LabelledTimeSeriesClassificationData KfoldTimeSeriesData::getTrainingFoldData(const UINT foldIndex, const UINT numSamplesPerClass) const {
UINT index = 0;
unsigned int randomNumber;
unsigned int indexClassLabel;
unsigned int numSamplesRemaining;
LabelledTimeSeriesClassificationData trainingData;
if( !crossValidationSetup ) {
cout << "getTrainingFoldData(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 ) {
cout << "Fold index too big" << endl;
return trainingData;
}
Random random;
trainingData.setNumDimensions( numDimensions );
/* Put all K-1 training folds in one data set */
vector <vector< UINT > > MergedIndexs(inputDataset.getNumClasses());
for(UINT k = 0; k < kFoldValue; k++) {
if( k == foldIndex ) {
continue;
}
for (UINT classLabel = 0 ; classLabel < crossValidationIndexs[k].size(); classLabel++) {
for (UINT i = 0; i < crossValidationIndexs[k][classLabel].size(); i++) {
MergedIndexs[classLabel].push_back(crossValidationIndexs[k][classLabel][i]);
}
}
}
/* For each class peak randomly "numSamplesPerClass" samples */
for (unsigned int classLabel = 0; classLabel < inputDataset.getNumClasses() ; classLabel++) {
for (unsigned int numSamples = 1; numSamples <= numSamplesPerClass; numSamples++) {
numSamplesRemaining = MergedIndexs[classLabel].size();
if (numSamplesRemaining == 0) {
printf("The \"numSamplesPerClass\" variable is bigger that the samples for this class");
break;
}
randomNumber = random.getRandomNumberInt(0, numSamplesRemaining);
index = MergedIndexs[classLabel][randomNumber];
/* Remove added sample so that it is not added again */
MergedIndexs[classLabel].erase(MergedIndexs[classLabel].begin() + randomNumber);
trainingData.addSample( inputDataset[ index ].getClassLabel(),
inputDataset[ index ].getData() );
}
}
return trainingData;
}
bool KfoldTimeSeriesData::spiltDataIntoKFolds(const GRT::UINT K) {
kFoldValue = K;
//K can not be zero
if( K == 0 ){
std::cout << "spiltDataIntoKFolds(UINT K) - K can not be zero!" << std::endl;
return false;
}
//K can not be larger than the number of examples
if( K > inputDataset.getNumSamples()){
std::cout << "spiltDataIntoKFolds(UINT K,bool useStratifiedSampling) - K can not be 0!" << std::endl;
return false;
}
//K can not be larger than the number of examples in a specific class if the stratified sampling option is true
for(UINT c=0; c < inputDataset.getNumClasses(); c++) {
if( K > classTracker[c].counter ){
cout << "spiltDataIntoKFolds(UINT K,bool useStratifiedSampling) - K can not be larger than the number of samples in any given class!" << std::endl;
return false;
}
}
//Setup the dataset for k-fold cross validation
kFoldValue = K;
vector< UINT > indexs( inputDataset.getNumSamples() );
//Work out how many samples are in each fold, the last fold might have more samples than the others
UINT numSamplesPerFold = (UINT) floor( inputDataset.getNumSamples() / double(K) );
//Create the random partion indexs
Random random;
UINT randomIndex = 0;
//Break the data into seperate classes
vector< vector< UINT > > classData( inputDataset.getNumClasses() );
//Add the indexs to their respective classes
for(UINT i = 0; i < inputDataset.getNumSamples(); i++) {
classData[ inputDataset.getClassLabelIndexValue(
inputDataset[i].getClassLabel() ) ].push_back( i );
}
//Randomize the order of the indexs in each of the class index buffers
for(UINT c = 0; c < inputDataset.getNumClasses(); c++) {
UINT numSamples = (UINT)classData[c].size();
for(UINT x = 0; x < numSamples; x++) {
//Pick a random index
randomIndex = random.getRandomNumberInt(0, numSamples);
//Swap the indexs
SWAP( classData[c][ x ] , classData[c][ randomIndex ] );
}
}
//Resize the cross validation indexs buffer
crossValidationIndexs.resize( K );
for (UINT k = 0; k < K; k++) {
crossValidationIndexs[k].resize(inputDataset.getNumClasses());
}
//Loop over each of the classes and add the data equally to each of the k folds until there is no data left
vector< UINT >::iterator iter;
for(UINT c = 0; c < inputDataset.getNumClasses(); c++){
iter = classData[ c ].begin();
UINT k = 0;
while( iter != classData[c].end() ){
crossValidationIndexs[ k ][c].push_back( *iter );
iter++;
k = ++k % K;
}
}
crossValidationSetup = true;
return true;
}
////////////////////////// TRAINING FUNCTIONS //////////////////////////
bool DTW::train(LabelledTimeSeriesClassificationData labelledTrainingData){
UINT bestIndex = 0;
//Cleanup Memory
templatesBuffer.clear();
classLabels.clear();
trained = false;
continuousInputDataBuffer.clear();
if( trimTrainingData ){
LabelledTimeSeriesClassificationSampleTrimmer timeSeriesTrimmer(trimThreshold,maximumTrimPercentage);
LabelledTimeSeriesClassificationData tempData;
tempData.setNumDimensions( labelledTrainingData.getNumDimensions() );
for(UINT i=0; i<labelledTrainingData.getNumSamples(); i++){
if( timeSeriesTrimmer.trimTimeSeries( labelledTrainingData[i] ) ){
tempData.addSample(labelledTrainingData[i].getClassLabel(), labelledTrainingData[i].getData());
}else{
trainingLog << "Removing training sample " << i << " from the dataset as it could not be trimmed!" << endl;
}
}
//Overwrite the original training data with the trimmed dataset
labelledTrainingData = tempData;
}
if( labelledTrainingData.getNumSamples() == 0 ){
errorLog << "_train(LabelledTimeSeriesClassificationData &labelledTrainingData) - Can't train model as there are no samples in training data!" << endl;
return false;
}
//Assign
numClasses = labelledTrainingData.getNumClasses();
numTemplates = labelledTrainingData.getNumClasses();
numFeatures = labelledTrainingData.getNumDimensions();
templatesBuffer.resize( numClasses );
classLabels.resize( numClasses );
nullRejectionThresholds.resize( numClasses );
averageTemplateLength = 0;
//Need to copy the labelled training data incase we need to scale it or znorm it
LabelledTimeSeriesClassificationData trainingData( labelledTrainingData );
//Perform any scaling or normalisation
rangesBuffer = trainingData.getRanges();
if( useScaling ) scaleData( trainingData );
if( useZNormalisation ) znormData( trainingData );
//For each class, run a one-to-one DTW and find the template the best describes the data
for(UINT k=0; k<numTemplates; k++){
//Get the class label for the cth class
UINT classLabel = trainingData.getClassTracker()[k].classLabel;
LabelledTimeSeriesClassificationData classData = trainingData.getClassData( classLabel );
UINT numExamples = classData.getNumSamples();
bestIndex = 0;
//Set the class label of this template
templatesBuffer[k].classLabel = classLabel;
//Set the kth class label
classLabels[k] = classLabel;
trainingLog << "Training Template: " << k << " Class: " << classLabel << endl;
//Check to make sure we actually have some training examples
if(numExamples<1){
errorLog << "_train(LabelledTimeSeriesClassificationData &labelledTrainingData) - Can not train model: Num of Example is < 1! Class: " << classLabel << endl;
return false;
}
if(numExamples==1){//If we have just one training example then we have to use it as the template
bestIndex = 0;
nullRejectionThresholds[k] = 0.0;//TODO-We need a better way of calculating this!
warningLog << "_train(LabelledTimeSeriesClassificationData &labelledTrainingData) - Can't compute reject thresholds for class " << classLabel << " as there is only 1 training example" << endl;
}else{
//Search for the best training example for this class
if( !train_NDDTW(classData,templatesBuffer[k],bestIndex) ){
errorLog << "_train(LabelledTimeSeriesClassificationData &labelledTrainingData) - Failed to train template for class with label: " << classLabel << endl;
return false;
}
}
//Add the template with the best index to the buffer
int trainingMethod = 0;
if(useSmoothing) trainingMethod = 1;
switch (trainingMethod) {
case(0)://Standard Training
templatesBuffer[k].timeSeries = classData[bestIndex].getData();
break;
case(1)://Training using Smoothing
//Smooth the data, reducing its size by a factor set by smoothFactor
smoothData(classData[ bestIndex ].getData(),smoothingFactor,templatesBuffer[k].timeSeries);
break;
default:
cout<<"Can not train model: Unknown training method \n";
return false;
break;
}
if( offsetUsingFirstSample ){
offsetTimeseries( templatesBuffer[k].timeSeries );
}
//Add the average length of the training examples for this template to the overall averageTemplateLength
averageTemplateLength += templatesBuffer[k].averageTemplateLength;
}
//Flag that the models have been trained
trained = true;
averageTemplateLength = (UINT) averageTemplateLength/double(numTemplates);
//Recompute the null rejection thresholds
recomputeNullRejectionThresholds();
//Resize the prediction results to make sure it is setup for realtime prediction
continuousInputDataBuffer.clear();
continuousInputDataBuffer.resize(averageTemplateLength,vector<double>(numFeatures,0));
classLikelihoods.resize(numTemplates,DEFAULT_NULL_LIKELIHOOD_VALUE);
classDistances.resize(numTemplates,0);
predictedClassLabel = GRT_DEFAULT_NULL_CLASS_LABEL;
maxLikelihood = DEFAULT_NULL_LIKELIHOOD_VALUE;
//Training complete
return true;
}
bool HMM::train(LabelledTimeSeriesClassificationData trainingData){
if( trainingData.getNumSamples() == 0 ){
errorLog << "train(LabelledTimeSeriesClassificationData trainingData) - There are no training samples to train the HMM classifer!" << endl;
return false;
}
if( trainingData.getNumDimensions() != 1 ){
errorLog << "train(LabelledTimeSeriesClassificationData trainingData) - The number of dimensions in the training data must be 1. If your training data is not 1 dimensional then you must quantize the training data using one of the GRT quantization algorithms" << endl;
return false;
}
//Reset the HMM
trained = false;
useScaling = false;
numFeatures = trainingData.getNumDimensions();
numClasses = trainingData.getNumClasses();
models.clear();
classLabels.clear();
models.resize( numClasses );
classLabels.resize( numClasses );
//Init the models
for(UINT k=0; k<numClasses; k++){
models[k].resetModel(numStates,numSymbols,modelType,delta);
models[k].maxNumIter = maxNumIter;
models[k].minImprovement = minImprovement;
}
//Train each of the models
for(UINT k=0; k<numClasses; k++){
//Get the class ID of this gesture
UINT classID = trainingData.getClassTracker()[k].classLabel;
classLabels[k] = classID;
//Convert this classes training data into a list of observation sequences
LabelledTimeSeriesClassificationData classData = trainingData.getClassData( classID );
vector< vector< UINT > > observationSequences;
if( !convertDataToObservationSequence( classData, observationSequences ) ){
return false;
}
//Train the model
if( !models[k].train( observationSequences ) ){
errorLog << "train(LabelledTimeSeriesClassificationData &trainingData) - Failed to train HMM for class " << classID << endl;
return false;
}
}
//Compute the rejection thresholds
nullRejectionThresholds.resize(numClasses);
for(UINT k=0; k<numClasses; k++){
//Get the class ID of this gesture
UINT classID = trainingData.getClassTracker()[k].classLabel;
classLabels[k] = classID;
//Convert this classes training data into a list of observation sequences
LabelledTimeSeriesClassificationData classData = trainingData.getClassData( classID );
vector< vector< UINT > > observationSequences;
if( !convertDataToObservationSequence( classData, observationSequences ) ){
return false;
}
//Test the model
double loglikelihood = 0;
double avgLoglikelihood = 0;
for(UINT i=0; i<observationSequences.size(); i++){
loglikelihood = models[k].predict( observationSequences[i] );
avgLoglikelihood += fabs( loglikelihood );
cout << "Class: " << classID << " PredictedLogLikelihood: " << -loglikelihood << endl;
}
nullRejectionThresholds[k] = -( avgLoglikelihood / double( observationSequences.size() ) );
cout << "Class: " << classID << " NullRejectionThreshold: " << nullRejectionThresholds[k] << endl;
}
for(UINT k=0; k<numClasses; k++){
models[k].printAB();
}
trained = true;
return true;
}
