private IEnumerable <Configuration> SortedConfigsByError(List <Configuration> configs, List <Feature> model)
{
List <Tuple <Configuration, double> > list = new List <Tuple <Configuration, double> >();
foreach (Configuration c in configs)
{
double estimatedValue = FeatureSubsetSelection.estimate(model, c);
double realValue = c.GetNFPValue(GlobalState.currentNFP);
double error = 0;
switch (mlSettings.lossFunction)
{
case ML_Settings.LossFunction.RELATIVE:
error = Math.Abs((estimatedValue - realValue) / realValue);
break;
case ML_Settings.LossFunction.LEASTSQUARES:
error = Math.Pow(realValue - estimatedValue, 2);
break;
case ML_Settings.LossFunction.ABSOLUTE:
error = Math.Abs(realValue - estimatedValue);
break;
}
list.Add(new Tuple <Configuration, double>(c, error));
}
return(list.OrderByDescending(tuple => tuple.Item2).Select(tuple => tuple.Item1));
}
public void learn()
{
if (!hasNecessaryData())
return;
if (this.mLsettings.bagging)
{
//Get number of cores
int coreCount = 0;
foreach (var item in new System.Management.ManagementObjectSearcher("Select NumberOfCores from Win32_Processor").Get())
{
coreCount += int.Parse(item["NumberOfCores"].ToString());
}
createThreadPool(coreCount);
this.nbBaggings = this.mLsettings.baggingNumbers;
iCount = this.nbBaggings;
Random rand = new Random();
int nbOfConfigs = (testSet.Count * this.mLsettings.baggingTestDataFraction) / 100;
for (int i = 0; i < nbBaggings; i++)
{
InfluenceModel infMod = new InfluenceModel(GlobalState.varModel, GlobalState.currentNFP);
FeatureSubsetSelection sel = new FeatureSubsetSelection(infMod, this.mLsettings);
this.models.Add(sel);
List<int> selection = new List<int>();
for (int r = 0; r <= nbOfConfigs; r++)
{
selection.Add(rand.Next(nbOfConfigs));
}
List<Configuration> newTestSet = new List<Configuration>();
List<Configuration> newValidationSet = new List<Configuration>();
for (int r = 0; r <= selection.Count; r++)
{
if (selection.Contains(r))
newTestSet.Add(testSet[r]);
else
newValidationSet.Add(testSet[r]);
}
sel.setLearningSet(newTestSet);
sel.setValidationSet(newValidationSet);
Task task = EnqueueTask(() => sel.learn());
}
eventX.WaitOne(Timeout.Infinite, true);
averageModels();
}
else
{
InfluenceModel infMod = new InfluenceModel(GlobalState.varModel, GlobalState.currentNFP);
FeatureSubsetSelection sel = new FeatureSubsetSelection(infMod, this.mLsettings);
this.models.Add(sel);
sel.setLearningSet(testSet);
sel.setValidationSet(this.validationSet);
Stopwatch sw = new Stopwatch();
sw.Start();
sel.learn();
sw.Stop();
Console.WriteLine("Elapsed={0}", sw.Elapsed);
}
}
/// <summary>
/// Clears the binary and numeric selections stored in this object.
/// </summary>
public void clearSampling()
{
binarySamplings_Learning = "";
binarySelections_Learning = new List<List<BinaryOption>>();
binarySamplings_Validation = "";
binarySelections_Validation = new List<List<BinaryOption>>();
numericSamplings_Learning = "";
numericSelection_Learning = new List<Dictionary<NumericOption, double>>();
numericSamplings_Validation = "";
numericSelection_Validation = new List<Dictionary<NumericOption, double>>();
this.learning = new FeatureSubsetSelection();
}
