def test_2d_1fi_cokriging(self):
# CoKrigingSurrogate with one fidelity could be used as a KrigingSurrogate
# Same test as for KrigingSurrogate... well with predicted test value adjustment
def branin(x):
y = (x[1]-(5.1/(4.*pi**2.))*x[0]**2.+5.*x[0]/pi-6.)**2.+10.*(1.-1./(8.*pi))*cos(x[0])+10.
return y
x = array([[-2., 0.], [-0.5, 1.5], [1., 3.], [8.5, 4.5],
[-3.5, 6.], [4., 7.5], [-5., 9.], [5.5, 10.5],
[10., 12.], [7., 13.5], [2.5, 15.]])
y = array([branin(case) for case in x])
krig1 = MultiFiCoKrigingSurrogate()
krig1.train(x, y)
pred1 = krig1.predict([-2., 0.])
self.assertAlmostEqual(branin(x[0]), pred1.mu, places=5)
self.assertAlmostEqual(0., pred1.sigma, places=5)
pred2 = krig1.predict([5., 5.])
self.assertAlmostEqual(22, pred2.mu, delta=1)
self.assertAlmostEqual(13, pred2.sigma, delta=1)
# Test with theta setting instead of estimation
krig2 = MultiFiCoKrigingSurrogate(theta=[0.1])
krig1.train(x, y)
pred1 = krig1.predict([-2., 0.])
self.assertAlmostEqual(branin(x[0]), pred1.mu, places=5)
self.assertAlmostEqual(0., pred1.sigma, places=5)
pred2 = krig1.predict([5., 5.])
self.assertAlmostEqual(22, pred2.mu, delta=1)
self.assertAlmostEqual(13, pred2.sigma, delta=1)
def test_1d_1fi_cokriging(self):
# CoKrigingSurrogate with one fidelity could be used as a KrigingSurrogate
# Same test as for KrigingSurrogate... well with predicted test value adjustment
x = array([[0.05], [.25], [0.61], [0.95]])
y = array([0.738513784857542, -0.210367746201974, -0.489015457891476, 12.3033138316612])
krig1 = MultiFiCoKrigingSurrogate()
krig1.train(x, y)
new_x = array([0.5])
pred1 = krig1.predict(x[0])
self.assertTrue(isinstance(pred1, NormalDistribution))
self.assertAlmostEqual(y[0] , pred1.mu, places=4)
self.assertAlmostEqual(.0, pred1.sigma, places=4)
pred2 = krig1.predict(new_x)
self.assertTrue(isinstance(pred2, NormalDistribution))
self.assertAlmostEqual( -2.0279, pred2.mu, places=3)
self.assertAlmostEqual(1.3408, pred2.sigma, places=3)
# Test with theta setting instead of estimation
krig2 = MultiFiCoKrigingSurrogate(theta=0.1)
krig2.train(x, y)
pred1 = krig2.predict(x[0])
self.assertTrue(isinstance(pred1, NormalDistribution))
self.assertAlmostEqual(y[0] , pred1.mu, places=4)
self.assertAlmostEqual(.0, pred1.sigma, places=4)
pred2 = krig2.predict(new_x)
self.assertTrue(isinstance(pred2, NormalDistribution))
self.assertAlmostEqual( -1.2719, pred2.mu, places=3)
self.assertAlmostEqual(0.0439, pred2.sigma, places=3)
self.assertAlmostEqual(0., pred.sigma, delta=0.02)
def test_2d_1fi_cokriging(self):
# CoKrigingSurrogate with one fidelity could be used as a KrigingSurrogate
# Same test as for KrigingSurrogate... well with predicted test value adjustment
def branin(x):
y = (x[1]-(5.1/(4.*pi**2.))*x[0]**2.+5.*x[0]/pi-6.)**2.+10.*(1.-1./(8.*pi))*cos(x[0])+10.
return y
x = array([[-2., 0.], [-0.5, 1.5], [1., 3.], [8.5, 4.5],
[-3.5, 6.], [4., 7.5], [-5., 9.], [5.5, 10.5],
[10., 12.], [7., 13.5], [2.5, 15.]])
y = array([branin(case) for case in x])
krig1 = MultiFiCoKrigingSurrogate()
krig1.train(x, y)
pred1 = krig1.predict([-2., 0.])
self.assertAlmostEqual(branin(x[0]), pred1.mu, places=5)
self.assertAlmostEqual(0., pred1.sigma, places=5)
pred2 = krig1.predict([5., 5.])
self.assertAlmostEqual(22, pred2.mu, delta=1)
self.assertAlmostEqual(13, pred2.sigma, delta=1)
# Test with theta setting instead of estimation
krig2 = MultiFiCoKrigingSurrogate(theta=[0.1])
krig1.train(x, y)
pred1 = krig1.predict([-2., 0.])
self.assertAlmostEqual(branin(x[0]), pred1.mu, places=5)
