertEquals(stats.getKurtosis(), statsProvider.getKurtosis(), 1e-3); //Skewness Assert.assertEquals(stats.getSkewness(), statsProvider.getSkewness(), 1e-3); for (double d = 10.0; d < 100.0; d += 10) { //This is a sketch, so we're a bit more forgiving here in our choice of \epsilon. Assert.assertEquals("Percentile mismatch for " + d + "th %ile", statsProvider.getPercentile(d), stats.getPercentile(d), 1e-2); } }
From source file:org.apache.solr.client.solrj.io.eval.DescribeEvaluator.java
@Override public Object doWork(Object value) throws IOException { if (!(value instanceof List<?>)) { throw new IOException( String.format(Locale.ROOT, "Invalid expression %s - expecting a numeric list but found %s", toExpression(constructingFactory), value.getClass().getSimpleName())); }/* ww w . j a v a 2 s . c o m*/ // we know each value is a BigDecimal or a list of BigDecimals DescriptiveStatistics descriptiveStatistics = new DescriptiveStatistics(); ((List<?>) value).stream().mapToDouble(innerValue -> ((BigDecimal) innerValue).doubleValue()) .forEach(innerValue -> descriptiveStatistics.addValue(innerValue)); Map<String, Number> map = new HashMap<>(); map.put("max", descriptiveStatistics.getMax()); map.put("mean", descriptiveStatistics.getMean()); map.put("min", descriptiveStatistics.getMin()); map.put("stdev", descriptiveStatistics.getStandardDeviation()); map.put("sum", descriptiveStatistics.getSum()); map.put("N", descriptiveStatistics.getN()); map.put("var", descriptiveStatistics.getVariance()); map.put("kurtosis", descriptiveStatistics.getKurtosis()); map.put("skewness", descriptiveStatistics.getSkewness()); map.put("popVar", descriptiveStatistics.getPopulationVariance()); map.put("geometricMean", descriptiveStatistics.getGeometricMean()); map.put("sumsq", descriptiveStatistics.getSumsq()); return new Tuple(map); }
From source file:org.deidentifier.arx.aggregates.StatisticsBuilder.java
/** * Returns summary statistics for all attributes. * /*from w w w . j av a 2 s . co m*/ * @param listwiseDeletion A flag enabling list-wise deletion * @return */ @SuppressWarnings({ "unchecked", "rawtypes" }) public <T> Map<String, StatisticsSummary<?>> getSummaryStatistics(boolean listwiseDeletion) { // Reset stop flag interrupt.value = false; Map<String, DescriptiveStatistics> statistics = new HashMap<String, DescriptiveStatistics>(); Map<String, StatisticsSummaryOrdinal> ordinal = new HashMap<String, StatisticsSummaryOrdinal>(); Map<String, DataScale> scales = new HashMap<String, DataScale>(); Map<String, GeometricMean> geomean = new HashMap<String, GeometricMean>(); // Detect scales for (int col = 0; col < handle.getNumColumns(); col++) { // Meta String attribute = handle.getAttributeName(col); DataType<?> type = handle.getDataType(attribute); // Scale DataScale scale = type.getDescription().getScale(); // Try to replace nominal scale with ordinal scale based on base data type if (scale == DataScale.NOMINAL && handle.getGeneralization(attribute) != 0) { if (!(handle.getBaseDataType(attribute) instanceof ARXString) && getHierarchy(col, true) != null) { scale = DataScale.ORDINAL; } } // Store scales.put(attribute, scale); statistics.put(attribute, new DescriptiveStatistics()); geomean.put(attribute, new GeometricMean()); ordinal.put(attribute, getSummaryStatisticsOrdinal(handle.getGeneralization(attribute), handle.getDataType(attribute), handle.getBaseDataType(attribute), getHierarchy(col, true))); } // Compute summary statistics for (int row = 0; row < handle.getNumRows(); row++) { // Check, if we should include this row boolean include = true; if (listwiseDeletion) { for (int col = 0; col < handle.getNumColumns(); col++) { if (handle.isOutlier(row) || DataType.isNull(handle.getValue(row, col))) { include = false; break; } } } // Check checkInterrupt(); // If yes, add if (include) { // For each column for (int col = 0; col < handle.getNumColumns(); col++) { // Meta String value = handle.getValue(row, col); String attribute = handle.getAttributeName(col); DataType<?> type = handle.getDataType(attribute); // Analyze if (!DataType.isAny(value) && !DataType.isNull(value)) { ordinal.get(attribute).addValue(value); if (type instanceof DataTypeWithRatioScale) { double doubleValue = ((DataTypeWithRatioScale) type).toDouble(type.parse(value)); statistics.get(attribute).addValue(doubleValue); geomean.get(attribute).increment(doubleValue + 1d); } } } } } // Convert Map<String, StatisticsSummary<?>> result = new HashMap<String, StatisticsSummary<?>>(); for (int col = 0; col < handle.getNumColumns(); col++) { // Check checkInterrupt(); // Depending on scale String attribute = handle.getAttributeName(col); DataScale scale = scales.get(attribute); DataType<T> type = (DataType<T>) handle.getDataType(attribute); ordinal.get(attribute).analyze(); if (scale == DataScale.NOMINAL) { StatisticsSummaryOrdinal stats = ordinal.get(attribute); result.put(attribute, new StatisticsSummary<T>(DataScale.NOMINAL, stats.getNumberOfMeasures(), stats.getMode(), type.parse(stats.getMode()))); } else if (scale == DataScale.ORDINAL) { StatisticsSummaryOrdinal stats = ordinal.get(attribute); result.put(attribute, new StatisticsSummary<T>(DataScale.ORDINAL, stats.getNumberOfMeasures(), stats.getMode(), type.parse(stats.getMode()), stats.getMedian(), type.parse(stats.getMedian()), stats.getMin(), type.parse(stats.getMin()), stats.getMax(), type.parse(stats.getMax()))); } else if (scale == DataScale.INTERVAL) { StatisticsSummaryOrdinal stats = ordinal.get(attribute); DescriptiveStatistics stats2 = statistics.get(attribute); boolean isPeriod = type.getDescription().getWrappedClass() == Date.class; // TODO: Something is wrong with commons math's kurtosis double kurtosis = stats2.getKurtosis(); kurtosis = kurtosis < 0d ? Double.NaN : kurtosis; double range = stats2.getMax() - stats2.getMin(); double stddev = Math.sqrt(stats2.getVariance()); result.put(attribute, new StatisticsSummary<T>(DataScale.INTERVAL, stats.getNumberOfMeasures(), stats.getMode(), type.parse(stats.getMode()), stats.getMedian(), type.parse(stats.getMedian()), stats.getMin(), type.parse(stats.getMin()), stats.getMax(), type.parse(stats.getMax()), toString(type, stats2.getMean(), false, false), toValue(type, stats2.getMean()), stats2.getMean(), toString(type, stats2.getVariance(), isPeriod, true), toValue(type, stats2.getVariance()), stats2.getVariance(), toString(type, stats2.getPopulationVariance(), isPeriod, true), toValue(type, stats2.getPopulationVariance()), stats2.getPopulationVariance(), toString(type, stddev, isPeriod, false), toValue(type, stddev), stddev, toString(type, range, isPeriod, false), toValue(type, range), stats2.getMax() - stats2.getMin(), toString(type, kurtosis, isPeriod, false), toValue(type, kurtosis), kurtosis)); } else if (scale == DataScale.RATIO) { StatisticsSummaryOrdinal stats = ordinal.get(attribute); DescriptiveStatistics stats2 = statistics.get(attribute); GeometricMean geo = geomean.get(attribute); // TODO: Something is wrong with commons math's kurtosis double kurtosis = stats2.getKurtosis(); kurtosis = kurtosis < 0d ? Double.NaN : kurtosis; double range = stats2.getMax() - stats2.getMin(); double stddev = Math.sqrt(stats2.getVariance()); result.put(attribute, new StatisticsSummary<T>(DataScale.RATIO, stats.getNumberOfMeasures(), stats.getMode(), type.parse(stats.getMode()), stats.getMedian(), type.parse(stats.getMedian()), stats.getMin(), type.parse(stats.getMin()), stats.getMax(), type.parse(stats.getMax()), toString(type, stats2.getMean(), false, false), toValue(type, stats2.getMean()), stats2.getMean(), toString(type, stats2.getVariance(), false, false), toValue(type, stats2.getVariance()), stats2.getVariance(), toString(type, stats2.getPopulationVariance(), false, false), toValue(type, stats2.getPopulationVariance()), stats2.getPopulationVariance(), toString(type, stddev, false, false), toValue(type, stddev), stddev, toString(type, range, false, false), toValue(type, range), range, toString(type, kurtosis, false, false), toValue(type, kurtosis), kurtosis, toString(type, geo.getResult() - 1d, false, false), toValue(type, geo.getResult() - 1d), stats2.getGeometricMean())); } } return result; }
From source file:org.jenetics.stat.DoubleMomentStatisticsTest.java
@Test(dataProvider = "sampleCounts") public void summary(final Integer sampleCounts, final Double epsilon) { final List<Double> numbers = numbers(sampleCounts); final DescriptiveStatistics expected = new DescriptiveStatistics(); numbers.forEach(expected::addValue); final DoubleMomentStatistics summary = numbers.stream() .collect(toDoubleMomentStatistics(Double::doubleValue)); Assert.assertEquals(summary.getCount(), numbers.size()); assertEqualsDouble(min(summary.getMin()), expected.getMin(), 0.0); assertEqualsDouble(max(summary.getMax()), expected.getMax(), 0.0); assertEqualsDouble(summary.getSum(), expected.getSum(), epsilon); assertEqualsDouble(summary.getMean(), expected.getMean(), epsilon); assertEqualsDouble(summary.getVariance(), expected.getVariance(), epsilon); assertEqualsDouble(summary.getSkewness(), expected.getSkewness(), epsilon); assertEqualsDouble(summary.getKurtosis(), expected.getKurtosis(), epsilon); }
From source file:org.jenetics.stat.DoubleMomentStatisticsTest.java
@Test(dataProvider = "parallelSampleCounts") public void parallelSummary(final Integer sampleCounts, final Double epsilon) { final List<Double> numbers = numbers(sampleCounts); final DescriptiveStatistics expected = new DescriptiveStatistics(); numbers.forEach(expected::addValue); final DoubleMomentStatistics summary = numbers.parallelStream() .collect(toDoubleMomentStatistics(Double::doubleValue)); Assert.assertEquals(summary.getCount(), numbers.size()); assertEqualsDouble(min(summary.getMin()), expected.getMin(), 0.0); assertEqualsDouble(max(summary.getMax()), expected.getMax(), 0.0); assertEqualsDouble(summary.getSum(), expected.getSum(), epsilon); assertEqualsDouble(summary.getMean(), expected.getMean(), epsilon); assertEqualsDouble(summary.getVariance(), expected.getVariance(), epsilon); assertEqualsDouble(summary.getSkewness(), expected.getSkewness(), epsilon); assertEqualsDouble(summary.getKurtosis(), expected.getKurtosis(), epsilon); }
From source file:org.jenetics.stat.IntMomentStatisticsTest.java
@Test(dataProvider = "sampleCounts") public void summary(final Integer sampleCounts, final Double epsilon) { final List<Integer> numbers = numbers(sampleCounts); final DescriptiveStatistics expected = new DescriptiveStatistics(); numbers.forEach(expected::addValue); final IntMomentStatistics summary = numbers.stream().collect(toIntMomentStatistics(Integer::intValue)); Assert.assertEquals(summary.getCount(), numbers.size()); assertEqualsDouble(min(summary.getMin()), expected.getMin(), 0.0); assertEqualsDouble(max(summary.getMax()), expected.getMax(), 0.0); assertEqualsDouble(summary.getSum(), expected.getSum(), epsilon); assertEqualsDouble(summary.getMean(), expected.getMean(), epsilon); assertEqualsDouble(summary.getVariance(), expected.getVariance(), epsilon); assertEqualsDouble(summary.getSkewness(), expected.getSkewness(), epsilon); assertEqualsDouble(summary.getKurtosis(), expected.getKurtosis(), epsilon); }
From source file:org.jenetics.stat.IntMomentStatisticsTest.java
@Test(dataProvider = "parallelSampleCounts") public void parallelSummary(final Integer sampleCounts, final Double epsilon) { final List<Integer> numbers = numbers(sampleCounts); final DescriptiveStatistics expected = new DescriptiveStatistics(); numbers.forEach(expected::addValue); final IntMomentStatistics summary = numbers.parallelStream() .collect(toIntMomentStatistics(Integer::intValue)); Assert.assertEquals(summary.getCount(), numbers.size()); assertEqualsDouble(min(summary.getMin()), expected.getMin(), 0.0); assertEqualsDouble(max(summary.getMax()), expected.getMax(), 0.0); assertEqualsDouble(summary.getSum(), expected.getSum(), epsilon); assertEqualsDouble(summary.getMean(), expected.getMean(), epsilon); assertEqualsDouble(summary.getVariance(), expected.getVariance(), epsilon); assertEqualsDouble(summary.getSkewness(), expected.getSkewness(), epsilon); assertEqualsDouble(summary.getKurtosis(), expected.getKurtosis(), epsilon); }
From source file:org.jenetics.stat.LongMomentStatisticsTest.java
@Test(dataProvider = "sampleCounts") public void summary(final Integer sampleCounts, final Double epsilon) { final List<Long> numbers = numbers(sampleCounts); final DescriptiveStatistics expected = new DescriptiveStatistics(); numbers.forEach(expected::addValue); final LongMomentStatistics summary = numbers.stream().collect(toLongMomentStatistics(Long::longValue)); Assert.assertEquals(summary.getCount(), numbers.size()); assertEqualsDouble(min(summary.getMin()), expected.getMin(), 0.0); assertEqualsDouble(max(summary.getMax()), expected.getMax(), 0.0); assertEqualsDouble(summary.getSum(), expected.getSum(), epsilon); assertEqualsDouble(summary.getMean(), expected.getMean(), epsilon); assertEqualsDouble(summary.getVariance(), expected.getVariance(), epsilon); assertEqualsDouble(summary.getSkewness(), expected.getSkewness(), epsilon); assertEqualsDouble(summary.getKurtosis(), expected.getKurtosis(), epsilon); }