int MoveScaleTree::move()
{
numcalls++;
// Propose to change all nodes and recedges by a scaled amount
RecTree * rectree=param->getRecTree();
double lprior=rectree->prior(param)+param->logPriorOfRho()+param->logPriorOfTheta();
// update the tree
double logscale=param->getScaleTreeSize() *(gsl_rng_uniform(rng) * 2.0 -1.0);
double scale =exp(logscale);
dlog(1)<<"Proposing to scale tree TMRCA by "<<scale<<"...";
scaleTree(scale);
param->setRho(param->getRho()/scale);
param->setTheta(param->getTheta()/scale);
double newlprior=rectree->prior(param) + param->logPriorOfRho() + param->logPriorOfTheta();
if(log(gsl_rng_uniform(rng))>newlprior-lprior+(2.0*rectree->numRecEdge()+rectree->getN()-3.0)*logscale)
{
dlog(1)<<" Rejected!"<<endl;
scaleTree(1.0/scale);
param->setRho(param->getRho()*scale);
param->setTheta(param->getTheta()*scale);
#if defined DEBUG
//test its still ok
int tmp=0;
for (int i=0; i<param->getData()->getL(); i++)
if(fround(param->getLLsite(i),5)!=fround(store[i],5))
{
tmp=1;
cout<<"Site "<<i<<" has ll before "<<store[i]<<" and after "<<param->getLLsite(i)<<" ";
for (int j=0; j<rectree->numRecEdge(); j++)
{
if (rectree->getRecEdge(j)->affectsSite(i))
cout<<j<<" ";
}
cout<<endl;
}
if(fround(ll,5)!=fround(param->getLL(),5))
{
cout<<"Total ll before "<<ll<<" and after "<<param->getLL()<<endl;
}
try
{
param->testTree();
}
catch(char * x)
{
cout<<x<<endl<<"Movescaletree restore: broke the log liks"<<endl;
exit(1);
}
if(tmp==1)
{
cerr<<"Problem replacing after move"<<endl;
throw("Move not reversed correctly");
}
#endif
return(0);
}
else dlog(1)<<" Accepted!"<<endl;// accept the modified tree
numaccept++;
return(1);
}
void
TreeCanvas::zoomToFit(void) {
QMutexLocker locker(&layoutMutex);
if (root != NULL) {
BoundingBox bb;
bb = root->getBoundingBox();
QWidget* p = parentWidget();
if (p) {
double newXScale =
static_cast<double>(p->width()) / (bb.right - bb.left +
Layout::extent);
double newYScale =
static_cast<double>(p->height()) / (root->getShape()->depth() *
Layout::dist_y +
2*Layout::extent);
int scale0 = static_cast<int>(std::min(newXScale, newYScale)*100);
if (scale0<LayoutConfig::minScale)
scale0 = LayoutConfig::minScale;
if (scale0>LayoutConfig::maxAutoZoomScale)
scale0 = LayoutConfig::maxAutoZoomScale;
if (!smoothScrollAndZoom) {
scaleTree(scale0);
} else {
zoomTimeLine.stop();
int zoomCurrent = static_cast<int>(scale*100);
int targetZoom = scale0;
targetZoom = std::min(std::max(targetZoom, LayoutConfig::minScale),
LayoutConfig::maxAutoZoomScale);
zoomTimeLine.setFrameRange(zoomCurrent,targetZoom);
zoomTimeLine.start();
}
}
}
}
void
TreeCanvas::wheelEvent(QWheelEvent* event) {
if (event->modifiers() & Qt::ShiftModifier) {
event->accept();
if (event->orientation() == Qt::Vertical && !autoZoom)
scaleTree(scale*100+ceil(static_cast<double>(event->delta())/4.0),
event->x(), event->y());
} else {
event->ignore();
}
}
void
TreeCanvas::timerEvent(QTimerEvent* e) {
if (e->timerId() == layoutDoneTimerId) {
if (!smoothScrollAndZoom) {
scaleTree(targetScale);
} else {
zoomTimeLine.stop();
int zoomCurrent = static_cast<int>(scale*100);
int targetZoom = targetScale;
targetZoom = std::min(std::max(targetZoom, LayoutConfig::minScale),
LayoutConfig::maxAutoZoomScale);
zoomTimeLine.setFrameRange(zoomCurrent,targetZoom);
zoomTimeLine.start();
}
QWidget::update();
killTimer(layoutDoneTimerId);
layoutDoneTimerId = 0;
}
}
void updateWeightsAndTrim( int treeidx, vector<int>& sidx )
{
int i, n = (int)w->sidx.size();
int nvars = (int)varIdx.size();
double sumw = 0., C = 1.;
cv::AutoBuffer<double> buf(n + nvars);
double* result = buf.data();
float* sbuf = (float*)(result + n);
Mat sample(1, nvars, CV_32F, sbuf);
int predictFlags = bparams.boostType == Boost::DISCRETE ? (PREDICT_MAX_VOTE | RAW_OUTPUT) : PREDICT_SUM;
predictFlags |= COMPRESSED_INPUT;
for( i = 0; i < n; i++ )
{
w->data->getSample(varIdx, w->sidx[i], sbuf );
result[i] = predictTrees(Range(treeidx, treeidx+1), sample, predictFlags);
}
// now update weights and other parameters for each type of boosting
if( bparams.boostType == Boost::DISCRETE )
{
// Discrete AdaBoost:
// weak_eval[i] (=f(x_i)) is in {-1,1}
// err = sum(w_i*(f(x_i) != y_i))/sum(w_i)
// C = log((1-err)/err)
// w_i *= exp(C*(f(x_i) != y_i))
double err = 0.;
for( i = 0; i < n; i++ )
{
int si = w->sidx[i];
double wval = w->sample_weights[si];
sumw += wval;
err += wval*(result[i] != w->cat_responses[si]);
}
if( sumw != 0 )
err /= sumw;
C = -log_ratio( err );
double scale = std::exp(C);
sumw = 0;
for( i = 0; i < n; i++ )
{
int si = w->sidx[i];
double wval = w->sample_weights[si];
if( result[i] != w->cat_responses[si] )
wval *= scale;
sumw += wval;
w->sample_weights[si] = wval;
}
scaleTree(roots[treeidx], C);
}
else if( bparams.boostType == Boost::REAL || bparams.boostType == Boost::GENTLE )
{
// Real AdaBoost:
// weak_eval[i] = f(x_i) = 0.5*log(p(x_i)/(1-p(x_i))), p(x_i)=P(y=1|x_i)
// w_i *= exp(-y_i*f(x_i))
// Gentle AdaBoost:
// weak_eval[i] = f(x_i) in [-1,1]
// w_i *= exp(-y_i*f(x_i))
for( i = 0; i < n; i++ )
{
int si = w->sidx[i];
CV_Assert( std::abs(w->ord_responses[si]) == 1 );
double wval = w->sample_weights[si]*std::exp(-result[i]*w->ord_responses[si]);
sumw += wval;
w->sample_weights[si] = wval;
}
}
else if( bparams.boostType == Boost::LOGIT )
{
// LogitBoost:
// weak_eval[i] = f(x_i) in [-z_max,z_max]
// sum_response = F(x_i).
// F(x_i) += 0.5*f(x_i)
// p(x_i) = exp(F(x_i))/(exp(F(x_i)) + exp(-F(x_i))=1/(1+exp(-2*F(x_i)))
// reuse weak_eval: weak_eval[i] <- p(x_i)
// w_i = p(x_i)*1(1 - p(x_i))
// z_i = ((y_i+1)/2 - p(x_i))/(p(x_i)*(1 - p(x_i)))
// store z_i to the data->data_root as the new target responses
const double lb_weight_thresh = FLT_EPSILON;
const double lb_z_max = 10.;
for( i = 0; i < n; i++ )
{
int si = w->sidx[i];
sumResult[i] += 0.5*result[i];
double p = 1./(1 + std::exp(-2*sumResult[i]));
double wval = std::max( p*(1 - p), lb_weight_thresh ), z;
w->sample_weights[si] = wval;
sumw += wval;
if( w->ord_responses[si] > 0 )
{
z = 1./p;
w->ord_responses[si] = std::min(z, lb_z_max);
}
else
{
z = 1./(1-p);
w->ord_responses[si] = -std::min(z, lb_z_max);
}
}
}
else
CV_Error(CV_StsNotImplemented, "Unknown boosting type");
/*if( bparams.boostType != Boost::LOGIT )
{
double err = 0;
for( i = 0; i < n; i++ )
{
sumResult[i] += result[i]*C;
if( bparams.boostType != Boost::DISCRETE )
err += sumResult[i]*w->ord_responses[w->sidx[i]] < 0;
else
err += sumResult[i]*w->cat_responses[w->sidx[i]] < 0;
}
printf("%d trees. C=%.2f, training error=%.1f%%, working set size=%d (out of %d)\n", (int)roots.size(), C, err*100./n, (int)sidx.size(), n);
}*/
// renormalize weights
if( sumw > FLT_EPSILON )
normalizeWeights();
if( bparams.weightTrimRate <= 0. || bparams.weightTrimRate >= 1. )
return;
for( i = 0; i < n; i++ )
result[i] = w->sample_weights[w->sidx[i]];
std::sort(result, result + n);
// as weight trimming occurs immediately after updating the weights,
// where they are renormalized, we assume that the weight sum = 1.
sumw = 1. - bparams.weightTrimRate;
for( i = 0; i < n; i++ )
{
double wval = result[i];
if( sumw <= 0 )
break;
sumw -= wval;
}
double threshold = i < n ? result[i] : DBL_MAX;
sidx.clear();
for( i = 0; i < n; i++ )
{
int si = w->sidx[i];
if( w->sample_weights[si] >= threshold )
sidx.push_back(si);
}
}
