List of usage examples for org.apache.commons.math.stat.descriptive.moment Variance evaluate
@Override public double evaluate(final double[] values)
Double.NaN if the array is empty. From source file:com.discursive.jccook.math.StatExample.java
public static void main(String[] args) { double[] values = new double[] { 2.3, 5.4, 6.2, 7.3, 23.3 }; System.out.println("min: " + StatUtils.min(values)); System.out.println("max: " + StatUtils.max(values)); System.out.println("mean: " + StatUtils.mean(values)); System.out.println("product: " + StatUtils.product(values)); System.out.println("sum: " + StatUtils.sum(values)); System.out.println("variance: " + StatUtils.variance(values)); // Measures from previous example Min min = new Min(); System.out.println("min: " + min.evaluate(values)); Max max = new Max(); System.out.println("max: " + max.evaluate(values)); Mean mean = new Mean(); System.out.println("mean: " + mean.evaluate(values)); Product product = new Product(); System.out.println("product: " + product.evaluate(values)); Sum sum = new Sum(); System.out.println("sum: " + sum.evaluate(values)); Variance variance = new Variance(); System.out.println("variance: " + variance.evaluate(values)); // New measures Percentile percentile = new Percentile(); System.out.println("80 percentile value: " + percentile.evaluate(values, 80.0)); GeometricMean geoMean = new GeometricMean(); System.out.println("geometric mean: " + geoMean.evaluate(values)); StandardDeviation stdDev = new StandardDeviation(); System.out.println("standard dev: " + stdDev.evaluate(values)); Skewness skewness = new Skewness(); System.out.println("skewness: " + skewness.evaluate(values)); Kurtosis kurtosis = new Kurtosis(); System.out.println("kurtosis: " + kurtosis.evaluate(values)); }
From source file:laboGrid.graphs.replication.ReplicationGraphHeuristicGenerator.java
protected static void balanceMatrix(int[][] edges, int[] peerSize, double stopCriterion) { double[] normIn = new double[peerSize.length]; for (int i = 0; i < peerSize.length; ++i) { for (int j = 0; j < peerSize.length; ++j) { normIn[j] += edges[i][j];//from w w w. j a v a 2 s . c om } } for (int j = 0; j < peerSize.length; ++j) { normIn[j] /= peerSize[j]; } Variance v = new Variance(); double var1 = v.evaluate(normIn); System.out.println("Initial variance on DA incoming edges is " + var1); double var2 = 0; int k = 0; int maxJ = 1, minJ = 1; boolean updateVar1 = false; while ((var1 - var2) >= stopCriterion) { // First line (to ignore element (0,0)) double maxNorm = normIn[1], minNorm = normIn[1]; maxJ = 1; minJ = 1; for (int j = 1; j < peerSize.length; ++j) { if (normIn[j] > maxNorm) { maxJ = j; maxNorm = normIn[j]; } if (normIn[j] < minNorm) { minJ = j; minNorm = normIn[j]; } } if (minJ != maxJ) { balanceRow(0, edges, peerSize, minJ, maxJ, normIn); } // Other lines for (int i = 1; i < peerSize.length; ++i) { maxNorm = normIn[0]; minNorm = normIn[0]; maxJ = 0; minJ = 0; for (int j = 0; j < peerSize.length; ++j) { if (normIn[j] > maxNorm && i != j) { maxJ = j; maxNorm = normIn[j]; } if (normIn[j] < minNorm && i != j) { minJ = j; minNorm = normIn[j]; } } if (minJ != maxJ) { balanceRow(i, edges, peerSize, minJ, maxJ, normIn); } } double tmpVar = v.evaluate(normIn); if (updateVar1) var1 = var2; else updateVar1 = true; var2 = tmpVar; System.out.println( "After pass " + k + ", variance on DA incoming edges is " + var2 + " (vs. " + var1 + ")"); ++k; } }
From source file:com.clican.pluto.dataprocess.dpl.function.impl.Beta.java
private double getBeta(double[] referValueList, double[] estimateValueList) { Variance var = new Variance(false); Covariance cov = new Covariance(); double varValue = var.evaluate(referValueList); double covValue = cov.covariance(referValueList, estimateValueList, false); if (log.isDebugEnabled()) { log.debug("Covariance=[" + covValue + "],Variance=[" + varValue + "]"); }// w w w .java2 s .com Double beta = covValue / varValue; return beta; }
From source file:Covariance.java
/** * Compute a covariance matrix from a matrix whose columns represent * covariates. /*from w w w. jav a 2s . c o m*/ * @param matrix input matrix (must have at least two columns and two rows) * @param biasCorrected determines whether or not covariance estimates are bias-corrected * @return covariance matrix */ protected RealMatrix computeCovarianceMatrix(RealMatrix matrix, boolean biasCorrected) { int dimension = matrix.getColumnDimension(); Variance variance = new Variance(biasCorrected); RealMatrix outMatrix = new BlockRealMatrix(dimension, dimension); for (int i = 0; i < dimension; i++) { for (int j = 0; j < i; j++) { double cov = covariance(matrix.getColumn(i), i, matrix.getColumn(j), j, biasCorrected); outMatrix.setEntry(i, j, cov); outMatrix.setEntry(j, i, cov); } outMatrix.setEntry(i, i, variance.evaluate(matrix.getColumn(i))); } return outMatrix; }
From source file:org.beedraz.semantics_II.MathBugDemonstration.java
/** * @param args// w w w. j av a 2 s .com */ public static void main(String[] args) { // difference between getResult and evaluate // double[] values = new double[] {1.0, 2.0, Double.POSITIVE_INFINITY}; // Variance var1 = new Variance(); // double value1 = var1.evaluate(values); // Variance var2 = new Variance(); // var2.incrementAll(values); // double value2 = var2.getResult(); // System.out.println(value1); // System.out.println(value2); // difference between getResult and evaluate double[] values = new double[] { 1.0, 2.0, Double.NEGATIVE_INFINITY }; Variance var1 = new Variance(); double value1 = var1.evaluate(values); Variance var2 = new Variance(); var2.incrementAll(values); double value2 = var2.getResult(); var2.evaluate(values); System.out.println(value1); System.out.println(value2); // // evaluate method changes internal representation // double[] values = new double[] {1.0, 2.0, Double.NEGATIVE_INFINITY}; // Variance var1 = new Variance(); // var1.incrementAll(values); // System.out.println(var1.getN()); // System.out.println(var1.getResult()); // double value1 = var1.evaluate(values); // System.out.println(var1.getN()); // System.out.println(var1.getResult()); // System.out.println(value1); }
From source file:org.gwaspi.statistics.ChiSqrBoundaryCalculator.java
protected static void calculateChisqrBoundaryByVariance() throws IOException, MathException { FileWriter repFW = new FileWriter(boundaryPath); BufferedWriter repBW = new BufferedWriter(repFW); NetcdfFile ncfile = NetcdfFile.open(netCDFFile); List<Dimension> dims = ncfile.getDimensions(); Dimension sizeDim = dims.get(0); Dimension simsDim = dims.get(1); String varName = "distributions"; Variable distributions = ncfile.findVariable(varName); try {/*from w ww.j a v a 2s. com*/ for (int i = 0; i < pointsNb; i++) { // distributions(i:i:1, 0:simsNb:1) ArrayDouble.D2 rdDoubleArrayD2 = (ArrayDouble.D2) distributions .read(i + ":" + i + ":1, 0:" + (simsDim.getLength() - 1) + ":1"); ArrayDouble.D1 rdDoubleArrayD1 = (D1) rdDoubleArrayD2.reduce(); double sampleSize = rdDoubleArrayD2.getSize(); double currentTot = 0; double[] allValues = new double[(int) sampleSize]; for (int j = 0; j < sampleSize; j++) { allValues[j] = rdDoubleArrayD1.get(j); currentTot += rdDoubleArrayD1.get(j); } Variance variance = new Variance(); double varianceValue = variance.evaluate(allValues); double currentAvg = currentTot / simNb; double low95 = currentAvg - varianceValue; double top95 = currentAvg + varianceValue; StringBuilder sb = new StringBuilder(); sb.append(top95); sb.append(","); sb.append(currentAvg); sb.append(","); sb.append(low95); repBW.append(sb + "\n"); } } catch (IOException ex) { log.error("Cannot read data", ex); } catch (InvalidRangeException ex) { log.error("Cannot read data", ex); } repBW.close(); repFW.close(); log.info("Confidence boundary created for {} points", N); }