Package org.apache.commons.math3.optim

Examples of org.apache.commons.math3.optim.PointVectorValuePair

475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
        Arrays.fill(weights, 2);
        for (int i = 0; i < points.length; ++i) {
            circle.addPoint(points[i][0], points[i][1]);
        }
        AbstractLeastSquaresOptimizer optimizer = createOptimizer();
        PointVectorValuePair optimum
            = optimizer.optimize(new MaxEval(100),
                                 circle.getModelFunction(),
                                 circle.getModelFunctionJacobian(),
                                 new Target(target),
                                 new Weight(weights),
                                 new InitialGuess(new double[] { -12, -12 }));
        Vector2D center = new Vector2D(optimum.getPointRef()[0], optimum.getPointRef()[1]);
        Assert.assertTrue(optimizer.getEvaluations() < 25);
        Assert.assertEquals( 0.043, optimizer.getRMS(), 1e-3);
        Assert.assertEquals( 0.292235,  circle.getRadius(center), 1e-6);
        Assert.assertEquals(-0.151738,  center.getX(),            1e-6);
        Assert.assertEquals( 0.2075001, center.getY(),            1e-6);
View Full Code Here
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
        Arrays.fill(weights, 2);
        for (int i = 0; i < points.length; ++i) {
            circle.addPoint(points[i][0], points[i][1]);
        }
        AbstractLeastSquaresOptimizer optimizer = createOptimizer();
        PointVectorValuePair optimum =
            optimizer.optimize(new MaxEval(100),
                               circle.getModelFunction(),
                               circle.getModelFunctionJacobian(),
                               new Target(target),
                               new Weight(weights),
                               new InitialGuess(new double[] { 0, 0 }));
        Assert.assertEquals(-0.1517383071957963, optimum.getPointRef()[0], 1e-6);
        Assert.assertEquals(0.2074999736353867,  optimum.getPointRef()[1], 1e-6);
        Assert.assertEquals(0.04268731682389561, optimizer.getRMS(),       1e-8);
    }
View Full Code Here
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
        Arrays.fill(w, 1);

        final double[][] data = dataset.getData();
        final double[] initial = dataset.getStartingPoint(0);
        final StatisticalReferenceDataset.LeastSquaresProblem problem = dataset.getLeastSquaresProblem();
        final PointVectorValuePair optimum
            = optimizer.optimize(new MaxEval(100),
                                 problem.getModelFunction(),
                                 problem.getModelFunctionJacobian(),
                                 new Target(data[1]),
                                 new Weight(w),
                                 new InitialGuess(initial));

        final double[] actual = optimum.getPoint();
        for (int i = 0; i < actual.length; i++) {
            double expected = dataset.getParameter(i);
            double delta = FastMath.abs(errParams * expected);
            Assert.assertEquals(dataset.getName() + ", param #" + i,
                                expected, actual[i], delta);
View Full Code Here
32
33
34
35
36
37
38
39
40
            @Override
            protected PointVectorValuePair doOptimize() {
                final double[] params = getStartPoint();
                final double[] res = computeResiduals(computeObjectiveValue(params));
                setCost(computeCost(res));
                return new PointVectorValuePair(params, null);
            }
        };
    }
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
        Arrays.fill(w, 1);

        StatisticalReferenceDataset.LeastSquaresProblem problem
            = dataset.getLeastSquaresProblem();

        final PointVectorValuePair optimum
            = optimizer.optimize(new MaxEval(1),
                                 problem.getModelFunction(),
                                 problem.getModelFunctionJacobian(),
                                 new Target(y),
                                 new Weight(w),
                                 new InitialGuess(a));

        final double[] sig = optimizer.computeSigma(optimum.getPoint(), 1e-14);

        final int dof = y.length - a.length;
        final double[] expected = dataset.getParametersStandardDeviations();
        for (int i = 0; i < sig.length; i++) {
            final double actual = FastMath.sqrt(optimizer.getChiSquare() / dof) * sig[i];
 
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
            // Direct solution (using simple regression).
            final double[] regress = problem.solve();

            // Estimation of the standard deviation (diagonal elements of the
            // covariance matrix).
            final PointVectorValuePair optimum
                = optim.optimize(new MaxEval(Integer.MAX_VALUE),
                                 problem.getModelFunction(),
                                 problem.getModelFunctionJacobian(),
                                 new Target(problem.target()),
                                 new Weight(problem.weight()),
                                 new InitialGuess(init));
            final double[] sigma = optim.computeSigma(optimum.getPoint(), 1e-14);

            // Accumulate statistics.
            for (int i = 0; i < numParams; i++) {
                paramsFoundByDirectSolution[i].addValue(regress[i]);
                sigmaEstimate[i].addValue(sigma[i]);
View Full Code Here
327
328
329
330
331
332
333
    @Override
    public PointVectorValuePair doOptimize() {
        final double[] params = getStartPoint();
        final double[] res = computeResiduals(computeObjectiveValue(params));
        setCost(computeCost(res));
        return new PointVectorValuePair(params, null);
    }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
                {  2, 1,  3 },
                { -3, 0, -9 }
        }, new double[] { 1, 1, 1 });

        AbstractLeastSquaresOptimizer optimizer = createOptimizer();
        PointVectorValuePair optimum
            = optimizer.optimize(new MaxEval(100),
                                 problem.getModelFunction(),
                                 problem.getModelFunctionJacobian(),
                                 problem.getTarget(),
                                 new Weight(new double[] { 1, 1, 1 }),
                                 new InitialGuess(new double[] { 0, 0, 0 }));
        Assert.assertTrue(FastMath.sqrt(optimizer.getTargetSize()) * optimizer.getRMS() > 0.6);

        optimizer.computeCovariances(optimum.getPoint(), 1.5e-14);
    }
View Full Code Here
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
        }

        final LevenbergMarquardtOptimizer optimizer
            = new LevenbergMarquardtOptimizer();

        final PointVectorValuePair optimum
            = optimizer.optimize(new MaxEval(100),
                                 problem.getModelFunction(),
                                 problem.getModelFunctionJacobian(),
                                 new Target(dataPoints[1]),
                                 new Weight(weights),
                                 new InitialGuess(new double[] { 10, 900, 80, 27, 225 }));

        final double[] solution = optimum.getPoint();
        final double[] expectedSolution = { 10.4, 958.3, 131.4, 33.9, 205.0 };

        final double[][] covarMatrix = optimizer.computeCovariances(solution, 1e-14);
        final double[][] expectedCovarMatrix = {
            { 3.38, -3.69, 27.98, -2.34, -49.24 },
View Full Code Here
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
        // First guess for the center's coordinates and radius.
        final double[] init = { 90, 659, 115 };

        final LevenbergMarquardtOptimizer optimizer
            = new LevenbergMarquardtOptimizer();
        final PointVectorValuePair optimum = optimizer.optimize(new MaxEval(100),
                                                                circle.getModelFunction(),
                                                                circle.getModelFunctionJacobian(),
                                                                new Target(circle.target()),
                                                                new Weight(circle.weight()),
                                                                new InitialGuess(init));

        final double[] paramFound = optimum.getPoint();

        // Retrieve errors estimation.
        final double[] asymptoticStandardErrorFound = optimizer.computeSigma(paramFound, 1e-14);

        // Check that the parameters are found within the assumed error bars.
View Full Code Here
TOP

Related Classes of org.apache.commons.math3.optim.PointVectorValuePair

  • org.apache.commons.math3.analysis.differentiation.DerivativeStructure
  • org.apache.commons.math3.analysis.differentiation.MultivariateDifferentiableVectorFunction
  • 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
  • org.apache.commons.math3.analysis.solvers.BrentSolver
  • org.apache.commons.math3.analysis.UnivariateFunction
  • org.apache.commons.math3.complex.Complex
    • 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.