bool LabelledClassificationData::loadDatasetFromCSVFile(string filename,UINT classLabelColumnIndex){
numDimensions = 0;
datasetName = "NOT_SET";
infoText = "";
//Clear any previous data
clear();
//Parse the CSV file
FileParser parser;
if( !parser.parseCSVFile(filename,true) ){
errorLog << "loadDatasetFromCSVFile(string filename) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(string filename) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
if( parser.getColumnSize() <= 1 ){
errorLog << "loadDatasetFromCSVFile(string filename) - The CSV file does not have enough columns! It should contain at least two columns!" << endl;
return false;
}
//Set the number of dimensions
numDimensions = parser.getColumnSize()-1;
UINT classLabel = 0;
UINT j = 0;
UINT n = 0;
VectorDouble sample(numDimensions);
for(UINT i=0; i<parser.getRowSize(); i++){
//Get the class label
classLabel = Util::stringToInt( parser[i][classLabelColumnIndex] );
//Get the sample data
j=0;
n=0;
while( j != numDimensions ){
if( n != classLabelColumnIndex ){
sample[j++] = Util::stringToDouble( parser[i][n] );
}
n++;
}
//Add the labelled sample to the dataset
if( !addSample(classLabel, sample) ){
warningLog << "loadDatasetFromCSVFile(string filename) - Could not add sample " << i << " to the dataset!" << endl;
}
}
sortClassLabels();
return true;
}
bool MatrixDouble::loadFromCSVFile(const string &filename){
//Parse the CSV file
FileParser parser;
if( !parser.parseCSVFile(filename,true) ){
errorLog << "loadFromCSVFile(const string &filename) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadFromCSVFile(const string &filename) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
const UINT rows = parser.getRowSize();
const UINT cols = parser.getColumnSize();
//Resize the data
resize(rows, cols);
for(UINT i=0; i<rows; i++){
//Get the input vector
for(UINT j=0; j<cols; j++){
dataPtr[i][j] = Util::stringToDouble( parser[i][j] );
}
}
return true;
}
bool LabelledRegressionData::loadDatasetFromCSVFile(const string &filename,const UINT numInputDimensions,const UINT numTargetDimensions){
fstream file;
string value;
clear();
datasetName = "NOT_SET";
infoText = "";
//Clear any previous data
clear();
//Parse the CSV file
FileParser parser;
if( !parser.parseCSVFile(filename,true) ){
errorLog << "loadDatasetFromCSVFile(...) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(...) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
if( parser.getColumnSize() != numInputDimensions+numTargetDimensions ){
errorLog << "loadDatasetFromCSVFile(...) - The number of columns in the CSV file (" << parser.getColumnSize() << ")";
errorLog << " does not match the number of input dimensions plus the number of target dimensions (" << numInputDimensions+numTargetDimensions << ")" << endl;
return false;
}
//Setup the labelled classification data
setInputAndTargetDimensions(numInputDimensions, numTargetDimensions);
UINT n = 0;
VectorDouble inputVector(numInputDimensions);
VectorDouble targetVector(numTargetDimensions);
for(UINT i=0; i<parser.getRowSize(); i++){
//Reset n
n = 0;
//Get the input vector
for(UINT j=0; j<numInputDimensions; j++){
inputVector[j] = Util::stringToDouble( parser[i][n++] );
}
//Get the target vector
for(UINT j=0; j<numTargetDimensions; j++){
targetVector[j] = Util::stringToDouble( parser[i][n++] );
}
//Add the labelled sample to the dataset
if( !addSample(inputVector, targetVector) ){
warningLog << "loadDatasetFromCSVFile(string filename) - Could not add sample " << i << " to the dataset!" << endl;
}
}
return true;
}
bool UnlabelledClassificationData::loadDatasetFromCSVFile(string filename) {
string value;
datasetName = "NOT_SET";
infoText = "";
//Clear any previous data
clear();
//Parse the CSV file
FileParser parser;
if( !parser.parseCSVFile(filename,true) ) {
errorLog << "loadDatasetFromCSVFile(string filename) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ) {
errorLog << "loadDatasetFromCSVFile(string filename) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
//Setup the labelled classification data
numDimensions = parser.getColumnSize();
VectorDouble sample(numDimensions);
for(UINT i=0; i<parser.getRowSize(); i++) {
//Get the input vector
for(UINT j=0; j<numDimensions; j++) {
sample[j] = Util::stringToDouble( parser[i][j] );
}
//Add the labelled sample to the dataset
if( !addSample(sample) ) {
warningLog << "loadDatasetFromCSVFile(string filename) - Could not add sample " << i << " to the dataset!" << endl;
}
}
return true;
}
bool ClassificationData::loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex){
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,const UINT classLabelColumnIndex) - Failed to parse CSV file!" << endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndexe) - The CSV file does not have a consistent number of columns!" << endl;
return false;
}
if( parser.getColumnSize() <= 1 ){
errorLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex) - The CSV file does not have enough columns! It should contain at least two columns!" << endl;
return false;
}
//Set the number of dimensions
numDimensions = parser.getColumnSize()-1;
//Reserve the memory for the data
data.resize( parser.getRowSize(), ClassificationSample(numDimensions) );
//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 = Util::stringToInt( 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++] = Util::stringToDouble( 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;
}
bool TimeSeriesClassificationData::loadDatasetFromCSVFile(const std::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 std::string &filename) - Failed to parse CSV file!" << std::endl;
return false;
}
if( !parser.getConsistentColumnSize() ){
errorLog << "loadDatasetFromCSVFile(const std::string &filename) - The CSV file does not have a consistent number of columns!" << std::endl;
return false;
}
if( parser.getColumnSize() <= 2 ){
errorLog << "loadDatasetFromCSVFile(const std::string &filename) - The CSV file does not have enough columns! It should contain at least three columns!" << std::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;
VectorFloat sample(numDimensions);
MatrixFloat timeseries;
for(UINT i=0; i<parser.getRowSize(); i++){
sampleCounter = grt_from_str< UINT >( 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 std::string &filename,const UINT classLabelColumnIndex) - Could not add sample " << i << " to the dataset!" << std::endl;
}
timeseries.clear();
}
lastSampleCounter = sampleCounter;
//Get the class label
classLabel = grt_from_str< UINT >( parser[i][1] );
//Get the sample data
j=0;
n=2;
while( j != numDimensions ){
sample[j++] = grt_from_str< Float >( 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 std::string &filename,const UINT classLabelColumnIndex) - Could not add sample " << parser.getRowSize()-1 << " to the dataset!" << std::endl;
}
return true;
}
