void DecisionTree::computeTree(Pool& pool)
{
double max =0;
int varChosen=0;
std::vector<int> occurrencesInResp(pool.levelSize());
for(int j=0;j<pool.levelSize();j++)
occurrencesInResp[j] = pool.idxs(j).size();
double firstTerm = entropy(occurrencesInResp,pool.sampleSize());
for(int i=0;i<matComp.size();i++)
{
double calc = infoGain(matComp[i],pool,firstTerm);
if(calc>=max)
{
max = calc;
varChosen = i;
}
}
if(max>0)
{
pool.setVarIdx(varChosen);
pool.setInfoGain(max);
int splits = matComp[varChosen].levelSize();
for(int j=0;j<splits;j++)
{
std::vector<int> descIdxs = matComp[varChosen].idxs(j);
std::vector<int> respIdxs = pool.allIdxs();
std::vector<int> intersec;
intersec.reserve(pool.sampleSize());
std::set_intersection(descIdxs.begin(),descIdxs.end(),respIdxs.begin(),
respIdxs.end(),std::back_inserter(intersec));
pool.add_node(Pool(intersec,pool.labsFromIdx(intersec),matComp[varChosen].getLevel(j)));
Pool& poolToCheck = pool.getNext(j);
if(poolToCheck.levelSize()<=1)
continue;
else
computeTree(poolToCheck);
}
}
}
void RandomForest::recAssignNode(Node* pNode, vector<pair<int,int> >& idx_orig, string pre, int depth, int& node_cnt, double& tree_gini) {
double best_ig=-1;
int best_attr=-1;
bool rand_best_f = false;
double best_cutVal=0.5;
vector<vector<int> > best_a_l_cnt(2,vector<int>(2,0));
vector<pair<int,int> > idx0, idx1;
idx0.empty();
idx1.empty();
pNode->node0 = NULL;
pNode->node1 = NULL;
vector<int> features;
int feature_sample_cnt = (int)((double)base_feature_sample_cnt_ * pow(progressive_factor_,depth));
if(feature_sample_cnt > good_features_.size()) feature_sample_cnt = good_features_.size();
create_feature_list(features, feature_sample_cnt, good_features_);
if(debug && 0) {
int last=-1;
for(int i=0; i<features.size(); i++) {
if(features[i] == last) cerr << endl << "ERROR: repeat feature" << endl;
last = features[i];
cerr << features[i] << ",";
}
cerr << endl;
}
vector<vector<int> > a_l_cnt(2,vector<int>(2,0));
double cutVal;
double ig=-1;
int approach = 1;
vector<f_ig_cut> vBestF;
int step_size = (int)(0.01*(double)idx_orig.size());
if(step_size < 1) step_size = 1;
for(int attr_idx = 0; attr_idx < feature_sample_cnt; attr_idx++) {
//double cutVal = (double)((rand() % 1000)+1)/(double)(1001);
//cerr << features[attr_idx] << ":" << pXD_->attr_class[features[attr_idx]] << ":" << pXD_->attr_class.size() << endl;
if(pXD_->attr_class[features[attr_idx]] == 1 and approach == 1) {
double best_ig = -1;
vector<pair<int,double> > attr_sort_idx(idx_orig.size(),pair<int,double>(0,0.0));
a_l_cnt.assign(2,vector<int>(2,0));
for(int exi = 0; exi < idx_orig.size(); exi++) {
attr_sort_idx[exi] = pair<int,double>(exi,pXD_->trn_attr[idx_orig[exi].first][features[attr_idx]]);
a_l_cnt[1][(int)pXD_->trn_labl[idx_orig[exi].first]] += idx_orig[exi].second;
}
sort(attr_sort_idx.begin(),attr_sort_idx.end(),idx_double_sort);
int ex_id, ex_id_next, ex_cnt, labl;
double attr_val;
for(int exii = 0; exii < (attr_sort_idx.size()-step_size); exii++) {
ex_id = idx_orig[attr_sort_idx[exii].first].first;
ex_id_next = idx_orig[attr_sort_idx[exii+step_size].first].first;
ex_cnt = idx_orig[attr_sort_idx[exii].first].second;
labl = (int)pXD_->trn_labl[ex_id];
attr_val = pXD_->trn_attr[ex_id][features[attr_idx]];
a_l_cnt[0][labl] += ex_cnt;
a_l_cnt[1][labl] -= ex_cnt;
if (pXD_->trn_attr[ex_id_next][features[attr_idx]] == attr_val || (exii % step_size) != 0) continue;
ig = infoGain(a_l_cnt);
if(ig>best_ig) {
best_ig = ig;
cutVal = attr_val; //be sure to cut at <= cutVal or > cutVal
}
}
ig = best_ig;
} else {
a_l_cnt.assign(2,vector<int>(2,0));
if(approach == 1 || approach == 2) {
cutVal = pXD_->attr_avg[features[attr_idx]];
} else {
cutVal = (double)((rand() % 1000)+1)/(double)(1001);
}
int attr_split;
for(int exi = 0; exi < idx_orig.size(); exi++) {
attr_split = (pXD_->trn_attr[idx_orig[exi].first][features[attr_idx]] > cutVal) ? 1 : 0;
a_l_cnt[attr_split][(int)pXD_->trn_labl[idx_orig[exi].first]] += idx_orig[exi].second;
}
ig = infoGain(a_l_cnt);
}
if(rand_best_f) {
f_ig_cut newcut;
newcut.ig = ig;
newcut.attr = features[attr_idx];
newcut.cutVal = cutVal;
newcut.a_l_cnt = a_l_cnt;
vBestF.push_back(newcut);
}
if(ig > best_ig) {
best_ig = ig;
best_attr = features[attr_idx];
best_cutVal = cutVal;
best_a_l_cnt = a_l_cnt;
}
//cerr << features[attr_idx] << "," << pXD_->attr_class[features[attr_idx]] << "," << ig << endl;
}
if(rand_best_f) {
sort(vBestF.begin(), vBestF.end(), f_ig_cut_sort);
int id = (int)(pow((double)(rand() % 1000)/1000.0,11) * 3 /*vBestF.size()*/);
//cerr << id << endl;
//cerr << vBestF[0].ig << "," << best_ig << endl;
best_ig = vBestF[id].ig;
best_attr = vBestF[id].attr;
best_cutVal = vBestF[id].cutVal;
best_a_l_cnt = vBestF[id].a_l_cnt;
}
pNode->ig = best_ig;
pNode->attr_id = best_attr;
pNode->cutVal = best_cutVal;
pNode->a_l_cnt = best_a_l_cnt;
int cnt_a1=0, cnt_a0=0, onesCnt_a1=0, onesCnt_a0=0;
for(int exi = 0; exi < idx_orig.size(); exi++) {
if(pXD_->trn_attr[idx_orig[exi].first][best_attr] > best_cutVal) {
idx1.push_back(idx_orig[exi]);
onesCnt_a1 += (pXD_->trn_labl[idx_orig[exi].first] > 0.5) ? idx_orig[exi].second : 0;
cnt_a1 += idx_orig[exi].second;
} else {
idx0.push_back(idx_orig[exi]);
onesCnt_a0 += (pXD_->trn_labl[idx_orig[exi].first] > 0.5) ? idx_orig[exi].second : 0;
cnt_a0 += idx_orig[exi].second;
}
}
//double ls1=1, ls2=2; // laplace smoothing to avoid infinite values
double ls1=0, ls2=0; // laplace smoothing to avoid infinite values
if(cnt_a0 > 0) pNode->class_a0 = ((double)onesCnt_a0 + ls1)/((double)cnt_a0 + ls2);
else pNode->class_a0 = 0.5;
if(cnt_a1 > 0) pNode->class_a1 = ((double)onesCnt_a1 + ls1)/((double)cnt_a1 + ls2);
else pNode->class_a1 = 0.5;
pNode->exCnt = cnt_a0 + cnt_a1;
/*
cerr << pre << idx_orig.size() << "," << best_attr << "(" << pXD_->attr_class[best_attr] << ")," << best_ig << ","
<< idx0.size() << "," << pNode->class_a0 << ","
<< idx1.size() << "," << pNode->class_a1 << endl;
*/
{
int ls1=0, ls2=0;
if(best_ig > 0 or (feature_sample_cnt < good_features_.size() and progressive_factor_ > 1)) {
if(idx0.size() > 1 and onesCnt_a0 != 0 and onesCnt_a0 != cnt_a0) {
pNode->node0 = new Node;
recAssignNode(pNode->node0, idx0, pre + " ", depth+1, node_cnt, tree_gini);
} else {
if(cnt_a0 > 0) {
node_cnt++;
tree_gini += (double)(cnt_a0*2*(cnt_a0-onesCnt_a0+ls1)*(onesCnt_a0+ls1)) / (double)((cnt_a0 + ls2)*(cnt_a0 + ls2));
}
}
if(idx1.size() > 1 and onesCnt_a1 != 0 and onesCnt_a1 != cnt_a1) {
pNode->node1 = new Node;
recAssignNode(pNode->node1, idx1, pre + " ", depth+1, node_cnt, tree_gini);
} else {
if(cnt_a1 > 0) {
node_cnt++;
tree_gini += (double)(cnt_a1*2*(cnt_a1-onesCnt_a1+ls1)*(onesCnt_a1+ls1)) / (double)((cnt_a1 + ls2)*(cnt_a1+ls2));
}
}
} else {
if(cnt_a0 > 0) {
node_cnt += 1;
tree_gini += (double)(cnt_a0*2*(cnt_a0-onesCnt_a0+ls1)*(onesCnt_a0+ls1)) / (double)((cnt_a0 + ls2)*(cnt_a0+ls2));
}
if(cnt_a1 > 0) {
node_cnt += 1;
tree_gini += (double)(cnt_a1*2*(cnt_a1-onesCnt_a1+ls1)*(onesCnt_a1+ls1)) / (double)((cnt_a1 + ls2)*(cnt_a1+ls2));
}
}
}
}
