bool TimeSeriesClassificationData::loadDatasetFromCSVFile(const string &filename){
numDimensions = 0;
datasetName = "NOT_SET";
infoText = "";
//Clear any previous data
clear();
//Parse the CSV file
FileParser parser;
if( !parser.parseCSVFile(filename,true) ){
errorLog << "loadDatasetFromCSVFile(const string &filename) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(const string &filename) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
if( parser.getColumnSize() <= 2 ){
errorLog << "loadDatasetFromCSVFile(const string &filename) - The CSV file does not have enough columns! It should contain at least three columns!" << endl;
return false;
}
//Set the number of dimensions
numDimensions = parser.getColumnSize()-2;
//Reserve the memory for the data
data.reserve( parser.getRowSize() );
UINT sampleCounter = 0;
UINT lastSampleCounter = 0;
UINT classLabel = 0;
UINT j = 0;
UINT n = 0;
VectorDouble sample(numDimensions);
MatrixDouble timeseries;
for(UINT i=0; i<parser.getRowSize(); i++){
sampleCounter = Util::stringToInt( parser[i][0] );
//Check to see if a new timeseries has started, if so then add the previous time series as a sample and start recording the new time series
if( sampleCounter != lastSampleCounter && i != 0 ){
//Add the labelled sample to the dataset
if( !addSample(classLabel, timeseries) ){
warningLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex) - Could not add sample " << i << " to the dataset!" << endl;
}
timeseries.clear();
}
lastSampleCounter = sampleCounter;
//Get the class label
classLabel = Util::stringToInt( parser[i][1] );
//Get the sample data
j=0;
n=2;
while( j != numDimensions ){
sample[j++] = Util::stringToDouble( parser[i][n] );
n++;
}
//Add the sample to the timeseries
timeseries.push_back( sample );
}
if ( timeseries.getSize() > 0 )
//Add the labelled sample to the dataset
if( !addSample(classLabel, timeseries) ){
warningLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex) - Could not add sample " << parser.getRowSize()-1 << " to the dataset!" << endl;
}
return true;
}
int main (int argc, const char * argv[])
{
//Create a new instance of the TimeSeriesClassificationData
TimeSeriesClassificationData 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;
MatrixDouble trainingSample;
//For now we will just add 10 x 20 random walk data timeseries
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++){
//Clear any previous timeseries
trainingSample.clear();
//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<startPos.size(); j++){
sample[j] += random.getRandomNumberUniform(-0.1,0.1);
}
//Add the sample to the training sample
trainingSample.push_back( sample );
}
//Add the training sample to the dataset
trainingData.addSample( gestureLabel, trainingSample );
}
}
//After recording your training data you can then save it to a file
if( !trainingData.saveDatasetToFile( "TrainingData.txt" ) ){
cout << "Failed to save dataset to file!\n";
return EXIT_FAILURE;
}
//This can then be loaded later
if( !trainingData.loadDatasetFromFile( "TrainingData.txt" ) ){
cout << "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;
//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 you want to partition the dataset into a training dataset and a test dataset then you can use the partition function
//A value of 80 means that 80% of the original data will remain in the training dataset and 20% will be returned as the test dataset
TimeSeriesClassificationData testData = trainingData.partition( 80 );
//If you have multiple datasets that you want to merge together then use the merge function
if( !trainingData.merge( testData ) ){
cout << "Failed to merge datasets!\n";
return EXIT_FAILURE;
}
//If you want to run K-Fold cross validation using the dataset then you should first spilt the dataset into K-Folds
//A value of 10 splits the dataset into 10 folds and the true parameter signals that stratified sampling should be used
if( !trainingData.spiltDataIntoKFolds( 10, true ) ){
cout << "Failed to spiltDataIntoKFolds!\n";
return EXIT_FAILURE;
}
//After you have called the spilt function you can then get the training and test sets for each fold
for(UINT foldIndex=0; foldIndex<10; foldIndex++){
TimeSeriesClassificationData foldTrainingData = trainingData.getTrainingFoldData( foldIndex );
TimeSeriesClassificationData foldTestingData = trainingData.getTestFoldData( foldIndex );
}
//If need you can clear any training data that you have recorded
trainingData.clear();
return EXIT_SUCCESS;
}
