protected override IClassificationProblemData ImportData(string path, ClassificationImportType type, TableFileParser csvFileParser)
{
int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
List <IList> values = csvFileParser.Values;
if (type.Shuffle)
{
values = Shuffle(values);
if (type.UniformlyDistributeClasses)
{
values = Shuffle(values, csvFileParser.VariableNames.ToList().FindIndex(x => x.Equals(type.TargetVariable)),
type.TrainingPercentage, out trainingPartEnd);
}
}
Dataset dataset = new Dataset(csvFileParser.VariableNames, values);
// turn of input variables that are constant in the training partition
var allowedInputVars = new List <string>();
var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
if (trainingIndizes.Count() >= 2)
{
foreach (var variableName in dataset.DoubleVariables)
{
if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
variableName != type.TargetVariable)
{
allowedInputVars.Add(variableName);
}
}
}
else
{
allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(type.TargetVariable)));
}
ClassificationProblemData classificationData = new ClassificationProblemData(dataset, allowedInputVars, type.TargetVariable);
classificationData.TrainingPartition.Start = 0;
classificationData.TrainingPartition.End = trainingPartEnd;
classificationData.TestPartition.Start = trainingPartEnd;
classificationData.TestPartition.End = csvFileParser.Rows;
classificationData.Name = Path.GetFileName(path);
return(classificationData);
}
protected override IClassificationProblemData ImportData(string path, ClassificationImportType type, TableFileParser csvFileParser) {
int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
List<IList> values = csvFileParser.Values;
if (type.Shuffle) {
values = Shuffle(values);
if (type.UniformlyDistributeClasses) {
values = Shuffle(values, csvFileParser.VariableNames.ToList().FindIndex(x => x.Equals(type.TargetVariable)),
type.TrainingPercentage, out trainingPartEnd);
}
}
Dataset dataset = new Dataset(csvFileParser.VariableNames, values);
// turn of input variables that are constant in the training partition
var allowedInputVars = new List<string>();
var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
if (trainingIndizes.Count() >= 2) {
foreach (var variableName in dataset.DoubleVariables) {
if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
variableName != type.TargetVariable)
allowedInputVars.Add(variableName);
}
} else {
allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(type.TargetVariable)));
}
ClassificationProblemData classificationData = new ClassificationProblemData(dataset, allowedInputVars, type.TargetVariable);
classificationData.TrainingPartition.Start = 0;
classificationData.TrainingPartition.End = trainingPartEnd;
classificationData.TestPartition.Start = trainingPartEnd;
classificationData.TestPartition.End = csvFileParser.Rows;
classificationData.Name = Path.GetFileName(path);
return classificationData;
}