本文整理汇总了C++中TRandom3::Binomial方法的典型用法代码示例。如果您正苦于以下问题：C++ TRandom3::Binomial方法的具体用法？C++ TRandom3::Binomial怎么用？C++ TRandom3::Binomial使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类TRandom3的用法示例。
在下文中一共展示了TRandom3::Binomial方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的C++代码示例。
示例1: main
int main() {
TRandom3 u;
u.SetSeed(0);
vector <double> s_vec;
vector <double> mu_vec;
//Starting values for the param
//----------------------------
double start_s, start_mu;
start_s=10;
start_mu=1;
s_vec.push_back(start_s); mu_vec.push_back(start_mu);
// Read the data data are the observables, fdata the density evaluated at data
//-------------
vector<double> data;
vector<double> fdata;
double temp_data,temp_fdata;
ifstream file("data.txt");
while (!file.eof()) {
file >> temp_data >> temp_fdata;
data.push_back(temp_data); fdata.push_back(temp_fdata);
}
data.pop_back(); fdata.pop_back();
//Function for likelihood
//---------------------
TF1* f1 = new TF1("density",density,-20,20,2);
const int nMCmax=1000;
//MCMC running
//-----------
for (int nMC=0; nMC<nMCmax; nMC++){
double width=.1;
s_vec.push_back(s_vec[nMC]+width*u.Gaus(0,1));
mu_vec.push_back(mu_vec[nMC]+width*u.Gaus(0,1));
double like_i=0; double like_f=0;
for (int k=0; k<data.size(); k++){
//initial likelihood
//------------------
f1->SetParameter(0,s_vec[nMC]); f1->SetParameter(1,mu_vec[nMC]);
like_i=like_i+log(f1->Eval(data[k]));
//cout << k << " " << like_i<< " " <<data[k] << endl;
//final likelihood
//------------------
f1->SetParameter(0,s_vec[nMC+1]); f1->SetParameter(1,mu_vec[nMC+1]);
like_f=like_f+log(f1->Eval(data[k]));
}
//cout << like_i<<" "<<like_f<<" " <<s_vec[nMC]<<" " << s_vec[nMC+1]<<" " <<mu_vec[nMC]<<" " << mu_vec[nMC+1]<< endl;
//Acceptance probability
//----------------------
double prob_ratio=exp(like_f-like_i);
double accept=TMath::Min(1.,prob_ratio);
if (u.Binomial(1,accept)==0) {
s_vec.pop_back(); mu_vec.pop_back();
s_vec.push_back(s_vec[nMC]); mu_vec.push_back(mu_vec[nMC]);
}
cout <<accept << " " << prob_ratio<<" " << like_i<<" "<<like_f<< " " <<s_vec[nMC]<<" " << s_vec[nMC+1]<<" " <<mu_vec[nMC]<<" " << mu_vec[nMC+1]<< endl;
//cout << like_i<<" "<<like_f<<" " <<s_vec[nMC]<<" " << s_vec[nMC+1]<<" " <<mu_vec[nMC]<<" " << mu_vec[nMC+1]<< endl;
}
//End of MCMC running
//-----------
double s_tabl[nMCmax+1]; double mu_tabl[nMCmax+1];
double nMC_tabl[nMCmax+1];
for (int k=0; k<=nMCmax; k++) {
nMC_tabl[k]=k;
s_tabl[k]=s_vec[k]; mu_tabl[k]=mu_vec[k];
}
TGraph *gr_s = new TGraph (nMCmax, nMC_tabl, s_tabl);
gr_s->SetLineColor(kRed);
gr_s->SetLineWidth(2);
gr_s->SetName("Sigma");
TGraph *gr_mu = new TGraph (nMCmax, nMC_tabl, mu_tabl);
gr_mu->SetLineColor(kBlue);
gr_mu->SetLineWidth(2);
gr_mu->SetName("Mean");
TFile f("graph_MCMC_simplified.root","recreate");
gr_s->Write(); gr_mu->Write();
f.Close();
return 0;
}