bool BAG::train_(ClassificationData &trainingData){
//Clear any previous models
clear();
const unsigned int M = trainingData.getNumSamples();
const unsigned int N = trainingData.getNumDimensions();
const unsigned int K = trainingData.getNumClasses();
if( M == 0 ){
errorLog << "train_(ClassificationData &trainingData) - Training data has zero samples!" << endl;
return false;
}
numInputDimensions = N;
numClasses = K;
classLabels.resize(K);
ranges = trainingData.getRanges();
//Scale the training data if needed
if( useScaling ){
//Scale the training data between 0 and 1
trainingData.scale(0, 1);
}
UINT ensembleSize = (UINT)ensemble.size();
if( ensembleSize == 0 ){
errorLog << "train_(ClassificationData &trainingData) - The ensemble size is zero! You need to add some classifiers to the ensemble first." << endl;
return false;
}
for(UINT i=0; i<ensembleSize; i++){
if( ensemble[i] == NULL ){
errorLog << "train_(ClassificationData &trainingData) - The classifier at ensemble index " << i << " has not been set!" << endl;
return false;
}
}
//Train the ensemble
for(UINT i=0; i<ensembleSize; i++){
ClassificationData boostedDataset = trainingData.getBootstrappedDataset();
trainingLog << "Training ensemble " << i+1 << ". Ensemble type: " << ensemble[i]->getClassType() << endl;
//Train the classifier with the bootstrapped dataset
if( !ensemble[i]->train( boostedDataset ) ){
errorLog << "train_(ClassificationData &trainingData) - The classifier at ensemble index " << i << " failed training!" << endl;
return false;
}
}
//Set the class labels
classLabels = trainingData.getClassLabels();
//Flag that the model has been trained
trained = true;
return trained;
}
bool AdaBoost::train_(ClassificationData &trainingData){
//Clear any previous model
clear();
if( trainingData.getNumSamples() <= 1 ){
errorLog << "train_(ClassificationData &trainingData) - There are not enough training samples to train a model! Number of samples: " << trainingData.getNumSamples() << endl;
return false;
}
numInputDimensions = trainingData.getNumDimensions();
numClasses = trainingData.getNumClasses();
const UINT M = trainingData.getNumSamples();
const UINT POSITIVE_LABEL = WEAK_CLASSIFIER_POSITIVE_CLASS_LABEL;
const UINT NEGATIVE_LABEL = WEAK_CLASSIFIER_NEGATIVE_CLASS_LABEL;
double alpha = 0;
const double beta = 0.001;
double epsilon = 0;
TrainingResult trainingResult;
const UINT K = (UINT)weakClassifiers.size();
if( K == 0 ){
errorLog << "train_(ClassificationData &trainingData) - No weakClassifiers have been set. You need to set at least one weak classifier first." << endl;
return false;
}
classLabels.resize(numClasses);
models.resize(numClasses);
ranges = trainingData.getRanges();
//Scale the training data if needed
if( useScaling ){
trainingData.scale(ranges,0,1);
}
//Create the weights vector
VectorDouble weights(M);
//Create the error matrix
MatrixDouble errorMatrix(K,M);
for(UINT classIter=0; classIter<numClasses; classIter++){
//Get the class label for the current class
classLabels[classIter] = trainingData.getClassLabels()[classIter];
//Set the class label of the current model
models[ classIter ].setClassLabel( classLabels[classIter] );
//Setup the labels for this class, POSITIVE_LABEL == 1, NEGATIVE_LABEL == 2
ClassificationData classData;
classData.setNumDimensions(trainingData.getNumDimensions());
for(UINT i=0; i<M; i++){
UINT label = trainingData[i].getClassLabel()==classLabels[classIter] ? POSITIVE_LABEL : NEGATIVE_LABEL;
VectorDouble trainingSample = trainingData[i].getSample();
classData.addSample(label,trainingSample);
}
//Setup the initial training sample weights
std::fill(weights.begin(),weights.end(),1.0/M);
//Run the boosting loop
bool keepBoosting = true;
UINT t = 0;
while( keepBoosting ){
//Pick the classifier from the family of classifiers that minimizes the total error
UINT bestClassifierIndex = 0;
double minError = numeric_limits<double>::max();
for(UINT k=0; k<K; k++){
//Get the k'th possible classifier
WeakClassifier *weakLearner = weakClassifiers[k];
//Train the current classifier
if( !weakLearner->train(classData,weights) ){
errorLog << "Failed to train weakLearner!" << endl;
return false;
}
//Compute the weighted error for this clasifier
double e = 0;
double positiveLabel = weakLearner->getPositiveClassLabel();
double numCorrect = 0;
double numIncorrect = 0;
for(UINT i=0; i<M; i++){
//Only penalize errors
double prediction = weakLearner->predict( classData[i].getSample() );
if( (prediction == positiveLabel && classData[i].getClassLabel() != POSITIVE_LABEL) || //False positive
(prediction != positiveLabel && classData[i].getClassLabel() == POSITIVE_LABEL) ){ //False negative
e += weights[i]; //Increase the error proportional to the weight of the example
errorMatrix[k][i] = 1; //Flag that there was an error
numIncorrect++;
}else{
errorMatrix[k][i] = 0; //Flag that there was no error
numCorrect++;
}
}
trainingLog << "PositiveClass: " << classLabels[classIter] << " Boosting Iter: " << t << " Classifier: " << k << " WeightedError: " << e << " NumCorrect: " << numCorrect/M << " NumIncorrect: " <<numIncorrect/M << endl;
if( e < minError ){
minError = e;
bestClassifierIndex = k;
}
}
epsilon = minError;
//Set alpha, using the M1 weight value, small weights (close to 0) will receive a strong weight in the final classifier
alpha = 0.5 * log( (1.0-epsilon)/epsilon );
trainingLog << "PositiveClass: " << classLabels[classIter] << " Boosting Iter: " << t << " Best Classifier Index: " << bestClassifierIndex << " MinError: " << minError << " Alpha: " << alpha << endl;
if( isinf(alpha) ){ keepBoosting = false; trainingLog << "Alpha is INF. Stopping boosting for current class" << endl; }
if( 0.5 - epsilon <= beta ){ keepBoosting = false; trainingLog << "Epsilon <= Beta. Stopping boosting for current class" << endl; }
if( ++t >= numBoostingIterations ) keepBoosting = false;
trainingResult.setClassificationResult(t, minError, this);
trainingResults.push_back(trainingResult);
trainingResultsObserverManager.notifyObservers( trainingResult );
if( keepBoosting ){
//Add the best weak classifier to the committee
models[ classIter ].addClassifierToCommitee( weakClassifiers[bestClassifierIndex], alpha );
//Update the weights for the next boosting iteration
double reWeight = (1.0 - epsilon) / epsilon;
double oldSum = 0;
double newSum = 0;
for(UINT i=0; i<M; i++){
oldSum += weights[i];
//Only update the weights that resulted in an incorrect prediction
if( errorMatrix[bestClassifierIndex][i] == 1 ) weights[i] *= reWeight;
newSum += weights[i];
}
//Normalize all the weights
//This results to increasing the weights of the samples that were incorrectly labelled
//While decreasing the weights of the samples that were correctly classified
reWeight = oldSum/newSum;
for(UINT i=0; i<M; i++){
weights[i] *= reWeight;
}
}else{
trainingLog << "Stopping boosting training at iteration : " << t-1 << " with an error of " << epsilon << endl;
if( t-1 == 0 ){
//Add the best weak classifier to the committee (we have to add it as this is the first iteration)
if( isinf(alpha) ){ alpha = 1; } //If alpha is infinite then the first classifier got everything correct
models[ classIter ].addClassifierToCommitee( weakClassifiers[bestClassifierIndex], alpha );
}
}
}
}
//Normalize the weights
for(UINT k=0; k<numClasses; k++){
models[k].normalizeWeights();
}
//Flag that the model has been trained
trained = true;
//Setup the data for prediction
predictedClassLabel = 0;
maxLikelihood = 0;
classLikelihoods.resize(numClasses);
classDistances.resize(numClasses);
return true;
}
bool RandomForests::train_(ClassificationData &trainingData){
//Clear any previous model
clear();
const unsigned int M = trainingData.getNumSamples();
const unsigned int N = trainingData.getNumDimensions();
const unsigned int K = trainingData.getNumClasses();
if( M == 0 ){
errorLog << "train_(ClassificationData &trainingData) - Training data has zero samples!" << endl;
return false;
}
if( bootstrappedDatasetWeight <= 0.0 || bootstrappedDatasetWeight > 1.0 ){
errorLog << "train_(ClassificationData &trainingData) - Bootstrapped Dataset Weight must be [> 0.0 and <= 1.0]" << endl;
return false;
}
numInputDimensions = N;
numClasses = K;
classLabels = trainingData.getClassLabels();
ranges = trainingData.getRanges();
//Scale the training data if needed
if( useScaling ){
//Scale the training data between 0 and 1
trainingData.scale(0, 1);
}
//Flag that the main algorithm has been trained encase we need to trigger any callbacks
trained = true;
//Train the random forest
forest.reserve( forestSize );
for(UINT i=0; i<forestSize; i++){
//Get a balanced bootstrapped dataset
UINT datasetSize = (UINT)(trainingData.getNumSamples() * bootstrappedDatasetWeight);
ClassificationData data = trainingData.getBootstrappedDataset( datasetSize, true );
DecisionTree tree;
tree.setDecisionTreeNode( *decisionTreeNode );
tree.enableScaling( false ); //We have already scaled the training data so we do not need to scale it again
tree.setTrainingMode( trainingMode );
tree.setNumSplittingSteps( numRandomSplits );
tree.setMinNumSamplesPerNode( minNumSamplesPerNode );
tree.setMaxDepth( maxDepth );
tree.enableNullRejection( useNullRejection );
tree.setRemoveFeaturesAtEachSpilt( removeFeaturesAtEachSpilt );
trainingLog << "Training forest " << i+1 << "/" << forestSize << "..." << endl;
//Train this tree
if( !tree.train( data ) ){
errorLog << "train_(ClassificationData &labelledTrainingData) - Failed to train tree at forest index: " << i << endl;
clear();
return false;
}
//Deep copy the tree into the forest
forest.push_back( tree.deepCopyTree() );
}
return true;
}
bool RandomForests::train_(ClassificationData &trainingData){
//Clear any previous model
clear();
const unsigned int M = trainingData.getNumSamples();
const unsigned int N = trainingData.getNumDimensions();
const unsigned int K = trainingData.getNumClasses();
if( M == 0 ){
errorLog << "train_(ClassificationData &trainingData) - Training data has zero samples!" << std::endl;
return false;
}
if( bootstrappedDatasetWeight <= 0.0 || bootstrappedDatasetWeight > 1.0 ){
errorLog << "train_(ClassificationData &trainingData) - Bootstrapped Dataset Weight must be [> 0.0 and <= 1.0]" << std::endl;
return false;
}
numInputDimensions = N;
numClasses = K;
classLabels = trainingData.getClassLabels();
ranges = trainingData.getRanges();
//Scale the training data if needed
if( useScaling ){
//Scale the training data between 0 and 1
trainingData.scale(0, 1);
}
if( useValidationSet ){
validationSetAccuracy = 0;
validationSetPrecision.resize( useNullRejection ? K+1 : K, 0 );
validationSetRecall.resize( useNullRejection ? K+1 : K, 0 );
}
//Flag that the main algorithm has been trained encase we need to trigger any callbacks
trained = true;
//Train the random forest
forest.reserve( forestSize );
for(UINT i=0; i<forestSize; i++){
//Get a balanced bootstrapped dataset
UINT datasetSize = (UINT)(trainingData.getNumSamples() * bootstrappedDatasetWeight);
ClassificationData data = trainingData.getBootstrappedDataset( datasetSize, true );
Timer timer;
timer.start();
DecisionTree tree;
tree.setDecisionTreeNode( *decisionTreeNode );
tree.enableScaling( false ); //We have already scaled the training data so we do not need to scale it again
tree.setUseValidationSet( useValidationSet );
tree.setValidationSetSize( validationSetSize );
tree.setTrainingMode( trainingMode );
tree.setNumSplittingSteps( numRandomSplits );
tree.setMinNumSamplesPerNode( minNumSamplesPerNode );
tree.setMaxDepth( maxDepth );
tree.enableNullRejection( useNullRejection );
tree.setRemoveFeaturesAtEachSpilt( removeFeaturesAtEachSpilt );
trainingLog << "Training decision tree " << i+1 << "/" << forestSize << "..." << std::endl;
//Train this tree
if( !tree.train_( data ) ){
errorLog << "train_(ClassificationData &trainingData) - Failed to train tree at forest index: " << i << std::endl;
clear();
return false;
}
Float computeTime = timer.getMilliSeconds();
trainingLog << "Decision tree trained in " << (computeTime*0.001)/60.0 << " minutes" << std::endl;
if( useValidationSet ){
Float forestNorm = 1.0 / forestSize;
validationSetAccuracy += tree.getValidationSetAccuracy();
VectorFloat precision = tree.getValidationSetPrecision();
VectorFloat recall = tree.getValidationSetRecall();
grt_assert( precision.getSize() == validationSetPrecision.getSize() );
grt_assert( recall.getSize() == validationSetRecall.getSize() );
for(UINT i=0; i<validationSetPrecision.getSize(); i++){
validationSetPrecision[i] += precision[i] * forestNorm;
}
for(UINT i=0; i<validationSetRecall.getSize(); i++){
validationSetRecall[i] += recall[i] * forestNorm;
}
}
//Deep copy the tree into the forest
forest.push_back( tree.deepCopyTree() );
}
if( useValidationSet ){
validationSetAccuracy /= forestSize;
trainingLog << "Validation set accuracy: " << validationSetAccuracy << std::endl;
trainingLog << "Validation set precision: ";
for(UINT i=0; i<validationSetPrecision.getSize(); i++){
trainingLog << validationSetPrecision[i] << " ";
}
trainingLog << std::endl;
trainingLog << "Validation set recall: ";
for(UINT i=0; i<validationSetRecall.getSize(); i++){
trainingLog << validationSetRecall[i] << " ";
}
trainingLog << std::endl;
}
return true;
}
