private static void CreateClusters(IDataset data, string target, int contours, out IClusteringModel contourCluster, out Dictionary <int, string> contourNames, out double[][] borders)
{
var cpd = new ClusteringProblemData((Dataset)data, new[] { target });
contourCluster = KMeansClustering.CreateKMeansSolution(cpd, contours, 3).Model;
borders = Enumerable.Range(0, contours).Select(x => new[] { double.MaxValue, double.MinValue }).ToArray();
var clusters = contourCluster.GetClusterValues(cpd.Dataset, cpd.AllIndices).ToArray();
var targetvalues = cpd.Dataset.GetDoubleValues(target).ToArray();
foreach (var i in cpd.AllIndices)
{
var cl = clusters[i] - 1;
var clv = targetvalues[i];
if (borders[cl][0] > clv)
{
borders[cl][0] = clv;
}
if (borders[cl][1] < clv)
{
borders[cl][1] = clv;
}
}
contourNames = new Dictionary <int, string>();
for (var i = 0; i < contours; i++)
{
contourNames.Add(i, "[" + borders[i][0] + ";" + borders[i][1] + "]");
}
}
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 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);
}
private IDataAnalysisProblemData CreateClusteringData(ClusteringProblemData oldProblemData)
{
return(new ClusteringProblemData(ExportedDataset, GetDoubleInputVariables(String.Empty), Transformations));
}
