int main(int argc, char ** argv)
{
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, "", "", NULL);
#else
QUESO::FullEnvironment env("", "", NULL);
#endif
QUESO::VectorSpace<> paramSpace1(env, "param1_", 4, NULL);
QUESO::VectorSpace<> paramSpace2(env, "param2_", 2, NULL);
QUESO::GslVector paramMins1(paramSpace1.zeroVector());
paramMins1[0] = 1e2;
paramMins1[1] = -1e5;
paramMins1[2] = 4e-3;
paramMins1[3] = 1;
QUESO::GslVector paramMaxs1(paramSpace1.zeroVector());
paramMaxs1[0] = 2e2;
paramMaxs1[1] = 1e5;
paramMaxs1[2] = 6e-3;
paramMaxs1[3] = 11;
QUESO::BoxSubset<> paramDomain1("", paramSpace1, paramMins1, paramMaxs1);
QUESO::GslVector paramMins2(paramSpace2.zeroVector());
paramMins2[0] = -1e5;
paramMins2[1] = 2e-3;
QUESO::GslVector paramMaxs2(paramSpace2.zeroVector());
paramMaxs2[0] = 1e5;
paramMaxs2[1] = 4e-3;
QUESO::BoxSubset<> paramDomain2("", paramSpace2, paramMins2, paramMaxs2);
QUESO::VectorSpace<> paramSpace(env, "param_", 6, NULL);
QUESO::ConcatenationSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("",paramSpace,paramDomain1,paramDomain2);
QUESO::GslVector centroid(paramSpace.zeroVector());
paramDomain.centroid(centroid);
const char *msg = "ConcatenationSubset centroid is incorrect";
queso_require_less_equal_msg(std::abs(centroid[0]-1.5e2), TOL, msg);
queso_require_less_equal_msg(std::abs(centroid[1]), TOL, msg);
queso_require_less_equal_msg(std::abs(centroid[2]-5e-3), TOL, msg);
queso_require_less_equal_msg(std::abs(centroid[3]-6), TOL, msg);
queso_require_less_equal_msg(std::abs(centroid[4]), TOL, msg);
queso_require_less_equal_msg(std::abs(centroid[5]-3e-3), TOL, msg);
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
void compute(const QUESO::FullEnvironment& env) {
// Step 1 of 6: Instantiate the parameter space
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix>
paramSpace(env, "param_", 2, NULL);
// Step 2 of 6: Instantiate the parameter domain
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(-INFINITY);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet( INFINITY);
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("param_",paramSpace,paramMins,paramMaxs);
// Step 3 of 6: Instantiate the qoi space
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix>
qoiSpace(env, "qoi_", 1, NULL);
// Step 4 of 6: Instantiate the qoi function object
qoiRoutine_DataType qoiRoutine_Data;
qoiRoutine_Data.coef1 = 1.;
qoiRoutine_Data.coef2 = 1.;
QUESO::GenericVectorFunction<QUESO::GslVector,QUESO::GslMatrix,
QUESO::GslVector,QUESO::GslMatrix>
qoiFunctionObj("qoi_",
paramDomain,
qoiSpace,
qoiRoutine,
(void *) &qoiRoutine_Data);
// Step 5 of 6: Instantiate the forward problem
// Parameters are Gaussian RV
QUESO::GslVector meanVector( paramSpace.zeroVector() );
meanVector[0] = -1;
meanVector[1] = 2;
QUESO::GslMatrix covMatrix = QUESO::GslMatrix(paramSpace.zeroVector());
covMatrix(0,0) = 4.;
covMatrix(0,1) = 0.;
covMatrix(1,0) = 0.;
covMatrix(1,1) = 1.;
QUESO::GaussianVectorRV<QUESO::GslVector,QUESO::GslMatrix>
paramRv("param_",paramDomain,meanVector,covMatrix);
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix>
qoiRv("qoi_", qoiSpace);
QUESO::StatisticalForwardProblem<QUESO::GslVector,QUESO::GslMatrix,
QUESO::GslVector,QUESO::GslMatrix>
fp("", NULL, paramRv, qoiFunctionObj, qoiRv);
// Step 6 of 6: Solve the forward problem
fp.solveWithMonteCarlo(NULL);
return;
}
void compute(const QUESO::FullEnvironment& env) {
// Step 1 of 5: Instantiate the parameter space
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix>
paramSpace(env, "param_", 2, NULL);
// Step 2 of 5: Instantiate the parameter domain
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(-INFINITY);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet( INFINITY);
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("param_",paramSpace,paramMins,paramMaxs);
// Step 3 of 5: Instantiate the likelihood function object
QUESO::GslVector meanVector(paramSpace.zeroVector());
meanVector[0] = -1;
meanVector[1] = 2;
QUESO::GslMatrix covMatrix(paramSpace.zeroVector());
covMatrix(0,0) = 4.; covMatrix(0,1) = 0.;
covMatrix(1,0) = 0.; covMatrix(1,1) = 1.;
likelihoodRoutine_DataType likelihoodRoutine_Data;
likelihoodRoutine_Data.meanVector = &meanVector;
likelihoodRoutine_Data.covMatrix = &covMatrix;
QUESO::GenericScalarFunction<QUESO::GslVector,QUESO::GslMatrix>
likelihoodFunctionObj("like_",
paramDomain,
likelihoodRoutine,
(void *) &likelihoodRoutine_Data,
true); // routine computes [ln(function)]
// Step 4 of 5: Instantiate the inverse problem
QUESO::UniformVectorRV<QUESO::GslVector,QUESO::GslMatrix>
priorRv("prior_", paramDomain);
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix>
postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector,QUESO::GslMatrix>
ip("", NULL, priorRv, likelihoodFunctionObj, postRv);
// Step 5 of 5: Solve the inverse problem
QUESO::GslVector paramInitials(paramSpace.zeroVector());
paramInitials[0] = 0.1;
paramInitials[1] = -1.4;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0,0) = 8.; proposalCovMatrix(0,1) = 4.;
proposalCovMatrix(1,0) = 4.; proposalCovMatrix(1,1) = 16.;
ip.solveWithBayesMetropolisHastings(NULL,paramInitials, &proposalCovMatrix);
return;
}
int main(int argc, char ** argv) {
MPI_Init(&argc, &argv);
// Step 0 of 5: Set up environment
QUESO::FullEnvironment env(MPI_COMM_WORLD, argv[1], "", NULL);
// Step 1 of 5: Instantiate the parameter space
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", 1, NULL);
// Step 2 of 5: Set up the prior
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(min_val);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
// Uniform prior here. Could be a different prior.
QUESO::UniformVectorRV<QUESO::GslVector, QUESO::GslMatrix> priorRv("prior_",
paramDomain);
// Step 3 of 5: Set up the likelihood using the class above
Likelihood<QUESO::GslVector, QUESO::GslMatrix> lhood("llhd_", paramDomain);
// Step 4 of 5: Instantiate the inverse problem
QUESO::GenericVectorRV<QUESO::GslVector, QUESO::GslMatrix>
postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector, QUESO::GslMatrix>
ip("", NULL, priorRv, lhood, postRv);
// Step 5 of 5: Solve the inverse problem
QUESO::GslVector paramInitials(paramSpace.zeroVector());
// Initial condition of the chain
paramInitials[0] = 0.0;
paramInitials[1] = 0.0;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
for (unsigned int i = 0; i < 2; i++) {
// Might need to tweak this
proposalCovMatrix(i, i) = 0.1;
}
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
MPI_Finalize();
return 0;
}
int main(int argc, char ** argv)
{
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, "", "", NULL);
#else
QUESO::FullEnvironment env("", "", NULL);
#endif
QUESO::VectorSpace<> paramSpace(env, "param_", 1, NULL);
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(0.0);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(1.0);
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMins, paramMaxs);
// We should test the other cases of alpha and beta
QUESO::GslVector alpha(paramSpace.zeroVector());
alpha[0] = 2.0;
QUESO::GslVector beta(paramSpace.zeroVector());
beta[0] = 3.0;
QUESO::BetaJointPdf<> pdf("", paramDomain, alpha, beta);
QUESO::GslVector mean(paramSpace.zeroVector());
pdf.distributionMean(mean);
const char *msg = "BetaJointPdf mean is incorrect";
double real_mean = alpha[0] / (alpha[0] + beta[0]);
queso_require_less_equal_msg(std::abs(mean[0]-real_mean), TOL, msg);
QUESO::GslMatrix var(paramSpace.zeroVector());
pdf.distributionVariance(var);
const char *msgv = "BetaJointPdf variance is incorrect";
double real_var = alpha[0] * beta[0] / (alpha[0] + beta[0]) /
(alpha[0] + beta[0]) / (alpha[0] + beta[0] + 1);
queso_require_less_equal_msg(std::abs(var(0,0)-real_var), TOL, msgv);
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
void compute(const QUESO::FullEnvironment& env) {
//step 1: instatiate parameter space
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix>
paramSpace(env, "param_", 1, NULL);
//step 2: instantiate the parameter domain
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(0.001);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(100.); //TODO: this is not working with gsl sampling right now in FP
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("param_", paramSpace, paramMins, paramMaxs);
//step 3: instantiate the qoi space
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix>
qoiSpace(env, "qoi_", 1, NULL);
//step 4: instantiate the qoi function object
qoiRoutine_DataType qoiRoutine_Data;
qoiRoutine_Data.coef1 = 1.;
QUESO::GenericVectorFunction<QUESO::GslVector,QUESO::GslMatrix,
QUESO::GslVector,QUESO::GslMatrix>
qoiFunctionObj("qoi_",
paramDomain,
qoiSpace,
qoiRoutine,
(void *) &qoiRoutine_Data);
//step 5: instantiate the forward problem
//parameter is Jeffreys RV
QUESO::JeffreysVectorRV<QUESO::GslVector,QUESO::GslMatrix>
paramRv("param_", paramDomain);
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix>
qoiRv("qoi_",qoiSpace);
QUESO::StatisticalForwardProblem<QUESO::GslVector,QUESO::GslMatrix,
QUESO::GslVector,QUESO::GslMatrix>
fp("", NULL, paramRv, qoiFunctionObj, qoiRv);
//step 6: solve the forward problem
fp.solveWithMonteCarlo(NULL);
}
int main(int argc, char ** argv) {
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, argv[1], "", NULL);
QUESO::VectorSpace<> paramSpace(env, "param_", 1, NULL);
QUESO::GslVector paramMins(paramSpace.zeroVector());
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
double min_val = 0.0;
double max_val = 1.0;
paramMins.cwSet(min_val);
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMins, paramMaxs);
QUESO::UniformVectorRV<> priorRv("prior_", paramDomain);
Likelihood<> lhood("llhd_", paramDomain);
QUESO::GenericVectorRV<> postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<> ip("", NULL, priorRv, lhood, postRv);
QUESO::GslVector paramInitials(paramSpace.zeroVector());
paramInitials[0] = 0.0;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0, 0) = 0.1;
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
MPI_Finalize();
return 0;
}
int main(int argc, char* argv[])
{
#ifndef QUESO_HAS_MPI
// Skip this test if we're not in parallel
return 77;
#else
MPI_Init(&argc, &argv);
std::string inputFileName = argv[1];
const char * test_srcdir = std::getenv("srcdir");
if (test_srcdir)
inputFileName = test_srcdir + ('/' + inputFileName);
// Initialize QUESO environment
QUESO::FullEnvironment env(MPI_COMM_WORLD, inputFileName, "", NULL);
//================================================================
// Statistical inverse problem (SIP): find posterior PDF for 'g'
//================================================================
//------------------------------------------------------
// SIP Step 1 of 6: Instantiate the parameter space
//------------------------------------------------------
QUESO::VectorSpace<> paramSpace(env, "param_", 1, NULL);
//------------------------------------------------------
// SIP Step 2 of 6: Instantiate the parameter domain
//------------------------------------------------------
QUESO::GslVector paramMinValues(paramSpace.zeroVector());
QUESO::GslVector paramMaxValues(paramSpace.zeroVector());
paramMinValues[0] = 8.;
paramMaxValues[0] = 11.;
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMinValues,
paramMaxValues);
//------------------------------------------------------
// SIP Step 3 of 6: Instantiate the likelihood function
// object to be used by QUESO.
//------------------------------------------------------
Likelihood<> lhood("like_", paramDomain);
//------------------------------------------------------
// SIP Step 4 of 6: Define the prior RV
//------------------------------------------------------
QUESO::UniformVectorRV<> priorRv("prior_", paramDomain);
//------------------------------------------------------
// SIP Step 5 of 6: Instantiate the inverse problem
//------------------------------------------------------
// Extra prefix before the default "rv_" prefix
QUESO::GenericVectorRV<> postRv("post_", paramSpace);
// No extra prefix before the default "ip_" prefix
QUESO::StatisticalInverseProblem<> ip("", NULL, priorRv, lhood, postRv);
//------------------------------------------------------
// SIP Step 6 of 6: Solve the inverse problem, that is,
// set the 'pdf' and the 'realizer' of the posterior RV
//------------------------------------------------------
QUESO::GslVector paramInitials(paramSpace.zeroVector());
priorRv.realizer().realization(paramInitials);
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0,0) = std::pow(std::abs(paramInitials[0]) / 20.0, 2.0);
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
//================================================================
// Statistical forward problem (SFP): find the max distance
// traveled by an object in projectile motion; input pdf for 'g'
// is the solution of the SIP above.
//================================================================
//------------------------------------------------------
// SFP Step 1 of 6: Instantiate the parameter *and* qoi spaces.
// SFP input RV = FIP posterior RV, so SFP parameter space
// has been already defined.
//------------------------------------------------------
QUESO::VectorSpace<> qoiSpace(env, "qoi_", 1, NULL);
//------------------------------------------------------
// SFP Step 2 of 6: Instantiate the parameter domain
//------------------------------------------------------
// Not necessary because input RV of the SFP = output RV of SIP.
// Thus, the parameter domain has been already defined.
//------------------------------------------------------
// SFP Step 3 of 6: Instantiate the qoi object
// to be used by QUESO.
//------------------------------------------------------
Qoi<> qoi("qoi_", paramDomain, qoiSpace);
//------------------------------------------------------
// SFP Step 4 of 6: Define the input RV
//------------------------------------------------------
// Not necessary because input RV of SFP = output RV of SIP
// (postRv).
//------------------------------------------------------
// SFP Step 5 of 6: Instantiate the forward problem
//------------------------------------------------------
QUESO::GenericVectorRV<> qoiRv("qoi_", qoiSpace);
QUESO::StatisticalForwardProblem<> fp("", NULL, postRv, qoi, qoiRv);
//------------------------------------------------------
// SFP Step 6 of 6: Solve the forward problem
//------------------------------------------------------
fp.solveWithMonteCarlo(NULL);
MPI_Finalize();
return 0;
#endif // QUESO_HAS_MPI
}
int main(int argc, char ** argv) {
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
#endif
QUESO::EnvOptionsValues envOptions;
envOptions.m_numSubEnvironments = 1;
envOptions.m_subDisplayFileName = "test_outputNoInputFile/display";
envOptions.m_subDisplayAllowAll = 1;
envOptions.m_displayVerbosity = 2;
envOptions.m_syncVerbosity = 0;
envOptions.m_seed = 0;
#ifdef QUESO_HAS_MPI
QUESO::FullEnvironment env(MPI_COMM_WORLD, "", "", &envOptions);
#else
QUESO::FullEnvironment env("", "", &envOptions);
#endif
unsigned int dim = 2;
QUESO::VectorSpace<> paramSpace(env, "param_", dim, NULL);
QUESO::GslVector paramMins(paramSpace.zeroVector());
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
double min_val = -10.0;
double max_val = 10.0;
paramMins.cwSet(min_val);
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMins, paramMaxs);
QUESO::UniformVectorRV<> priorRv("prior_", paramDomain);
Likelihood<> lhood("llhd_", paramDomain);
QUESO::GenericVectorRV<> postRv("post_", paramSpace);
QUESO::SipOptionsValues sipOptions;
sipOptions.m_computeSolution = 1;
sipOptions.m_dataOutputFileName = "test_outputNoInputFile/sipOutput";
sipOptions.m_dataOutputAllowedSet.clear();
sipOptions.m_dataOutputAllowedSet.insert(0);
QUESO::StatisticalInverseProblem<> ip("", &sipOptions, priorRv, lhood,
postRv);
QUESO::GslVector paramInitials(paramSpace.zeroVector());
paramInitials[0] = 0.0;
paramInitials[1] = 0.0;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0, 0) = 1.0;
proposalCovMatrix(0, 1) = 0.0;
proposalCovMatrix(1, 0) = 0.0;
proposalCovMatrix(1, 1) = 1.0;
QUESO::MhOptionsValues mhOptions;
mhOptions.m_dataOutputFileName = "test_outputNoInputFile/sipOutput";
mhOptions.m_dataOutputAllowAll = 1;
mhOptions.m_rawChainGenerateExtra = 0;
mhOptions.m_rawChainDisplayPeriod = 50000;
mhOptions.m_rawChainMeasureRunTimes = 1;
mhOptions.m_rawChainDataOutputFileName = "test_outputNoInputFile/ip_raw_chain";
mhOptions.m_rawChainDataOutputAllowAll = 1;
mhOptions.m_displayCandidates = 0;
mhOptions.m_tkUseLocalHessian = 0;
mhOptions.m_tkUseNewtonComponent = 1;
mhOptions.m_filteredChainGenerate = 0;
mhOptions.m_rawChainSize = 1000;
mhOptions.m_putOutOfBoundsInChain = false;
mhOptions.m_drMaxNumExtraStages = 1;
mhOptions.m_drScalesForExtraStages.resize(1);
mhOptions.m_drScalesForExtraStages[0] = 5.0;
mhOptions.m_amInitialNonAdaptInterval = 100;
mhOptions.m_amAdaptInterval = 100;
mhOptions.m_amEta = (double) 2.4 * 2.4 / dim; // From Gelman 95
mhOptions.m_amEpsilon = 1.e-8;
mhOptions.m_doLogitTransform = false;
mhOptions.m_algorithm = "random_walk";
mhOptions.m_tk = "random_walk";
ip.solveWithBayesMetropolisHastings(&mhOptions, paramInitials,
&proposalCovMatrix);
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
int main(int argc, char ** argv) {
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, "test_gaussian_likelihoods/queso_input.txt", "", NULL);
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", 1, NULL);
double min_val = -INFINITY;
double max_val = INFINITY;
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(min_val);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
// Set up observation space
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> obsSpace(env,
"obs_", 2, NULL);
// Fill up observation vector
QUESO::GslVector observations(obsSpace.zeroVector());
observations[0] = 1.0;
observations[1] = 1.0;
// Fill up covariance 'matrix'
QUESO::GslVector covariance(obsSpace.zeroVector());
covariance[0] = 1.0;
covariance[1] = 2.0;
// Pass in observations to Gaussian likelihood object
Likelihood<QUESO::GslVector, QUESO::GslMatrix> lhood("llhd_", paramDomain,
observations, covariance);
double lhood_value;
double truth_value;
QUESO::GslVector point(paramSpace.zeroVector());
point[0] = 0.0;
lhood_value = lhood.actualValue(point, NULL, NULL, NULL, NULL);
truth_value = std::exp(-3.0);
if (std::abs(lhood_value - truth_value) > TOL) {
std::cerr << "Scalar Gaussian test case failure." << std::endl;
std::cerr << "Computed likelihood value is: " << lhood_value << std::endl;
std::cerr << "Likelihood value should be: " << truth_value << std::endl;
queso_error();
}
point[0] = -2.0;
lhood_value = lhood.actualValue(point, NULL, NULL, NULL, NULL);
truth_value = 1.0;
if (std::abs(lhood_value - truth_value) > TOL) {
std::cerr << "Scalar Gaussian test case failure." << std::endl;
std::cerr << "Computed likelihood value is: " << lhood_value << std::endl;
std::cerr << "Likelihood value should be: " << truth_value << std::endl;
queso_error();
}
MPI_Finalize();
return 0;
}
void compute(const QUESO::FullEnvironment& env) {
struct timeval timevalNow;
gettimeofday(&timevalNow, NULL);
std::cout << std::endl << "Beginning run of 'Hysteretic' example at "
<< ctime(&timevalNow.tv_sec);
//------------------------------------------------------
// Step 1 of 5: Instantiate the parameter space
//------------------------------------------------------
QUESO::VectorSpace<> paramSpaceA(env, "paramA_", 1, NULL);
QUESO::VectorSpace<> paramSpaceB(env, "paramB_", 14, NULL);
QUESO::VectorSpace<> paramSpace (env, "param_", 15, NULL);
//------------------------------------------------------
// Step 2 of 5: Instantiate the parameter domain
//------------------------------------------------------
QUESO::GslVector paramMinsA(paramSpaceA.zeroVector());
paramMinsA.cwSet(0);
QUESO::GslVector paramMaxsA(paramSpaceA.zeroVector());
paramMaxsA.cwSet(5);
QUESO::BoxSubset<> paramDomainA("paramA_",paramSpaceA,paramMinsA,paramMaxsA);
QUESO::GslVector paramMinsB(paramSpaceB.zeroVector());
paramMinsB.cwSet(-INFINITY);
QUESO::GslVector paramMaxsB(paramSpaceB.zeroVector());
paramMaxsB.cwSet( INFINITY);
QUESO::BoxSubset<> paramDomainB("paramB_",paramSpaceB,paramMinsB,paramMaxsB);
QUESO::ConcatenationSubset<> paramDomain("",paramSpace,paramDomainA,paramDomainB);
//------------------------------------------------------
// Step 3 of 5: Instantiate the likelihood function object
//------------------------------------------------------
std::cout << "\tInstantiating the Likelihood; calling internally the hysteretic model"
<< std::endl;
Likelihood<> likelihood("like_", paramDomain);
likelihood.floor.resize(4,NULL);
unsigned int numTimeSteps = 401;
for (unsigned int i = 0; i < 4; ++i) {
likelihood.floor[i] = new std::vector<double>(numTimeSteps,0.);
}
likelihood.accel.resize(numTimeSteps,0.);
FILE *inp;
inp = fopen("an.txt","r");
unsigned int numObservations = 0;
double tmpA;
while (fscanf(inp,"%lf",&tmpA) != EOF) {
likelihood.accel[numObservations] = tmpA;
numObservations++;
}
numObservations=1;
FILE *inp1_1;
inp1_1=fopen("measured_data1_1.txt","r");
while (fscanf(inp1_1,"%lf",&tmpA) != EOF) {
(*likelihood.floor[0])[numObservations]=tmpA;
numObservations++;
}
numObservations=0;
FILE *inp1_2;
inp1_2=fopen("measured_data1_2.txt","r");
while (fscanf(inp1_2,"%lf",&tmpA) != EOF) {
(*likelihood.floor[1])[numObservations]=tmpA;
numObservations++;
}
numObservations=0;
FILE *inp1_3;
inp1_3=fopen("measured_data1_3.txt","r");
while (fscanf(inp1_3,"%lf",&tmpA) != EOF) {
(*likelihood.floor[2])[numObservations]=tmpA;
numObservations++;
}
numObservations=0;
FILE *inp1_4;
inp1_4=fopen("measured_data1_4.txt","r");
while (fscanf(inp1_4,"%lf",&tmpA) != EOF) {
(*likelihood.floor[3])[numObservations]=tmpA;
numObservations++;
}
//------------------------------------------------------
// Step 4 of 5: Instantiate the inverse problem
//------------------------------------------------------
std::cout << "\tInstantiating the SIP" << std::endl;
QUESO::UniformVectorRV<> priorRvA("priorA_", paramDomainA);
QUESO::GslVector meanVec(paramSpaceB.zeroVector());
QUESO::GslVector diagVec(paramSpaceB.zeroVector());
diagVec.cwSet(0.6*0.6);
QUESO::GslMatrix covMatrix(diagVec);
QUESO::GaussianVectorRV<> priorRvB("priorB_", paramDomainB,meanVec,covMatrix);
QUESO::ConcatenatedVectorRV<> priorRv("prior_", priorRvA, priorRvB, paramDomain);
QUESO::GenericVectorRV<> postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<> ip("", NULL, priorRv, likelihood, postRv);
//------------------------------------------------------
// Step 5 of 5: Solve the inverse problem
//------------------------------------------------------
std::cout << "\tSolving the SIP with Multilevel method" << std::endl;
ip.solveWithBayesMLSampling();
gettimeofday(&timevalNow, NULL);
std::cout << "Ending run of 'Hysteretic' example at "
<< ctime(&timevalNow.tv_sec) << std::endl;
return;
}
void
uqAppl(const QUESO::BaseEnvironment& env)
{
if (env.fullRank() == 0) {
std::cout << "Beginning run of 'uqTgaExample' example\n"
<< std::endl;
}
//int iRC;
struct timeval timevalRef;
struct timeval timevalNow;
//******************************************************
// Task 1 of 5: instantiation of basic classes
//******************************************************
// Instantiate the parameter space
std::vector<std::string> paramNames(2,"");
paramNames[0] = "A_param";
paramNames[1] = "E_param";
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix> paramSpace(env,"param_",paramNames.size(),¶mNames);
// Instantiate the parameter domain
QUESO::GslVector paramMinValues(paramSpace.zeroVector());
paramMinValues[0] = 2.40e+11;
paramMinValues[1] = 1.80e+05;
QUESO::GslVector paramMaxValues(paramSpace.zeroVector());
paramMaxValues[0] = 2.80e+11;
paramMaxValues[1] = 2.20e+05;
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix> paramDomain("param_",
paramSpace,
paramMinValues,
paramMaxValues);
// Instantiate the qoi space
std::vector<std::string> qoiNames(1,"");
qoiNames[0] = "TimeFor25PercentOfMass";
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix> qoiSpace(env,"qoi_",qoiNames.size(),&qoiNames);
// Instantiate the validation cycle
QUESO::ValidationCycle<QUESO::GslVector,QUESO::GslMatrix,QUESO::GslVector,QUESO::GslMatrix> cycle(env,
"", // No extra prefix
paramSpace,
qoiSpace);
//********************************************************
// Task 2 of 5: calibration stage
//********************************************************
/*iRC = */gettimeofday(&timevalRef, NULL);
if (env.fullRank() == 0) {
std::cout << "Beginning 'calibration stage' at " << ctime(&timevalRef.tv_sec)
<< std::endl;
}
// Inverse problem: instantiate the prior rv
QUESO::UniformVectorRV<QUESO::GslVector,QUESO::GslMatrix> calPriorRv("cal_prior_", // Extra prefix before the default "rv_" prefix
paramDomain);
// Inverse problem: instantiate the likelihood
Likelihood<> calLikelihood("cal_like_",
paramDomain,
"inputData/scenario_5_K_min.dat",
"inputData/scenario_25_K_min.dat",
"inputData/scenario_50_K_min.dat");
// Inverse problem: instantiate it (posterior rv is instantiated internally)
cycle.instantiateCalIP(NULL,
calPriorRv,
calLikelihood);
// Inverse problem: solve it, that is, set 'pdf' and 'realizer' of the posterior rv
QUESO::GslVector paramInitialValues(paramSpace.zeroVector());
if (env.numSubEnvironments() == 1) {
// For regression test purposes
paramInitialValues[0] = 2.41e+11;
paramInitialValues[1] = 2.19e+05;
}
else {
calPriorRv.realizer().realization(paramInitialValues);
}
QUESO::GslMatrix* calProposalCovMatrix = cycle.calIP().postRv().imageSet().vectorSpace().newProposalMatrix(NULL,¶mInitialValues);
cycle.calIP().solveWithBayesMetropolisHastings(NULL,
paramInitialValues,
calProposalCovMatrix);
delete calProposalCovMatrix;
// Forward problem: instantiate it (parameter rv = posterior rv of inverse problem; qoi rv is instantiated internally)
double beta_prediction = 250.;
double criticalMass_prediction = 0.;
double criticalTime_prediction = 3.9;
qoiRoutine_Data calQoiRoutine_Data;
calQoiRoutine_Data.m_beta = beta_prediction;
calQoiRoutine_Data.m_criticalMass = criticalMass_prediction;
calQoiRoutine_Data.m_criticalTime = criticalTime_prediction;
cycle.instantiateCalFP(NULL,
qoiRoutine,
(void *) &calQoiRoutine_Data);
// Forward problem: solve it, that is, set 'realizer' and 'cdf' of the qoi rv
cycle.calFP().solveWithMonteCarlo(NULL); // no extra user entities needed for Monte Carlo algorithm
/*iRC = */gettimeofday(&timevalNow, NULL);
if (env.fullRank() == 0) {
std::cout << "Ending 'calibration stage' at " << ctime(&timevalNow.tv_sec)
<< "Total 'calibration stage' run time = " << timevalNow.tv_sec - timevalRef.tv_sec
<< " seconds\n"
<< std::endl;
}
//********************************************************
// Task 3 of 5: validation stage
//********************************************************
/*iRC = */gettimeofday(&timevalRef, NULL);
if (env.fullRank() == 0) {
std::cout << "Beginning 'validation stage' at " << ctime(&timevalRef.tv_sec)
<< std::endl;
}
// Inverse problem: no need to instantiate the prior rv (= posterior rv of calibration inverse problem)
// Inverse problem: instantiate the likelihood function object
Likelihood<> valLikelihood("val_like_",
paramDomain,
"inputData/scenario_100_K_min.dat",
NULL,
NULL);
// Inverse problem: instantiate it (posterior rv is instantiated internally)
cycle.instantiateValIP(NULL,valLikelihood);
// Inverse problem: solve it, that is, set 'pdf' and 'realizer' of the posterior rv
const QUESO::SequentialVectorRealizer<QUESO::GslVector,QUESO::GslMatrix>* tmpRealizer = dynamic_cast< const QUESO::SequentialVectorRealizer<QUESO::GslVector,QUESO::GslMatrix>* >(&(cycle.calIP().postRv().realizer()));
QUESO::GslMatrix* valProposalCovMatrix = cycle.calIP().postRv().imageSet().vectorSpace().newProposalMatrix(&tmpRealizer->unifiedSampleVarVector(), // Use 'realizer()' because post. rv was computed with MH
&tmpRealizer->unifiedSampleExpVector()); // Use these values as the initial values
cycle.valIP().solveWithBayesMetropolisHastings(NULL,
tmpRealizer->unifiedSampleExpVector(),
valProposalCovMatrix);
delete valProposalCovMatrix;
// Forward problem: instantiate it (parameter rv = posterior rv of inverse problem; qoi rv is instantiated internally)
qoiRoutine_Data valQoiRoutine_Data;
valQoiRoutine_Data.m_beta = beta_prediction;
valQoiRoutine_Data.m_criticalMass = criticalMass_prediction;
valQoiRoutine_Data.m_criticalTime = criticalTime_prediction;
cycle.instantiateValFP(NULL,
qoiRoutine,
(void *) &valQoiRoutine_Data);
// Forward problem: solve it, that is, set 'realizer' and 'cdf' of the qoi rv
cycle.valFP().solveWithMonteCarlo(NULL); // no extra user entities needed for Monte Carlo algorithm
/*iRC = */gettimeofday(&timevalNow, NULL);
if (env.fullRank() == 0) {
std::cout << "Ending 'validation stage' at " << ctime(&timevalNow.tv_sec)
<< "Total 'validation stage' run time = " << timevalNow.tv_sec - timevalRef.tv_sec
<< " seconds\n"
<< std::endl;
}
//********************************************************
// Task 4 of 5: comparison stage
//********************************************************
/*iRC = */gettimeofday(&timevalRef, NULL);
if (env.fullRank() == 0) {
std::cout << "Beginning 'comparison stage' at " << ctime(&timevalRef.tv_sec)
<< std::endl;
}
uqAppl_LocalComparisonStage(cycle);
if (env.numSubEnvironments() > 1) {
uqAppl_UnifiedComparisonStage(cycle);
}
/*iRC = */gettimeofday(&timevalNow, NULL);
if (env.fullRank() == 0) {
std::cout << "Ending 'comparison stage' at " << ctime(&timevalNow.tv_sec)
<< "Total 'comparison stage' run time = " << timevalNow.tv_sec - timevalRef.tv_sec
<< " seconds\n"
<< std::endl;
}
//******************************************************
// Task 5 of 5: release memory before leaving routine.
//******************************************************
if (env.fullRank() == 0) {
std::cout << "Finishing run of 'uqTgaExample' example"
<< std::endl;
}
return;
}
int main(int argc, char ** argv) {
std::string inputFileName = "test_gaussian_likelihoods/queso_input.txt";
const char * test_srcdir = std::getenv("srcdir");
if (test_srcdir)
inputFileName = test_srcdir + ('/' + inputFileName);
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, inputFileName, "", NULL);
#else
QUESO::FullEnvironment env(inputFileName, "", NULL);
#endif
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", 1, NULL);
double min_val = -INFINITY;
double max_val = INFINITY;
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(min_val);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
// Set up observation space
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> obsSpace(env,
"obs_", 1, NULL);
// Fill up observation vector
QUESO::GslVector observations(obsSpace.zeroVector());
observations[0] = 1.0;
// Pass in observations to Gaussian likelihood object
Likelihood<QUESO::GslVector, QUESO::GslMatrix> lhood("llhd_", paramDomain,
observations, 1.0);
double lhood_value;
double truth_value;
QUESO::GslVector point(paramSpace.zeroVector());
point[0] = 0.0;
lhood_value = lhood.actualValue(point, NULL, NULL, NULL, NULL);
truth_value = std::exp(-2.0);
if (std::abs(lhood_value - truth_value) > TOL) {
std::cerr << "Scalar Gaussian test case failure." << std::endl;
std::cerr << "Computed likelihood value is: " << lhood_value << std::endl;
std::cerr << "Likelihood value should be: " << truth_value << std::endl;
queso_error();
}
point[0] = -2.0;
lhood_value = lhood.actualValue(point, NULL, NULL, NULL, NULL);
truth_value = 1.0;
if (std::abs(lhood_value - truth_value) > TOL) {
std::cerr << "Scalar Gaussian test case failure." << std::endl;
std::cerr << "Computed likelihood value is: " << lhood_value << std::endl;
std::cerr << "Likelihood value should be: " << truth_value << std::endl;
queso_error();
}
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
int main(int argc, char ** argv)
{
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, "test_InterpolationSurrogate/queso_input.txt", "", NULL);
int return_flag = 0;
std::string vs_prefix = "param_";
// Filename for writing/reading surrogate data
std::string filename1 = "test_write_InterpolationSurrogateBuilder_1.dat";
std::string filename2 = "test_write_InterpolationSurrogateBuilder_2.dat";
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix>
paramSpace(env,vs_prefix.c_str(), 4, NULL);
// Point at which we will test the surrogate evaluation
QUESO::GslVector domainVector(paramSpace.zeroVector());
domainVector[0] = -0.4;
domainVector[1] = 3.0;
domainVector[2] = 1.5;
domainVector[3] = 1.65;
double exact_val_1 = four_d_fn_1(domainVector[0],domainVector[1],domainVector[2],domainVector[3]);
double exact_val_2 = four_d_fn_2(domainVector[0],domainVector[1],domainVector[2],domainVector[3]);
double tol = 2.0*std::numeric_limits<double>::epsilon();
// First test surrogate build directly from the computed values
{
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins[0] = -1;
paramMins[1] = -0.5;
paramMins[2] = 1.1;
paramMins[3] = -2.1;
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs[0] = 0.9;
paramMaxs[1] = 3.14;
paramMaxs[2] = 2.1;
paramMaxs[3] = 4.1;
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix>
paramDomain("param_", paramSpace, paramMins, paramMaxs);
std::vector<unsigned int> n_points(4);
n_points[0] = 11;
n_points[1] = 51;
n_points[2] = 31;
n_points[3] = 41;
// One dataset for each of the two functions
const unsigned int n_datasets = 2;
QUESO::InterpolationSurrogateDataSet<QUESO::GslVector, QUESO::GslMatrix>
data(paramDomain,n_points,n_datasets);
MyInterpolationBuilder<QUESO::GslVector,QUESO::GslMatrix>
builder( data );
builder.build_values();
QUESO::LinearLagrangeInterpolationSurrogate<QUESO::GslVector,QUESO::GslMatrix>
four_d_surrogate_1( data.get_dataset(0) );
QUESO::LinearLagrangeInterpolationSurrogate<QUESO::GslVector,QUESO::GslMatrix>
four_d_surrogate_2( data.get_dataset(1) );
double test_val_1 = four_d_surrogate_1.evaluate(domainVector);
double test_val_2 = four_d_surrogate_2.evaluate(domainVector);
return_flag = return_flag ||
test_val( test_val_1, exact_val_1, tol, "test_build_1" ) ||
test_val( test_val_2, exact_val_2, tol, "test_build_2" );
// Write the output to test reading next
QUESO::InterpolationSurrogateIOASCII<QUESO::GslVector,QUESO::GslMatrix>
data_writer;
data_writer.write( filename1, data.get_dataset(0) );
data_writer.write( filename2, data.get_dataset(1) );
}
// Now read the data and test
{
QUESO::InterpolationSurrogateIOASCII<QUESO::GslVector,QUESO::GslMatrix>
data_reader_1, data_reader_2;
data_reader_1.read( filename1, env, vs_prefix.c_str() );
data_reader_2.read( filename2, env, vs_prefix.c_str() );
// Build a new surrogate
QUESO::LinearLagrangeInterpolationSurrogate<QUESO::GslVector,QUESO::GslMatrix>
four_d_surrogate_1( data_reader_1.data() );
QUESO::LinearLagrangeInterpolationSurrogate<QUESO::GslVector,QUESO::GslMatrix>
four_d_surrogate_2( data_reader_2.data() );
double test_val_1 = four_d_surrogate_1.evaluate(domainVector);
double test_val_2 = four_d_surrogate_2.evaluate(domainVector);
return_flag = return_flag ||
test_val( test_val_1, exact_val_1, tol, "test_read_1" ) ||
test_val( test_val_2, exact_val_2, tol, "test_read_2" );
}
return return_flag;
}
int main(int argc, char ** argv)
{
std::string inputFileName = "test_InterpolationSurrogate/queso_input.txt";
const char * test_srcdir = std::getenv("srcdir");
if (test_srcdir)
inputFileName = test_srcdir + ('/' + inputFileName);
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, inputFileName, "", NULL);
#else
QUESO::FullEnvironment env(inputFileName, "", NULL);
#endif
int return_flag = 0;
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix>
paramSpace(env,"param_", 3, NULL);
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins[0] = -1;
paramMins[1] = -0.5;
paramMins[2] = 1.1;
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs[0] = 0.9;
paramMaxs[1] = 3.14;
paramMaxs[2] = 2.1;
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix>
paramDomain("param_", paramSpace, paramMins, paramMaxs);
std::vector<unsigned int> n_points(3);
n_points[0] = 101;
n_points[1] = 51;
n_points[2] = 31;
QUESO::InterpolationSurrogateData<QUESO::GslVector, QUESO::GslMatrix>
data(paramDomain,n_points);
std::vector<double> values(n_points[0]*n_points[1]*n_points[2]);
double spacing_x = (paramMaxs[0] - paramMins[0])/(n_points[0]-1);
double spacing_y = (paramMaxs[1] - paramMins[1])/(n_points[1]-1);
double spacing_z = (paramMaxs[2] - paramMins[2])/(n_points[2]-1);
for( unsigned int i = 0; i < n_points[0]; i++ )
{
for( unsigned int j = 0; j < n_points[1]; j++ )
{
for( unsigned int k = 0; k < n_points[2]; k++ )
{
unsigned int n = i + j*n_points[0] + k*n_points[0]*n_points[1];
double x = paramMins[0] + i*spacing_x;
double y = paramMins[1] + j*spacing_y;
double z = paramMins[2] + k*spacing_z;
values[n] = three_d_fn(x,y,z);
}
}
}
data.set_values( values );
QUESO::LinearLagrangeInterpolationSurrogate<QUESO::GslVector,QUESO::GslMatrix>
three_d_surrogate( data );
QUESO::GslVector domainVector(paramSpace.zeroVector());
domainVector[0] = -0.4;
domainVector[1] = 3.0;
domainVector[2] = 1.5;
double test_val = three_d_surrogate.evaluate(domainVector);
double exact_val = three_d_fn(domainVector[0],domainVector[1],domainVector[2]);
double tol = 2.0*std::numeric_limits<double>::epsilon();
double rel_error = (test_val - exact_val)/exact_val;
if( std::fabs(rel_error) > tol )
{
std::cerr << "ERROR: Tolerance exceeded for 3D Lagrange interpolation test."
<< std::endl
<< " test_val = " << test_val << std::endl
<< " exact_val = " << exact_val << std::endl
<< " rel_error = " << rel_error << std::endl
<< " tol = " << tol << std::endl;
return_flag = 1;
}
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return return_flag;
}
void infer_slope(const QUESO::FullEnvironment & env) {
// Statistical Inverse Problem: Compute posterior pdf for slope 'm' and y-intercept c
// Step 1: Instantiate the parameter space
QUESO::VectorSpace<> paramSpace(env, "param_", 2, NULL); // 2 since we have a 2D problem
// Step 2: Parameter domain
QUESO::GslVector paramMinValues(paramSpace.zeroVector());
QUESO::GslVector paramMaxValues(paramSpace.zeroVector());
paramMinValues[0] = 2.;
paramMaxValues[0] = 5.;
paramMinValues[1] = 3.;
paramMaxValues[1] = 7.;
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMinValues, paramMaxValues);
// Step 3: Instantiate likelihood
Likelihood<> lhood("like_", paramDomain);
// Step 4: Define the prior RV
QUESO::UniformVectorRV<> priorRv("prior_", paramDomain);
// Step 5: Instantiate the inverse problem
QUESO::GenericVectorRV<> postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<> ip("", NULL, priorRv, lhood, postRv);
// Step 6: Solve the inverse problem
// Randomly sample for the initial state?
QUESO::GslVector paramInitials(paramSpace.zeroVector());
priorRv.realizer().realization(paramInitials);
// Initialize the Cov matrix:
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0,0) = std::pow(std::abs(paramInitials[0]) / 20.0, 2.0);
proposalCovMatrix(1,1) = std::pow(std::abs(paramInitials[1]) / 20.0, 2.0);
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
// Using the posterior pdfs for m and c, compute 'y' at a given 'x'
// Step 1: Instantiate the qoi space
QUESO::VectorSpace<> qoiSpace(env, "qoi_", 1, NULL);
// Step 2: Instantiate the parameter domain
// Not necessary here because the posterior from SIP is used as the RV for SFP
// Step 3: Instantiate the qoi object to be used by QUESO
Qoi<> qoi("qoi_", paramDomain, qoiSpace);
// Step 4: Define the input RV
// Not required because we use the posterior as RV
// Step 5: Instantiate the forward problem
QUESO::GenericVectorRV<> qoiRv("qoi_", qoiSpace);
QUESO::StatisticalForwardProblem<> fp("", NULL, postRv, qoi, qoiRv);
// Step 6: Solve the forward problem
std::cout << "Solving the SFP with Monte Carlo" << std::endl << std::endl;
fp.solveWithMonteCarlo(NULL);
system("mv outputData/sfp_lineSlope_qoi_seq.txt outputData/sfp_lineSlope_qoi_seq_post.txt");
// SENSITIVITY ANALYSIS
// For m
Qoi_m<> qoi_m("qoi_", paramDomain, qoiSpace);
// Step 4: Define the input RV
// Not required because we use the prior as RV for sensitivity analysis
// Step 5: Instantiate the forward problem
QUESO::StatisticalForwardProblem<> fp_m("", NULL, priorRv, qoi_m, qoiRv);
// Step 6: Solve the forward problem
fp_m.solveWithMonteCarlo(NULL);
system("mv outputData/sfp_lineSlope_qoi_seq.txt outputData/sense_m.txt");
// For c
Qoi_c<> qoi_c("qoi_", paramDomain, qoiSpace);
// Step 4: Define the input RV
// Not required because we use the prior as RV for sensitivity analysis
// Step 5: Instantiate the forward problem
QUESO::StatisticalForwardProblem<> fp_c("", NULL, priorRv, qoi_c, qoiRv);
// Step 6: Solve the forward problem
fp_c.solveWithMonteCarlo(NULL);
system("mv outputData/sfp_lineSlope_qoi_seq.txt outputData/sense_c.txt");
// For both, m and c
Qoi_mc<> qoi_mc("qoi_", paramDomain, qoiSpace);
// Step 4: Define the input RV
// Not required because we use the prior as RV for sensitivity analysis
// Step 5: Instantiate the forward problem
QUESO::StatisticalForwardProblem<> fp_mc("", NULL, priorRv, qoi_mc, qoiRv);
// Step 6: Solve the forward problem
fp_mc.solveWithMonteCarlo(NULL);
system("mv outputData/sfp_lineSlope_qoi_seq.txt outputData/sense_mc.txt");
}
int main(int argc, char ** argv) {
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, argv[1], "", NULL);
#else
QUESO::FullEnvironment env(argv[1], "", NULL);
#endif
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", 1, NULL);
double min_val = 0.0;
double max_val = 1.0;
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(min_val);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(max_val);
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
QUESO::UniformVectorRV<QUESO::GslVector, QUESO::GslMatrix> priorRv("prior_",
paramDomain);
// Set up observation space
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> obsSpace(env,
"obs_", 2, NULL);
// Fill up observation vector
QUESO::GslVector observations(obsSpace.zeroVector());
observations[0] = 1.0;
observations[1] = 1.0;
// Pass in observations to Gaussian likelihood object
Likelihood<QUESO::GslVector, QUESO::GslMatrix> lhood("llhd_", paramDomain,
observations, 1.0);
QUESO::GenericVectorRV<QUESO::GslVector, QUESO::GslMatrix>
postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector, QUESO::GslMatrix>
ip("", NULL, priorRv, lhood, postRv);
QUESO::GslVector paramInitials(paramSpace.zeroVector());
paramInitials[0] = 0.0;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
for (unsigned int i = 0; i < 1; i++) {
proposalCovMatrix(i, i) = 0.1;
}
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
void compute(const uqFullEnvironmentClass& env, bool useExperiments, bool useML)
{
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "Entering compute()..."
<< std::endl;
}
//***********************************************************************
// Step 01 of 09: Instantiate parameter space, parameter domain, and prior Rv
//***********************************************************************
unsigned int paper_p_t = 1; // parameter dimension; 'p_t' in paper; drag coefficient 'C' in tower example
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>
paper_p_t_space(env, "param_", paper_p_t, NULL);
uqGslVectorClass paramMins(paper_p_t_space.zeroVector());
uqGslVectorClass paramMaxs(paper_p_t_space.zeroVector());
paramMins[0] = 0.;
paramMaxs[0] = 1.;
uqBoxSubsetClass<uqGslVectorClass,uqGslMatrixClass>
paramDomain("param_",paper_p_t_space,paramMins,paramMaxs);
uqUniformVectorRVClass<uqGslVectorClass,uqGslMatrixClass>* paramPriorRvPtr = NULL;
//uqGaussianVectorRVClass<uqGslVectorClass,uqGslMatrixClass>* paramPriorRvPtr = NULL;
//***********************************************************************
// Step 02 of 09: Instantiate the 'scenario' and 'output' spaces
//***********************************************************************
unsigned int paper_p_x = 1; // scenario dimension; 'p_x' in paper; ball radius 'R' in tower example
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>
paper_p_x_space(env, "scenario_", paper_p_x, NULL);
unsigned int paper_n_eta = 16; // simulation output dimension; 'n_eta' in paper; 16 in tower example
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>
paper_n_eta_space(env, "output_", paper_n_eta, NULL);
//***********************************************************************
// Step 03 of 09: Instantiate the simulation storage
// Regarding simulation scenario input values, QUESO will standardize them so that
// they exist inside a hypercube: this will be done in the 'uqSimulationModelClass'
// constructor, step 04 of 09.
// Regarding simulation output data, QUESO will transform it so that the mean is
// zero and the variance is one: this will be done in the 'uqSimulationModelClass'
// constructor, step 04 of 09.
//***********************************************************************
unsigned int paper_m = 25; // number of simulations; 'm' in paper; 25 in tower example
uqSimulationStorageClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>
simulationStorage(paper_p_x_space,paper_p_t_space,paper_n_eta_space,paper_m);
// Add simulations: what if none?
uqGslVectorClass extraSimulationGridVec(paper_n_eta_space.zeroVector());
std::vector<uqGslVectorClass* > simulationScenarios(paper_m,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > paramVecs (paper_m,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > outputVecs (paper_m,(uqGslVectorClass*) NULL);
for (unsigned int i = 0; i < paper_m; ++i) {
simulationScenarios[i] = new uqGslVectorClass(paper_p_x_space.zeroVector()); // 'x_{i+1}^*' in paper
paramVecs [i] = new uqGslVectorClass(paper_p_t_space.zeroVector()); // 't_{i+1}^*' in paper
outputVecs [i] = new uqGslVectorClass(paper_n_eta_space.zeroVector()); // 'eta_{i+1}' in paper
}
// Populate all objects just instantiated
std::set<unsigned int> tmpSetStep03;
tmpSetStep03.insert(env.subId());
extraSimulationGridVec.subReadContents("inputData/extraSimulHeights",
"m",
tmpSetStep03);
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>
paper_m_space(env, "simulation_", paper_m, NULL);
uqGslVectorClass inputSimulScenarioVector(paper_m_space.zeroVector());
inputSimulScenarioVector.subReadContents("inputData/allSimulScenarios",
"m",
tmpSetStep03);
uqGslVectorClass inputSimulParameterVector(paper_m_space.zeroVector());
inputSimulParameterVector.subReadContents("inputData/allSimulParameters",
"m",
tmpSetStep03);
uqGslMatrixClass inputSimulOutputsMatrix(env,paper_n_eta_space.map(),paper_m);
inputSimulOutputsMatrix.subReadContents("inputData/allSimulOutputs",
"m",
tmpSetStep03);
for (unsigned int i = 0; i < paper_m; ++i) {
(*(simulationScenarios[i]))[0] = inputSimulScenarioVector [i];
(*(paramVecs [i]))[0] = inputSimulParameterVector[i];
inputSimulOutputsMatrix.getColumn(i,*(outputVecs[i]));
}
// Finally, add information to the simulation storage
for (unsigned int i = 0; i < paper_m; ++i) {
simulationStorage.addSimulation(*(simulationScenarios[i]),*(paramVecs[i]),*(outputVecs[i]));
}
//***********************************************************************
// Step 04 of 09: Instantiate the simulation model
//***********************************************************************
uqSimulationModelClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>
simulationModel("", // prefix
NULL, // options values
simulationStorage);
unsigned int paper_p_eta = simulationModel.numBasis(); // number of simulation basis; 'p_eta' in paper; 2 in tower example
//***********************************************************************
// Step 05 of 09: Instantiate the experiment storage
// Regarding experimental scenario input values, QUESO will standardize them so that
// they exist inside a hypercube: this will be done in the 'uqExperimentModelClass'
// constructor, step 06 of 09.
// Regarding experimental data, the user has to provide it already in transformed
// format, that is, with mean zero and standard deviation one.
//***********************************************************************
uqExperimentStorageClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>* experimentStoragePtr = NULL;
uqExperimentModelClass <uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>* experimentModelPtr = NULL;
unsigned int paper_n = 0;
std::vector<uqGslVectorClass* > experimentScenarios_original(paper_n,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > experimentScenarios_standard(paper_n,(uqGslVectorClass*) NULL);
std::vector<unsigned int> experimentDims (paper_n,0);
std::vector<uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>* > experimentSpaces (paper_n,(uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>*) NULL);
std::vector<uqGslVectorClass* > extraExperimentGridVecs (paper_n,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > experimentVecs_original (paper_n,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > experimentVecs_auxMean (paper_n,(uqGslVectorClass*) NULL);
std::vector<uqGslVectorClass* > experimentVecs_transformed (paper_n,(uqGslVectorClass*) NULL);
std::vector<uqGslMatrixClass* > experimentMats_original (paper_n,(uqGslMatrixClass*) NULL);
std::vector<uqGslMatrixClass* > experimentMats_transformed (paper_n,(uqGslMatrixClass*) NULL);
std::vector<uqGslMatrixClass* > DobsMats (paper_n, (uqGslMatrixClass*) NULL);
std::vector<uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>* > Kmats_interp_spaces (paper_n, (uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>*) NULL);
std::vector<uqGslMatrixClass* > Kmats_interp (paper_n, (uqGslMatrixClass*) NULL); // Interpolations of 'Kmat_eta' = 'K_i's' in paper
if (useExperiments) {
paper_n = 3; // number of experiments; 'n' in paper; 3 in tower example
experimentStoragePtr = new uqExperimentStorageClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>(paper_p_x_space, paper_n);
// Add experiments
experimentScenarios_original.resize(paper_n,(uqGslVectorClass*) NULL);
experimentScenarios_standard.resize(paper_n,(uqGslVectorClass*) NULL);
experimentDims.resize (paper_n,0);
experimentSpaces.resize (paper_n,(uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>*) NULL);
extraExperimentGridVecs.resize (paper_n,(uqGslVectorClass*) NULL);
experimentVecs_original.resize (paper_n,(uqGslVectorClass*) NULL);
experimentVecs_auxMean.resize (paper_n,(uqGslVectorClass*) NULL);
experimentVecs_transformed.resize (paper_n,(uqGslVectorClass*) NULL);
experimentMats_original.resize (paper_n,(uqGslMatrixClass*) NULL);
experimentMats_transformed.resize (paper_n,(uqGslMatrixClass*) NULL);
experimentDims[0] = 4; // 'n_y_1' in paper; 4 in tower example
experimentDims[1] = 4; // 'n_y_2' in paper; 4 in tower example
experimentDims[2] = 3; // 'n_y_3' in paper; 3 in tower example
for (unsigned int i = 0; i < paper_n; ++i) {
experimentScenarios_original[i] = new uqGslVectorClass (paper_p_x_space.zeroVector()); // 'x_{i+1}' in paper
experimentScenarios_standard[i] = new uqGslVectorClass (paper_p_x_space.zeroVector()); // 'x_{i+1}' in paper
experimentSpaces [i] = new uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>(env, "expSpace", experimentDims[i], NULL);
extraExperimentGridVecs [i] = new uqGslVectorClass (experimentSpaces[i]->zeroVector()); //
experimentVecs_original [i] = new uqGslVectorClass (experimentSpaces[i]->zeroVector()); //
experimentVecs_auxMean [i] = new uqGslVectorClass (experimentSpaces[i]->zeroVector()); //
experimentVecs_transformed [i] = new uqGslVectorClass (experimentSpaces[i]->zeroVector()); // 'y_{i+1}' in paper
experimentMats_original [i] = new uqGslMatrixClass (experimentSpaces[i]->zeroVector()); //
experimentMats_transformed [i] = new uqGslMatrixClass (experimentSpaces[i]->zeroVector()); // 'W_{i+1}' in paper
}
//***********************************************************************
// Populate information regarding experiment '0'
//***********************************************************************
(*(experimentScenarios_original[0]))[0] = 0.1; // 'x_1' in paper; Radius in tower example
*(experimentScenarios_standard[0]) = *(experimentScenarios_original[0]);
*(experimentScenarios_standard[0]) -= simulationModel.xSeq_original_mins();
for (unsigned int j = 0; j < paper_p_x; ++j) {
(*(experimentScenarios_standard[0]))[j] /= simulationModel.xSeq_original_ranges()[j];
}
(*(extraExperimentGridVecs[0]))[0] = 5.;
(*(extraExperimentGridVecs[0]))[1] = 10.;
(*(extraExperimentGridVecs[0]))[2] = 15.;
(*(extraExperimentGridVecs[0]))[3] = 20.;
(*(experimentVecs_original[0]))[0] = 1.2180;
(*(experimentVecs_original[0]))[1] = 2.0126;
(*(experimentVecs_original[0]))[2] = 2.7942;
(*(experimentVecs_original[0]))[3] = 3.5747;
experimentVecs_auxMean[0]->matlabLinearInterpExtrap(extraSimulationGridVec,simulationModel.etaSeq_original_mean(),*(extraExperimentGridVecs[0]));
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05, experiment 0:"
<< "\n extraSimulationGridVec = " << extraSimulationGridVec
<< "\n simulationModel.etaSeq_original_mean() = " << simulationModel.etaSeq_original_mean()
<< "\n *(extraExperimentGridVecs[0]) = " << *(extraExperimentGridVecs[0])
<< "\n *(experimentVecs_auxMean[0]) = " << *(experimentVecs_auxMean[0])
<< std::endl;
}
*(experimentVecs_transformed[0]) = (1./simulationModel.etaSeq_allStd()) * ( *(experimentVecs_original[0]) - *(experimentVecs_auxMean[0]) ); // 'y_1' in paper
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05, experiment 0:"
<< "\n *(experimentVecs_original[0]) = " << *(experimentVecs_original[0])
<< "\n *(experimentVecs_auxMean[0]) = " << *(experimentVecs_auxMean[0])
<< "\n simulationModel.etaSeq_allStd() = " << simulationModel.etaSeq_allStd()
<< "\n *(experimentVecs_transformed[0]) = " << *(experimentVecs_transformed[0])
<< std::endl;
}
(*(experimentMats_original[0]))(0,0) = 1.;
(*(experimentMats_original[0]))(1,1) = 1.;
(*(experimentMats_original[0]))(2,2) = 1.;
(*(experimentMats_original[0]))(3,3) = 1.;
*(experimentMats_transformed[0]) = *(experimentMats_original[0]);
//***********************************************************************
// Populate information regarding experiment '1'
//***********************************************************************
(*(experimentScenarios_original[1]))[0] = 0.2; // 'x_2' in paper; Radius in tower example
*(experimentScenarios_standard[1]) = *(experimentScenarios_original[1]);
*(experimentScenarios_standard[1]) -= simulationModel.xSeq_original_mins();
for (unsigned int j = 0; j < paper_p_x; ++j) {
(*(experimentScenarios_standard[1]))[j] /= simulationModel.xSeq_original_ranges()[j];
}
(*(extraExperimentGridVecs[1]))[0] = 5.;
(*(extraExperimentGridVecs[1]))[1] = 10.;
(*(extraExperimentGridVecs[1]))[2] = 15.;
(*(extraExperimentGridVecs[1]))[3] = 20.;
(*(experimentVecs_original[1]))[0] = 1.1129;
(*(experimentVecs_original[1]))[1] = 1.7225;
(*(experimentVecs_original[1]))[2] = 2.2898;
(*(experimentVecs_original[1]))[3] = 2.8462;
experimentVecs_auxMean[1]->matlabLinearInterpExtrap(extraSimulationGridVec,simulationModel.etaSeq_original_mean(),*(extraExperimentGridVecs[1]));
*(experimentVecs_transformed[1]) = (1./simulationModel.etaSeq_allStd()) * ( *(experimentVecs_original[1]) - *(experimentVecs_auxMean[1]) ); // 'y_2' in paper
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05, experiment 1:"
<< "\n *(experimentVecs_original[1]) = " << *(experimentVecs_original[1])
<< "\n *(experimentVecs_auxMean[1]) = " << *(experimentVecs_auxMean[1])
<< "\n simulationModel.etaSeq_allStd() = " << simulationModel.etaSeq_allStd()
<< "\n *(experimentVecs_transformed[1]) = " << *(experimentVecs_transformed[1])
<< std::endl;
}
(*(experimentMats_original[1]))(0,0) = 1.;
(*(experimentMats_original[1]))(1,1) = 1.;
(*(experimentMats_original[1]))(2,2) = 1.;
(*(experimentMats_original[1]))(3,3) = 1.;
*(experimentMats_transformed[1]) = *(experimentMats_original[1]);
//***********************************************************************
// Populate information regarding experiment '2'
//***********************************************************************
(*(experimentScenarios_original[2]))[0] = 0.4; // 'x_3' in paper; Radius in tower example
*(experimentScenarios_standard[2]) = *(experimentScenarios_original[2]);
*(experimentScenarios_standard[2]) -= simulationModel.xSeq_original_mins();
for (unsigned int j = 0; j < paper_p_x; ++j) {
(*(experimentScenarios_standard[2]))[j] /= simulationModel.xSeq_original_ranges()[j];
}
(*(extraExperimentGridVecs[2]))[0] = 5.;
(*(extraExperimentGridVecs[2]))[1] = 10.;
(*(extraExperimentGridVecs[2]))[2] = 15.;
(*(experimentVecs_original[2]))[0] = 1.0611;
(*(experimentVecs_original[2]))[1] = 1.5740;
(*(experimentVecs_original[2]))[2] = 2.0186;
experimentVecs_auxMean[2]->matlabLinearInterpExtrap(extraSimulationGridVec,simulationModel.etaSeq_original_mean(),*(extraExperimentGridVecs[2]));
*(experimentVecs_transformed[2]) = (1./simulationModel.etaSeq_allStd()) * ( *(experimentVecs_original[2]) - *(experimentVecs_auxMean[2]) ); // 'y_3' in paper
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05, experiment 2:"
<< "\n *(experimentVecs_original[2]) = " << *(experimentVecs_original[2])
<< "\n *(experimentVecs_auxMean[2]) = " << *(experimentVecs_auxMean[2])
<< "\n simulationModel.etaSeq_allStd() = " << simulationModel.etaSeq_allStd()
<< "\n *(experimentVecs_transformed[2]) = " << *(experimentVecs_transformed[2])
<< std::endl;
}
(*(experimentMats_original[2]))(0,0) = 1.;
(*(experimentMats_original[2]))(1,1) = 1.;
(*(experimentMats_original[2]))(2,2) = 1.;
*(experimentMats_transformed[2]) = *(experimentMats_original[2]);
//***********************************************************************
// Finally, add information to the experiment storage
//***********************************************************************
for (unsigned int i = 0; i < paper_n; ++i) {
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05"
<< ": calling experimentStoragePtr->addExperiment() for experiment of id '" << i << "'..."
<< std::endl;
}
experimentStoragePtr->addExperiment(*(experimentScenarios_standard[i]),*(experimentVecs_transformed[i]),*(experimentMats_transformed[i]));
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute(), step 05"
<< ": returned from experimentStoragePtr->addExperiment() for experiment of id '" << i << "'"
<< std::endl;
}
}
//***********************************************************************
// Step 06 of 09: Instantiate the experiment model
// User has to provide 'D' matrices
// User has to interpolate 'K_eta' matrix in order to form 'K_i' matrices
// 'K_eta' is 'Ksim' in the GPMSA tower example document (page 9)
// 'K_i' is 'Kobs' in the GPMSA tower example document (page 9)
//***********************************************************************
unsigned int paper_p_delta = 13; // number of experiment basis; 'p_delta' in paper; 13 in tower example
//***********************************************************************
// Form and compute 'DsimMat'
// Not mentioned in the paper
// 'Dsim' in the GPMSA tower example document (page 11)
//***********************************************************************
double kernelSigma = 2.;
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> paper_p_delta_space(env, "paper_p_delta_space", paper_p_delta, NULL);
uqGslVectorClass kernelCenters(paper_p_delta_space.zeroVector());
for (unsigned int i = 1; i < paper_p_delta; ++i) { // Yes, '1'
kernelCenters[i] = kernelSigma*((double) i);
}
uqGslMatrixClass DsimMat(env,paper_n_eta_space.map(),paper_p_delta); // Important matrix (not mentioned on paper)
uqGslVectorClass DsimCol(paper_n_eta_space.zeroVector());
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> oneDSpace(env, "oneDSpace", 1, NULL);
uqGslVectorClass oneDVec(oneDSpace.zeroVector());
uqGslMatrixClass oneDMat(oneDSpace.zeroVector());
oneDMat(0,0) = kernelSigma*kernelSigma;
for (unsigned int colId = 0; colId < DsimMat.numCols(); ++colId) {
oneDVec[0] = kernelCenters[colId];
uqGaussianJointPdfClass<uqGslVectorClass,uqGslMatrixClass> kernelPdf("",oneDSpace,oneDVec,oneDMat);
for (unsigned int rowId = 0; rowId < paper_n_eta; ++rowId) {
oneDVec[0] = extraSimulationGridVec[rowId];
DsimCol[rowId] = kernelPdf.actualValue(oneDVec,NULL,NULL,NULL,NULL);
}
DsimMat.setColumn(colId,DsimCol);
}
//***********************************************************************
// Populate information regarding experiment 'i'
// 'D_{i+1}' in the paper
// 'Dobs' in the GPMSA tower example document (page 11)
//***********************************************************************
DobsMats.resize(paper_n, (uqGslMatrixClass*) NULL); // Important matrices (D_i's on paper)
for (unsigned int i = 0; i < paper_n; ++i) {
DobsMats[i] = new uqGslMatrixClass(env,experimentSpaces[i]->map(),paper_p_delta); // 'D_{i+1}' in paper
uqGslVectorClass DobsCol(experimentSpaces[i]->zeroVector());
for (unsigned int colId = 0; colId < DobsMats[i]->numCols(); ++colId) {
oneDVec[0] = kernelCenters[colId];
uqGaussianJointPdfClass<uqGslVectorClass,uqGslMatrixClass> kernelPdf("",oneDSpace,oneDVec,oneDMat);
for (unsigned int rowId = 0; rowId < DobsCol.sizeLocal(); ++rowId) {
oneDVec[0] = (*(extraExperimentGridVecs[1]))[rowId];
DobsCol[rowId] = kernelPdf.actualValue(oneDVec,NULL,NULL,NULL,NULL);
}
DobsMats[i]->setColumn(colId,DobsCol);
}
}
//***********************************************************************
// Normalize 'DsimMat' and all 'DobsMats'
//***********************************************************************
uqGslMatrixClass DsimMatTranspose(env,paper_p_delta_space.map(),paper_n_eta);
DsimMatTranspose.fillWithTranspose(0,0,DsimMat,true,true);
double Dmax = (DsimMat * DsimMatTranspose).max();
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute()"
<< ": Dmax = " << Dmax
<< std::endl;
}
DsimMat /= std::sqrt(Dmax);
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
DsimMat.setPrintHorizontally(false);
*env.subDisplayFile() << "In compute()"
<< ": 'DsimMat'"
<< ", nRows = " << DsimMat.numRowsLocal()
<< ", nCols = " << DsimMat.numCols()
<< ", contents =\n " << DsimMat
<< std::endl;
}
for (unsigned int i = 0; i < paper_n; ++i) {
*(DobsMats[i]) /= std::sqrt(Dmax);
DobsMats[i]->setPrintHorizontally(false);
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute()"
<< ": 'DobsMats', i = " << i
<< ", nRows = " << DobsMats[i]->numRowsLocal()
<< ", nCols = " << DobsMats[i]->numCols()
<< ", contents =\n" << *(DobsMats[i])
<< std::endl;
}
}
//***********************************************************************
// Compute 'K_i' matrices
// 'Kobs' in the GPMSA tower example document (page 9)
//***********************************************************************
Kmats_interp_spaces.resize(paper_n, (uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>*) NULL);
Kmats_interp.resize (paper_n, (uqGslMatrixClass*) NULL); // Important matrices (K_i's on paper)
for (unsigned int i = 0; i < paper_n; ++i) {
Kmats_interp_spaces[i] = new uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass>(env,"Kmats_interp_spaces_",experimentStoragePtr->n_ys_transformed()[i],NULL);
Kmats_interp [i] = new uqGslMatrixClass(env,Kmats_interp_spaces[i]->map(),paper_p_eta);
Kmats_interp [i]->matlabLinearInterpExtrap(extraSimulationGridVec,simulationModel.Kmat_eta(),*(extraExperimentGridVecs[i])); // Important matrix (K_eta on paper)
Kmats_interp[i]->setPrintHorizontally(false);
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute()"
<< ": 'Kmats_interp', i = " << i
<< ", nRows = " << Kmats_interp[i]->numRowsLocal()
<< ", nCols = " << Kmats_interp[i]->numCols()
<< ", contents =\n" << *(Kmats_interp[i])
<< std::endl;
}
}
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": finished computing 'K_i' matrices"
<< std::endl;
}
//***********************************************************************
// The constructor below will read from the options file:
// --> the 'G' values (a total of 'F' of them); 'Gs' in paper; G[0] = 13 in tower example
// --> 'F' in paper = number of groups of experiment basis; 1 in tower example
//***********************************************************************
experimentModelPtr = new uqExperimentModelClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>("", // prefix
NULL, // options values
*experimentStoragePtr,
DobsMats,
Kmats_interp);
paramPriorRvPtr = new uqUniformVectorRVClass<uqGslVectorClass,uqGslMatrixClass>("prior_",paramDomain);
//uqGslVectorClass meanVec(paper_p_t_space.zeroVector());
//meanVec[0] = 0.5;
//uqGslMatrixClass covaMat(paper_p_t_space.zeroVector());
//covaMat(0,0) = 100.;
//paramPriorRvPtr = new uqGaussianVectorRVClass<uqGslVectorClass,uqGslMatrixClass>("prior_",paramDomain/*paper_p_t_space*/,meanVec,covaMat);
} // if (useExperiments)
//***********************************************************************
// Step 07 of 09: Instantiate the GPMSA computer model
//***********************************************************************
uqGpmsaComputerModelClass<uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass,uqGslVectorClass,uqGslMatrixClass>* gcm;
gcm = new uqGpmsaComputerModelClass<uqGslVectorClass,uqGslMatrixClass,
uqGslVectorClass,uqGslMatrixClass,
uqGslVectorClass,uqGslMatrixClass,
uqGslVectorClass,uqGslMatrixClass>
("",
NULL,
simulationStorage,
simulationModel,
experimentStoragePtr, // pass "NULL" if there is no experimental data available
experimentModelPtr, // pass "NULL" if there is no experimental data available
paramPriorRvPtr); // pass "NULL" if there is no experimental data available
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": finished instantiating 'gcm'"
<< ", gcm->totalSpace().dimLocal() = " << gcm->totalSpace().dimLocal()
<< std::endl;
}
//***********************************************************************
// Step 08 of 09: Calibrate the computer model
//***********************************************************************
uqGslVectorClass totalInitialVec(gcm->totalSpace().zeroVector());
gcm->totalPriorRv().realizer().realization(totalInitialVec); // todo_r
uqGslVectorClass diagVec(gcm->totalSpace().zeroVector());
diagVec.cwSet(0.25);
if (useExperiments) {
#if 1
// Use same initial values as matlab code, for debug
totalInitialVec[ 0] = 2.9701e+04; // lambda_eta = lamWOs
totalInitialVec[ 1] = 1.; // lambda_w_1 = lamUz
totalInitialVec[ 2] = 1.; // lambda_w_2 =
totalInitialVec[ 3] = std::exp(-0.1*0.25); // rho_w_1_1 = exp(-model.betaU.*(0.5^2));
totalInitialVec[ 4] = std::exp(-0.1*0.25); // rho_w_1_2 =
totalInitialVec[ 5] = std::exp(-0.1*0.25); // rho_w_2_1 =
totalInitialVec[ 6] = std::exp(-0.1*0.25); // rho_w_2_2 =
totalInitialVec[ 7] = 1000.; // lambda_s_1 = lamWs
totalInitialVec[ 8] = 1000.; // lambda_s_2 =
totalInitialVec[ 9] = 999.999; // lambda_y = lamOs
totalInitialVec[10] = 20.; // lambda_v_1 = lamVz
totalInitialVec[11] = std::exp(-0.1*0.25); // rho_v_1_1 = betaV
totalInitialVec[12] = 0.5; // theta_1 = theta
#endif
diagVec[ 0] = 2500.; // lambda_eta = lamWOs
diagVec[ 1] = 0.09; // lambda_w_1 = lamUz
diagVec[ 2] = 0.09; // lambda_w_2 =
diagVec[ 3] = 0.01; // rho_w_1_1 = betaU
diagVec[ 4] = 0.01; // rho_w_1_2 =
diagVec[ 5] = 0.01; // rho_w_2_1 =
diagVec[ 6] = 0.01; // rho_w_2_2 =
diagVec[ 7] = 2500.; // lambda_s_1 = lamWs
diagVec[ 8] = 2500; // lambda_s_2 =
diagVec[ 9] = 2500; // lambda_y = lamOs
diagVec[10] = 2500; // lambda_v_1 = lamVz
diagVec[11] = 0.01; // rho_v_1_1 = betaV
diagVec[12] = 100.; // theta_1 = theta
}
else {
#if 1
// Use same initial values as matlab code, for debug
totalInitialVec[ 0] = 2.9701e+04; // lambda_eta = lamWOs
totalInitialVec[ 1] = 1.; // lambda_w_1 = lamUz
totalInitialVec[ 2] = 1.; // lambda_w_2 =
totalInitialVec[ 3] = std::exp(-0.1*0.25); // rho_w_1_1 = exp(-model.betaU.*(0.5^2));
totalInitialVec[ 4] = std::exp(-0.1*0.25); // rho_w_1_2 =
totalInitialVec[ 5] = std::exp(-0.1*0.25); // rho_w_2_1 =
totalInitialVec[ 6] = std::exp(-0.1*0.25); // rho_w_2_2 =
totalInitialVec[ 7] = 1000.; // lambda_s_1 = lamWs
totalInitialVec[ 8] = 1000.; // lambda_s_2 =
#endif
diagVec[ 0] = 2500.; // lambda_eta = lamWOs
diagVec[ 1] = 0.09; // lambda_w_1 = lamUz
diagVec[ 2] = 0.09; // lambda_w_2 =
diagVec[ 3] = 0.01; // rho_w_1_1 = betaU
diagVec[ 4] = 0.01; // rho_w_1_2 =
diagVec[ 5] = 0.01; // rho_w_2_1 =
diagVec[ 6] = 0.01; // rho_w_2_2 =
diagVec[ 7] = 2500.; // lambda_s_1 = lamWs
diagVec[ 8] = 2500; // lambda_s_2 =
}
uqGslMatrixClass totalInitialProposalCovMatrix(diagVec); // todo_r
if (useML) {
gcm->calibrateWithBayesMLSampling();
}
else {
gcm->calibrateWithBayesMetropolisHastings(NULL,totalInitialVec,&totalInitialProposalCovMatrix);
}
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": finished calibrating 'gcm'"
<< std::endl;
}
//***********************************************************************
// Step 09 of 09: Make predictions with the calibrated computer model
// Substep 09a: predict 'v' and 'u' weights
// Substep 09b: predict 'w' weights
// Substep 09c: predict new experiment results
// Substep 09d: predict new simulation outputs
//***********************************************************************
unsigned int dim1 = 16;
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> predictionGrid1Space(env, "predictionGrid1_", dim1, NULL);
uqGslVectorClass predictionGrid1Vec(predictionGrid1Space.zeroVector());
for (unsigned int i = 0; i < dim1; ++i) {
predictionGrid1Vec[i] = ((double) i)/((double) (dim1-1));
}
unsigned int dim2 = 16;
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> predictionGrid2Space(env, "predictionGrid2_", dim2, NULL);
uqGslVectorClass predictionGrid2Vec(predictionGrid2Space.zeroVector());
for (unsigned int j = 0; j < dim2; ++j) {
predictionGrid2Vec[j] = ((double) j)/((double) (dim2-1));
}
if (env.fullRank() == 0) { // Yes, only one processor in all 'full' communicator
std::set<unsigned int> tmpSet;
tmpSet.insert(0);
predictionGrid1Vec.subWriteContents("towerPredictionGrid1", // varNamePrefix,
"predictionGrid1",
"m",
tmpSet); // allowedSubEnvIds
predictionGrid2Vec.subWriteContents("towerPredictionGrid2", // varNamePrefix,
"predictionGrid2",
"m",
tmpSet); // allowedSubEnvIds
}
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> paper_p_eta_space(env, "paper_p_eta_", paper_p_eta, NULL); // = gcm->unique_u_space() or gcm->unique_w_space()
if (useExperiments) {
#if 1 // Might put '0' while code is not finished
//***********************************************************************
// Substep 09a of 09: Predict 'v' and 'u' weights
//***********************************************************************
uqGslVectorClass tmpExperimentScenarioVec (paper_p_x_space.zeroVector());
uqGslVectorClass tmpSimulationParameterVec(paper_p_t_space.zeroVector());
unsigned int paper_p_delta = 13; // todo_rr: repeated
uqVectorSpaceClass<uqGslVectorClass,uqGslMatrixClass> paper_p_delta_space(env, "paper_p_delta_space", paper_p_delta, NULL); // todo_rr: repeated // = gcm_unique_v_space()
std::vector<uqGslMatrixClass* > predictionGridVMats(paper_p_delta,NULL);
for (unsigned int k = 0; k < paper_p_delta; ++k) {
predictionGridVMats[k] = new uqGslMatrixClass(predictionGrid1Space.zeroVector());
}
std::vector<uqGslMatrixClass* > predictionGridUMats(paper_p_eta,NULL);
for (unsigned int k = 0; k < paper_p_eta; ++k) {
predictionGridUMats[k] = new uqGslMatrixClass(predictionGrid1Space.zeroVector());
}
uqGslVectorClass vuMeanVec (gcm->unique_vu_space().zeroVector());
uqGslMatrixClass vuCovMatrix(gcm->unique_vu_space().zeroVector());
uqGslVectorClass vMeanVec (paper_p_delta_space.zeroVector());
uqGslMatrixClass vCovMatrix (paper_p_delta_space.zeroVector());
uqGslVectorClass uMeanVec (paper_p_eta_space.zeroVector());
uqGslMatrixClass uCovMatrix (paper_p_eta_space.zeroVector());
for (unsigned int i = 0; i < dim1; ++i) {
tmpExperimentScenarioVec[0] = predictionGrid1Vec[i];
for (unsigned int j = 0; j < dim2; ++j) {
tmpSimulationParameterVec[0] = predictionGrid2Vec[j];
#if 1
gcm->predictVUsAtGridPoint(tmpExperimentScenarioVec,
tmpSimulationParameterVec,
vuMeanVec,
vuCovMatrix,
vMeanVec,
vCovMatrix,
uMeanVec,
uCovMatrix);
#endif
for (unsigned int k = 0; k < paper_p_delta; ++k) {
(*predictionGridVMats[k])(i,j) = vMeanVec[k];
}
for (unsigned int k = 0; k < paper_p_eta; ++k) {
(*predictionGridUMats[k])(i,j) = uMeanVec[k];
}
}
}
if (env.fullRank() == 0) { // Yes, only one processor in all 'full' communicator
std::set<unsigned int> tmpSet;
tmpSet.insert(0);
char varNamePrefix[32+1];
char fileName [32+1];
for (unsigned int i = 0; i < paper_p_delta; ++i) {
sprintf(varNamePrefix,"towerV%dmat",i+1);
sprintf(fileName, "v%dmat", i+1);
predictionGridVMats[i]->subWriteContents(varNamePrefix,
fileName,
"m",
tmpSet); // allowedSubEnvIds
}
for (unsigned int i = 0; i < paper_p_eta; ++i) {
sprintf(varNamePrefix,"towerU%dmat",i+1);
sprintf(fileName, "u%dmat", i+1);
predictionGridUMats[i]->subWriteContents(varNamePrefix,
fileName,
"m",
tmpSet); // allowedSubEnvIds
}
}
for (unsigned int i = 0; i < paper_p_eta; ++i) {
delete predictionGridUMats[i];
}
for (unsigned int i = 0; i < paper_p_delta; ++i) {
delete predictionGridVMats[i];
}
#endif // Might put '0'
} // if (useExperiments)
#if 1 // Might put '0' while code is not finished
//***********************************************************************
// Substep 09b of 09: Predict 'w' weights
//***********************************************************************
uqGslVectorClass tmpSimulationScenarioVec (paper_p_x_space.zeroVector());
uqGslVectorClass tmpSimulationParameterVec(paper_p_t_space.zeroVector());
uqGslVectorClass wMeanVec (paper_p_eta_space.zeroVector());
uqGslMatrixClass wCovMatrix(paper_p_eta_space.zeroVector());
#if 0 // For debug only
tmpSimulationScenarioVec [0] = 0.4;
tmpSimulationParameterVec[0] = 0.4;
uqGslVectorClass forcingSampleVecForDebug(gcm->totalSpace().zeroVector());
forcingSampleVecForDebug[ 0] = 2.9700e+04; // lambda_eta = lamWOs
forcingSampleVecForDebug[ 1] = 1.0000; // lambda_w_1 = lamUz
forcingSampleVecForDebug[ 2] = 1.0083; // lambda_w_2 =
forcingSampleVecForDebug[ 3] = std::exp(-0.1004*0.25); // rho_w_1_1 = exp(-model.betaU.*(0.5^2));
forcingSampleVecForDebug[ 4] = std::exp(-0.1022*0.25); // rho_w_1_2 =
forcingSampleVecForDebug[ 5] = std::exp(-0.1013*0.25); // rho_w_2_1 =
forcingSampleVecForDebug[ 6] = std::exp(-0.1011*0.25); // rho_w_2_2 =
forcingSampleVecForDebug[ 7] = 999.5113; // lambda_s_1 = lamWs
forcingSampleVecForDebug[ 8] = 999.3138; // lambda_s_2 =
forcingSampleVecForDebug[ 9] = 996.6176; // lambda_y = lamOs
forcingSampleVecForDebug[10] = 20.0194; // lambda_v_1 = lamVz
forcingSampleVecForDebug[11] = std::exp(-0.1020*0.25); // rho_v_1_1 = betaV
forcingSampleVecForDebug[12] = 0.5000; // theta_1 = theta
gcm->predictWsAtGridPoint(tmpSimulationScenarioVec,
tmpSimulationParameterVec,
&forcingSampleVecForDebug,
wMeanVec,
wCovMatrix);
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": for scenario = " << tmpSimulationScenarioVec [0]
<< " and parameter = " << tmpSimulationParameterVec[0]
<< ", wMeanVec = " << wMeanVec
<< ", wCovMatrix = " << wCovMatrix
<< std::endl;
}
env.fullComm().Barrier();
sleep(1);
exit(1);
#endif
std::vector<uqGslMatrixClass* > predictionGridWMats(paper_p_eta,NULL);
for (unsigned int k = 0; k < paper_p_eta; ++k) {
predictionGridWMats[k] = new uqGslMatrixClass(env,predictionGrid1Space.map(),dim2);
}
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": beginning loop on predictions"
<< ", dim1 = " << dim1
<< ", dim2 = " << dim2
<< std::endl;
}
for (unsigned int i = 0; i < dim1; ++i) {
tmpSimulationScenarioVec[0] = predictionGrid1Vec[i];
for (unsigned int j = 0; j < dim2; ++j) {
tmpSimulationParameterVec[0] = predictionGrid2Vec[j];
struct timeval timevalBeforePredict;
int iRC = gettimeofday(&timevalBeforePredict, NULL);
if (iRC) {}; // just to remove compiler warning
gcm->predictWsAtGridPoint(tmpSimulationScenarioVec,
tmpSimulationParameterVec,
NULL,
wMeanVec,
wCovMatrix);
double predictTime = uqMiscGetEllapsedSeconds(&timevalBeforePredict);
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 3)) {
*env.subDisplayFile() << "In compute()"
<< ": looping on predictions"
<< ", i = " << i << " < " << dim1
<< ", j = " << j << " < " << dim2
<< ", returned from 'gcm->predictWsAtGridPoint()' after " << predictTime << " seconds"
<< std::endl;
}
for (unsigned int k = 0; k < paper_p_eta; ++k) {
(*predictionGridWMats[k])(i,j) = wMeanVec[k];
}
}
}
if (env.fullRank() == 0) { // Yes, only one processor in all 'full' communicator
std::set<unsigned int> tmpSet;
tmpSet.insert(0);
char varNamePrefix[32+1];
char fileName [32+1];
for (unsigned int i = 0; i < paper_p_eta; ++i) {
sprintf(varNamePrefix,"towerW%dmat",i+1);
sprintf(fileName, "w%dmat", i+1);
predictionGridWMats[i]->subWriteContents(varNamePrefix,
fileName,
"m",
tmpSet); // allowedSubEnvIds
}
}
for (unsigned int i = 0; i < paper_p_eta; ++i) {
delete predictionGridWMats[i];
}
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "In compute()"
<< ": finished making predictions"
<< std::endl;
}
#endif // Might put '0'
#if 0 // Might put '0' while code is not finished
//***********************************************************************
// Substep 09c of 09: Predict new experiment results
//***********************************************************************
uqGslVectorClass newExperimentScenarioVec(paper_p_x_space.zeroVector()); // todo_rr
uqGslMatrixClass newKmat_interp (env,paper_n_eta_space.map(),paper_p_eta); // todo_rr
uqGslMatrixClass newDmat (env,paper_n_eta_space.map(),paper_p_delta); // todo_rr
uqGslVectorClass simulationOutputMeanVec (paper_n_eta_space.zeroVector()); // Yes, size of simulation, since it is a prediction using the emulator
uqGslVectorClass discrepancyMeanVec (paper_n_eta_space.zeroVector());
gcm->predictExperimentResults(newExperimentScenarioVec,newKmat_interp,newDmat,simulationOutputMeanVec,discrepancyMeanVec);
//***********************************************************************
// Substep 09d of 09: Predict new simulation outputs
//***********************************************************************
uqGslVectorClass newSimulationScenarioVec (paper_p_x_space.zeroVector ()); // todo_rr
uqGslVectorClass newSimulationParameterVec(paper_p_t_space.zeroVector ()); // todo_rr
uqGslVectorClass simulationOutputMeanVec2 (paper_n_eta_space.zeroVector());
gcm->predictSimulationOutputs(newSimulationScenarioVec,newSimulationParameterVec,simulationOutputMeanVec2);
#endif // Might put '0'
//***********************************************************************
// Clean memory
//***********************************************************************
env.fullComm().Barrier();
delete paramPriorRvPtr;
delete experimentModelPtr;
delete experimentStoragePtr;
for (unsigned int i = 0; i < paper_n; ++i) {
delete Kmats_interp [i];
delete Kmats_interp_spaces[i];
}
for (unsigned int i = 0; i < paper_m; ++i) {
delete outputVecs [i];
delete paramVecs [i];
delete simulationScenarios[i];
}
for (unsigned int i = 0; i < paper_n; ++i) {
delete experimentMats_transformed [i];
delete experimentMats_original [i];
delete experimentVecs_transformed [i];
delete experimentVecs_original [i];
delete experimentSpaces [i];
delete experimentScenarios_standard[i];
delete experimentScenarios_original[i];
}
delete gcm;
if ((env.subDisplayFile()) && (env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "Leaving compute()"
<< std::endl;
}
return;
}
int main(int argc, char ** argv)
{
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, "", "", NULL);
#else
QUESO::FullEnvironment env("", "", NULL);
#endif
unsigned int dim = 3;
QUESO::VectorSpace<> paramSpace(env, "param_", dim, NULL);
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins.cwSet(-INFINITY);
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs.cwSet(INFINITY);
QUESO::BoxSubset<> paramDomain("param_", paramSpace, paramMins, paramMaxs);
QUESO::GslVector mean(paramSpace.zeroVector());
QUESO::GslMatrix var(paramSpace.zeroVector());
mean[0] = 2.0;
mean[1] = 3.0;
mean[2] = 4.0;
var(0,0) = 5.0;
var(1,1) = 6.0;
var(2,2) = 7.0;
// Construct a Gaussian PDF
QUESO::GaussianJointPdf<> pdf("", paramDomain, mean, var);
// Vectors to store gradient calculations
QUESO::GslVector lnGradVector(paramSpace.zeroVector());
QUESO::GslVector gradVector(paramSpace.zeroVector());
// Where to evaluate the gradient. Evaluating at the mean (the mode for a
// Gaussian) should give a gradient consisting of a vector of zeros.
QUESO::GslVector point(mean);
// We are testing that the gradient of log of the pdf is all zeros
pdf.lnValue(point, NULL, &lnGradVector, NULL, NULL);
queso_require_less_equal_msg(std::abs(lnGradVector[0]), TOL, "grad log gaussian pdf values are incorrect");
queso_require_less_equal_msg(std::abs(lnGradVector[1]), TOL, "grad log gaussian pdf values are incorrect");
queso_require_less_equal_msg(std::abs(lnGradVector[2]), TOL, "grad log gaussian pdf values are incorrect");
// We are testing that the of the pdf is all zeros
pdf.actualValue(point, NULL, &gradVector, NULL, NULL);
queso_require_less_equal_msg(std::abs(gradVector[0]), TOL, "grad guassian pdf values are incorrect");
queso_require_less_equal_msg(std::abs(gradVector[1]), TOL, "grad guassian pdf values are incorrect");
queso_require_less_equal_msg(std::abs(gradVector[2]), TOL, "grad guassian pdf values are incorrect");
// Now construct another Gaussian. This time we're constructing a Gaussian
// that we know will have a gradient consisting entirely of ones (in log
// space).
mean[0] = 0.0;
mean[1] = 0.0;
mean[2] = 0.0;
var(0,0) = 1.0;
var(0,1) = 0.8;
var(0,2) = 0.7;
var(1,0) = 0.8;
var(1,1) = 2.0;
var(1,2) = 0.6;
var(2,0) = 0.7;
var(2,1) = 0.6;
var(2,2) = 3.0;
point[0] = -2.5;
point[1] = -3.4;
point[2] = -4.3;
QUESO::GaussianJointPdf<> pdf2("", paramDomain, mean, var);
pdf2.lnValue(point, NULL, &lnGradVector, NULL, NULL);
queso_require_less_equal_msg(std::abs(lnGradVector[0] - 1.0), TOL, "grad log gaussian pdf2 values are incorrect");
queso_require_less_equal_msg(std::abs(lnGradVector[1] - 1.0), TOL, "grad log gaussian pdf2 values are incorrect");
queso_require_less_equal_msg(std::abs(lnGradVector[2] - 1.0), TOL, "grad log gaussian pdf2 values are incorrect");
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
void compute(const QUESO::FullEnvironment& env, unsigned int numModes) {
////////////////////////////////////////////////////////
// Step 1 of 5: Instantiate the parameter space
////////////////////////////////////////////////////////
#ifdef APPLS_MODAL_USES_CONCATENATION
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix>
paramSpaceA(env, "paramA_", 2, NULL);
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix>
paramSpaceB(env, "paramB_", 1, NULL);
#endif
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix>
paramSpace(env, "param_", 3, NULL);
////////////////////////////////////////////////////////
// Step 2 of 5: Instantiate the parameter domain
////////////////////////////////////////////////////////
#ifdef APPLS_MODAL_USES_CONCATENATION
QUESO::GslVector paramMinsA(paramSpaceA.zeroVector());
paramMinsA[0] = 0.;
paramMinsA[1] = 0.;
QUESO::GslVector paramMaxsA(paramSpaceA.zeroVector());
paramMaxsA[0] = 3.;
paramMaxsA[1] = 3.;
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomainA("paramA_",paramSpaceA,paramMinsA,paramMaxsA);
QUESO::GslVector paramMinsB(paramSpaceB.zeroVector());
paramMinsB[0] = 0.;
QUESO::GslVector paramMaxsB(paramSpaceB.zeroVector());
paramMaxsB[0] = INFINITY;
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomainB("paramB_",paramSpaceB,paramMinsB,paramMaxsB);
QUESO::ConcatenationSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("",paramSpace,paramDomainA,paramDomainB);
#else
QUESO::GslVector paramMins(paramSpace.zeroVector());
paramMins[0] = 0.;
paramMins[1] = 0.;
paramMins[2] = 0.;
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMaxs[0] = 3.;
paramMaxs[1] = 3.;
paramMaxs[2] = .3;
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("param_",paramSpace,paramMins,paramMaxs);
#endif
////////////////////////////////////////////////////////
// Step 3 of 5: Instantiate the likelihood function object
////////////////////////////////////////////////////////
likelihoodRoutine_DataType likelihoodRoutine_Data;
likelihoodRoutine_Data.numModes = numModes;
QUESO::GenericScalarFunction<QUESO::GslVector,QUESO::GslMatrix>
likelihoodFunctionObj("like_",
paramDomain,
likelihoodRoutine,
(void *) &likelihoodRoutine_Data,
true); // routine computes [-2.*ln(function)]
////////////////////////////////////////////////////////
// Step 4 of 5: Instantiate the inverse problem
////////////////////////////////////////////////////////
#ifdef APPLS_MODAL_USES_CONCATENATION
QUESO::UniformVectorRV<QUESO::GslVector,QUESO::GslMatrix>
priorRvA("priorA_", paramDomainA);
QUESO::GslVector alpha(paramSpaceB.zeroVector());
alpha[0] = 3.;
QUESO::GslVector beta(paramSpaceB.zeroVector());
if (numModes == 1) {
beta[0] = 0.09709133373799;
}
else {
beta[0] = 0.08335837191688;
}
QUESO::InverseGammaVectorRV<QUESO::GslVector,QUESO::GslMatrix>
priorRvB("priorB_", paramDomainB,alpha,beta);
QUESO::ConcatenatedVectorRV<QUESO::GslVector,QUESO::GslMatrix>
priorRv("prior_", priorRvA, priorRvB, paramDomain);
#else
QUESO::UniformVectorRV<QUESO::GslVector,QUESO::GslMatrix>
priorRv("prior_", paramDomain);
#endif
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix>
postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector,QUESO::GslMatrix>
ip("", NULL, priorRv, likelihoodFunctionObj, postRv);
////////////////////////////////////////////////////////
// Step 5 of 5: Solve the inverse problem
////////////////////////////////////////////////////////
ip.solveWithBayesMLSampling();
////////////////////////////////////////////////////////
// Print some statistics
////////////////////////////////////////////////////////
unsigned int numPosTotal = postRv.realizer().subPeriod();
if (env.subDisplayFile()) {
*env.subDisplayFile() << "numPosTotal = " << numPosTotal
<< std::endl;
}
QUESO::GslVector auxVec(paramSpace.zeroVector());
unsigned int numPosTheta1SmallerThan1dot5 = 0;
for (unsigned int i = 0; i < numPosTotal; ++i) {
postRv.realizer().realization(auxVec);
if (auxVec[0] < 1.5) numPosTheta1SmallerThan1dot5++;
}
if (env.subDisplayFile()) {
*env.subDisplayFile() << "numPosTheta1SmallerThan1dot5 = " << numPosTheta1SmallerThan1dot5
<< ", ratio = " << ((double) numPosTheta1SmallerThan1dot5)/((double) numPosTotal)
<< std::endl;
}
return;
}
void computeGravityAndTraveledDistance(const QUESO::FullEnvironment& env) {
struct timeval timevalNow;
gettimeofday(&timevalNow, NULL);
if (env.fullRank() == 0) {
std::cout << "\nBeginning run of 'Gravity + Projectile motion' example at "
<< ctime(&timevalNow.tv_sec)
<< "\n my fullRank = " << env.fullRank()
<< "\n my subEnvironmentId = " << env.subId()
<< "\n my subRank = " << env.subRank()
<< "\n my interRank = " << env.inter0Rank()
<< std::endl << std::endl;
}
// Just examples of possible calls
if ((env.subDisplayFile() ) &&
(env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "Beginning run of 'Gravity + Projectile motion' example at "
<< ctime(&timevalNow.tv_sec)
<< std::endl;
}
env.fullComm().Barrier();
env.subComm().Barrier(); // Just an example of a possible call
//================================================================
// Statistical inverse problem (SIP): find posterior PDF for 'g'
//================================================================
gettimeofday(&timevalNow, NULL);
if (env.fullRank() == 0) {
std::cout << "Beginning 'SIP -> Gravity estimation' at "
<< ctime(&timevalNow.tv_sec)
<< std::endl;
}
//------------------------------------------------------
// SIP Step 1 of 6: Instantiate the parameter space
//------------------------------------------------------
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix> paramSpace(env, "param_", 1, NULL);
//------------------------------------------------------
// SIP Step 2 of 6: Instantiate the parameter domain
//------------------------------------------------------
QUESO::GslVector paramMinValues(paramSpace.zeroVector());
QUESO::GslVector paramMaxValues(paramSpace.zeroVector());
paramMinValues[0] = 8.;
paramMaxValues[0] = 11.;
QUESO::BoxSubset<QUESO::GslVector,QUESO::GslMatrix>
paramDomain("param_",
paramSpace,
paramMinValues,
paramMaxValues);
//------------------------------------------------------
// SIP Step 3 of 6: Instantiate the likelihood function
// object to be used by QUESO.
//------------------------------------------------------
likelihoodRoutine_Data likelihoodRoutine_Data(env);
QUESO::GenericScalarFunction<QUESO::GslVector,QUESO::GslMatrix>
likelihoodFunctionObj("like_",
paramDomain,
likelihoodRoutine,
(void *) &likelihoodRoutine_Data,
true); // the routine computes [ln(function)]
//------------------------------------------------------
// SIP Step 4 of 6: Define the prior RV
//------------------------------------------------------
#ifdef PRIOR_IS_GAUSSIAN
QUESO::GslVector meanVector( paramSpace.zeroVector() );
meanVector[0] = 9;
QUESO::GslMatrix covMatrix = QUESO::GslMatrix(paramSpace.zeroVector());
covMatrix(0,0) = 1.;
// Create a Gaussian prior RV
QUESO::GaussianVectorRV<QUESO::GslVector,QUESO::GslMatrix> priorRv("prior_",paramDomain,meanVector,covMatrix);
#else
// Create an uniform prior RV
QUESO::UniformVectorRV<QUESO::GslVector,QUESO::GslMatrix> priorRv("prior_",paramDomain);
#endif
//------------------------------------------------------
// SIP Step 5 of 6: Instantiate the inverse problem
//------------------------------------------------------
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix>
postRv("post_", // Extra prefix before the default "rv_" prefix
paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector,QUESO::GslMatrix>
ip("", // No extra prefix before the default "ip_" prefix
NULL,
priorRv,
likelihoodFunctionObj,
postRv);
//------------------------------------------------------
// SIP Step 6 of 6: Solve the inverse problem, that is,
// set the 'pdf' and the 'realizer' of the posterior RV
//------------------------------------------------------
std::cout << "Solving the SIP with Metropolis Hastings"
<< std::endl << std::endl;
QUESO::GslVector paramInitials(paramSpace.zeroVector());
priorRv.realizer().realization(paramInitials);
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
proposalCovMatrix(0,0) = std::pow( fabs(paramInitials[0])/20. , 2. );
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
//================================================================
// Statistical forward problem (SFP): find the max distance
// traveled by an object in projectile motion; input pdf for 'g'
// is the solution of the SIP above.
//================================================================
gettimeofday(&timevalNow, NULL);
std::cout << "Beginning 'SFP -> Projectile motion' at "
<< ctime(&timevalNow.tv_sec)
<< std::endl;
//------------------------------------------------------
// SFP Step 1 of 6: Instantiate the parameter *and* qoi spaces.
// SFP input RV = FIP posterior RV, so SFP parameter space
// has been already defined.
//------------------------------------------------------
QUESO::VectorSpace<QUESO::GslVector,QUESO::GslMatrix> qoiSpace(env, "qoi_", 1, NULL);
//------------------------------------------------------
// SFP Step 2 of 6: Instantiate the parameter domain
//------------------------------------------------------
// Not necessary because input RV of the SFP = output RV of SIP.
// Thus, the parameter domain has been already defined.
//------------------------------------------------------
// SFP Step 3 of 6: Instantiate the qoi function object
// to be used by QUESO.
//------------------------------------------------------
qoiRoutine_Data qoiRoutine_Data;
qoiRoutine_Data.m_angle = M_PI/4.0; //45 degrees (radians)
qoiRoutine_Data.m_initialVelocity= 5.; //initial speed (m/s)
qoiRoutine_Data.m_initialHeight = 0.; //initial height (m)
QUESO::GenericVectorFunction<QUESO::GslVector,QUESO::GslMatrix,QUESO::GslVector,QUESO::GslMatrix>
qoiFunctionObj("qoi_",
paramDomain,
qoiSpace,
qoiRoutine,
(void *) &qoiRoutine_Data);
//------------------------------------------------------
// SFP Step 4 of 6: Define the input RV
//------------------------------------------------------
// Not necessary because input RV of SFP = output RV of SIP
// (postRv).
//------------------------------------------------------
// SFP Step 5 of 6: Instantiate the forward problem
//------------------------------------------------------
QUESO::GenericVectorRV<QUESO::GslVector,QUESO::GslMatrix> qoiRv("qoi_", qoiSpace);
QUESO::StatisticalForwardProblem<QUESO::GslVector,QUESO::GslMatrix,QUESO::GslVector,QUESO::GslMatrix>
fp("",
NULL,
postRv,
qoiFunctionObj,
qoiRv);
//------------------------------------------------------
// SFP Step 6 of 6: Solve the forward problem
//------------------------------------------------------
std::cout << "Solving the SFP with Monte Carlo"
<< std::endl << std::endl;
fp.solveWithMonteCarlo(NULL);
//------------------------------------------------------
gettimeofday(&timevalNow, NULL);
if ((env.subDisplayFile() ) &&
(env.displayVerbosity() >= 2)) {
*env.subDisplayFile() << "Ending run of 'Gravity + Projectile motion' example at "
<< ctime(&timevalNow.tv_sec)
<< std::endl;
}
if (env.fullRank() == 0) {
std::cout << "Ending run of 'Gravity + Projectile motion' example at "
<< ctime(&timevalNow.tv_sec)
<< std::endl;
}
return;
}
void GaussianMean1DRegressionCompute(const QUESO::BaseEnvironment& env,
double priorMean, double priorVar, const likelihoodData& dat)
{
// parameter space: 1-D on (-infinity, infinity)
QUESO::VectorSpace<P_V, P_M> paramSpace(
env, // queso environment
"param_", // name prefix
1, // dimensions
NULL); // names
P_V paramMin(paramSpace.zeroVector());
P_V paramMax(paramSpace.zeroVector());
paramMin[0] = -INFINITY;
paramMax[0] = INFINITY;
QUESO::BoxSubset<P_V, P_M> paramDomain(
"paramBox_", // name prefix
paramSpace, // vector space
paramMin, // min values
paramMax); // max values
// gaussian prior with user supplied mean and variance
P_V priorMeanVec(paramSpace.zeroVector());
P_V priorVarVec(paramSpace.zeroVector());
priorMeanVec[0] = priorMean;
priorVarVec[0] = priorVar;
QUESO::GaussianVectorRV<P_V, P_M> priorRv("prior_", paramDomain, priorMeanVec,
priorVarVec);
// likelihood is important
QUESO::GenericScalarFunction<P_V, P_M> likelihoodFunctionObj(
"like_", // name prefix
paramDomain, // image set
LikelihoodFunc<P_V, P_M>, // routine
(void *) &dat, // routine data ptr
true); // routineIsForLn
QUESO::GenericVectorRV<P_V, P_M> postRv(
"post_", // name prefix
paramSpace); // image set
// Initialize and solve the Inverse Problem with Bayes multi-level sampling
QUESO::StatisticalInverseProblem<P_V, P_M> invProb(
"", // name prefix
NULL, // alt options
priorRv, // prior RV
likelihoodFunctionObj, // likelihood fcn
postRv); // posterior RV
invProb.solveWithBayesMLSampling();
// compute mean and second moment of samples on each proc via Knuth online mean/variance algorithm
int N = invProb.postRv().realizer().subPeriod();
double subMean = 0.0;
double subM2 = 0.0;
double delta;
P_V sample(paramSpace.zeroVector());
for (int n = 1; n <= N; n++) {
invProb.postRv().realizer().realization(sample);
delta = sample[0] - subMean;
subMean += delta / n;
subM2 += delta * (sample[0] - subMean);
}
// gather all Ns, means, and M2s to proc 0
std::vector<int> unifiedNs(env.inter0Comm().NumProc());
std::vector<double> unifiedMeans(env.inter0Comm().NumProc());
std::vector<double> unifiedM2s(env.inter0Comm().NumProc());
MPI_Gather(&N, 1, MPI_INT, &(unifiedNs[0]), 1, MPI_INT, 0,
env.inter0Comm().Comm());
MPI_Gather(&subMean, 1, MPI_DOUBLE, &(unifiedMeans[0]), 1, MPI_DOUBLE, 0,
env.inter0Comm().Comm());
MPI_Gather(&subM2, 1, MPI_DOUBLE, &(unifiedM2s[0]), 1, MPI_DOUBLE, 0,
env.inter0Comm().Comm());
// get the total number of likelihood calls at proc 0
unsigned long totalLikelihoodCalls = 0;
MPI_Reduce(&likelihoodCalls, &totalLikelihoodCalls, 1, MPI_UNSIGNED_LONG,
MPI_SUM, 0, env.inter0Comm().Comm());
// compute global posterior mean and std via Chan algorithm, output results on proc 0
if (env.inter0Rank() == 0) {
int postN = unifiedNs[0];
double postMean = unifiedMeans[0];
double postVar = unifiedM2s[0];
for (unsigned int i = 1; i < unifiedNs.size(); i++) {
delta = unifiedMeans[i] - postMean;
postMean = (postN * postMean + unifiedNs[i] * unifiedMeans[i]) /
(postN + unifiedNs[i]);
postVar += unifiedM2s[i] + delta * delta *
(((double)postN * unifiedNs[i]) / (postN + unifiedNs[i]));
postN += unifiedNs[i];
}
postVar /= postN;
//compute exact answer - available in this case since the exact posterior is a gaussian
N = dat.dataSet.size();
double dataSum = 0.0;
for (int i = 0; i < N; i++)
dataSum += dat.dataSet[i];
double datMean = dataSum / N;
double postMeanExact = (N * priorVar / (N * priorVar + dat.samplingVar)) *
datMean + (dat.samplingVar / (N * priorVar + dat.samplingVar)) * priorMean;
double postVarExact = 1.0 / (N / dat.samplingVar + 1.0 / priorVar);
std::cout << "Number of posterior samples: " << postN << std::endl;
std::cout << "Estimated posterior mean: " << postMean << " +/- "
<< std::sqrt(postVar) << std::endl;
std::cout << "Likelihood function calls: " << totalLikelihoodCalls
<< std::endl;
std::cout << "\nExact posterior: Gaussian with mean " << postMeanExact
<< ", standard deviation " << std::sqrt(postVarExact) << std::endl;
}
}
int main(int argc, char ** argv) {
MPI_Init(&argc, &argv);
QUESO::FullEnvironment env(MPI_COMM_WORLD, argv[1], "", NULL);
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", 2, NULL);
double min_val = 0.0;
double max_val = 1.0;
QUESO::GslVector paramMins(paramSpace.zeroVector());
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
// Model parameter between 0 and 1
paramMins[0] = 0.0;
paramMaxs[0] = 1.0;
// Hyperparameter (multiplicative coefficient of observational error
// covariance matrix) between 0.0 and \infty
paramMins[1] = 0.0;
paramMaxs[1] = INFINITY;
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
QUESO::UniformVectorRV<QUESO::GslVector, QUESO::GslMatrix> priorRv("prior_",
paramDomain);
// Set up observation space
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> obsSpace(env,
"obs_", 2, NULL);
// Fill up observation vector
QUESO::GslVector observations(obsSpace.zeroVector());
observations[0] = 1.0;
observations[1] = 1.0;
// Fill up covariance 'matrix'
QUESO::GslMatrix covariance(obsSpace.zeroVector());
covariance(0, 0) = 1.0;
covariance(0, 1) = 0.0;
covariance(1, 0) = 0.0;
covariance(1, 1) = 1.0;
// Pass in observations to Gaussian likelihood object
Likelihood<QUESO::GslVector, QUESO::GslMatrix> lhood("llhd_", paramDomain,
observations, covariance);
QUESO::GenericVectorRV<QUESO::GslVector, QUESO::GslMatrix>
postRv("post_", paramSpace);
QUESO::StatisticalInverseProblem<QUESO::GslVector, QUESO::GslMatrix>
ip("", NULL, priorRv, lhood, postRv);
QUESO::GslVector paramInitials(paramSpace.zeroVector());
paramInitials[0] = 0.0;
QUESO::GslMatrix proposalCovMatrix(paramSpace.zeroVector());
for (unsigned int i = 0; i < 1; i++) {
proposalCovMatrix(i, i) = 0.1;
}
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
MPI_Finalize();
return 0;
}
int main(int argc, char ** argv) {
// Step 0: Set up some variables
unsigned int numExperiments = 10; // Number of experiments
unsigned int numUncertainVars = 5; // Number of things to calibrate
unsigned int numSimulations = 50; // Number of simulations
unsigned int numConfigVars = 1; // Dimension of configuration space
unsigned int numEta = 1; // Number of responses the model is returning
unsigned int experimentSize = 1; // Size of each experiment
#ifdef QUESO_HAS_MPI
MPI_Init(&argc, &argv);
// Step 1: Set up QUESO environment
QUESO::FullEnvironment env(MPI_COMM_WORLD, argv[1], "", NULL);
#else
QUESO::FullEnvironment env(argv[1], "", NULL);
#endif
// Step 2: Set up prior for calibration parameters
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> paramSpace(env,
"param_", numUncertainVars, NULL);
// Parameter (theta) bounds:
// descriptors 'k_tmasl' 'k_xkle' 'k_xkwew' 'k_xkwlx' 'k_cd'
// upper_bounds 1.05 1.1 1.1 1.1 1.1
// lower_bounds 0.95 0.9 0.9 0.9 0.9
//
// These bounds are dealt with when reading in the data
QUESO::GslVector paramMins(paramSpace.zeroVector());
QUESO::GslVector paramMaxs(paramSpace.zeroVector());
paramMins.cwSet(0.0);
paramMaxs.cwSet(1.0);
QUESO::BoxSubset<QUESO::GslVector, QUESO::GslMatrix> paramDomain("param_",
paramSpace, paramMins, paramMaxs);
QUESO::UniformVectorRV<QUESO::GslVector, QUESO::GslMatrix> priorRv("prior_",
paramDomain);
// Step 3: Instantiate the 'scenario' and 'output' spaces for simulation
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> configSpace(env,
"scenario_", numConfigVars, NULL);
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> nEtaSpace(env,
"output_", numEta, NULL);
// Step 4: Instantiate the 'output' space for the experiments
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> experimentSpace(env,
"experimentspace_", experimentSize, NULL);
QUESO::VectorSpace<QUESO::GslVector, QUESO::GslMatrix> totalExperimentSpace(env,
"experimentspace_", experimentSize * numExperiments, NULL);
// Step 5: Instantiate the Gaussian process emulator object
//
// Regarding simulation scenario input values, the user should standardise
// them so that they exist inside a hypercube.
//
// Regarding simulation output data, the user should transform it so that the
// mean is zero and the variance is one.
//
// Regarding experimental scenario input values, the user should standardize
// them so that they exist inside a hypercube.
//
// Regarding experimental data, the user should transformed it so that it has
// zero mean and variance one.
// GPMSA stores all the information about our simulation
// data and experimental data. It also stores default information about the
// hyperparameter distributions.
QUESO::GPMSAFactory<QUESO::GslVector, QUESO::GslMatrix>
gpmsaFactory(env,
NULL,
priorRv,
configSpace,
paramSpace,
nEtaSpace,
experimentSpace,
numSimulations,
numExperiments);
// std::vector containing all the points in scenario space where we have
// simulations
std::vector<QUESO::GslVector *> simulationScenarios(numSimulations,
(QUESO::GslVector *) NULL);
// std::vector containing all the points in parameter space where we have
// simulations
std::vector<QUESO::GslVector *> paramVecs(numSimulations,
(QUESO::GslVector *) NULL);
// std::vector containing all the simulation output data
std::vector<QUESO::GslVector *> outputVecs(numSimulations,
(QUESO::GslVector *) NULL);
// std::vector containing all the points in scenario space where we have
// experiments
std::vector<QUESO::GslVector *> experimentScenarios(numExperiments,
(QUESO::GslVector *) NULL);
// std::vector containing all the experimental output data
std::vector<QUESO::GslVector *> experimentVecs(numExperiments,
(QUESO::GslVector *) NULL);
// The experimental output data observation error covariance matrix
QUESO::GslMatrix experimentMat(totalExperimentSpace.zeroVector());
// Instantiate each of the simulation points/outputs
for (unsigned int i = 0; i < numSimulations; i++) {
simulationScenarios[i] = new QUESO::GslVector(configSpace.zeroVector()); // 'x_{i+1}^*' in paper
paramVecs [i] = new QUESO::GslVector(paramSpace.zeroVector()); // 't_{i+1}^*' in paper
outputVecs [i] = new QUESO::GslVector(nEtaSpace.zeroVector()); // 'eta_{i+1}' in paper
}
for (unsigned int i = 0; i < numExperiments; i++) {
experimentScenarios[i] = new QUESO::GslVector(configSpace.zeroVector()); // 'x_{i+1}' in paper
experimentVecs[i] = new QUESO::GslVector(experimentSpace.zeroVector());
}
// Read in data and store the standard deviation of the simulation data. We
// will need the standard deviation when we pass the experiment error
// covariance matrix to QUESO.
double stdsim = readData(simulationScenarios,
paramVecs,
outputVecs,
experimentScenarios,
experimentVecs);
for (unsigned int i = 0; i < numExperiments; i++) {
// Passing in error of experiments (standardised).
experimentMat(i, i) = (0.025 / stdsim) * (0.025 / stdsim);
}
// Add simulation and experimental data
gpmsaFactory.addSimulations(simulationScenarios, paramVecs, outputVecs);
gpmsaFactory.addExperiments(experimentScenarios, experimentVecs, &experimentMat);
QUESO::GenericVectorRV<QUESO::GslVector, QUESO::GslMatrix> postRv(
"post_",
gpmsaFactory.prior().imageSet().vectorSpace());
QUESO::StatisticalInverseProblem<QUESO::GslVector, QUESO::GslMatrix> ip("",
NULL, gpmsaFactory, postRv);
QUESO::GslVector paramInitials(
gpmsaFactory.prior().imageSet().vectorSpace().zeroVector());
// Initial condition of the chain
// Have to set each of these by hand, *and* the sampler is sensitive to these
// values
paramInitials[0] = 0.5; // param 1
paramInitials[1] = 0.5; // param 2
paramInitials[2] = 0.5; // param 3
paramInitials[3] = 0.5; // param 4
paramInitials[4] = 0.5; // param 5
paramInitials[5] = 0.4; // not used. emulator mean
paramInitials[6] = 0.4; // emulator precision
paramInitials[7] = 0.97; // emulator corr str
paramInitials[8] = 0.97; // emulator corr str
paramInitials[9] = 0.97; // emulator corr str
paramInitials[10] = 0.97; // emulator corr str
paramInitials[11] = 0.20; // emulator corr str
paramInitials[12] = 0.80; // emulator corr str
paramInitials[13] = 10.0; // discrepancy precision
paramInitials[14] = 0.97; // discrepancy corr str
paramInitials[15] = 8000.0; // emulator data precision
QUESO::GslMatrix proposalCovMatrix(
gpmsaFactory.prior().imageSet().vectorSpace().zeroVector());
// Setting the proposal covariance matrix by hand. This requires great
// forethough, and can generally be referred to as a massive hack. These
// values were taken from the gpmsa matlab code and fiddled with.
double scale = 600.0;
proposalCovMatrix(0, 0) = 3.1646 / 10.0; // param 1
proposalCovMatrix(1, 1) = 3.1341 / 10.0; // param 2
proposalCovMatrix(2, 2) = 3.1508 / 10.0; // param 3
proposalCovMatrix(3, 3) = 0.3757 / 10.0; // param 4
proposalCovMatrix(4, 4) = 0.6719 / 10.0; // param 5
proposalCovMatrix(5, 5) = 0.1 / scale; // not used. emulator mean
proposalCovMatrix(6, 6) = 0.4953 / scale; // emulator precision
proposalCovMatrix(7, 7) = 0.6058 / scale; // emulator corr str
proposalCovMatrix(8, 8) = 7.6032e-04 / scale; // emulator corr str
proposalCovMatrix(9, 9) = 8.3815e-04 / scale; // emulator corr str
proposalCovMatrix(10, 10) = 7.5412e-04 / scale; // emulator corr str
proposalCovMatrix(11, 11) = 0.2682 / scale; // emulator corr str
proposalCovMatrix(12, 12) = 0.0572 / scale; // emulator corr str
proposalCovMatrix(13, 13) = 1.3417 / scale; // discrepancy precision
proposalCovMatrix(14, 14) = 0.3461 / scale; // discrepancy corr str
proposalCovMatrix(15, 15) = 495.3 / scale; // emulator data precision
// Square to get variances
for (unsigned int i = 0; i < 16; i++) {
proposalCovMatrix(i, i) = proposalCovMatrix(i, i) * proposalCovMatrix(i, i);
}
ip.solveWithBayesMetropolisHastings(NULL, paramInitials, &proposalCovMatrix);
#ifdef QUESO_HAS_MPI
MPI_Finalize();
#endif
return 0;
}
