double PDM::pdf(const Matrix &Pi, bool logscale) const {
double ans(0);
for (uint i = 0; i < Pi.nrow(); ++i) {
ans += ddirichlet(Pi.row(i), Nu().row(1), true);
}
return logscale ? ans : exp(ans);
}
Foam::tmp<Foam::volScalarField>
Foam::heatTransferModels::RanzMarshall::K() const
{
volScalarField Nu(scalar(2) + 0.6*pair_.Re()*cbrt(pair_.Pr()));
return 6.0*pair_.continuous().kappa()*Nu/sqr(pair_.dispersed().d());
}
PDM::ProductDirichletModel(const Vector &wgt, const Matrix &Pi)
: ParamPolicy(new MatrixParams(Pi)),
DataPolicy(new PDS(wgt.size())),
PriorPolicy() {
SpdMatrix W(wgt.size());
W.set_diag(wgt);
set_Nu(W * Nu());
}
void MCS::check_pi0()const{
if(!!pi0_) return;
ostringstream err;
err << "A Markov chain model has a free initial distribution "
<< "parameter (pi0) that was not assigned a prior."
<< endl
<< "Prior for transition counts was:" <<endl
<< Nu() << endl;
throw_exception<std::runtime_error>(err.str());
}
double PDM::loglike(const Vector &Nu_columns) const {
Matrix Nu(dim(), dim(), Nu_columns.data());
const Matrix &sumlog(suf()->sumlog());
double n = suf()->n();
double ans = 0;
for (uint i = 0; i < nrow(Nu); ++i)
ans += dirichlet_loglike(Nu.row(i), 0, 0, sumlog.row(i), n);
return ans;
}
void MVT::mle() {
const double eps = 1e-5;
double dloglike = eps + 1;
double loglike = this->loglike(vectorize_params());
double old = loglike;
Vector Nu(1, nu());
while (dloglike > eps) {
Estep();
mvn->mle();
MvtNuTF f(this);
loglike = max_nd1(Nu, Target(f), dTarget(f));
set_nu(Nu[0]);
dloglike = loglike - old;
old = loglike;
}
}
scalar RanzMarshall::relaxationTime
(
const scalar liquidDensity,
const scalar diameter,
const scalar liquidcL,
const scalar kappa,
const scalar ReynoldsNumber,
const scalar PrandtlNumber
) const
{
scalar time = liquidDensity*pow(diameter, 2.0)*liquidcL/(6.0*kappa*Nu(ReynoldsNumber, PrandtlNumber));
time = max(SMALL, time);
return time;
}
double PDM::dloglike(const Vector &Nu_columns, Vector &g) const {
Matrix Nu(dim(), dim(), Nu_columns.data());
const Matrix &sumlog(suf()->sumlog());
double n = suf()->n();
uint nr = nrow(Nu);
Matrix G(nr, nr);
Vector g_row(nr);
double ans = 0;
for (uint i = 0; i < nrow(Nu); ++i) {
ans += dirichlet_loglike(Nu.row(i), &g_row, 0, sumlog.row(i), n);
G.row(i) = g_row;
}
G = G.transpose();
g.assign(G.begin(), G.end());
// need to check that g is vectorized in the right way.. virtual
// functions might expect columns instead of rows.
return ans;
}
void PDPS::draw(){
const Mat & sumlog(m_->suf()->sumlog());
double nobs(m_->suf()->n());
Mat Nu(m_->Nu());
uint d= nrow(Nu);
for(uint i=0; i<d; ++i){
Vec sumlog_i(sumlog.row(i));
Vec nu(Nu.row(i));
for(uint j=0; j<d; ++j){
DirichletLogp logp(j, nu, sumlog_i, nobs,
phi_row_prior_[i], alpha_row_prior_[i],
min_nu_);
ScalarSliceSampler sam(logp, true);
sam.set_lower_limit(min_nu_);
nu[j]= sam.draw(nu[j]);
}
Nu.row(i) = nu;
}
m_->set_Nu(Nu);
}
void CEmpEdit::OnBnClickedButton5()
{
// TODO: Add
CString SqlString,s1;
CString var_name,var_id,var_sh,var_sa,var_dep;
// ( [Employee ID], [Employee Name], [Deprtment], [Shift], [Salary])
// int s;
s1.Format("INSERT INTO EmpTable ( [Employee ID], [Employee Name], [Deprtment], [Shift], [Salary] ) VALUES ( ");
int flg=0;
EID->GetWindowText(var_id);
ENA->GetWindowText(var_name);
EWO->GetWindowText(var_sh);
ESA->GetWindowText(var_sa);
EDE->GetWindowText(var_dep);
//int p=_ttoi(var_price);
CString coma(", ");
CString CB(" );");
CString Quo("'");
CString Nu(" NULL ,");
SqlString=s1+Quo+var_id+Quo+coma+Quo+var_name+Quo+coma+Quo+var_dep+Quo+coma+Quo+var_sh+Quo+coma+var_sa+CB;
try
{
database.ExecuteSQL(SqlString);
}
catch(CDBException* pe)
{
flg=1;
// The error code is in pe->m_nRetCode
pe->ReportError();
pe->Delete();
}
if (flg == 0)
{
MessageBox(_T("Record Successfully Added To The Database"),_T("Successfull"));
}
}
void DM::set_nu(const Vector &newnu) { Nu()->set(newnu); }
const Vector &DM::nu() const { return Nu()->value(); }
Matrix PDM::sim(RNG &rng) const {
uint d = dim();
Matrix ans(d, d);
for (uint i = 0; i < d; ++i) ans.row(i) = rdirichlet_mt(rng, Nu().row(i));
return ans;
}
uint PDM::dim() const { return Nu().nrow(); }
