Package org.apache.commons.math3.linear

Examples of org.apache.commons.math3.linear.Array2DRowRealMatrix

125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
    @Test
    public void testLeastSquares1() {

        final RealMatrix factors =
            new Array2DRowRealMatrix(new double[][] {
                    { 1, 0 },
                    { 0, 1 }
                }, false);
        LeastSquaresConverter ls = new LeastSquaresConverter(new MultivariateVectorFunction() {
                public double[] value(double[] variables) {
                    return factors.operate(variables);
                }
            }, new double[] { 2.0, -3.0 });
        SimplexOptimizer optimizer = new SimplexOptimizer(-1, 1e-6);
        optimizer.setSimplex(new NelderMeadSimplex(2));
        PointValuePair optimum =
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
    @Test
    public void testLeastSquares2() {

        final RealMatrix factors =
            new Array2DRowRealMatrix(new double[][] {
                    { 1, 0 },
                    { 0, 1 }
                }, false);
        LeastSquaresConverter ls = new LeastSquaresConverter(new MultivariateVectorFunction() {
                public double[] value(double[] variables) {
                    return factors.operate(variables);
                }
            }, new double[] { 2, -3 }, new double[] { 10, 0.1 });
        SimplexOptimizer optimizer = new SimplexOptimizer(-1, 1e-6);
        optimizer.setSimplex(new NelderMeadSimplex(2));
        PointValuePair optimum =
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
    @Test
    public void testLeastSquares3() {

        final RealMatrix factors =
            new Array2DRowRealMatrix(new double[][] {
                    { 1, 0 },
                    { 0, 1 }
                }, false);
        LeastSquaresConverter ls = new LeastSquaresConverter(new MultivariateVectorFunction() {
                public double[] value(double[] variables) {
                    return factors.operate(variables);
                }
            }, new double[] { 2, -3 }, new Array2DRowRealMatrix(new double [][] {
                    { 1, 1.2 }, { 1.2, 2 }
                }));
        SimplexOptimizer optimizer = new SimplexOptimizer(-1, 1e-6);
        optimizer.setSimplex(new NelderMeadSimplex(2));
        PointValuePair optimum =
View Full Code Here
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
        if (minDiff < requiredMinDiff) {
            initialTrustRegionRadius = minDiff / 3.0;
        }

        // Initialize the data structures used by the "bobyqa" method.
        bMatrix = new Array2DRowRealMatrix(dimension + numberOfInterpolationPoints,
                                           dimension);
        zMatrix = new Array2DRowRealMatrix(numberOfInterpolationPoints,
                                           numberOfInterpolationPoints - dimension - 1);
        interpolationPoints = new Array2DRowRealMatrix(numberOfInterpolationPoints,
                                                       dimension);
        originShift = new ArrayRealVector(dimension);
        fAtInterpolationPoints = new ArrayRealVector(numberOfInterpolationPoints);
        trustRegionCenterOffset = new ArrayRealVector(dimension);
        gradientAtTrustRegionCenter = new ArrayRealVector(dimension);
View Full Code Here
133
134
135
136
137
138
139
140
            }
            for (int j = noIntercept ? 0 : 1; j < cols; j++) {
                x[i][j] = data[pointer++];
            }
        }
        this.xMatrix = new Array2DRowRealMatrix(x);
        this.yVector = new ArrayRealVector(y);
    }
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
        }
        if (x.length == 0) {
            throw new NoDataException();
        }
        if (noIntercept) {
            this.xMatrix = new Array2DRowRealMatrix(x, true);
        } else { // Augment design matrix with initial unitary column
            final int nVars = x[0].length;
            final double[][] xAug = new double[x.length][nVars + 1];
            for (int i = 0; i < x.length; i++) {
                if (x[i].length != nVars) {
                    throw new DimensionMismatchException(x[i].length, nVars);
                }
                xAug[i][0] = 1.0d;
                System.arraycopy(x[i], 0, xAug[i], 1, nVars);
            }
            this.xMatrix = new Array2DRowRealMatrix(xAug, false);
        }
    }
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
        // create a matrix of the correct size
        int width = numDecisionVariables + numSlackVariables +
        numArtificialVariables + getNumObjectiveFunctions() + 1; // + 1 is for RHS
        int height = constraints.size() + getNumObjectiveFunctions();
        Array2DRowRealMatrix matrix = new Array2DRowRealMatrix(height, width);

        // initialize the objective function rows
        if (getNumObjectiveFunctions() == 2) {
            matrix.setEntry(0, 0, -1);
        }
        int zIndex = (getNumObjectiveFunctions() == 1) ? 0 : 1;
        matrix.setEntry(zIndex, zIndex, maximize ? 1 : -1);
        RealVector objectiveCoefficients =
            maximize ? f.getCoefficients().mapMultiply(-1) : f.getCoefficients();
        copyArray(objectiveCoefficients.toArray(), matrix.getDataRef()[zIndex]);
        matrix.setEntry(zIndex, width - 1,
            maximize ? f.getConstantTerm() : -1 * f.getConstantTerm());

        if (!restrictToNonNegative) {
            matrix.setEntry(zIndex, getSlackVariableOffset() - 1,
                getInvertedCoefficientSum(objectiveCoefficients));
        }

        // initialize the constraint rows
        int slackVar = 0;
        int artificialVar = 0;
        for (int i = 0; i < constraints.size(); i++) {
            LinearConstraint constraint = constraints.get(i);
            int row = getNumObjectiveFunctions() + i;

            // decision variable coefficients
            copyArray(constraint.getCoefficients().toArray(), matrix.getDataRef()[row]);

            // x-
            if (!restrictToNonNegative) {
                matrix.setEntry(row, getSlackVariableOffset() - 1,
                    getInvertedCoefficientSum(constraint.getCoefficients()));
            }

            // RHS
            matrix.setEntry(row, width - 1, constraint.getValue());

            // slack variables
            if (constraint.getRelationship() == Relationship.LEQ) {
                matrix.setEntry(row, getSlackVariableOffset() + slackVar++, 1);  // slack
            } else if (constraint.getRelationship() == Relationship.GEQ) {
                matrix.setEntry(row, getSlackVariableOffset() + slackVar++, -1); // excess
            }

            // artificial variables
            if ((constraint.getRelationship() == Relationship.EQ) ||
                    (constraint.getRelationship() == Relationship.GEQ)) {
                matrix.setEntry(0, getArtificialVariableOffset() + artificialVar, 1);
                matrix.setEntry(row, getArtificialVariableOffset() + artificialVar++, 1);
                matrix.setRowVector(0, matrix.getRowVector(0).subtract(matrix.getRowVector(row)));
            }
        }

        return matrix;
    }
View Full Code Here
360
361
362
363
364
365
366
367
        for (int i = columnsToDrop.size() - 1; i >= 0; i--) {
          columnLabels.remove((int) columnsToDrop.get(i));
        }

        this.tableau = new Array2DRowRealMatrix(matrix);
        this.numArtificialVariables = 0;
    }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
    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 {
View Full Code Here
65
66
67
68
69
70
71
72
     * Add the covariance data.
     *
     * @param omega the [n,n] array representing the covariance
     */
    protected void newCovarianceData(double[][] omega){
        this.Omega = new Array2DRowRealMatrix(omega);
        this.OmegaInverse = null;
    }
View Full Code Here
TOP

Related Classes of org.apache.commons.math3.linear.Array2DRowRealMatrix

  • com.cloudera.oryx.common.math.LinearSystemSolverTest
  • edu.cmu.sphinx.speakerid.SpeakerCluster
  • edu.cmu.sphinx.speakerid.SpeakerIdentification
  • net.myrrix.common.math.MatrixUtils
  • org.apache.commons.math3.analysis.differentiation.DerivativeStructure
  • org.apache.commons.math3.analysis.function.HarmonicOscillator
  • org.apache.commons.math3.analysis.function.Sin
  • org.apache.commons.math3.analysis.function.Sinc
  • org.apache.commons.math3.analysis.MultivariateFunction
  • org.apache.commons.math3.analysis.QuinticFunction
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.