public void PerformClassification(OperationContext context, ExperimentTruthTable truthTable, ClassificationDatasetSeparationEnum distributionRule, ILogBuilder log)
{
log.log("Performing classification");
if (truthTable == null)
{
truthTable = new ExperimentTruthTable();
notes.log(":: DEPLOYING IN-FOLD TRUTH TABLE ::");
truthTable.Deploy(context.featureSpace, context.spaceModel.labels.Select(x => x.name).ToList(), log);
}
DistributeTrainingAndTestSets(distributionRule, truthTable, context.featureSpace, log, context.testSet, context.trainingSet);
if (!context.trainingSet.Any())
{
notes.log("TRAINING SET EMPTY ---- APPLYING 1:1 EXPERIMENT SHEME: training and test set are the same");
}
else
{
notes.log("Training [" + classifier.name + "] with [" + context.trainingSet.Count + "] feature vectors.");
classifier.DoTraining(context.trainingSet, log);
log.log("Training [" + classifier.name + "] completed.");
notes.log("Testing [" + classifier.name + "] with [" + context.testSet.Count + "] feature vectors.");
context.testResults = new List <FeatureVectorWithLabelID>();
var ts = context.testSet.Select(x => x.vector);
foreach (FeatureVector fv in ts)
{
Int32 result = classifier.DoSelect(fv, log);
FeatureVectorWithLabelID fvl = new FeatureVectorWithLabelID(fv, result);
context.testResults.Add(fvl);
}
log.log("Testing [" + classifier.name + "] completed.");
}
}
public void PerformClassification(OperationContext context, ExperimentTruthTable truthTable, ClassificationDatasetSeparationEnum distributionRule, ILogBuilder log)
{
log.log("Performing classification");
if (truthTable == null)
{
truthTable = new ExperimentTruthTable();
notes.log(":: DEPLOYING IN-FOLD TRUTH TABLE ::");
log.log(":: DEPLOYING IN-FOLD TRUTH TABLE ::");
truthTable.Deploy(context.featureSpace, context.spaceModel.labels.Select(x => x.name).ToList(), log);
}
DistributeTrainingAndTestSets(distributionRule, truthTable, context.featureSpace, log, context.testSet, context.trainingSet);
if (!context.trainingSet.Any())
{
notes.log("TRAINING SET EMPTY ---- APPLYING 1:1 EXPERIMENT SHEME: training and test set are the same");
}
else
{
notes.log("Training [" + classifier.name + "] with [" + context.trainingSet.Count + "] feature vectors.");
classifier.DoTraining(context.trainingSet, log);
log.log("Training [" + classifier.name + "] completed.");
notes.log("Testing [" + classifier.name + "] with [" + context.testSet.Count + "] feature vectors.");
context.testResults = new List <FeatureVectorWithLabelID>();
var ts = context.testSet.Select(x => x.vector);
List <Int32> distinctResults = new List <int>();
foreach (FeatureVector fv in ts)
{
Int32 result = classifier.DoSelect(fv, log);
if (!distinctResults.Contains(result))
{
distinctResults.Add(result);
}
FeatureVectorWithLabelID fvl = new FeatureVectorWithLabelID(fv, result);
context.testResults.Add(fvl);
}
if (distinctResults.Count < truthTable.labels_without_unknown.Count)
{
List <String> no_match_labels = truthTable.labels_without_unknown.ToList();
foreach (Int32 d in distinctResults)
{
no_match_labels.Remove(truthTable.labels_without_unknown[d]);
}
log.log("WARNING --- [" + classifier.name + "] ONLY [" + distinctResults.Count + "] of [" + truthTable.labels_without_unknown.Count + "] were assigned by the classifier");
foreach (String l in no_match_labels)
{
log.log("Class [" + l + "] received no assigment");
}
foreach (var v in context.testSet)
{
var dist = v.GetDistinctValuesAtVector();
if (dist.Count < 2)
{
log.log("Test vector [" + v.name + "] has [" + dist.Count + "] distinct values at [" + v.dimensions.Length + "] dimensions!");
}
}
foreach (var v in context.trainingSet)
{
var dist = v.GetDistinctValuesAtVector();
if (dist.Count < 2)
{
log.log("Training vector [" + v.name + "] has [" + dist.Count + "] distinct values at [" + v.dimensions.Length + "] dimensions!");
}
}
}
log.log("Testing [" + classifier.name + "] completed.");
}
}