Examples with RealVector org.apache.commons.math3.linear.RealVector used on opensource projects

Example 36 with RealVector

use of org.apache.commons.math3.linear.RealVector in project knime-core by knime.

the class BinaryNominalSplitsPCATest method testCalculateWeightedCovarianceMatrix.

@Test
public void testCalculateWeightedCovarianceMatrix() {
    final CombinedAttributeValues[] attVals = createTestAttVals();
    final double totalSumWeight = 300;
    final int numTargetVals = 3;
    final RealVector meanClassProbabilityVector = BinaryNominalSplitsPCA.calculateMeanClassProbabilityVector(attVals, totalSumWeight, numTargetVals);
    RealMatrix weightedCovarianceMatrix = BinaryNominalSplitsPCA.calculateWeightedCovarianceMatrix(attVals, meanClassProbabilityVector, totalSumWeight, numTargetVals);
    // the reference matrix is altered to be easily readable therefore we have to do the same to the calculated matrix
    weightedCovarianceMatrix = weightedCovarianceMatrix.scalarMultiply(1 / weightedCovarianceMatrix.getEntry(0, 0));
    weightedCovarianceMatrix = weightedCovarianceMatrix.scalarMultiply(10);
    final RealMatrix expectedWeightedCovarianceMatrix = MatrixUtils.createRealMatrix(new double[][] { { 10.0, -4.167, -5.833 }, { -4.167, 14.167, -10.0 }, { -5.833, -10.0, 15.833 } });
    // RealMatrix does overwrite equals but all entries must be exactly the same for two matrices to be equal
    // Therefore we need to use the asserEquals method that allows to define a delta
    assertEquals(expectedWeightedCovarianceMatrix.getRowDimension(), weightedCovarianceMatrix.getRowDimension());
    assertEquals(expectedWeightedCovarianceMatrix.getColumnDimension(), weightedCovarianceMatrix.getColumnDimension());
    for (int r = 0; r < weightedCovarianceMatrix.getRowDimension(); r++) {
        for (int c = 0; c < weightedCovarianceMatrix.getColumnDimension(); c++) {
            assertEquals(expectedWeightedCovarianceMatrix.getEntry(r, c), weightedCovarianceMatrix.getEntry(r, c), 0.001);
        }
    }
}

Example 37 with RealVector

use of org.apache.commons.math3.linear.RealVector in project imagingbook-common by imagingbook.

the class AffineFit method fit.

@Override
public void fit(List<double[]> X, List<double[]> Y) {
    // fits n-dimensional data sets with affine model
    if (X.size() != Y.size())
        throw new IllegalArgumentException("point sequences X, Y must have same length");
    this.m = X.size();
    this.n = X.get(0).length;
    RealMatrix M = MatrixUtils.createRealMatrix(2 * m, 2 * (n + 1));
    RealVector b = new ArrayRealVector(2 * m);
    // mount matrix M:
    int row = 0;
    for (double[] x : X) {
        for (int j = 0; j < n; j++) {
            M.setEntry(row, j, x[j]);
            M.setEntry(row, n, 1);
            row++;
        }
        for (int j = 0; j < n; j++) {
            M.setEntry(row, j + n + 1, x[j]);
            M.setEntry(row, 2 * n + 1, 1);
            row++;
        }
    }
    // mount vector b
    row = 0;
    for (double[] y : Y) {
        for (int j = 0; j < n; j++) {
            b.setEntry(row, y[j]);
            row++;
        }
    }
    SingularValueDecomposition svd = new SingularValueDecomposition(M);
    DecompositionSolver solver = svd.getSolver();
    RealVector a = solver.solve(b);
    A = makeTransformationMatrix(a);
}

Example 38 with RealVector

use of org.apache.commons.math3.linear.RealVector in project imagingbook-common by imagingbook.

the class ProcrustesFit method makeDataMatrix.

private RealMatrix makeDataMatrix(List<double[]> X, double[] meanX) {
    if (meanX == null) {
        return makeDataMatrix(X);
    }
    final int m = X.size();
    final int n = X.get(0).length;
    RealMatrix M = MatrixUtils.createRealMatrix(n, m);
    RealVector mean = MatrixUtils.createRealVector(meanX);
    int i = 0;
    for (double[] x : X) {
        RealVector xi = MatrixUtils.createRealVector(x).subtract(mean);
        M.setColumnVector(i, xi);
        i++;
    }
    return M;
}

Example 39 with RealVector

use of org.apache.commons.math3.linear.RealVector in project imagingbook-common by imagingbook.

the class ProcrustesFit method fit.

@Override
public void fit(List<double[]> X, List<double[]> Y) {
    if (X.size() != Y.size())
        throw new IllegalArgumentException("point sequences X, Y must have same length");
    this.m = X.size();
    this.n = X.get(0).length;
    double[] meanX = null;
    double[] meanY = null;
    if (this.allowTranslation) {
        meanX = getMeanVec(X);
        meanY = getMeanVec(Y);
    }
    RealMatrix P = makeDataMatrix(X, meanX);
    RealMatrix Q = makeDataMatrix(Y, meanY);
    // P, Q of same dimensions?
    MatrixUtils.checkAdditionCompatible(P, Q);
    RealMatrix QPt = Q.multiply(P.transpose());
    SingularValueDecomposition svd = new SingularValueDecomposition(QPt);
    RealMatrix U = svd.getU();
    RealMatrix S = svd.getS();
    RealMatrix V = svd.getV();
    double d = (svd.getRank() >= n) ? det(QPt) : det(U) * det(V);
    RealMatrix D = MatrixUtils.createRealIdentityMatrix(n);
    if (d < 0 && forceRotation)
        D.setEntry(n - 1, n - 1, -1);
    R = U.multiply(D).multiply(V.transpose());
    double normP = P.getFrobeniusNorm();
    double normQ = Q.getFrobeniusNorm();
    c = (this.allowScaling) ? S.multiply(D).getTrace() / sqr(normP) : 1.0;
    if (allowTranslation) {
        RealVector ma = MatrixUtils.createRealVector(meanX);
        RealVector mb = MatrixUtils.createRealVector(meanY);
        t = mb.subtract(R.scalarMultiply(c).operate(ma));
    } else {
        // zero vector
        t = new ArrayRealVector(n);
    }
    err = sqr(normQ) - sqr(S.multiply(D).getTrace() / normP);
}

Example 40 with RealVector

use of org.apache.commons.math3.linear.RealVector in project imagingbook-common by imagingbook.

the class ProcrustesFit method getEuclideanError.

/**
 * Calculates the total error for the estimated fit as
 * the sum of the squared Euclidean distances between the
 * transformed point set X and the reference set Y.
 * This method is provided for testing as an alternative to
 * the quicker {@link getError} method.
 * @param X Sequence of n-dimensional points.
 * @param Y Sequence of n-dimensional points (reference).
 * @return The total error for the estimated fit.
 */
public double getEuclideanError(List<double[]> X, List<double[]> Y) {
    RealMatrix cR = R.scalarMultiply(c);
    double ee = 0;
    for (int i = 0; i < X.size(); i++) {
        RealVector ai = new ArrayRealVector(X.get(i));
        RealVector bi = new ArrayRealVector(Y.get(i));
        RealVector aiT = cR.operate(ai).add(t);
        double ei = aiT.subtract(bi).getNorm();
        ee = ee + sqr(ei);
    }
    return ee;
}