typename SubstNodeScore<V,D>::value_type
SubstNodeScore<V,D>::
node_score(const Data& xx, const Data& yy,
uint i, uint j) const
{
const std::vector<Node>& x(xx.tree);
const std::vector<Node>& y(yy.tree);
value_type v_c = 0.0;
DAG::bp_freq_iterator ix,iy;
for (ix=x[i].bp_freq_begin(); ix!=x[i].bp_freq_end(); ++ix) {
rna_t a = ix->first.first;
rna_t b = ix->first.second;
value_type cx = ix->second;
for (iy=y[j].bp_freq_begin(); iy!=y[j].bp_freq_end(); ++iy) {
rna_t c = iy->first.first;
rna_t d = iy->first.second;
value_type cy = iy->second;
v_c += co_subst_[a][b][c][d]*cx*cy;
}
}
{
const Seq& x_seq(xx.seq);
const Seq& y_seq(yy.seq);
value_type nbp_x = x_seq[x[i].first()][RNA_GAP];
/*value_type nbp_x = x_seq[x[i].last()][RNA_GAP];*/
v_c += node_score(yy, j) * nbp_x / x_seq.n_seqs();
value_type nbp_y = y_seq[y[j].first()][RNA_GAP];
/*value_type nbp_y = y_seq[y[j].last()][RNA_GAP];*/
v_c += node_score(xx, i) * nbp_y / y_seq.n_seqs();
}
return v_c;
}
//-----------------------------------------------------------------------------
int main()
{
{
// Generate some data
plJointDistribution orig = make_model();
generate_data(orig, "model_asia.csv", 10000);
plCSVDataDescriptor dataset("model_asia.csv", orig.get_variables());
plNodeScoreBIC node_score(dataset);
std::cout << "Original model: " << orig << std::endl
<< "BIC score of the original model on the whole dataset: "
<< node_score(orig) << std::endl;
save("model_asia", orig);
}
plSymbol A("A", PL_BINARY_TYPE); // visit to Asia?
plSymbol S("S", PL_BINARY_TYPE); // Smoker?
plSymbol T("T", PL_BINARY_TYPE); // has Tuberculosis
plSymbol L("L", PL_BINARY_TYPE); // has Lung cancer
plSymbol B("B", PL_BINARY_TYPE); // has Bronchitis
plSymbol O("O", PL_BINARY_TYPE); // has tuberculosis Or cancer
plSymbol X("X", PL_BINARY_TYPE); // positive X-Ray
plSymbol D("D", PL_BINARY_TYPE); // Dyspnoea?
plVariablesConjunction variables = A^S^T^L^B^O^X^D;
plCSVDataDescriptor dataset("model_asia.csv", variables);
plStructureLearner learner(variables);
// Learn the dependancy structure between our variables from the
// dataset, using the Directed Maximum Spanning Tree algorithm.
unsigned int root_index = 0; // using 'A' as the root node.
std::vector<plSymbol> order;
plEdgeScoreBIC edge_score(dataset);
bool result = learner.DMST(edge_score, order, variables[root_index]);
plJointDistribution result_dmst = learner.get_joint_distribution(dataset);
// Apply the GS algorithm with BIC score on the same dataset.
// Use the output of the DMST algo as a starting point.
plNodeScoreBIC node_score(dataset);
learner.GS(node_score);
plJointDistribution result_gs = learner.get_joint_distribution(dataset);
std::cout << "DMST-BIC obtained the following model: " << result_dmst
<< std::endl
<< "BIC score of the learned model on the whole dataset: "
<< node_score(result_dmst) << std::endl;
std::cout << "DMST + GS obtained the following model: " << result_gs
<< std::endl
<< "BIC score of the learned model on the whole dataset: "
<< node_score(result_gs) << std::endl;
save("dmst_bic", result_dmst);
save("dmst-gs_bic", result_gs);
// On Windows (Visual C++, MinGW) only.
#if defined(WIN32) || defined(_WIN32)
std::cout << "Press any key to terminate..." << std::endl;
getchar();
#endif
return 0;
}
