ClassificationData ClassificationData::getTestFoldData(const UINT foldIndex) const{
ClassificationData testData;
testData.setNumDimensions( numDimensions );
testData.setAllowNullGestureClass( allowNullGestureClass );
if( !crossValidationSetup ) return testData;
if( foldIndex >= kFoldValue ) return testData;
//Add the class labels to make sure they all exist
for(UINT k=0; k<getNumSamples(); k++){
testData.addClass( classTracker[k].classLabel, classTracker[k].className );
}
testData.reserve( (UINT)crossValidationIndexs[ foldIndex ].size() );
//Add the data to the test fold
UINT index = 0;
for(UINT i=0; i<crossValidationIndexs[ foldIndex ].size(); i++){
index = crossValidationIndexs[ foldIndex ][i];
testData.addSample( data[ index ].getClassLabel(), data[ index ].getSample() );
}
//Sort the class labels
testData.sortClassLabels();
return testData;
}
ClassificationData ClassificationData::getTrainingFoldData(const UINT foldIndex) const{
ClassificationData trainingData;
trainingData.setNumDimensions( numDimensions );
trainingData.setAllowNullGestureClass( allowNullGestureClass );
if( !crossValidationSetup ){
errorLog << "getTrainingFoldData(const UINT foldIndex) - Cross Validation has not been setup! You need to call the spiltDataIntoKFolds(UINT K,bool useStratifiedSampling) function first before calling this function!" << endl;
return trainingData;
}
if( foldIndex >= kFoldValue ) return trainingData;
//Add the class labels to make sure they all exist
for(UINT k=0; k<getNumSamples(); k++){
trainingData.addClass( classTracker[k].classLabel, classTracker[k].className );
}
//Add the data to the training set, this will consist of all the data that is NOT in the foldIndex
UINT index = 0;
for(UINT k=0; k<kFoldValue; k++){
if( k != foldIndex ){
for(UINT i=0; i<crossValidationIndexs[k].size(); i++){
index = crossValidationIndexs[k][i];
trainingData.addSample( data[ index ].getClassLabel(), data[ index ].getSample() );
}
}
}
//Sort the class labels
trainingData.sortClassLabels();
return trainingData;
}
ClassificationData ClassificationData::getBootstrappedDataset(UINT numSamples) const{
Random rand;
ClassificationData newDataset;
newDataset.setNumDimensions( getNumDimensions() );
newDataset.setAllowNullGestureClass( allowNullGestureClass );
newDataset.setExternalRanges( externalRanges, useExternalRanges );
if( numSamples == 0 ) numSamples = totalNumSamples;
newDataset.reserve( numSamples );
//Add all the class labels to the new dataset to ensure the dataset has a list of all the labels
for(UINT k=0; k<getNumClasses(); k++){
newDataset.addClass( classTracker[k].classLabel );
}
//Randomly select the training samples to add to the new data set
UINT randomIndex;
for(UINT i=0; i<numSamples; i++){
randomIndex = rand.getRandomNumberInt(0, totalNumSamples);
newDataset.addSample(data[randomIndex].getClassLabel(), data[randomIndex].getSample());
}
//Sort the class labels so they are in order
newDataset.sortClassLabels();
return newDataset;
}
ClassificationData ClassificationData::getBootstrappedDataset(UINT numSamples,bool balanceDataset) const{
Random rand;
ClassificationData newDataset;
newDataset.setNumDimensions( getNumDimensions() );
newDataset.setAllowNullGestureClass( allowNullGestureClass );
newDataset.setExternalRanges( externalRanges, useExternalRanges );
if( numSamples == 0 ) numSamples = totalNumSamples;
newDataset.reserve( numSamples );
const UINT K = getNumClasses();
//Add all the class labels to the new dataset to ensure the dataset has a list of all the labels
for(UINT k=0; k<K; k++){
newDataset.addClass( classTracker[k].classLabel );
}
if( balanceDataset ){
//Group the class indexs
std::vector< std::vector< UINT > > classIndexs( K );
for(UINT i=0; i<totalNumSamples; i++){
classIndexs[ getClassLabelIndexValue( data[i].getClassLabel() ) ].push_back( i );
}
//Get the class with the minimum number of examples
UINT numSamplesPerClass = (UINT)floor( numSamples / double(K) );
//Randomly select the training samples from each class
UINT classIndex = 0;
UINT classCounter = 0;
UINT randomIndex = 0;
for(UINT i=0; i<numSamples; i++){
randomIndex = rand.getRandomNumberInt(0, (UINT)classIndexs[ classIndex ].size() );
randomIndex = classIndexs[ classIndex ][ randomIndex ];
newDataset.addSample(data[ randomIndex ].getClassLabel(), data[ randomIndex ].getSample());
if( classCounter++ >= numSamplesPerClass && classIndex+1 < K ){
classCounter = 0;
classIndex++;
}
}
}else{
//Randomly select the training samples to add to the new data set
UINT randomIndex;
for(UINT i=0; i<numSamples; i++){
randomIndex = rand.getRandomNumberInt(0, totalNumSamples);
newDataset.addSample( data[randomIndex].getClassLabel(), data[randomIndex].getSample() );
}
}
//Sort the class labels so they are in order
newDataset.sortClassLabels();
return newDataset;
}
