public override IClusteringProblemData ImportData(string path) {
var csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
// turn of input variables that are constant in the training partition
var allowedInputVars = new List<string>();
var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
if (trainingIndizes.Count() >= 2) {
foreach (var variableName in dataset.DoubleVariables) {
if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0)
allowedInputVars.Add(variableName);
}
} else {
allowedInputVars.AddRange(dataset.DoubleVariables);
}
ClusteringProblemData clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
int trainingPartEnd = trainingIndizes.Last();
clusteringData.TrainingPartition.Start = trainingIndizes.First();
clusteringData.TrainingPartition.End = trainingPartEnd;
clusteringData.TestPartition.Start = trainingPartEnd;
clusteringData.TestPartition.End = csvFileParser.Rows;
clusteringData.Name = Path.GetFileName(path);
return clusteringData;
}
protected override IClusteringProblemData ImportData(string path, DataAnalysisImportType type, TableFileParser csvFileParser) {
List<IList> values = csvFileParser.Values;
if (type.Shuffle) {
values = Shuffle(values);
}
Dataset dataset = new Dataset(csvFileParser.VariableNames, values);
// turn of input variables that are constant in the training partition
var allowedInputVars = new List<string>();
int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
if (trainingIndizes.Count() >= 2) {
foreach (var variableName in dataset.DoubleVariables) {
if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0)
allowedInputVars.Add(variableName);
}
} else {
allowedInputVars.AddRange(dataset.DoubleVariables);
}
ClusteringProblemData clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
clusteringData.TrainingPartition.Start = 0;
clusteringData.TrainingPartition.End = trainingPartEnd;
clusteringData.TestPartition.Start = trainingPartEnd;
clusteringData.TestPartition.End = csvFileParser.Rows;
clusteringData.Name = Path.GetFileName(path);
return clusteringData;
}
public ClusteringProblem()
: base()
{
ProblemData = new ClusteringProblemData();
}
private ClusteringProblemData(ClusteringProblemData original, Cloner cloner)
: base(original, cloner)
{
}
private IDataAnalysisProblemData CreateClusteringData(ClusteringProblemData oldProblemData) {
return new ClusteringProblemData(ExportedDataset, GetDoubleInputVariables(String.Empty), Transformations);
}
private ClusteringProblemData(ClusteringProblemData original, Cloner cloner)
: base(original, cloner) {
}
