UnlabelledClassificationData UnlabelledClassificationData::getTrainingFoldData(UINT foldIndex) {
UnlabelledClassificationData trainingData;
if( !crossValidationSetup ) {
errorLog << "getTrainingFoldData(UINT foldIndex) - Cross Validation has not been setup! You need to call the spiltDataIntoKFolds(UINT K) function first before calling this function!" << endl;
return trainingData;
}
if( foldIndex >= kFoldValue ) return trainingData;
trainingData.setNumDimensions( numDimensions );
//Add the data to the training set, this will consist of all the data that is NOT in the foldIndex
UINT index = 0;
for(UINT k=0; k<kFoldValue; k++) {
if( k != foldIndex ) {
for(UINT i=0; i<crossValidationIndexs[k].size(); i++) {
index = crossValidationIndexs[k][i];
trainingData.addSample( data.getRowVector(index) );
}
}
}
return trainingData;
}
UnlabelledClassificationData LabelledClassificationData::reformatAsUnlabelledClassificationData() const{
UnlabelledClassificationData unlabelledData;
if( totalNumSamples == 0 ){
return unlabelledData;
}
unlabelledData.setNumDimensions( numDimensions );
for(UINT i=0; i<totalNumSamples; i++){
unlabelledData.addSample( data[i].getSample() );
}
return unlabelledData;
}
bool UnlabelledClassificationData::merge(UnlabelledClassificationData &unlabelledData) {
if( unlabelledData.getNumDimensions() != numDimensions ) {
errorLog << "merge(UnlabelledClassificationData &unlabelledData) - The number of dimensions in the unlabelledData (" << unlabelledData.getNumDimensions() << ") does not match the number of dimensions of this dataset (" << numDimensions << ")" << endl;
return false;
}
//The dataset has changed so flag that any previous cross validation setup will now not work
crossValidationSetup = false;
crossValidationIndexs.clear();
//Add the data from the labelledData to this instance
for(UINT i=0; i<unlabelledData.getNumSamples(); i++) {
addSample( unlabelledData[i] );
}
return true;
}
UnlabelledClassificationData LabelledTimeSeriesClassificationData::reformatAsUnlabelledClassificationData() const {
UnlabelledClassificationData unlabelledData;
if( totalNumSamples == 0 ){
return unlabelledData;
}
unlabelledData.setNumDimensions( numDimensions );
for(UINT i=0; i<totalNumSamples; i++){
for(UINT x=0; x<data[i].getLength(); x++){
unlabelledData.addSample( data[i].getData().getRowVector( x ) );
}
}
return unlabelledData;
}
UnlabelledClassificationData UnlabelledClassificationData::getTestFoldData(UINT foldIndex) {
UnlabelledClassificationData testData;
if( !crossValidationSetup ) return testData;
if( foldIndex >= kFoldValue ) return testData;
//Add the data to the training
testData.setNumDimensions( numDimensions );
UINT index = 0;
for(UINT i=0; i<crossValidationIndexs[ foldIndex ].size(); i++) {
index = crossValidationIndexs[ foldIndex ][i];
testData.addSample( data.getRowVector( index ) );
}
return testData;
}
bool KMeansQuantizer::train(UnlabelledClassificationData &trainingData){
MatrixDouble data = trainingData.getDataAsMatrixDouble();
return train( data );
}
