def setup_dr(self):
model, options, parameters, data, covariance, __, __, __, __ = gf.setup_mcmc_case_dr(
)
RDR = covariance._RDR
invR = covariance._invR
old_set = ParameterSet(theta=np.random.rand(2),
ss=np.array([10.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5]))
new_set = ParameterSet(theta=np.random.rand(2),
ss=np.array([8.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5]))
priorobj = PriorFunction(
priorfun=model.prior_function,
mu=parameters._thetamu[parameters._parind[:]],
sigma=parameters._thetasigma[parameters._parind[:]])
sosobj = SumOfSquares(model, data, parameters)
DR = DelayedRejection()
DR._initialize_dr_metrics(options=options)
accept, out_set, outbound = DR.run_delayed_rejection(
old_set=old_set,
new_set=new_set,
RDR=RDR,
ntry=2,
parameters=parameters,
invR=invR,
sosobj=sosobj,
priorobj=priorobj)
return accept, out_set, outbound
def test_alphafun(self):
invR = []
invR.append(np.array([[0.4, 0.1], [0., 0.2]]))
invR.append(np.array([[0.4, 0.1], [0., 0.2]]) / 4)
invR.append(np.array([[0.4, 0.1], [0., 0.2]]) / 5)
trypath = []
trypath.append(
ParameterSet(theta=0.1,
ss=np.array([10.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5])))
trypath.append(
ParameterSet(theta=0.2,
ss=np.array([8.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5])))
trypath.append(
ParameterSet(theta=0.2,
ss=np.array([8.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5])))
trypath.append(
ParameterSet(theta=0.2,
ss=np.array([8.2]),
sigma2=np.array([0.5]),
prior=np.array([0.5])))
__, options, __, __ = gf.setup_mcmc()
DR = DelayedRejection()
DR._initialize_dr_metrics(options=options)
alpha = DR.alphafun(trypath=trypath, invR=invR)
self.assertIsInstance(alpha,
np.ndarray,
msg='Expect numpy array return')
self.assertEqual(alpha.size, 1, msg='Expect single element array')
def test_addbasic_false(self):
model, options, parameters, data, covariance, rejected, chain, s2chain, sschain = gf.setup_mcmc_case_dr(
)
DR = DelayedRejection()
DR._initialize_dr_metrics(options)
RS = ResultsStructure()
self.assertFalse(RS.add_dram(drscale=options.drscale,
RDR=covariance._RDR,
total_rejected=rejected['total'],
drsettings=DR),
msg='basic features not added to result structure')
def test_dr_metrics(self):
DR = DelayedRejection()
__, options, __, data, covariance, rejected, chain, s2chain, sschain = gf.setup_mcmc_case_dr(
)
DR._initialize_dr_metrics(options=options)
self.assertTrue(np.array_equal(DR.iacce,
np.zeros(options.ntry, dtype=int)),
msg='Arrays should match')
self.assertEqual(DR.dr_step_counter,
0,
msg='Counter initialized to zero')
def test_next_set(self, mock_1):
DR = DelayedRejection()
npar = 2
old_theta = np.array([0.1, 0.2])
RDR = np.array([[0.4, 0.2], [0, 0.3]])
sigma2 = 0.24
next_set = DR.initialize_next_metropolis_step(npar=npar,
old_theta=old_theta,
sigma2=sigma2,
RDR=RDR)
self.assertEqual(next_set.sigma2, sigma2, msg='sigma2 should be 0.24')
self.assertTrue(np.array_equal(
next_set.theta,
(old_theta + np.dot(np.array([0.2, 0.5]), RDR)).reshape(npar)),
msg='Arrays should match')
def test_addbasic_true(self):
model, options, parameters, data, covariance, rejected, chain, s2chain, sschain = gf.setup_mcmc_case_dr(
)
covariance._RDR = np.random.random_sample(size=(2, 2))
DR = DelayedRejection()
DR._initialize_dr_metrics(options)
DR.dr_step_counter = 12000
RS = ResultsStructure()
RS.add_basic(nsimu=options.nsimu,
covariance=covariance,
parameters=parameters,
rejected=rejected,
simutime=0.001,
theta=chain[-1, :])
self.assertTrue(RS.add_dram(drscale=options.drscale,
RDR=covariance._RDR,
total_rejected=rejected['total'],
drsettings=DR),
msg='basic features added to result structure')
self.assertTrue(np.array_equal(RS.results['RDR'], covariance._RDR),
msg='RDR matches')
self.assertEqual(RS.results['alpha_count'],
DR.dr_step_counter,
msg='Alpha count matches dr step counter')