Java源码示例：org.apache.commons.math3.optim.nonlinear.vector.jacobian.LevenbergMarquardtOptimizer
示例1
@Test
public void testNoError() {
Random randomizer = new Random(64925784252l);
for (int degree = 1; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i <= degree; ++i) {
fitter.addObservedPoint(1.0, i, p.value(i));
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
Assert.assertEquals(0.0, error, 1.0e-6);
}
}
}
示例2
@Test
public void testLargeSample() {
Random randomizer = new Random(0x5551480dca5b369bl);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i < 40000; ++i) {
double x = -1.0 + i / 20000.0;
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.01);
}
}
Assert.assertTrue(maxError > 0.001);
}
示例3
@Test
public void testNoError() {
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 1.3; x += 0.01) {
fitter.addObservedPoint(1, x, f.value(x));
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 1.0e-13);
Assert.assertEquals(w, fitted[1], 1.0e-13);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1e-13);
HarmonicOscillator ff = new HarmonicOscillator(fitted[0], fitted[1], fitted[2]);
for (double x = -1.0; x < 1.0; x += 0.01) {
Assert.assertTrue(FastMath.abs(f.value(x) - ff.value(x)) < 1e-13);
}
}
示例4
@Test
public void test1PercentError() {
Random randomizer = new Random(64925784252l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 7.6e-4);
Assert.assertEquals(w, fitted[1], 2.7e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.3e-2);
}
示例5
@Test
public void testMath304() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1.6357215104109237, fitter.fit(sif, initialguess1)[0], 1.0e-14);
double[] initialguess2 = new double[1];
initialguess2[0] = 10.0d;
Assert.assertEquals(1.6357215104109237, fitter.fit(sif, initialguess1)[0], 1.0e-14);
}
示例6
@Test
public void testInitialGuess() {
Random randomizer = new Random(45314242l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit(new double[] { 0.15, 3.6, 4.5 });
Assert.assertEquals(a, fitted[0], 1.2e-3);
Assert.assertEquals(w, fitted[1], 3.3e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.7e-2);
}
示例7
@Test
public void testMath303() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1, fitter.fit(sif, initialguess1).length);
double[] initialguess2 = new double[2];
initialguess2[0] = 1.0d;
initialguess2[1] = .5d;
Assert.assertEquals(2, fitter.fit(sif, initialguess2).length);
}
示例8
@Test
public void testFit() {
final RealDistribution rng = new UniformRealDistribution(-100, 100);
rng.reseedRandomGenerator(64925784252L);
final LevenbergMarquardtOptimizer optim = new LevenbergMarquardtOptimizer();
final PolynomialFitter fitter = new PolynomialFitter(optim);
final double[] coeff = { 12.9, -3.4, 2.1 }; // 12.9 - 3.4 x + 2.1 x^2
final PolynomialFunction f = new PolynomialFunction(coeff);
// Collect data from a known polynomial.
for (int i = 0; i < 100; i++) {
final double x = rng.sample();
fitter.addObservedPoint(x, f.value(x));
}
// Start fit from initial guesses that are far from the optimal values.
final double[] best = fitter.fit(new double[] { -1e-20, 3e15, -5e25 });
TestUtils.assertEquals("best != coeff", coeff, best, 1e-12);
}
示例9
@Test
public void testNoError() {
Random randomizer = new Random(64925784252l);
for (int degree = 1; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i <= degree; ++i) {
fitter.addObservedPoint(1.0, i, p.value(i));
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
Assert.assertEquals(0.0, error, 1.0e-6);
}
}
}
示例10
@Test
public void testSmallError() {
Random randomizer = new Random(53882150042l);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (double x = -1.0; x < 1.0; x += 0.01) {
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.1);
}
}
Assert.assertTrue(maxError > 0.01);
}
示例11
@Test
public void testLargeSample() {
Random randomizer = new Random(0x5551480dca5b369bl);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i < 40000; ++i) {
double x = -1.0 + i / 20000.0;
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.01);
}
}
Assert.assertTrue(maxError > 0.001);
}
示例12
@Test
public void testMath303() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1, fitter.fit(sif, initialguess1).length);
double[] initialguess2 = new double[2];
initialguess2[0] = 1.0d;
initialguess2[1] = .5d;
Assert.assertEquals(2, fitter.fit(sif, initialguess2).length);
}
示例13
@Test
public void testMath304() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1.6357215104109237, fitter.fit(sif, initialguess1)[0], 1.0e-14);
double[] initialguess2 = new double[1];
initialguess2[0] = 10.0d;
Assert.assertEquals(1.6357215104109237, fitter.fit(sif, initialguess1)[0], 1.0e-14);
}
示例14
@Test
public void test1PercentError() {
Random randomizer = new Random(64925784252l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 7.6e-4);
Assert.assertEquals(w, fitted[1], 2.7e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.3e-2);
}
示例15
@Test
public void testInitialGuess() {
Random randomizer = new Random(45314242l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit(new double[] { 0.15, 3.6, 4.5 });
Assert.assertEquals(a, fitted[0], 1.2e-3);
Assert.assertEquals(w, fitted[1], 3.3e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.7e-2);
}
示例16
@Test
public void testLargeSample() {
Random randomizer = new Random(0x5551480dca5b369bl);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i < 40000; ++i) {
double x = -1.0 + i / 20000.0;
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.01);
}
}
Assert.assertTrue(maxError > 0.001);
}
示例17
@Test
public void testFit() {
final RealDistribution rng = new UniformRealDistribution(-100, 100);
rng.reseedRandomGenerator(64925784252L);
final LevenbergMarquardtOptimizer optim = new LevenbergMarquardtOptimizer();
final PolynomialFitter fitter = new PolynomialFitter(optim);
final double[] coeff = { 12.9, -3.4, 2.1 }; // 12.9 - 3.4 x + 2.1 x^2
final PolynomialFunction f = new PolynomialFunction(coeff);
// Collect data from a known polynomial.
for (int i = 0; i < 100; i++) {
final double x = rng.sample();
fitter.addObservedPoint(x, f.value(x));
}
// Start fit from initial guesses that are far from the optimal values.
final double[] best = fitter.fit(new double[] { -1e-20, 3e15, -5e25 });
TestUtils.assertEquals("best != coeff", coeff, best, 1e-12);
}
示例18
@Test
public void testLargeSample() {
Random randomizer = new Random(0x5551480dca5b369bl);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i < 40000; ++i) {
double x = -1.0 + i / 20000.0;
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.01);
}
}
Assert.assertTrue(maxError > 0.001);
}
示例19
@Test
public void testNoError() {
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 1.3; x += 0.01) {
fitter.addObservedPoint(1, x, f.value(x));
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 1.0e-13);
Assert.assertEquals(w, fitted[1], 1.0e-13);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1e-13);
HarmonicOscillator ff = new HarmonicOscillator(fitted[0], fitted[1], fitted[2]);
for (double x = -1.0; x < 1.0; x += 0.01) {
Assert.assertTrue(FastMath.abs(f.value(x) - ff.value(x)) < 1e-13);
}
}
示例20
@Test
public void testSmallError() {
Random randomizer = new Random(53882150042l);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (double x = -1.0; x < 1.0; x += 0.01) {
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.1);
}
}
Assert.assertTrue(maxError > 0.01);
}
示例21
@Test
public void testNoError() {
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 1.3; x += 0.01) {
fitter.addObservedPoint(1, x, f.value(x));
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 1.0e-13);
Assert.assertEquals(w, fitted[1], 1.0e-13);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1e-13);
HarmonicOscillator ff = new HarmonicOscillator(fitted[0], fitted[1], fitted[2]);
for (double x = -1.0; x < 1.0; x += 0.01) {
Assert.assertTrue(FastMath.abs(f.value(x) - ff.value(x)) < 1e-13);
}
}
示例22
@Test
public void test1PercentError() {
Random randomizer = new Random(64925784252l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit();
Assert.assertEquals(a, fitted[0], 7.6e-4);
Assert.assertEquals(w, fitted[1], 2.7e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.3e-2);
}
示例23
@Test
public void testMath303() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1, fitter.fit(sif, initialguess1).length);
double[] initialguess2 = new double[2];
initialguess2[0] = 1.0d;
initialguess2[1] = .5d;
Assert.assertEquals(2, fitter.fit(sif, initialguess2).length);
}
示例24
@Test
public void testSmallError() {
Random randomizer = new Random(53882150042l);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (double x = -1.0; x < 1.0; x += 0.01) {
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.1);
}
}
Assert.assertTrue(maxError > 0.01);
}
示例25
@Test
public void testFit() {
final RealDistribution rng = new UniformRealDistribution(-100, 100);
rng.reseedRandomGenerator(64925784252L);
final LevenbergMarquardtOptimizer optim = new LevenbergMarquardtOptimizer();
final PolynomialFitter fitter = new PolynomialFitter(optim);
final double[] coeff = { 12.9, -3.4, 2.1 }; // 12.9 - 3.4 x + 2.1 x^2
final PolynomialFunction f = new PolynomialFunction(coeff);
// Collect data from a known polynomial.
for (int i = 0; i < 100; i++) {
final double x = rng.sample();
fitter.addObservedPoint(x, f.value(x));
}
// Start fit from initial guesses that are far from the optimal values.
final double[] best = fitter.fit(new double[] { -1e-20, 3e15, -5e25 });
TestUtils.assertEquals("best != coeff", coeff, best, 1e-12);
}
示例26
@Test
public void testNoError() {
Random randomizer = new Random(64925784252l);
for (int degree = 1; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i <= degree; ++i) {
fitter.addObservedPoint(1.0, i, p.value(i));
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
Assert.assertEquals(0.0, error, 1.0e-6);
}
}
}
示例27
@Test
public void testSmallError() {
Random randomizer = new Random(53882150042l);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (double x = -1.0; x < 1.0; x += 0.01) {
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.1);
}
}
Assert.assertTrue(maxError > 0.01);
}
示例28
@Test
public void testInitialGuess() {
Random randomizer = new Random(45314242l);
final double a = 0.2;
final double w = 3.4;
final double p = 4.1;
HarmonicOscillator f = new HarmonicOscillator(a, w, p);
HarmonicFitter fitter =
new HarmonicFitter(new LevenbergMarquardtOptimizer());
for (double x = 0.0; x < 10.0; x += 0.1) {
fitter.addObservedPoint(1, x,
f.value(x) + 0.01 * randomizer.nextGaussian());
}
final double[] fitted = fitter.fit(new double[] { 0.15, 3.6, 4.5 });
Assert.assertEquals(a, fitted[0], 1.2e-3);
Assert.assertEquals(w, fitted[1], 3.3e-3);
Assert.assertEquals(p, MathUtils.normalizeAngle(fitted[2], p), 1.7e-2);
}
示例29
@Test
public void testLargeSample() {
Random randomizer = new Random(0x5551480dca5b369bl);
double maxError = 0;
for (int degree = 0; degree < 10; ++degree) {
PolynomialFunction p = buildRandomPolynomial(degree, randomizer);
PolynomialFitter fitter = new PolynomialFitter(new LevenbergMarquardtOptimizer());
for (int i = 0; i < 40000; ++i) {
double x = -1.0 + i / 20000.0;
fitter.addObservedPoint(1.0, x,
p.value(x) + 0.1 * randomizer.nextGaussian());
}
final double[] init = new double[degree + 1];
PolynomialFunction fitted = new PolynomialFunction(fitter.fit(init));
for (double x = -1.0; x < 1.0; x += 0.01) {
double error = FastMath.abs(p.value(x) - fitted.value(x)) /
(1.0 + FastMath.abs(p.value(x)));
maxError = FastMath.max(maxError, error);
Assert.assertTrue(FastMath.abs(error) < 0.01);
}
}
Assert.assertTrue(maxError > 0.001);
}
示例30
@Test
public void testMath303() {
LevenbergMarquardtOptimizer optimizer = new LevenbergMarquardtOptimizer();
CurveFitter<ParametricUnivariateFunction> fitter = new CurveFitter<ParametricUnivariateFunction>(optimizer);
fitter.addObservedPoint(2.805d, 0.6934785852953367d);
fitter.addObservedPoint(2.74333333333333d, 0.6306772025518496d);
fitter.addObservedPoint(1.655d, 0.9474675497289684);
fitter.addObservedPoint(1.725d, 0.9013594835804194d);
ParametricUnivariateFunction sif = new SimpleInverseFunction();
double[] initialguess1 = new double[1];
initialguess1[0] = 1.0d;
Assert.assertEquals(1, fitter.fit(sif, initialguess1).length);
double[] initialguess2 = new double[2];
initialguess2[0] = 1.0d;
initialguess2[1] = .5d;
Assert.assertEquals(2, fitter.fit(sif, initialguess2).length);
}
