Package org.apache.commons.math3.fitting.leastsquares.LeastSquaresProblem

Examples of org.apache.commons.math3.fitting.leastsquares.LeastSquaresProblem.Evaluation

326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345

        // Evaluate the function at the starting point and calculate its norm.
        evaluationCounter.incrementCount();
        //value will be reassigned in the loop
        Evaluation current = problem.evaluate(new ArrayRealVector(currentPoint));
        double[] currentResiduals = current.getResiduals().toArray();
        double currentCost = current.getCost();

        // Outer loop.
        boolean firstIteration = true;
        while (true) {
            iterationCounter.incrementCount();

            final Evaluation previous = current;

            // QR decomposition of the jacobian matrix
            final InternalData internalData
                    = qrDecomposition(current.getJacobian(), solvedCols);
            final double[][] weightedJacobian = internalData.weightedJacobian;
View Full Code Here
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
        }

        RealVector currentPoint = lsp.getStart();

        // iterate until convergence is reached
        Evaluation current = null;
        while (true) {
            iterationCounter.incrementCount();

            // evaluate the objective function and its jacobian
            Evaluation previous = current;
            // Value of the objective function at "currentPoint".
            evaluationCounter.incrementCount();
            current = lsp.evaluate(currentPoint);
            final RealVector currentResiduals = current.getResiduals();
            final RealMatrix weightedJacobian = current.getJacobian();
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
    @Test
    public void testComputeResiduals() {
        //setup
        RealVector point = new ArrayRealVector(2);
        Evaluation evaluation = new LeastSquaresBuilder()
                .target(new ArrayRealVector(new double[]{3,-1}))
                .model(new MultivariateJacobianFunction() {
                    public Pair<RealVector, RealMatrix> value(RealVector point) {
                        return new Pair<RealVector, RealMatrix>(
                                new ArrayRealVector(new double[]{1, 2}),
                                MatrixUtils.createRealIdentityMatrix(2)
                        );
                    }
                })
                .weight(MatrixUtils.createRealIdentityMatrix(2))
                .build()
                .evaluate(point);

        //action + verify
        Assert.assertArrayEquals(
                evaluation.getResiduals().toArray(),
                new double[]{2, -3},
                Precision.EPSILON);
    }
View Full Code Here
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    @Test
    public void testComputeCovariance() throws IOException {
        //setup
        RealVector point = new ArrayRealVector(2);
        Evaluation evaluation = new LeastSquaresBuilder()
                .model(new MultivariateJacobianFunction() {
                    public Pair<RealVector, RealMatrix> value(RealVector point) {
                        return new Pair<RealVector, RealMatrix>(
                                new ArrayRealVector(2),
                                MatrixUtils.createRealDiagonalMatrix(new double[]{1, 1e-2})
                        );
                    }
                })
                .weight(MatrixUtils.createRealDiagonalMatrix(new double[]{1, 1}))
                .target(new ArrayRealVector(2))
                .build()
                .evaluate(point);

        //action
        TestUtils.assertEquals(
                "covariance",
                evaluation.getCovariances(FastMath.nextAfter(1e-4, 0.0)),
                MatrixUtils.createRealMatrix(new double[][]{{1, 0}, {0, 1e4}}),
                Precision.EPSILON
        );

        //singularity fail
        try {
            evaluation.getCovariances(FastMath.nextAfter(1e-4, 1.0));
            Assert.fail("Expected Exception");
        } catch (SingularMatrixException e) {
            //expected
        }
    }
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
    @Test
    public void testComputeValueAndJacobian() {
        //setup
        final RealVector point = new ArrayRealVector(new double[]{1, 2});
        Evaluation evaluation = new LeastSquaresBuilder()
                .weight(new DiagonalMatrix(new double[]{16, 4}))
                .model(new MultivariateJacobianFunction() {
                    public Pair<RealVector, RealMatrix> value(RealVector actualPoint) {
                        //verify correct values passed in
                        Assert.assertArrayEquals(
                                point.toArray(), actualPoint.toArray(), Precision.EPSILON);
                        //return values
                        return new Pair<RealVector, RealMatrix>(
                                new ArrayRealVector(new double[]{3, 4}),
                                MatrixUtils.createRealMatrix(new double[][]{{5, 6}, {7, 8}})
                        );
                    }
                })
                .target(new double[2])
                .build()
                .evaluate(point);

        //action
        RealVector residuals = evaluation.getResiduals();
        RealMatrix jacobian = evaluation.getJacobian();

        //verify
        Assert.assertArrayEquals(evaluation.getPoint().toArray(), point.toArray(), 0);
        Assert.assertArrayEquals(new double[]{-12, -8}, residuals.toArray(), Precision.EPSILON);
        TestUtils.assertEquals(
                "jacobian",
                jacobian,
                MatrixUtils.createRealMatrix(new double[][]{{20, 24},{14, 16}}),
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
        final LeastSquaresProblem lsp = builder(dataset).build();

        final double[] expected = dataset.getParametersStandardDeviations();

        final Evaluation evaluation = lsp.evaluate(lsp.getStart());
        final double cost = evaluation.getCost();
        final RealVector sig = evaluation.getSigma(1e-14);
        final int dof = lsp.getObservationSize() - lsp.getParameterSize();
        for (int i = 0; i < sig.getDimension(); i++) {
            final double actual = FastMath.sqrt(cost * cost / dof) * sig.getEntry(i);
            Assert.assertEquals(dataset.getName() + ", parameter #" + i,
                                expected[i], actual, 1e-6 * expected[i]);
 
View Full Code Here
207
208
209
210
211
212
213
214
215
216
217
218
                = StatisticalReferenceDatasetFactory.createKirby2();
        LeastSquaresProblem lsp = builder(dataset).build();
        RealVector point = new ArrayRealVector(lsp.getParameterSize());

        //action
        Evaluation evaluation = lsp.evaluate(point);

        //verify
        Assert.assertNotSame(point, evaluation.getPoint());
        point.setEntry(0, 1);
        Assert.assertEquals(evaluation.getPoint().getEntry(0), 0, 0);
    }
View Full Code Here
227
228
229
230
231
232
233
234
235
236
237
            // build the P matrix elements from Taylor series formulas
            final BigFraction[] pI = pData[i];
            final int factor = -(i + 1);
            int aj = factor;
            for (int j = 0; j < pI.length; ++j) {
                pI[j] = new BigFraction(aj * (j + 2));
                aj *= factor;
            }
        }

        return new Array2DRowFieldMatrix<BigFraction>(pData, false);
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
     
      List<SiteWithPolynomial> nearestSites =
          nearestSiteMap.get(site);
     
      RealVector vector = new ArrayRealVector(SITES_FOR_APPROX);
      RealMatrix matrix = new Array2DRowRealMatrix(
          SITES_FOR_APPROX, DefaultPolynomial.NUM_COEFFS);
     
      for (int row = 0; row < SITES_FOR_APPROX; row++) {
        SiteWithPolynomial nearSite = nearestSites.get(row);
        DefaultPolynomial.populateMatrix(matrix, row, nearSite.pos.x, nearSite.pos.z);
View Full Code Here
288
289
290
291
292
293
294
295
296
        }

        // solve the rectangular system in the least square sense
        // to get the best estimate of the Nordsieck vector [s2 ... sk]
        QRDecomposition decomposition;
        decomposition = new QRDecomposition(new Array2DRowRealMatrix(a, false));
        RealMatrix x = decomposition.getSolver().solve(new Array2DRowRealMatrix(b, false));
        return new Array2DRowRealMatrix(x.getData(), false);
    }
View Full Code Here
TOP

Related Classes of org.apache.commons.math3.fitting.leastsquares.LeastSquaresProblem.Evaluation

  • 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.