bool TimeSeriesClassificationDataStream::loadDatasetFromFile(const string &filename){
std::fstream file;
file.open(filename.c_str(), std::ios::in);
UINT numClasses = 0;
UINT numTrackingPoints = 0;
clear();
if( !file.is_open() ){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to open file!" << endl;
return false;
}
string word;
//Check to make sure this is a file with the Training File Format
file >> word;
if(word != "GRT_LABELLED_CONTINUOUS_TIME_SERIES_CLASSIFICATION_FILE_V1.0"){
file.close();
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find file header!" << endl;
return false;
}
//Get the name of the dataset
file >> word;
if(word != "DatasetName:"){
errorLog << "loadDatasetFromFile(string filename) - failed to find DatasetName!" << endl;
file.close();
return false;
}
file >> datasetName;
file >> word;
if(word != "InfoText:"){
errorLog << "loadDatasetFromFile(string filename) - failed to find InfoText!" << endl;
file.close();
return false;
}
//Load the info text
file >> word;
infoText = "";
while( word != "NumDimensions:" ){
infoText += word + " ";
file >> word;
}
//Get the number of dimensions in the training data
if(word != "NumDimensions:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find NumDimensions!" << endl;
file.close();
return false;
}
file >> numDimensions;
//Get the total number of training examples in the training data
file >> word;
if(word != "TotalNumSamples:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find TotalNumSamples!" << endl;
file.close();
return false;
}
file >> totalNumSamples;
//Get the total number of classes in the training data
file >> word;
if(word != "NumberOfClasses:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find NumberOfClasses!" << endl;
file.close();
return false;
}
file >> numClasses;
//Resize the class counter buffer and load the counters
classTracker.resize(numClasses);
//Get the total number of classes in the training data
file >> word;
if(word != "ClassIDsAndCounters:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find ClassIDsAndCounters!" << endl;
file.close();
return false;
}
for(UINT i=0; i<classTracker.size(); i++){
file >> classTracker[i].classLabel;
file >> classTracker[i].counter;
}
//Get the NumberOfPositionTrackers
file >> word;
if(word != "NumberOfPositionTrackers:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find NumberOfPositionTrackers!" << endl;
file.close();
return false;
}
file >> numTrackingPoints;
timeSeriesPositionTracker.resize( numTrackingPoints );
//Get the TimeSeriesPositionTrackers
file >> word;
if(word != "TimeSeriesPositionTrackers:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find TimeSeriesPositionTrackers!" << endl;
file.close();
return false;
}
for(UINT i=0; i<timeSeriesPositionTracker.size(); i++){
UINT classLabel;
UINT startIndex;
UINT endIndex;
file >> classLabel;
file >> startIndex;
file >> endIndex;
timeSeriesPositionTracker[i].setTracker(startIndex,endIndex,classLabel);
}
//Check if the dataset should be scaled using external ranges
file >> word;
if(word != "UseExternalRanges:"){
errorLog << "loadDatasetFromFile(string filename) - failed to find DatasetName!" << endl;
file.close();
return false;
}
file >> useExternalRanges;
//If we are using external ranges then load them
if( useExternalRanges ){
externalRanges.resize(numDimensions);
for(UINT i=0; i<externalRanges.size(); i++){
file >> externalRanges[i].minValue;
file >> externalRanges[i].maxValue;
}
}
//Get the main time series data
file >> word;
if(word != "LabelledContinuousTimeSeriesClassificationData:"){
errorLog<< "loadDatasetFromFile(string fileName) - Failed to find LabelledContinuousTimeSeriesClassificationData!" << endl;
file.close();
return false;
}
//Reset the memory
data.resize( totalNumSamples, ClassificationSample() );
//Load each sample
for(UINT i=0; i<totalNumSamples; i++){
UINT classLabel = 0;
vector<double> sample(numDimensions);
file >> classLabel;
for(UINT j=0; j<numDimensions; j++){
file >> sample[j];
}
data[i].set(classLabel,sample);
}
file.close();
return true;
}
bool ClassificationData::loadDatasetFromCSVFile(const std::string &filename,const UINT classLabelColumnIndex){
numDimensions = 0;
datasetName = "NOT_SET";
infoText = "";
//Clear any previous data
clear();
//Parse the CSV file
FileParser parser;
Timer timer;
timer.start();
if( !parser.parseCSVFile(filename,true) ){
errorLog << "loadDatasetFromCSVFile(const std::string &filename,const UINT classLabelColumnIndex) - Failed to parse CSV file!" << std::endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(const std::string &filename,const UINT classLabelColumnIndexe) - The CSV file does not have a consistent number of columns!" << std::endl;
return false;
}
if( parser.getColumnSize() <= 1 ){
errorLog << "loadDatasetFromCSVFile(const std::string &filename,const UINT classLabelColumnIndex) - The CSV file does not have enough columns! It should contain at least two columns!" << std::endl;
return false;
}
//Set the number of dimensions
numDimensions = parser.getColumnSize()-1;
timer.start();
//Reserve the memory for the data
data.resize( parser.getRowSize(), ClassificationSample(numDimensions) );
timer.start();
//Loop over the samples and add them to the data set
UINT classLabel = 0;
UINT j = 0;
UINT n = 0;
totalNumSamples = parser.getRowSize();
for(UINT i=0; i<totalNumSamples; i++){
//Get the class label
classLabel = grt_from_str< UINT >( parser[i][classLabelColumnIndex] );
//Set the class label
data[i].setClassLabel( classLabel );
//Get the sample data
j=0;
n=0;
while( j != numDimensions ){
if( n != classLabelColumnIndex ){
data[i][j++] = grt_from_str< Float >( parser[i][n] );
}
n++;
}
//Update the class tracker
if( classTracker.size() == 0 ){
ClassTracker tracker(classLabel,1);
classTracker.push_back(tracker);
}else{
bool labelFound = false;
const size_t numClasses = classTracker.size();
for(size_t i=0; i<numClasses; i++){
if( classLabel == classTracker[i].classLabel ){
classTracker[i].counter++;
labelFound = true;
break;
}
}
if( !labelFound ){
ClassTracker tracker(classLabel,1);
classTracker.push_back(tracker);
}
}
}
//Sort the class labels
sortClassLabels();
return true;
}
ClassificationSample TimeSeriesClassificationDataStream::getNextSample(){
if( totalNumSamples == 0 ) return ClassificationSample();
UINT index = playbackIndex++ % totalNumSamples;
return data[ index ];
}
