void FeatureFileIO::SaveFeatureFileMultipleParts (const KKStr& _fileName,
FeatureNumListConst& _selFeatures,
FeatureVectorList& _examples,
VolConstBool& _cancelFlag,
bool& _successful,
RunLog& _log
)
{
kkuint32 numExamplesWritten = 0;
SaveFeatureFile (_fileName, _selFeatures, _examples, numExamplesWritten, _cancelFlag, _successful, _log);
if (_cancelFlag || (!_successful))
return;
if (_examples.QueueSize () > 64000)
{
kkint32 numPartsNeeded = (_examples.QueueSize () / 64000);
if ((_examples.QueueSize () % 64000) > 0)
numPartsNeeded++;
kkuint32 maxPartSize = (_examples.QueueSize () / numPartsNeeded) + 1;
kkint32 partNum = 0;
FeatureVectorList::const_iterator idx = _examples.begin ();
while ((idx != _examples.end ()) && (_successful) && (!_cancelFlag))
{
FeatureVectorListPtr part = _examples.ManufactureEmptyList (false);
while ((idx != _examples.end ()) && (part->QueueSize () < maxPartSize))
{
part->PushOnBack (*idx);
idx++;
}
KKStr partFileName = osRemoveExtension (_fileName) + "-" +
StrFormatInt (partNum, "00") + "." +
osGetFileExtension (_fileName);
SaveFeatureFile (partFileName, _selFeatures, *part, numExamplesWritten, _cancelFlag, _successful, _log);
partNum++;
delete part; part = NULL;
}
}
} /* SaveFeatureFileMultipleParts */
/**
* @brief Will run M number of Train then Test passes.
*
* @param[in] numExamplsToUseForTraining The number examples in each ordering(group)
* that are to be used for training, the remaining examples will be
* used as test data.
*/
void CrossValidationMxN::RunTrainAndTest (kkuint32 numExamplsToUseForTraining,
RunLog& log
)
{
CleanUpMemory ();
meanConfusionMatrix = new ConfusionMatrix2 (*(orderings->MLClasses ()));
kkuint32 cvIDX = 0;
MLClassListPtr mlClasses = orderings->MLClasses ();
for (cvIDX = 0; cvIDX < numOfOrderings; cvIDX++)
{
FeatureVectorListPtr data = orderings->Ordering (cvIDX);
FeatureVectorList trainingData (fileDesc, false);
FeatureVectorList testData (fileDesc, false);
FeatureVectorList::iterator fvIDX;
for (fvIDX = data->begin (); fvIDX != data->end (); fvIDX++)
{
FeatureVectorPtr example = *fvIDX;
if (trainingData.QueueSize () < numExamplsToUseForTraining)
trainingData.PushOnBack (example);
else
testData.PushOnBack (example);
}
CrossValidationPtr cv = new CrossValidation (config,
&trainingData,
mlClasses,
numOfFolds,
false,
fileDesc,
log,
cancelFlag
);
cv->RunValidationOnly (&testData,
NULL, // No McNemars test going to be performed.
log
);
accuracies.push_back (cv->Accuracy ());
supportPoints.push_back ((float)cv->NumOfSupportVectors ());
trainingTimes.push_back (cv->TrainTimeTotal ());
testTimes.push_back (cv->TestTimeTotal ());
meanConfusionMatrix->AddIn (*(cv->ConfussionMatrix ()), log);
delete cv;
}
CalcMeanAndStdDev (accuracies, accuracyMean, accuracyStdDev);
CalcMeanAndStdDev (supportPoints, supportPointsMean, supportPointsStdDev);
CalcMeanAndStdDev (trainingTimes, trainingTimeMean, trainingTimeStdDev);
CalcMeanAndStdDev (testTimes, testTimeMean, testTimeStdDev);
double factor = 1.0 / (double)numOfOrderings;
meanConfusionMatrix->FactorCounts (factor);
} /* RunTrainAndTest */