public override ITimeSeriesPrognosisProblemData ImportData(string path) {
TableFileParser csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
string targetVar = csvFileParser.VariableNames.Last();
IEnumerable<string> allowedInputVars = dataset.DoubleVariables.Where(x => !x.Equals(targetVar));
ITimeSeriesPrognosisProblemData timeSeriesPrognosisData = new TimeSeriesPrognosisProblemData(dataset, allowedInputVars, targetVar);
int trainingPartEnd = csvFileParser.Rows * 2 / 3;
timeSeriesPrognosisData.TrainingPartition.Start = 0;
timeSeriesPrognosisData.TrainingPartition.End = trainingPartEnd;
timeSeriesPrognosisData.TestPartition.Start = trainingPartEnd;
timeSeriesPrognosisData.TestPartition.End = csvFileParser.Rows;
int pos = path.LastIndexOf('\\');
if (pos < 0)
timeSeriesPrognosisData.Name = path;
else {
pos++;
timeSeriesPrognosisData.Name = path.Substring(pos, path.Length - pos);
}
return timeSeriesPrognosisData;
}
private IDataAnalysisProblemData CreateTimeSeriesPrognosisData(TimeSeriesPrognosisProblemData oldProblemData) {
var targetVariable = oldProblemData.TargetVariable;
if (!context.Data.VariableNames.Contains(targetVariable))
targetVariable = context.Data.VariableNames.First();
var inputVariables = GetDoubleInputVariables(targetVariable);
var newProblemData = new TimeSeriesPrognosisProblemData(ExportedDataset, inputVariables, targetVariable, Transformations) {
TrainingHorizon = oldProblemData.TrainingHorizon,
TestHorizon = oldProblemData.TestHorizon
};
return newProblemData;
}
protected TimeSeriesPrognosisProblemData(TimeSeriesPrognosisProblemData original, Cloner cloner) : base(original, cloner) { }
protected override ITimeSeriesPrognosisProblemData ImportData(string path, TimeSeriesPrognosisImportType type, TableFileParser csvFileParser) {
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
// turn of input variables that are constant in the training partition
var allowedInputVars = new List<string>();
int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
trainingPartEnd = trainingPartEnd > 0 ? trainingPartEnd : 1;
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)));
}
TimeSeriesPrognosisProblemData timeSeriesPrognosisData = new TimeSeriesPrognosisProblemData(dataset, allowedInputVars, type.TargetVariable);
timeSeriesPrognosisData.TrainingPartition.Start = 0;
timeSeriesPrognosisData.TrainingPartition.End = trainingPartEnd;
timeSeriesPrognosisData.TestPartition.Start = trainingPartEnd;
timeSeriesPrognosisData.TestPartition.End = csvFileParser.Rows;
timeSeriesPrognosisData.Name = Path.GetFileName(path);
return timeSeriesPrognosisData;
}
