void FilterBoostLearner::run(const nor_utils::Args& args)
{
// load the arguments
this->getArgs(args);
time_t startTime, currentTime;
time(&startTime);
// get the registered weak learner (type from name)
BaseLearner* pWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
// initialize learning options; normally it's done in the strong loop
// also, here we do it for Product learners, so input data can be created
pWeakHypothesisSource->initLearningOptions(args);
BaseLearner* pConstantWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner("ConstantLearner");
// get the training input data, and load it
InputData* pTrainingData = pWeakHypothesisSource->createInputData();
pTrainingData->initOptions(args);
pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);
const int numClasses = pTrainingData->getNumClasses();
const int numExamples = pTrainingData->getNumExamples();
//initialize the margins variable
_margins.resize( numExamples );
for( int i=0; i<numExamples; i++ )
{
_margins[i].resize( numClasses );
fill( _margins[i].begin(), _margins[i].end(), 0.0 );
}
// get the testing input data, and load it
InputData* pTestData = NULL;
if ( !_testFileName.empty() )
{
pTestData = pWeakHypothesisSource->createInputData();
pTestData->initOptions(args);
pTestData->load(_testFileName, IT_TEST, _verbose);
}
// The output information object
OutputInfo* pOutInfo = NULL;
if ( !_outputInfoFile.empty() )
{
// Baseline: constant classifier - goes into 0th iteration
BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
pConstantWeakHypothesis->initLearningOptions(args);
pConstantWeakHypothesis->setTrainingData(pTrainingData);
AlphaReal constantEnergy = pConstantWeakHypothesis->run();
pOutInfo = new OutputInfo(args);
pOutInfo->initialize(pTrainingData);
updateMargins( pTrainingData, pConstantWeakHypothesis );
if (pTestData)
pOutInfo->initialize(pTestData);
pOutInfo->outputHeader(pTrainingData->getClassMap() );
pOutInfo->outputIteration(-1);
pOutInfo->outputCustom(pTrainingData, pConstantWeakHypothesis);
if (pTestData)
{
pOutInfo->separator();
pOutInfo->outputCustom(pTestData, pConstantWeakHypothesis);
}
pOutInfo->outputCurrentTime();
pOutInfo->endLine();
pOutInfo->initialize(pTrainingData);
if (pTestData)
pOutInfo->initialize(pTestData);
}
// reload the previously found weak learners if -resume is set.
// otherwise just return 0
int startingIteration = resumeWeakLearners(pTrainingData);
Serialization ss(_shypFileName, _isShypCompressed );
ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called
// perform the resuming if necessary. If not it will just return
resumeProcess(ss, pTrainingData, pTestData, pOutInfo);
if (_verbose == 1)
cout << "Learning in progress..." << endl;
///////////////////////////////////////////////////////////////////////
// Starting the AdaBoost main loop
///////////////////////////////////////////////////////////////////////
for (int t = startingIteration; t < _numIterations; ++t)
{
if (_verbose > 1)
cout << "------- WORKING ON ITERATION " << (t+1) << " -------" << endl;
// create the weak learner
BaseLearner* pWeakHypothesis;
BaseLearner* pConstantWeakHypothesis;
pWeakHypothesis = pWeakHypothesisSource->create();
pWeakHypothesis->initLearningOptions(args);
//pTrainingData->clearIndexSet();
pWeakHypothesis->setTrainingData(pTrainingData);
AlphaReal edge, energy=0.0;
// create the constant learner
pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
pConstantWeakHypothesis->initLearningOptions(args);
pConstantWeakHypothesis->setTrainingData(pTrainingData);
AlphaReal constantEdge = -numeric_limits<AlphaReal>::max();
int currentNumberOfUsedData = static_cast<int>(_Cn * log(t+3.0));
if ( _onlineWeakLearning )
{
//check whether the weak learner is a ScalarLeaerner
try {
StochasticLearner* pStochasticLearner = dynamic_cast<StochasticLearner*>(pWeakHypothesis);
StochasticLearner* pStochasticConstantWeakHypothesis = dynamic_cast<StochasticLearner*> (pConstantWeakHypothesis);
pStochasticLearner->initLearning();
pStochasticConstantWeakHypothesis->initLearning();
if (_verbose>1)
cout << "Number of random instances: \t" << currentNumberOfUsedData << endl;
// set the weights
setWeightToMargins(pTrainingData);
//learning
for (int i=0; i<currentNumberOfUsedData; ++i )
{
int randomIndex = (rand() % pTrainingData->getNumExamples());
//int randomIndex = getRandomIndex();
pStochasticLearner->update(randomIndex);
pStochasticConstantWeakHypothesis->update(randomIndex);
}
pStochasticLearner->finishLearning();
pStochasticConstantWeakHypothesis->finishLearning();
}
catch (bad_cast& e) {
cerr << "The weak learner must be a StochasticLearner!!!" << endl;
exit(-1);
}
}
else
{
filter( pTrainingData, currentNumberOfUsedData );
if ( pTrainingData->getNumExamples() < 2 )
{
filter( pTrainingData, currentNumberOfUsedData, false );
}
if (_verbose > 1)
{
cout << "--> Size of training data = " << pTrainingData->getNumExamples() << endl;
}
energy = pWeakHypothesis->run();
pConstantWeakHypothesis->run();
}
//estimate edge
filter( pTrainingData, currentNumberOfUsedData, false );
edge = pWeakHypothesis->getEdge(true) / 2.0;
constantEdge = pConstantWeakHypothesis->getEdge() / 2.0;
if ( constantEdge > edge )
{
delete pWeakHypothesis;
pWeakHypothesis = pConstantWeakHypothesis;
edge = constantEdge;
} else {
delete pConstantWeakHypothesis;
}
// calculate alpha
AlphaReal alpha = 0.0;
alpha = 0.5 * log( ( 1 + edge ) / ( 1 - edge ) );
pWeakHypothesis->setAlpha( alpha );
_sumAlpha += alpha;
if (_verbose > 1)
cout << "Weak learner: " << pWeakHypothesis->getName()<< endl;
// Output the step-by-step information
pTrainingData->clearIndexSet();
printOutputInfo(pOutInfo, t, pTrainingData, pTestData, pWeakHypothesis);
// Updates the weights and returns the edge
//AlphaReal gamma = updateWeights(pTrainingData, pWeakHypothesis);
if (_verbose > 1)
{
cout << setprecision(5)
<< "--> Alpha = " << pWeakHypothesis->getAlpha() << endl
<< "--> Edge = " << edge << endl
<< "--> Energy = " << energy << endl
// << "--> ConstantEnergy = " << constantEnergy << endl
// << "--> difference = " << (energy - constantEnergy) << endl
;
}
// update the margins
//saveMargins();
updateMargins( pTrainingData, pWeakHypothesis );
// append the current weak learner to strong hypothesis file,
// that is, serialize it.
ss.appendHypothesis(t, pWeakHypothesis);
// Add it to the internal list of weak hypotheses
_foundHypotheses.push_back(pWeakHypothesis);
// check if the time limit has been reached
if (_maxTime > 0)
{
time( ¤tTime );
float diff = difftime(currentTime, startTime); // difftime is in seconds
diff /= 60; // = minutes
if (diff > _maxTime)
{
if (_verbose > 0)
cout << "Time limit of " << _maxTime
<< " minutes has been reached!" << endl;
break;
}
} // check for maxtime
delete pWeakHypothesis;
} // loop on iterations
/////////////////////////////////////////////////////////
// write the footer of the strong hypothesis file
ss.writeFooter();
// Free the two input data objects
if (pTrainingData)
delete pTrainingData;
if (pTestData)
delete pTestData;
if (pOutInfo)
delete pOutInfo;
if (_verbose > 0)
cout << "Learning completed." << endl;
}
void TreeLearnerUCT::calculateChildrenAndEnergies( NodePointUCT& bLearner, int depthIndex ) {
bLearner._extended = true;
_pTrainingData->loadIndexSet( bLearner._learnerIdxSet );
//separate the dataset
set< int > idxPos, idxNeg;
idxPos.clear();
idxNeg.clear();
float phix;
for (int i = 0; i < _pTrainingData->getNumExamples(); ++i) {
// this returns the phi value of classifier
phix = bLearner._learner->classify(_pTrainingData,i,0);
if ( phix < 0 )
idxNeg.insert( _pTrainingData->getRawIndex( i ) );
else if ( phix > 0 ) { // have to redo the multiplications, haven't been tested
idxPos.insert( _pTrainingData->getRawIndex( i ) );
}
}
if ( (idxPos.size() < 1 ) || (idxNeg.size() < 1 ) ) {
//retval.clear();
bLearner._extended = false;
//return retval;
}
_pTrainingData->loadIndexSet( idxPos );
if ( ! _pTrainingData->isSamplesFromOneClass() ) {
BaseLearner* posLearner = _baseLearners[0]->copyState();
//posLearner->run();
dynamic_cast<FeaturewiseLearner*>(posLearner)->run( depthIndex );
//
//float posEdge = getEdge( posLearner, _pTrainingData );
posLearner->setTrainingData( _pTrainingData );
bLearner._leftEdge = posLearner->getEdge();
//tmpPair.first = posEdge;
//tmpPair.second.first.first = posLearner;
bLearner._leftChild = posLearner;
//set the parent idx to zero
//tmpPair.second.first.second.first = 0;
//this means that it will be a left child in the tree
//tmpPair.second.first.second.second = 0;
//tmpPair.second.second = idxPos;
bLearner._leftChildIdxSet = idxPos;
} else {
BaseLearner* pConstantWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner("ConstantLearner");
BaseLearner* posLearner = pConstantWeakHypothesisSource->create();
posLearner->setTrainingData(_pTrainingData);
//float constantEnergy = posLearner->run();
dynamic_cast<FeaturewiseLearner*>(posLearner)->run( depthIndex );
//BaseLearner* posLearner = _baseLearners[0]->copyState();
//float posEdge = getEdge( posLearner, _pTrainingData );
posLearner->setTrainingData( _pTrainingData );
bLearner._leftEdge = posLearner->getEdge();
//tmpPair.first = posEdge;
//tmpPair.second.first.first = posLearner;
bLearner._leftChild = posLearner;
//set the parent idx to zero
//tmpPair.second.first.second.first = 0;
//this means that it will be a left child in the tree
//tmpPair.second.first.second.second = 0;
//tmpPair.second.second = idxPos;
bLearner._leftChildIdxSet = idxPos;
}
//retval.push_back( tmpPair );
_pTrainingData->loadIndexSet( idxNeg );
if ( ! _pTrainingData->isSamplesFromOneClass() ) {
BaseLearner* negLearner = _baseLearners[0]->copyState();
//negLearner->run();
dynamic_cast<FeaturewiseLearner*>(negLearner)->run( depthIndex );
//float negEdge = getEdge( negLearner, _pTrainingData );
negLearner->setTrainingData( _pTrainingData );
bLearner._rightEdge = negLearner->getEdge();
//tmpPair.first = negEdge;
//tmpPair.second.first.first = negLearner;
bLearner._rightChild = negLearner;
//set the parent idx to zero
//tmpPair.second.first.second.first = 0;
//this means that it will be a right child in the tree
//tmpPair.second.first.second.second = 1;
//tmpPair.second.second = idxNeg;
bLearner._rightChildIdxSet = idxNeg;
} else {
BaseLearner* pConstantWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner("ConstantLearner");
BaseLearner* negLearner = pConstantWeakHypothesisSource->create();
negLearner->setTrainingData(_pTrainingData);
//float constantEnergy = negLearner->run();
dynamic_cast<FeaturewiseLearner*>(negLearner)->run( depthIndex );
//tmpPair.first = getEdge( negLearner, _pTrainingData );;
bLearner._rightChild = negLearner;
bLearner._rightChild = negLearner;
//tmpPair.second.first.first = negLearner;
//set the parent idx to zero
//tmpPair.second.first.second.first = 0;
//this means that it will be a right child in the tree
//tmpPair.second.first.second.second = 1;
//tmpPair.second.second = idxNeg;
bLearner._rightChildIdxSet = idxNeg;
}
//retval.push_back( tmpPair );
//return retval;
}
void FilterBoostLearner::run(const nor_utils::Args& args)
{
// load the arguments
this->getArgs(args);
time_t startTime, currentTime;
time(&startTime);
// get the registered weak learner (type from name)
BaseLearner* pWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
// initialize learning options; normally it's done in the strong loop
// also, here we do it for Product learners, so input data can be created
pWeakHypothesisSource->initLearningOptions(args);
BaseLearner* pConstantWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner("ConstantLearner");
// get the training input data, and load it
InputData* pTrainingData = pWeakHypothesisSource->createInputData();
pTrainingData->initOptions(args);
pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);
const int numClasses = pTrainingData->getNumClasses();
const int numExamples = pTrainingData->getNumExamples();
//initialize the margins variable
_margins.resize( numExamples );
for( int i=0; i<numExamples; i++ )
{
_margins[i].resize( numClasses );
fill( _margins[i].begin(), _margins[i].end(), 0.0 );
}
// get the testing input data, and load it
InputData* pTestData = NULL;
if ( !_testFileName.empty() )
{
pTestData = pWeakHypothesisSource->createInputData();
pTestData->initOptions(args);
pTestData->load(_testFileName, IT_TEST, _verbose);
}
// The output information object
OutputInfo* pOutInfo = NULL;
if ( !_outputInfoFile.empty() )
{
// Baseline: constant classifier - goes into 0th iteration
BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
pConstantWeakHypothesis->initLearningOptions(args);
pConstantWeakHypothesis->setTrainingData(pTrainingData);
float constantEnergy = pConstantWeakHypothesis->run();
pOutInfo = new OutputInfo(_outputInfoFile);
pOutInfo->initialize(pTrainingData);
updateMargins( pTrainingData, pConstantWeakHypothesis );
if (pTestData)
pOutInfo->initialize(pTestData);
pOutInfo->outputHeader();
pOutInfo->outputIteration(-1);
pOutInfo->outputError(pTrainingData, pConstantWeakHypothesis);
if (pTestData)
pOutInfo->outputError(pTestData, pConstantWeakHypothesis);
/*
pOutInfo->outputMargins(pTrainingData, pConstantWeakHypothesis);
pOutInfo->outputEdge(pTrainingData, pConstantWeakHypothesis);
if (pTestData)
pOutInfo->outputMargins(pTestData, pConstantWeakHypothesis);
pOutInfo->outputMAE(pTrainingData);
if (pTestData)
pOutInfo->outputMAE(pTestData);
*/
pOutInfo->outputCurrentTime();
pOutInfo->endLine();
pOutInfo->initialize(pTrainingData);
if (pTestData)
pOutInfo->initialize(pTestData);
}
// reload the previously found weak learners if -resume is set.
// otherwise just return 0
int startingIteration = resumeWeakLearners(pTrainingData);
Serialization ss(_shypFileName, _isShypCompressed );
ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called
// perform the resuming if necessary. If not it will just return
resumeProcess(ss, pTrainingData, pTestData, pOutInfo);
if (_verbose == 1)
cout << "Learning in progress..." << endl;
///////////////////////////////////////////////////////////////////////
// Starting the AdaBoost main loop
///////////////////////////////////////////////////////////////////////
for (int t = startingIteration; t < _numIterations; ++t)
{
if (_verbose > 1)
cout << "------- WORKING ON ITERATION " << (t+1) << " -------" << endl;
filter( pTrainingData, (int)(_Cn * log(t+2.0)) );
if ( pTrainingData->getNumExamples() < 2 )
{
filter( pTrainingData, (int)(_Cn * log(t+2.0)), false );
}
if (_verbose > 1)
{
cout << "--> Size of training data = " << pTrainingData->getNumExamples() << endl;
}
BaseLearner* pWeakHypothesis = pWeakHypothesisSource->create();
pWeakHypothesis->initLearningOptions(args);
//pTrainingData->clearIndexSet();
pWeakHypothesis->setTrainingData(pTrainingData);
float energy = pWeakHypothesis->run();
BaseLearner* pConstantWeakHypothesis;
if (_withConstantLearner) // check constant learner if user wants it
{
pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
pConstantWeakHypothesis->initLearningOptions(args);
pConstantWeakHypothesis->setTrainingData(pTrainingData);
float constantEnergy = pConstantWeakHypothesis->run();
}
//estimate edge
filter( pTrainingData, (int)(_Cn * log(t+2.0)), false );
float edge = pWeakHypothesis->getEdge() / 2.0;
if (_withConstantLearner) // check constant learner if user wants it
{
float constantEdge = pConstantWeakHypothesis->getEdge() / 2.0;
if ( constantEdge > edge )
{
delete pWeakHypothesis;
pWeakHypothesis = pConstantWeakHypothesis;
edge = constantEdge;
} else {
delete pConstantWeakHypothesis;
}
}
// calculate alpha
float alpha = 0.0;
alpha = 0.5 * log( ( 0.5 + edge ) / ( 0.5 - edge ) );
pWeakHypothesis->setAlpha( alpha );
if (_verbose > 1)
cout << "Weak learner: " << pWeakHypothesis->getName()<< endl;
// Output the step-by-step information
pTrainingData->clearIndexSet();
printOutputInfo(pOutInfo, t, pTrainingData, pTestData, pWeakHypothesis);
// Updates the weights and returns the edge
float gamma = updateWeights(pTrainingData, pWeakHypothesis);
if (_verbose > 1)
{
cout << setprecision(5)
<< "--> Alpha = " << pWeakHypothesis->getAlpha() << endl
<< "--> Edge = " << gamma << endl
<< "--> Energy = " << energy << endl
// << "--> ConstantEnergy = " << constantEnergy << endl
// << "--> difference = " << (energy - constantEnergy) << endl
;
}
// update the margins
updateMargins( pTrainingData, pWeakHypothesis );
// append the current weak learner to strong hypothesis file,
// that is, serialize it.
ss.appendHypothesis(t, pWeakHypothesis);
// Add it to the internal list of weak hypotheses
_foundHypotheses.push_back(pWeakHypothesis);
// check if the time limit has been reached
if (_maxTime > 0)
{
time( ¤tTime );
float diff = difftime(currentTime, startTime); // difftime is in seconds
diff /= 60; // = minutes
if (diff > _maxTime)
{
if (_verbose > 0)
cout << "Time limit of " << _maxTime
<< " minutes has been reached!" << endl;
break;
}
} // check for maxtime
delete pWeakHypothesis;
} // loop on iterations
/////////////////////////////////////////////////////////
// write the footer of the strong hypothesis file
ss.writeFooter();
// Free the two input data objects
if (pTrainingData)
delete pTrainingData;
if (pTestData)
delete pTestData;
if (pOutInfo)
delete pOutInfo;
if (_verbose > 0)
cout << "Learning completed." << endl;
}
AlphaReal TreeLearnerUCT::run()
{
if ( _numOfCalling == 0 ) {
if (_verbose > 0) {
cout << "Initializing tree..." << endl;
}
InnerNodeUCTSparse::setDepth( _numBaseLearners );
InnerNodeUCTSparse::setBranchOrder( _pTrainingData->getNumAttributes() );
_root.setChildrenNum();
//createUCTTree();
}
_numOfCalling++;
set< int > tmpIdx, idxPos, idxNeg;
_pTrainingData->clearIndexSet();
for( int i = 0; i < _pTrainingData->getNumExamples(); i++ ) tmpIdx.insert( i );
vector< int > trajectory(0);
_root.getBestTrajectory( trajectory );
// for UCT
for(int ib = 0; ib < _numBaseLearners; ++ib)
_baseLearners[ib]->setTrainingData(_pTrainingData);
AlphaReal edge = numeric_limits<AlphaReal>::max();
BaseLearner* pPreviousBaseLearner = 0;
//floatBaseLearner tmpPair, tmpPairPos, tmpPairNeg;
// for storing the inner point (learneres) which will be extended
//vector< floatBaseLearner > bLearnerVector;
InnerNodeType innerNode;
priority_queue<InnerNodeType, deque<InnerNodeType>, greater_first<InnerNodeType> > pq;
//train the first learner
//_baseLearners[0]->run();
pPreviousBaseLearner = _baseLearners[0]->copyState();
dynamic_cast<FeaturewiseLearner*>(pPreviousBaseLearner)->run( trajectory[0] );
//this contains the number of baselearners
int ib = 0;
NodePointUCT tmpNodePoint, nodeLeft, nodeRight;
////////////////////////////////////////////////////////
//set the edge
//tmpPair.first = getEdge( pPreviousBaseLearner, _pTrainingData );
//tmpPair.second.first.first = pPreviousBaseLearner;
// set the pointer of the parent
//tmpPair.second.first.second.first = 0;
// set that this is a neg child
//tmpPair.second.first.second.second = 0;
//tmpPair.second.second = tmpIdx;
//bLearnerVector = calculateChildrenAndEnergies( tmpPair );
///
pPreviousBaseLearner->setTrainingData( _pTrainingData );
tmpNodePoint._edge = pPreviousBaseLearner->getEdge();
tmpNodePoint._learner = pPreviousBaseLearner;
tmpNodePoint._idx = 0;
tmpNodePoint._depth = 0;
tmpNodePoint._learnerIdxSet = tmpIdx;
calculateChildrenAndEnergies( tmpNodePoint, trajectory[1] );
////////////////////////////////////////////////////////
//insert the root into the priority queue
if ( tmpNodePoint._extended )
{
if (_verbose > 2) {
//cout << "Edges: (parent, pos, neg): " << bLearnerVector[0].first << " " << bLearnerVector[1].first << " " << bLearnerVector[2].first << endl << flush;
//cout << "alpha[" << (ib) << "] = " << _alpha << endl << flush;
cout << "Edges: (parent, pos, neg): " << tmpNodePoint._edge << " " << tmpNodePoint._leftEdge << " " << tmpNodePoint._rightEdge << endl << flush;
}
// if the energy is getting higher then we push it into the priority queue
if ( tmpNodePoint._edge < ( tmpNodePoint._leftEdge + tmpNodePoint._rightEdge ) ) {
float deltaEdge = abs( tmpNodePoint._edge - ( tmpNodePoint._leftEdge + tmpNodePoint._rightEdge ) );
innerNode.first = deltaEdge;
innerNode.second = tmpNodePoint;
pq.push( innerNode );
} else {
//delete bLearnerVector[0].second.first.first;
delete tmpNodePoint._leftChild;
delete tmpNodePoint._rightChild;
}
}
if ( pq.empty() ) {
// we don't extend the root
BaseLearner* tmpBL = _baseLearners[0];
_baseLearners[0] = tmpNodePoint._learner;
delete tmpBL;
ib = 1;
}
while ( ! pq.empty() && ( ib < _numBaseLearners ) ) {
//get the best learner from the priority queue
innerNode = pq.top();
if (_verbose > 2) {
cout << "Delta energy: " << innerNode.first << endl << flush;
cout << "Size of priority queue: " << pq.size() << endl << flush;
}
pq.pop();
tmpNodePoint = innerNode.second;
//tmpPair = bLearnerVector[0];
//tmpPairPos = bLearnerVector[1];
//tmpPairNeg = bLearnerVector[2];
nodeLeft._edge = tmpNodePoint._leftEdge;
nodeLeft._learner = tmpNodePoint._leftChild;
nodeLeft._learnerIdxSet = tmpNodePoint._leftChildIdxSet;
nodeRight._edge = tmpNodePoint._rightEdge;
nodeRight._learner = tmpNodePoint._rightChild;
nodeRight._learnerIdxSet = tmpNodePoint._rightChildIdxSet;
//store the baselearner if the deltaenrgy will be higher
if ( _verbose > 3 ) {
cout << "Insert learner: " << ib << endl << flush;
}
int parentIdx = tmpNodePoint._parentIdx;
BaseLearner* tmpBL = _baseLearners[ib];
_baseLearners[ib] = tmpNodePoint._learner;
delete tmpBL;
nodeLeft._parentIdx = ib;
nodeRight._parentIdx = ib;
nodeLeft._leftOrRightChild = 0;
nodeRight._leftOrRightChild = 1;
nodeLeft._depth = tmpNodePoint._depth + 1;
nodeRight._depth = tmpNodePoint._depth + 1;
if ( ib > 0 ) {
//set the descendant idx
_idxPairs[ parentIdx ][ tmpNodePoint._leftOrRightChild ] = ib;
}
ib++;
if ( ib >= _numBaseLearners ) break;
//extend positive node
if ( nodeLeft._learner ) {
calculateChildrenAndEnergies( nodeLeft, trajectory[ nodeLeft._depth + 1 ] );
} else {
nodeLeft._extended = false;
}
//calculateChildrenAndEnergies( nodeLeft );
// if the energie is getting higher then we push it into the priority queue
if ( nodeLeft._extended )
{
if (_verbose > 2) {
//cout << "Edges: (parent, pos, neg): " << bLearnerVector[0].first << " " << bLearnerVector[1].first << " " << bLearnerVector[2].first << endl << flush;
//cout << "alpha[" << (ib) << "] = " << _alpha << endl << flush;
cout << "Edges: (parent, pos, neg): " << nodeLeft._edge << " " << nodeLeft._leftEdge << " " << nodeLeft._rightEdge << endl << flush;
}
// if the energy is getting higher then we push it into the priority queue
if ( nodeLeft._edge < ( nodeLeft._leftEdge + nodeLeft._rightEdge ) ) {
float deltaEdge = abs( nodeLeft._edge - ( nodeLeft._leftEdge + nodeLeft._rightEdge ) );
innerNode.first = deltaEdge;
innerNode.second = nodeLeft;
pq.push( innerNode );
} else {
//delete bLearnerVector[0].second.first.first;
delete nodeLeft._leftChild;
delete nodeLeft._rightChild;
if ( ib >= _numBaseLearners ) {
delete nodeLeft._learner;
break;
} else {
//this will be a leaf, we do not extend further
int parentIdx = nodeLeft._parentIdx;
BaseLearner* tmpBL = _baseLearners[ib];
_baseLearners[ib] = nodeLeft._learner;
delete tmpBL;
_idxPairs[ parentIdx ][ 0 ] = ib;
ib += 1;
}
}
}
//extend negative node
if ( nodeRight._learner ) {
calculateChildrenAndEnergies( nodeRight, trajectory[ nodeRight._depth + 1 ] );
} else {
nodeRight._extended = false;
}
// if the energie is getting higher then we push it into the priority queue
if ( nodeRight._extended )
{
if (_verbose > 2) {
cout << "Edges: (parent, pos, neg): " << nodeRight._edge << " " << nodeRight._leftEdge << " " << nodeRight._rightEdge << endl << flush;
//cout << "alpha[" << (ib) << "] = " << _alpha << endl << flush;
}
// if the energie is getting higher then we push it into the priority queue
if ( nodeRight._edge < ( nodeRight._leftEdge + nodeRight._rightEdge ) ) {
float deltaEdge = abs( nodeRight._edge - ( nodeRight._leftEdge + nodeRight._rightEdge ) );
innerNode.first = deltaEdge;
innerNode.second = nodeRight;
pq.push( innerNode );
} else {
//delete bLearnerVector[0].second.first.first;
delete nodeRight._leftChild;
delete nodeRight._rightChild;
if ( ib >= _numBaseLearners ) {
delete nodeRight._learner;
break;
} else {
//this will be a leaf, we do not extend further
int parentIdx = nodeRight._parentIdx;
BaseLearner* tmpBL = _baseLearners[ib];
_baseLearners[ib] = nodeRight._learner;
delete tmpBL;
_idxPairs[ parentIdx ][ 1 ] = ib;
ib += 1;
}
}
}
}
for(int ib2 = ib; ib2 < _numBaseLearners; ++ib2) delete _baseLearners[ib2];
_numBaseLearners = ib;
if (_verbose > 2) {
cout << "Num of learners: " << _numBaseLearners << endl << flush;
}
//clear the priority queur
while ( ! pq.empty() && ( ib < _numBaseLearners ) ) {
//get the best learner from the priority queue
innerNode = pq.top();
pq.pop();
tmpNodePoint = innerNode.second;
delete tmpNodePoint._learner;
delete tmpNodePoint._leftChild;
delete tmpNodePoint._rightChild;
}
_id = _baseLearners[0]->getId();
for(int ib = 0; ib < _numBaseLearners; ++ib)
_id += "_x_" + _baseLearners[ib]->getId();
//calculate alpha
this->_alpha = 0.0;
float eps_min = 0.0, eps_pls = 0.0;
_pTrainingData->clearIndexSet();
for( int i = 0; i < _pTrainingData->getNumExamples(); i++ ) {
vector< Label> l = _pTrainingData->getLabels( i );
for( vector< Label >::iterator it = l.begin(); it != l.end(); it++ ) {
float result = this->classify( _pTrainingData, i, it->idx );
if ( ( result * it->y ) < 0 ) eps_min += it->weight;
if ( ( result * it->y ) > 0 ) eps_pls += it->weight;
}
}
//update the weights in the UCT tree
double updateWeight = 0.0;
if ( _updateRule == EDGE_SQUARE ) {
double edge = getEdge();
updateWeight = 1 - sqrt( 1 - ( edge * edge ) );
} else if ( _updateRule == ALPHAS ) {
double alpha = this->getAlpha();
updateWeight = alpha;
} else if ( _updateRule == ESQUARE ) {
double edge = getEdge();
updateWeight = edge * edge;
}
_root.updateInnerNodes( updateWeight, trajectory );
if (_verbose > 2) {
cout << "Update weight (" << updateWeight << ")" << "\tUpdate rule index: "<< _updateRule << endl << flush;
}
// set the smoothing value to avoid numerical problem
// when theta=0.
setSmoothingVal( (float)1.0 / (float)_pTrainingData->getNumExamples() * (float)0.01 );
this->_alpha = getAlpha( eps_min, eps_pls );
// calculate the energy (sum of the energy of the leaves
float energy = this->getEnergy( eps_min, eps_pls );
return energy;
}