List of usage examples for org.apache.commons.math3.linear RealMatrix getColumnDimension
int getColumnDimension();
From source file:org.ssascaling.model.timeseries.learner.apache.OLSMultipleLinearRegression.java
/** * <p>Compute the "hat" matrix./* w w w . j a va 2 s.c o m*/ * </p> * <p>The hat matrix is defined in terms of the design matrix X * by X(X<sup>T</sup>X)<sup>-1</sup>X<sup>T</sup> * </p> * <p>The implementation here uses the QR decomposition to compute the * hat matrix as Q I<sub>p</sub>Q<sup>T</sup> where I<sub>p</sub> is the * p-dimensional identity matrix augmented by 0's. This computational * formula is from "The Hat Matrix in Regression and ANOVA", * David C. Hoaglin and Roy E. Welsch, * <i>The American Statistician</i>, Vol. 32, No. 1 (Feb., 1978), pp. 17-22. * * @return the hat matrix */ public RealMatrix calculateHat() { // Create augmented identity matrix RealMatrix Q = qr.getQ(); final int p = qr.getR().getColumnDimension(); final int n = Q.getColumnDimension(); Array2DRowRealMatrix augI = new Array2DRowRealMatrix(n, n); double[][] augIData = augI.getDataRef(); for (int i = 0; i < n; i++) { for (int j = 0; j < n; j++) { if (i == j && i < p) { augIData[i][j] = 1d; } else { augIData[i][j] = 0d; } } } // Compute and return Hat matrix return Q.multiply(augI).multiply(Q.transpose()); }
From source file:org.ssascaling.model.timeseries.learner.apache.QRDecomposition.java
/** * Calculates the QR-decomposition of the given matrix. * * @param matrix The matrix to decompose. * @param threshold Singularity threshold. *//* w w w.j a v a2 s . c om*/ public QRDecomposition(RealMatrix matrix, double threshold) { this.threshold = threshold; final int m = matrix.getRowDimension(); final int n = matrix.getColumnDimension(); qrt = matrix.transpose().getData(); rDiag = new double[FastMath.min(m, n)]; cachedQ = null; cachedQT = null; cachedR = null; cachedH = null; /* * The QR decomposition of a matrix A is calculated using Householder * reflectors by repeating the following operations to each minor * A(minor,minor) of A: */ for (int minor = 0; minor < FastMath.min(m, n); minor++) { final double[] qrtMinor = qrt[minor]; /* * Let x be the first column of the minor, and a^2 = |x|^2. * x will be in the positions qr[minor][minor] through qr[m][minor]. * The first column of the transformed minor will be (a,0,0,..)' * The sign of a is chosen to be opposite to the sign of the first * component of x. Let's find a: */ double xNormSqr = 0; for (int row = minor; row < m; row++) { final double c = qrtMinor[row]; xNormSqr += c * c; } final double a = (qrtMinor[minor] > 0) ? -FastMath.sqrt(xNormSqr) : FastMath.sqrt(xNormSqr); rDiag[minor] = a; if (a != 0.0) { /* * Calculate the normalized reflection vector v and transform * the first column. We know the norm of v beforehand: v = x-ae * so |v|^2 = <x-ae,x-ae> = <x,x>-2a<x,e>+a^2<e,e> = * a^2+a^2-2a<x,e> = 2a*(a - <x,e>). * Here <x, e> is now qr[minor][minor]. * v = x-ae is stored in the column at qr: */ qrtMinor[minor] -= a; // now |v|^2 = -2a*(qr[minor][minor]) /* * Transform the rest of the columns of the minor: * They will be transformed by the matrix H = I-2vv'/|v|^2. * If x is a column vector of the minor, then * Hx = (I-2vv'/|v|^2)x = x-2vv'x/|v|^2 = x - 2<x,v>/|v|^2 v. * Therefore the transformation is easily calculated by * subtracting the column vector (2<x,v>/|v|^2)v from x. * * Let 2<x,v>/|v|^2 = alpha. From above we have * |v|^2 = -2a*(qr[minor][minor]), so * alpha = -<x,v>/(a*qr[minor][minor]) */ for (int col = minor + 1; col < n; col++) { final double[] qrtCol = qrt[col]; double alpha = 0; for (int row = minor; row < m; row++) { alpha -= qrtCol[row] * qrtMinor[row]; } alpha /= a * qrtMinor[minor]; // Subtract the column vector alpha*v from x. for (int row = minor; row < m; row++) { qrtCol[row] -= alpha * qrtMinor[row]; } } } } }
From source file:org.ujmp.commonsmath.AbstractCommonsMathDenseDoubleMatrix2D.java
public AbstractCommonsMathDenseDoubleMatrix2D(RealMatrix matrix) { super(matrix.getRowDimension(), matrix.getColumnDimension()); this.matrix = matrix; }
From source file:pl.matrix.core.MatrixCalculator.java
public Matrix transformToTriangularUpperMatrix(Matrix a) throws Exception { RealMatrix aRealMatrix = a.toRealMatrix(); if (aRealMatrix.getRowDimension() != aRealMatrix.getColumnDimension()) { throw new Exception(); }//ww w.jav a2 s .com int n = aRealMatrix.getRowDimension(); // iteracja (zerowanie i-tej kolumny) for (int i = 0; i < n - 1; i++) { // po wierszach for (int j = i + 1; j < n; j++) { double factor = aRealMatrix.getEntry(j, i) / aRealMatrix.getEntry(i, i); // po kolumnach for (int k = i; k < n; k++) { double newValue = aRealMatrix.getEntry(j, k) - factor * aRealMatrix.getEntry(i, k); aRealMatrix.setEntry(j, k, newValue); } } } Matrix result = new Matrix(aRealMatrix); return result; }
From source file:playground.sergioo.facilitiesGenerator2012.WorkFacilitiesGeneration.java
private static Set<PointPerson> getPCATransformation(Collection<PointPerson> points) { RealMatrix pointsM = new Array2DRowRealMatrix(points.iterator().next().getDimension(), points.size()); int k = 0;/*from w w w . j a v a2s. c om*/ for (PointND<Double> point : points) { for (int f = 0; f < point.getDimension(); f++) pointsM.setEntry(f, k, point.getElement(f)); k++; } RealMatrix means = new Array2DRowRealMatrix(pointsM.getRowDimension(), 1); for (int r = 0; r < means.getRowDimension(); r++) { double mean = 0; for (int c = 0; c < pointsM.getColumnDimension(); c++) mean += pointsM.getEntry(r, c) / pointsM.getColumnDimension(); means.setEntry(r, 0, mean); } RealMatrix deviations = new Array2DRowRealMatrix(pointsM.getRowDimension(), pointsM.getColumnDimension()); for (int r = 0; r < deviations.getRowDimension(); r++) for (int c = 0; c < deviations.getColumnDimension(); c++) deviations.setEntry(r, c, pointsM.getEntry(r, c) - means.getEntry(r, 0)); RealMatrix covariance = deviations.multiply(deviations.transpose()) .scalarMultiply(1 / (double) pointsM.getColumnDimension()); EigenDecomposition eigenDecomposition = new EigenDecomposition(covariance, 0); RealMatrix eigenVectorsT = eigenDecomposition.getVT(); RealVector eigenValues = new ArrayRealVector(eigenDecomposition.getD().getRowDimension()); for (int r = 0; r < eigenDecomposition.getD().getRowDimension(); r++) eigenValues.setEntry(r, eigenDecomposition.getD().getEntry(r, r)); for (int i = 0; i < eigenValues.getDimension(); i++) { for (int j = i + 1; j < eigenValues.getDimension(); j++) if (eigenValues.getEntry(i) < eigenValues.getEntry(j)) { double tempValue = eigenValues.getEntry(i); eigenValues.setEntry(i, eigenValues.getEntry(j)); eigenValues.setEntry(j, tempValue); RealVector tempVector = eigenVectorsT.getRowVector(i); eigenVectorsT.setRowVector(i, eigenVectorsT.getRowVector(j)); eigenVectorsT.setRowVector(j, tempVector); } eigenVectorsT.setRowVector(i, eigenVectorsT.getRowVector(i).mapMultiply(Math.sqrt(1 / eigenValues.getEntry(i)))); } RealVector standardDeviations = new ArrayRealVector(pointsM.getRowDimension()); for (int r = 0; r < covariance.getRowDimension(); r++) standardDeviations.setEntry(r, Math.sqrt(covariance.getEntry(r, r))); double zValue = standardDeviations.dotProduct(new ArrayRealVector(pointsM.getRowDimension(), 1)); RealMatrix zScore = deviations.scalarMultiply(1 / zValue); pointsM = eigenVectorsT.multiply(zScore); Set<PointPerson> pointsC = new HashSet<PointPerson>(); k = 0; for (PointPerson point : points) { PointPerson pointC = new PointPerson(point.getId(), point.getOccupation(), new Double[] { pointsM.getEntry(0, k), pointsM.getEntry(1, k) }, point.getPlaceType()); pointC.setWeight(point.getWeight()); pointsC.add(pointC); k++; } return pointsC; }
From source file:Pruning.Experiments.KendallsCorrelation.java
/** * Computes the Kendall's Tau rank correlation matrix for the columns of * the input matrix.// w w w . jav a2 s. c o m * * @param matrix matrix with columns representing variables to correlate * @return correlation matrix */ public RealMatrix computeCorrelationMatrix(final RealMatrix matrix) { int nVars = matrix.getColumnDimension(); RealMatrix outMatrix = new BlockRealMatrix(nVars, nVars); for (int i = 0; i < nVars; i++) { for (int j = 0; j < i; j++) { double corr = correlation(matrix.getColumn(i), matrix.getColumn(j), matrix.getColumn(i).length); outMatrix.setEntry(i, j, corr); outMatrix.setEntry(j, i, corr); } outMatrix.setEntry(i, i, 1d); } return outMatrix; }
From source file:put.ci.cevo.framework.algorithms.ApacheCMAES.java
/** * @param m Input matrix// w w w. j av a2s . co m * @return Matrix representing the element-wise logarithm of m. */ private static RealMatrix log(final RealMatrix m) { final double[][] d = new double[m.getRowDimension()][m.getColumnDimension()]; for (int r = 0; r < m.getRowDimension(); r++) { for (int c = 0; c < m.getColumnDimension(); c++) { d[r][c] = FastMath.log(m.getEntry(r, c)); } } return new Array2DRowRealMatrix(d, false); }
From source file:put.ci.cevo.framework.algorithms.ApacheCMAES.java
/** * @param m Input matrix./* w w w .java 2s . co m*/ * @return Matrix representing the element-wise square root of m. */ private static RealMatrix sqrt(final RealMatrix m) { final double[][] d = new double[m.getRowDimension()][m.getColumnDimension()]; for (int r = 0; r < m.getRowDimension(); r++) { for (int c = 0; c < m.getColumnDimension(); c++) { d[r][c] = FastMath.sqrt(m.getEntry(r, c)); } } return new Array2DRowRealMatrix(d, false); }
From source file:put.ci.cevo.framework.algorithms.ApacheCMAES.java
/** * @param m Input matrix.//from ww w . ja v a2s .c om * @return Matrix representing the element-wise square of m. */ private static RealMatrix square(final RealMatrix m) { final double[][] d = new double[m.getRowDimension()][m.getColumnDimension()]; for (int r = 0; r < m.getRowDimension(); r++) { for (int c = 0; c < m.getColumnDimension(); c++) { double e = m.getEntry(r, c); d[r][c] = e * e; } } return new Array2DRowRealMatrix(d, false); }
From source file:put.ci.cevo.framework.algorithms.ApacheCMAES.java
/** * @param m Input matrix 1./*from w w w . j a v a2 s . c o m*/ * @param n Input matrix 2. * @return the matrix where the elements of m and n are element-wise multiplied. */ private static RealMatrix times(final RealMatrix m, final RealMatrix n) { final double[][] d = new double[m.getRowDimension()][m.getColumnDimension()]; for (int r = 0; r < m.getRowDimension(); r++) { for (int c = 0; c < m.getColumnDimension(); c++) { d[r][c] = m.getEntry(r, c) * n.getEntry(r, c); } } return new Array2DRowRealMatrix(d, false); }