/// <summary>
/// saves ProblemOriginal to a file, separates into tr3 and tr4, normalizes, and converts the libsvm files into arff.
/// </summary>
public static void VectorizeAndNormalize(libSVM_ExtendedProblem problem)
{
string trainFileName = GuiPreferences.Instance.WorkDirectory /*+ GuiPreferences.Instance.FileName*/ + "TrainSet";
//todo add proper named to saved files, check if null is logical at all.
//if ((Preferences.Instance.ProblemOriginal.samples != null))
//{
problem.Save(trainFileName + ".libsvm", 80 * 80 * 32 + 1);
GuiPreferences.Instance.setLog("saved Original Problem LibSVM file: " + trainFileName + ".libsvm");
//}
//separate DS to 3rd and 4th TR
////example: ExecuteSelectKthVectorScript(@"TrainSet", @"H:\My_Dropbox\VERE\MRI_data\Tirosh\20120508.Rapid+NullClass.day2\4\rtp\");
KthExtractionManager.ExecuteSelectKthVectorScript(/*GuiPreferences.Instance.FileName +*/ "TrainSet", GuiPreferences.Instance.WorkDirectory);
//GuiPreferences.Instance.setLog("Created TR3, TR4, TR5, TR6 files (5+6 depends if added to the python script)");
//NORMALIZING all TR Files
NormalizationManager.ScaleTrFiles(GuiPreferences.Instance.WorkDirectory);
//CONVERTING all TR files
WekaCommonFileOperation.ConvertToArff(GuiPreferences.Instance.WorkDirectory);
}
public static Instances WekaPipeline_Unprocessed(libSVM_ExtendedProblem _trialProblem)
{
//export to libsvm file
if (_trialProblem.samples == null)
{
GuiPreferences.Instance.setLog("Export Failed: Problem has no samples!");
return(null);
}
string trainFileName = GuiPreferences.Instance.WorkDirectory /*+ GuiPreferences.Instance.FileName*/ + "TrainSet";
//todo add proper named to saved files, check if null is logical at all.
if ((_trialProblem.samples != null))
{
_trialProblem.Save(trainFileName + ".libsvm");
GuiPreferences.Instance.setLog("saved Original Problem LibSVM file: " + trainFileName + ".libsvm");
}
//separate DS to 3rd and 4th TR
////example: ExecuteSelectKthVectorScript(@"TrainSet", @"H:\My_Dropbox\VERE\MRI_data\Tirosh\20120508.Rapid+NullClass.day2\4\rtp\");
KthExtractionManager.ExecuteSelectKthVectorScript(/*GuiPreferences.Instance.FileName +*/ "TrainSet", GuiPreferences.Instance.WorkDirectory);
GuiPreferences.Instance.setLog("Created TR3 & TR4 files");
//normalize 3rd and 4th TR files.
NormalizationManager.ScaleTrFiles(GuiPreferences.Instance.WorkDirectory);
GuiPreferences.Instance.setLog("Normalized TR3 & TR4 files");
//convert tr4 and tr3 to arff + REMOVE 204801 FAKE FEATURE, THAT WAS PLACES TO MAKE SURE WE GET 204800 FEATURES IN THE ARFF FILE.
if (WekaCommonFileOperation.ConvertLIBSVM2ARFF(GuiPreferences.Instance.WorkDirectory + "TrainSet_3th_vectors_scaledCS.libsvm", 204800))
{
GuiPreferences.Instance.setLog("Converted to ARFF: TrainSet_3th_vectors_scaledCS.libsvm");
}
if (WekaCommonFileOperation.ConvertLIBSVM2ARFF(GuiPreferences.Instance.WorkDirectory + "TrainSet_4th_vectors_scaledCS.libsvm", 204800))
{
GuiPreferences.Instance.setLog("Converted to ARFF: TrainSet_4th_vectors_scaledCS.libsvm");
}
//---------------------------------- filter tr3 based on top 1000 from tr4 (the trick) -----------------------------
//load TR4
ConverterUtils.DataSource source = new ConverterUtils.DataSource(GuiPreferences.Instance.WorkDirectory + "TrainSet_4th_vectors_scaledCS.libsvm.arff");
Instances data = source.getDataSet();
//assign last as index.
if (data.classIndex() == -1)
{
data.setClassIndex(data.numAttributes() - 1);
}
//if class not nominal, convert to
if (!data.classAttribute().isNominal())
{
var filter = new weka.filters.unsupervised.attribute.NumericToNominal();
filter.setOptions(weka.core.Utils.splitOptions("-R last"));
//filter.setAttributeIndices("last");
filter.setInputFormat(data);
data = Filter.useFilter(data, filter);
}
//run ig and get top 1000 or up to 1000 bigger than zero, from tr4
WekaTrainingMethods.useLowLevelInformationGainFeatureSelection(data);
TrainingTesting_SharedVariables._trainTopIGFeatures = Preferences.Instance.attsel.selectedAttributes();
//this should be done ONCE
Preferences.Instance.fastvector = RealTimeProcessing.CreateFastVector(TrainingTesting_SharedVariables._trainTopIGFeatures.Length);
GuiPreferences.Instance.setLog("created fast vector of length " + TrainingTesting_SharedVariables._trainTopIGFeatures.Length.ToString());
//serialize (save) topIG indices to file.
XMLSerializer.serializeArrayToFile(GuiPreferences.Instance.WorkDirectory + "TrainSet_" + GuiPreferences.Instance.NudClassifyUsingTR.ToString() + "th_vectors_scaledCS_filteredIG_indices.xml", TrainingTesting_SharedVariables._trainTopIGFeatures);
GuiPreferences.Instance.setLog("saved IG indices to a file (in the same order as IG gave it)");
//int [] _trainTopIGFeatures_loaded = DeserializeArrayToFile(GuiPreferences.Instance.WorkDirectory + "TrainSet_3th_vectors_scaledCS_filteredIG_indices.xml");
GuiPreferences.Instance.setLog(TrainingTesting_SharedVariables._trainTopIGFeatures.Length.ToString() + " features above zero value selected (including the Class feature)");
//load tr3
source = new ConverterUtils.DataSource(GuiPreferences.Instance.WorkDirectory + "TrainSet_" + GuiPreferences.Instance.NudClassifyUsingTR.ToString() + "th_vectors_scaledCS.libsvm.arff");
data = source.getDataSet();
//filter top IG
data = WekaTrainingMethods.useRemoveFilter(data, TrainingTesting_SharedVariables._trainTopIGFeatures, true);
//after filtering last feature needs to be the class
if (data.classIndex() == -1)
{
data.setClassIndex(data.numAttributes() - 1);
}
//save filtered to a file
WekaCommonFileOperation.SaveLIBSVM(data, GuiPreferences.Instance.WorkDirectory + "TrainSet_" + GuiPreferences.Instance.NudClassifyUsingTR.ToString() + "th_vectors_scaledCS_filteredIG");
return(data);
}