Example usage for org.apache.commons.math3.linear EigenDecomposition EigenDecomposition

Introduction

In this page you can find the example usage for org.apache.commons.math3.linear EigenDecomposition EigenDecomposition.

Prototype

public EigenDecomposition(final RealMatrix matrix) throws MathArithmeticException 

Source Link

Document

Calculates the eigen decomposition of the given real matrix.

Usage

From source file:lanchester.TestEigen.java

public static void main(String[] args) {
    mat = getMat(4);/* w w  w .j av  a  2  s .  c o  m*/
    //        fillMat(mat);
    eigen = new EigenDecomposition(mat);
    double det = eigen.getDeterminant();
    double[] eVals = eigen.getRealEigenvalues();

    if (eigen.hasComplexEigenvalues()) {
        System.out.println("Complex eigenvalues");
    }
    Array2DRowRealMatrix eVectors = (Array2DRowRealMatrix) eigen.getV();
    EigenDecomposition eigen2 = new EigenDecomposition(eVectors);
    double det2 = eigen2.getDeterminant();
    System.out.println("Det 1 = " + det + " and Det 2 = " + det2);
}

---

From source file:bigdataproject.PCA.java

public double[][] reduceDimensions() {
    BlockRealMatrix matrix = new BlockRealMatrix(dataSet);
    Covariance cov = new Covariance(matrix, false);
    RealMatrix covarianceMatrix = cov.getCovarianceMatrix();
    EigenDecomposition dec = new EigenDecomposition(covarianceMatrix);
    RealVector principalEigenVector = dec.getEigenvector(0);
    RealVector secondEigenVector = dec.getEigenvector(1);
    BlockRealMatrix pca = new BlockRealMatrix(principalEigenVector.getDimension(), 2);
    pca.setColumnVector(0, principalEigenVector);
    pca.setColumnVector(1, secondEigenVector);
    BlockRealMatrix pcaTranspose = pca.transpose();
    BlockRealMatrix columnVectorMatrix = matrix.transpose();
    BlockRealMatrix matrix2D = pcaTranspose.multiply(columnVectorMatrix);
    return matrix2D.getData();
}

---

From source file:net.sf.dsp4j.octave_3_2_4.Eig.java

public static Complex[] eig(RealMatrix d) {
    EigenDecomposition eig = new EigenDecomposition(d);
    double[] realEigenvalues = eig.getRealEigenvalues();
    double[] imagEigenvalues = eig.getImagEigenvalues();

    final Complex[] result = new Complex[realEigenvalues.length];
    for (int i = 0; i < realEigenvalues.length; i++) {
        result[i] = new Complex(realEigenvalues[i], imagEigenvalues[i]);
    }//from w  w  w . ja va 2 s .  com
    return result;
}

---

From source file:com.itemanalysis.psychometrics.factoranalysis.PrincipalComponentsMethod.java

public double estimateParameters() {

    EigenDecomposition eigen = new EigenDecomposition(R);
    RealMatrix eigenVectors = eigen.getV().getSubMatrix(0, nVariables - 1, 0, nFactors - 1);

    double[] ev = new double[nFactors];
    for (int i = 0; i < nFactors; i++) {
        ev[i] = Math.sqrt(eigen.getRealEigenvalue(i));
    }/*ww w  . j av  a2  s  . c o  m*/
    DiagonalMatrix evMatrix = new DiagonalMatrix(ev);//USE Apache version of Diagonal matrix when upgrade to version 3.2
    RealMatrix LOAD = eigenVectors.multiply(evMatrix);

    //rotate factor loadings
    if (rotationMethod != RotationMethod.NONE) {
        GPArotation gpa = new GPArotation();
        RotationResults results = gpa.rotate(LOAD, rotationMethod);
        LOAD = results.getFactorLoadings();
    }

    Sum[] colSums = new Sum[nFactors];
    Sum[] colSumsSquares = new Sum[nFactors];

    for (int j = 0; j < nFactors; j++) {
        colSums[j] = new Sum();
        colSumsSquares[j] = new Sum();
    }

    factorLoading = new double[nVariables][nFactors];
    communality = new double[nVariables];
    uniqueness = new double[nVariables];

    for (int i = 0; i < nVariables; i++) {
        for (int j = 0; j < nFactors; j++) {
            factorLoading[i][j] = LOAD.getEntry(i, j);
            colSums[j].increment(factorLoading[i][j]);
            colSumsSquares[j].increment(Math.pow(factorLoading[i][j], 2));
            communality[i] += Math.pow(factorLoading[i][j], 2);
        }
    }

    //check sign of factor
    double sign = 1.0;
    for (int i = 0; i < nVariables; i++) {
        for (int j = 0; j < nFactors; j++) {
            if (colSums[j].getResult() < 0) {
                sign = -1.0;
            } else {
                sign = 1.0;
            }
            factorLoading[i][j] = factorLoading[i][j] * sign;
        }
        uniqueness[i] = 1.0 - communality[i];
    }

    double totSumOfSquares = 0.0;
    sumsOfSquares = new double[nFactors];
    proportionOfExplainedVariance = new double[nFactors];
    proportionOfVariance = new double[nFactors];
    for (int j = 0; j < nFactors; j++) {
        sumsOfSquares[j] = colSumsSquares[j].getResult();
        totSumOfSquares += sumsOfSquares[j];
    }
    for (int j = 0; j < nFactors; j++) {
        proportionOfExplainedVariance[j] = sumsOfSquares[j] / totSumOfSquares;
        proportionOfVariance[j] = sumsOfSquares[j] / nVariables;
    }

    return 0.0;

}

---

From source file:com.simiacryptus.mindseye.test.PCAUtil.java

/**
 * Pca features inv tensor [ ].//  w w w . j av  a  2s .  c om
 *
 * @param covariance        the covariance
 * @param components        the components
 * @param featureDimensions the feature dimensions
 * @param power             the power
 * @return the tensor [ ]
 */
public static Tensor[] pcaFeatures(final RealMatrix covariance, final int components,
        final int[] featureDimensions, final double power) {
    @Nonnull
    final EigenDecomposition decomposition = new EigenDecomposition(covariance);
    final int[] orderedVectors = IntStream.range(0, components).mapToObj(x -> x)
            .sorted(Comparator.comparing(x -> -decomposition.getRealEigenvalue(x))).mapToInt(x -> x).toArray();
    return IntStream.range(0, orderedVectors.length).mapToObj(i -> {
        @Nonnull
        final Tensor src = new Tensor(decomposition.getEigenvector(orderedVectors[i]).toArray(),
                featureDimensions).copy();
        return src.scale(1.0 / src.rms()).scale((Math.pow(decomposition.getRealEigenvalue(orderedVectors[i])
                / decomposition.getRealEigenvalue(orderedVectors[0]), power)));
    }).toArray(i -> new Tensor[i]);
}

---

From source file:com.opengamma.strata.math.impl.rootfinding.EigenvaluePolynomialRootFinder.java

@Override
public Double[] getRoots(RealPolynomialFunction1D function) {
    ArgChecker.notNull(function, "function");
    double[] coeffs = function.getCoefficients();
    int l = coeffs.length - 1;
    double[][] hessianDeref = new double[l][l];
    for (int i = 0; i < l; i++) {
        hessianDeref[0][i] = -coeffs[l - i - 1] / coeffs[l];
        for (int j = 1; j < l; j++) {
            hessianDeref[j][i] = 0;/*from   www  .  j  a  v a2s  .  com*/
            if (i != l - 1) {
                hessianDeref[i + 1][i] = 1;
            }
        }
    }
    RealMatrix hessian = new Array2DRowRealMatrix(hessianDeref);
    double[] d = new EigenDecomposition(hessian).getRealEigenvalues();
    Double[] result = new Double[d.length];
    for (int i = 0; i < d.length; i++) {
        result[i] = d[i];
    }
    return result;
}

---

From source file:de.biomedical_imaging.traJ.features.Asymmetry3Feature.java

/**
 * @return Returns an double array with the following elements [0]=Asymmetry
 *///from www.  ja  va 2s.c o  m
@Override
public double[] evaluate() {
    Array2DRowRealMatrix gyr = RadiusGyrationTensor2D.getRadiusOfGyrationTensor(t);
    EigenDecomposition eigdec = new EigenDecomposition(gyr);
    double e1 = eigdec.getRealEigenvalue(0);
    double e2 = eigdec.getRealEigenvalue(1);
    double asym = -1 * Math.log(1 - Math.pow(e1 - e2, 2) / (2 * Math.pow(e1 + e2, 2)));
    result = new double[] { asym };

    return result;
}

---

From source file:de.biomedical_imaging.traJ.features.Asymmetry2Feature.java

/**
 * @return Returns an double array with the following elements [0]=asymmetry
 *//*from   w ww  .  j ava 2s  .  com*/
@Override
public double[] evaluate() {
    Array2DRowRealMatrix gyr = RadiusGyrationTensor2D.getRadiusOfGyrationTensor(t);
    EigenDecomposition eigdec = new EigenDecomposition(gyr);
    double e1 = eigdec.getRealEigenvalue(0);
    double e2 = eigdec.getRealEigenvalue(1);

    double asym = e2 / e1; //-1*Math.log(1-Math.pow(e1-e2, 2)/(2*Math.pow(e1+e2, 2)));
    result = new double[] { asym };
    return result;
}

---

From source file:de.biomedical_imaging.traJ.features.AsymmetryFeature.java

/**
 * @return Returns an double array with the following elements [0]=Asymmetry
 *//*from ww  w  .  j  a v a 2 s.co  m*/
@Override
public double[] evaluate() {
    Array2DRowRealMatrix gyr = RadiusGyrationTensor2D.getRadiusOfGyrationTensor(t);
    EigenDecomposition eigdec = new EigenDecomposition(gyr);
    double e1 = eigdec.getRealEigenvalue(0);
    double e2 = eigdec.getRealEigenvalue(1);

    double asym = Math.pow(e1 * e1 - e2 * e2, 2) / (Math.pow(e1 * e1 + e2 * e2, 2)); //-1*Math.log(1-Math.pow(e1-e2, 2)/(2*Math.pow(e1+e2, 2)));
    result = new double[] { asym };
    return result;
}

---

From source file:com.itemanalysis.psychometrics.factoranalysis.FactorAnalysisTest.java

@Test
public void eigenValues() {
    RealMatrix R = new Array2DRowRealMatrix(readHarman74Data());

    int nFactors = 2;
    int nVariables = 24;
    double[] x = new double[nVariables];
    for (int i = 0; i < nVariables; i++) {
        x[i] = .5;//from  w  w w  .  j  av  a 2  s . c  o  m
    }

    for (int i = 0; i < nVariables; i++) {
        R.setEntry(i, i, 1.0 - x[i]);
    }

    EigenDecomposition eigen = new EigenDecomposition(R);
    RealMatrix eigenVectors = eigen.getV().getSubMatrix(0, nVariables - 1, 0, nFactors - 1);

    double[] ev = new double[nFactors];
    for (int i = 0; i < nFactors; i++) {
        ev[i] = Math.sqrt(eigen.getRealEigenvalue(i));
    }
    DiagonalMatrix evMatrix = new DiagonalMatrix(ev);// USE Apache version
    // of Diagonal
    // matrix when
    // upgrade to
    // version 3.2
    RealMatrix LAMBDA = eigenVectors.multiply(evMatrix);
    RealMatrix SIGMA = (LAMBDA.multiply(LAMBDA.transpose()));
    RealMatrix RESID = R.subtract(SIGMA);

    double sum = 0.0;
    double squared = 0.0;
    for (int i = 0; i < RESID.getRowDimension(); i++) {
        for (int j = 0; j < RESID.getColumnDimension(); j++) {
            if (i != j) {
                sum += Math.pow(RESID.getEntry(i, j), 2);
            }
        }
    }

    System.out.println(sum);

    // RealMatrix SIGMA = (LAMBDA.multiply(LAMBDA.transpose()));
    //
    // System.out.println("SIGMA");
    // for(int i=0;i<SIGMA.getRowDimension();i++){
    // for(int j=0;j<SIGMA.getColumnDimension();j++){
    // System.out.print(SIGMA.getEntry(i, j) + " ");
    // }
    // System.out.println();
    // }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• »