public TData ImportData(string path, ImportType type, DataAnalysisCSVFormat csvFormat)
{
TableFileParser csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFormat.NumberFormatInfo, csvFormat.DateTimeFormatInfo, csvFormat.Separator, csvFormat.VariableNamesAvailable);
return(ImportData(path, type, csvFileParser));
}
public override IRegressionProblemData LoadData(IDataDescriptor id)
{
var descriptor = (ResourceRegressionDataDescriptor)id;
var instanceArchiveName = GetResourceName(FileName + @"\.zip");
using (var instancesZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(instanceArchiveName), ZipArchiveMode.Read)) {
var entry = instancesZipFile.GetEntry(descriptor.ResourceName);
NumberFormatInfo numberFormat;
DateTimeFormatInfo dateFormat;
char separator;
using (Stream stream = entry.Open()) {
TableFileParser.DetermineFileFormat(stream, out numberFormat, out dateFormat, out separator);
}
TableFileParser csvFileParser = new TableFileParser();
using (Stream stream = entry.Open()) {
csvFileParser.Parse(stream, numberFormat, dateFormat, separator, true);
}
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
if (!descriptor.CheckVariableNames(csvFileParser.VariableNames))
{
throw new ArgumentException("Parsed file contains variables which are not in the descriptor.");
}
return(descriptor.GenerateRegressionData(dataset));
}
}
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;
}
public override ILogModellingProblemData ImportData(string path)
{
var csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
var dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
string caseIDVar = dataset.VariableNames.First();
string timestampVar = dataset.VariableNames.First();
string activityVar = dataset.VariableNames.First();
ILogModellingProblemData logData = new LogModellingProblemData(dataset, caseIDVar, timestampVar, activityVar);
IEnumerable <int> trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
int trainingPartEnd = trainingIndizes.Last();
//TODO: when (if not removed) separating test and training, group by caseid
logData.TrainingPartition.Start = trainingIndizes.First();
logData.TrainingPartition.End = trainingPartEnd;
logData.TestPartition.Start = trainingPartEnd;
logData.TestPartition.End = csvFileParser.Rows;
logData.Name = Path.GetFileName(path);
return(logData);
}
public override IRegressionProblemData ImportData(string path) {
TableFileParser csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
string targetVar = dataset.DoubleVariables.Last();
// turn off 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 &&
variableName != targetVar)
allowedInputVars.Add(variableName);
}
} else {
allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(targetVar)));
}
IRegressionProblemData regressionData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
var trainingPartEnd = trainingIndizes.Last();
regressionData.TrainingPartition.Start = trainingIndizes.First();
regressionData.TrainingPartition.End = trainingPartEnd;
regressionData.TestPartition.Start = trainingPartEnd;
regressionData.TestPartition.End = csvFileParser.Rows;
regressionData.Name = Path.GetFileName(path);
return regressionData;
}
public override IRegressionProblemData LoadData(IDataDescriptor id) {
var descriptor = (ResourceRegressionDataDescriptor)id;
var instanceArchiveName = GetResourceName(FileName + @"\.zip");
using (var instancesZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(instanceArchiveName), ZipArchiveMode.Read)) {
var entry = instancesZipFile.GetEntry(descriptor.ResourceName);
NumberFormatInfo numberFormat;
DateTimeFormatInfo dateFormat;
char separator;
using (Stream stream = entry.Open()) {
TableFileParser.DetermineFileFormat(stream, out numberFormat, out dateFormat, out separator);
}
TableFileParser csvFileParser = new TableFileParser();
using (Stream stream = entry.Open()) {
csvFileParser.Parse(stream, numberFormat, dateFormat, separator, true);
}
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
if (!descriptor.CheckVariableNames(csvFileParser.VariableNames)) {
throw new ArgumentException("Parsed file contains variables which are not in the descriptor.");
}
return descriptor.GenerateRegressionData(dataset);
}
}
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;
}
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);
}
public TData ImportData(string path, ImportType type, DataAnalysisCSVFormat csvFormat)
{
TableFileParser csvFileParser = new TableFileParser();
long fileSize = new FileInfo(path).Length;
csvFileParser.ProgressChanged += (sender, e) => {
OnProgressChanged(e / (double)fileSize);
};
csvFileParser.Parse(path, csvFormat.NumberFormatInfo, csvFormat.DateTimeFormatInfo, csvFormat.Separator, csvFormat.VariableNamesAvailable);
return(ImportData(path, type, csvFileParser));
}
public override IRegressionProblemData ImportData(string path)
{
TableFileParser csvFileParser = new TableFileParser();
csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
string targetVar = dataset.DoubleVariables.Last();
// turn off 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 &&
variableName != targetVar)
{
allowedInputVars.Add(variableName);
}
}
}
else
{
allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(targetVar)));
}
IRegressionProblemData regressionData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
var trainingPartEnd = trainingIndizes.Last();
regressionData.TrainingPartition.Start = trainingIndizes.First();
regressionData.TrainingPartition.End = trainingPartEnd;
regressionData.TestPartition.Start = trainingPartEnd;
regressionData.TestPartition.End = csvFileParser.Rows;
regressionData.Name = Path.GetFileName(path);
return(regressionData);
}
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);
}
