TimeSeriesClassificationDataStream KfoldTimeSeriesData::getTestFoldData(const UINT foldIndex) const {
TimeSeriesClassificationDataStream testData;
if( !crossValidationSetup ) {
cout << "getTestFoldData(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 testData;
}
if( foldIndex >= kFoldValue ) {
cout << "Fold index too big" << endl;
return testData;
}
//Add the data to the training
testData.setNumDimensions( numDimensions );
UINT index = 0;
for(UINT classLabel = 0; classLabel < crossValidationIndexs[foldIndex].size(); classLabel++) {
for (UINT i = 0; i < crossValidationIndexs[foldIndex][classLabel].size(); i++) {
index = crossValidationIndexs[foldIndex][classLabel][i];
testData.addSample( inputDataset[ index ].getClassLabel(),
inputDataset[ index ].getData() );
}
}
return testData;
}
TimeSeriesClassificationDataStream TimeSeriesClassificationDataStream::getSubset(const UINT startIndex,const UINT endIndex) const {
TimeSeriesClassificationDataStream subset;
if( endIndex >= totalNumSamples ){
warningLog << "getSubset(const UINT startIndex,const UINT endIndex) - The endIndex is greater than or equal to the number of samples in the current dataset!" << endl;
return subset;
}
if( startIndex >= endIndex ){
warningLog << "getSubset(const UINT startIndex,const UINT endIndex) - The startIndex is greater than or equal to the endIndex!" << endl;
return subset;
}
//Set the header info
subset.setNumDimensions( getNumDimensions() );
subset.setDatasetName( getDatasetName() );
subset.setInfoText( getInfoText() );
//Add the data
for(UINT i=startIndex; i<=endIndex; i++){
subset.addSample(data[i].getClassLabel(), data[i].getSample());
}
return subset;
}
bool KMeansFeatures::train_(TimeSeriesClassificationDataStream &trainingData){
MatrixDouble data = trainingData.getDataAsMatrixDouble();
return train_( data );
}
bool RBMQuantizer::train_(TimeSeriesClassificationDataStream &trainingData){
MatrixDouble data = trainingData.getDataAsMatrixDouble();
return train_( data );
}
int main (int argc, const char * argv[])
{
//Create a new instance of the TimeSeriesClassificationDataStream
TimeSeriesClassificationDataStream trainingData;
//Set the dimensionality of the data (you need to do this before you can add any samples)
trainingData.setNumDimensions( 3 );
//You can also give the dataset a name (the name should have no spaces)
trainingData.setDatasetName("DummyData");
//You can also add some info text about the data
trainingData.setInfoText("This data contains some dummy timeseries data");
//Here you would record a time series, when you have finished recording the time series then add the training sample to the training data
UINT gestureLabel = 1;
//For now we will just add 10 x 20 random walk data timeseries, each timeseries will be seperated by some noise which represents the null class
Random random;
for(UINT k=0; k<10; k++){//For the number of classes
gestureLabel = k+1;
//Get the init random walk position for this gesture
VectorDouble startPos( trainingData.getNumDimensions() );
for(UINT j=0; j<startPos.size(); j++){
startPos[j] = random.getRandomNumberUniform(-1.0,1.0);
}
//Generate the 20 time series
for(UINT x=0; x<20; x++){
//Generate the random walk
UINT randomWalkLength = random.getRandomNumberInt(90, 110);
VectorDouble sample = startPos;
for(UINT i=0; i<randomWalkLength; i++){
for(UINT j=0; j<sample.size(); j++){
sample[j] += random.getRandomNumberUniform(-0.1,0.1);
}
//Add the training sample to the dataset
trainingData.addSample(gestureLabel, sample );
}
//now add some noise to represent a null class
for(UINT i=0; i<50; i++){
for(UINT j=0; j<sample.size(); j++){
sample[j] = random.getRandomNumberUniform(-0.01,0.01);
}
//Add the training sample to the dataset, note that we set the gesture label to 0
trainingData.addSample(0, sample );
}
}
}
//After recording your training data you can then save it to a file
if( !trainingData.saveDatasetToFile( "TrainingData.txt" ) ){
cout << "ERROR: Failed to save dataset to file!\n";
return EXIT_FAILURE;
}
//This can then be loaded later
if( !trainingData.loadDatasetFromFile( "TrainingData.txt" ) ){
cout << "ERROR: Failed to load dataset from file!\n";
return EXIT_FAILURE;
}
//This is how you can get some stats from the training data
string datasetName = trainingData.getDatasetName();
string infoText = trainingData.getInfoText();
UINT numSamples = trainingData.getNumSamples();
UINT numDimensions = trainingData.getNumDimensions();
UINT numClasses = trainingData.getNumClasses();
cout << "Dataset Name: " << datasetName << endl;
cout << "InfoText: " << infoText << endl;
cout << "NumberOfSamples: " << numSamples << endl;
cout << "NumberOfDimensions: " << numDimensions << endl;
cout << "NumberOfClasses: " << numClasses << endl;
//Print the start and end indexs of each time series
vector< TimeSeriesPositionTracker > positionTracker = trainingData.getTimeSeriesPositionTracker();
for(UINT i=0; i<positionTracker.size(); i++){
cout << "Class Label: " << positionTracker[i].getClassLabel() << "\t";
cout << "Start Index: " << positionTracker[i].getStartIndex() << "\t";
cout << "End Index: " << positionTracker[i].getEndIndex() << "\t";
cout << "Length: " << positionTracker[i].getLength() << endl;
}
//You can also get the minimum and maximum ranges of the data
vector< MinMax > ranges = trainingData.getRanges();
cout << "The ranges of the dataset are: \n";
for(UINT j=0; j<ranges.size(); j++){
cout << "Dimension: " << j << " Min: " << ranges[j].minValue << " Max: " << ranges[j].maxValue << endl;
}
//If need you can clear any training data that you have recorded
trainingData.clear();
return EXIT_SUCCESS;
}