/// <summary>
/// Initializes a new instance of the <see cref="Version"/> class.
/// </summary>
/// <param name="versionId">The <see cref="VersionId"/>.</param>
/// <param name="revision">The revision.</param>
/// <param name="metadata">The <see cref="Metadata"/>.</param>
/// <param name="content">The content.</param>
/// <remarks>
/// Enables actions: all
/// </remarks>
public Version(VersionId versionId, string revision, Metadata metadata, Content content)
{
VersionId = versionId;
Revision = revision;
Metadata = metadata;
if (Metadata == null)
{
Metadata = new Data.Metadata();
}
Content = content;
}
public Dataset GetBinaryFlatLabelSubDataset(string positiveClassValue, string[] negativeClassValues)
{
string name = this._metadata.DatasetName;
int classIndex = this._metadata.Target.GetIndex(positiveClassValue);
DataMining.Data.Attribute[] attClone = new Attribute[this.Metadata.Attributes.Length];
for (int attributeIndex = 0; attributeIndex < this.Metadata.Attributes.Length; attributeIndex++)
{
attClone[attributeIndex] = this.Metadata.Attributes[attributeIndex].Clone();
}
Data.NominalAttribute target = new NominalAttribute("class", this._metadata.Target.Index, new string[] { "Yes", "No" });
DataMining.Data.Metadata metadata = new Data.Metadata(name, attClone, target, false);
Dataset dsResult = new Dataset(metadata);
int positiveClassIndex = this._metadata.Target.GetIndex(positiveClassValue);
List <Example> positive = new List <Example>();
int pcounter = 0;
foreach (int exampleIndex in this.Filter(classIndex))
{
positive.Add(new Example(dsResult.Metadata, pcounter++, this[exampleIndex].Values, 0));
}
List <Example> negative = new List <Example>();
int ncounter = 0;
foreach (string negativeClassValue in negativeClassValues)
{
int negativeClassIndex = this._metadata.Target.GetIndex(negativeClassValue);
foreach (int exampleIndex in this.Filter(negativeClassIndex))
{
if (!negative.Exists(e => e.Index == exampleIndex))
{
negative.Add(new Example(dsResult.Metadata, ncounter++, this[exampleIndex].Values, 1));
}
}
}
List <Example> examples = new List <Example>();
examples.AddRange(positive);
examples.AddRange(negative);
dsResult.SetExamples(examples.ToArray());
return(dsResult);
}
public Dataset[] Split(string [] classValues)
{
Dataset[] datasets = new Dataset[classValues.Length];
DataMining.Data.Attribute[] attClone = new Attribute[this.Metadata.Attributes.Length];
for (int attributeIndex = 0; attributeIndex < this.Metadata.Attributes.Length; attributeIndex++)
{
attClone[attributeIndex] = this.Metadata.Attributes[attributeIndex].Clone();
}
string name = this._metadata.DatasetName;
Data.Attribute target = new Attribute("class", this._metadata.Target.Index, classValues);
DataMining.Data.Metadata metadata = new Data.Metadata(name, attClone, target);
int newClassIndex = 0;
foreach (string classValue in classValues)
{
int counter = 0;
int classIndex = this._metadata.Target.GetIndex(classValue);
datasets[classIndex] = new Dataset(metadata);
List <Example> examples = new List <Example>();
foreach (int exampleIndex in this.Filter(classIndex))
{
examples.Add(new Example(datasets[newClassIndex].Metadata, counter++, this[exampleIndex].Values, newClassIndex));
}
datasets[newClassIndex].SetExamples(examples.ToArray());
classIndex++;
}
return(datasets);
}
public static Data.Dataset LoadHierarchicalDatasetFromTxt(string filePath, bool skipfirstAttribute)
{
StreamReader reader = new StreamReader(filePath);
string datasetName = null;
Data.Metadata metadata = null;
Data.Dataset dataset = null;
List<Data.Attribute> attributes = new List<Data.Attribute>();
List<Data.Example> examples = new List<Data.Example>();
List<Data.Node> nodes = new List<Data.Node>();
int attributeIndex = 0;
int exampleIndex = 0;
string mode = "start";
while (!reader.EndOfStream)
{
string line = reader.ReadLine();
if (!string.IsNullOrEmpty(line))
{
if (line.Contains("%"))
continue;
if (line.Contains("@relation"))
{
datasetName = line.Substring(line.IndexOf(' ')).Trim();
datasetName = datasetName.Contains("-weka") ? datasetName.Substring(0, datasetName.IndexOf("-weka")) : datasetName;
}
else if (line.Contains("@attribute"))
{
Data.Attribute attribute = ParseAttributeLine(line, attributeIndex);
if (attribute != null)
{
attributeIndex++;
attributes.Add(attribute);
}
}
else if (line.Contains("@ontology"))
{
mode = "ontolog";
}
else if (line.Contains("@data"))
{
List<string> classValues = new List<string>();
int counter = 0;
for(int i=1; i<nodes.Count;i++)
{
Data.Node node = nodes[i];
node.ValueIndex = counter;
classValues.Add(node.Name);
counter++;
}
Data.ClassHierarchy classHierarchy = new Data.ClassHierarchy(nodes.ToArray());
Data.HierarchicalAttribute target = new Data.HierarchicalAttribute("class", attributes.Count, classValues.ToArray(), classHierarchy);
metadata = new Data.Metadata(datasetName, attributes.ToArray(), target,true);
dataset = new Data.Dataset(metadata);
mode = "data";
}
else
{
if (mode == "ontolog")
{
Data.Node node = ParseOntologyLine(line);
if (!nodes.Exists(n => n.Name == node.Name))
nodes.Add(node);
}
else
{
Data.Example example = ParseHierarchicalExampleLine(exampleIndex, line, dataset, skipfirstAttribute);
exampleIndex++;
examples.Add(example);
}
}
}
}
dataset.SetExamples(examples.ToArray());
return dataset;
}
public static Data.Dataset LoadDatasetFromArff(string filePath)
{
StreamReader reader = new StreamReader(filePath);
string datasetName = null;
Data.Metadata metadata = null;
Data.Dataset dataset = null;
List<Data.Attribute> attributes = new List<Data.Attribute>();
List<Data.Example> examples = new List<Data.Example>();
int attributeIndex = 0;
int exampleIndex = 0;
List<string> exampleLines = new List<string>();
while (!reader.EndOfStream)
{
string line = reader.ReadLine();
if (!string.IsNullOrEmpty(line))
{
if (line.Contains("%"))
continue;
if (line.Contains("@relation"))
{
datasetName = line.Substring(line.IndexOf(' ')).Trim();
datasetName = datasetName.Contains("-weka") ? datasetName.Substring(0, datasetName.IndexOf("-weka")) : datasetName;
}
else if (line.Contains("@attribute"))
{
Data.Attribute attribute = ParseAttributeLine(line, attributeIndex);
if (attribute != null)
{
attributeIndex++;
attributes.Add(attribute);
}
}
else if (line.Contains("@data"))
{
int targetIndex = attributes.FindIndex(m => string.Compare(m.Name, "Class", true) == 0);
Data.NominalAttribute target = attributes[targetIndex] as Data.NominalAttribute;
attributes.RemoveAt(target.Index);
metadata = new Data.Metadata(datasetName, attributes.ToArray(), target,false);
dataset = new Data.Dataset(metadata);
}
else
{
if (exampleLines.Contains(line))
continue;
Data.Example example = ParseExampleLine(exampleIndex, line, dataset);
exampleIndex++;
examples.Add(example);
exampleLines.Add(line);
}
}
}
dataset.SetExamples(examples.ToArray());
return dataset;
}
/// <summary>
/// Initializes a new instance of the <see cref="Version"/> class.
/// </summary>
/// <param name="versionId">The <see cref="VersionId"/>.</param>
/// <param name="revision">The revision.</param>
/// <param name="metadata">The <see cref="Metadata"/>.</param>
/// <param name="content">The content.</param>
/// <remarks>
/// Enables actions: all
/// </remarks>
public Version(VersionId versionId, string revision, Metadata metadata, Content content)
{
VersionId = versionId;
Revision = revision;
Metadata = metadata;
if (Metadata == null) Metadata = new Data.Metadata();
Content = content;
}
private static Data.Example ParseExampleLine(int exampleIndex, string line, Data.Metadata metadata, List <int> nominalAttributesIndexes)
{
string [] parts = line.Split(',');
List <double> values = new List <double>();
int label = 0;
for (; label < metadata.Target.Length; label++)
{
if (metadata.Target[label] == parts[parts.Length - 1])
{
break;
}
}
int offset = 0;
for (int index = 0; index < parts.Length - 1; index++)
{
string stringValue = parts[index];
if (!nominalAttributesIndexes.Contains(index))
{
double value = double.NaN;
if (stringValue != "?")
{
value = double.Parse(stringValue);
}
values.Add(value);
offset++;
}
else
{
Data.Attribute attribute = metadata.Attributes[offset];
string attributeName = attribute.Name.Substring(0, attribute.Name.IndexOf("::"));
while (true)
{
attribute = metadata.Attributes[offset];
if (!attribute.Name.Contains("::"))
{
break;
}
string currentAttributeName = attribute.Name.Substring(0, attribute.Name.IndexOf("::"));
if (currentAttributeName != attributeName)
{
break;
}
string valueName = attribute.Name.Substring(attribute.Name.IndexOf("::") + 2);
if (valueName == stringValue)
{
values.Add(1);
}
else
{
values.Add(0);
}
offset++;
if (offset == metadata.Attributes.Length)
{
break;
}
}
}
}
Data.Example example = new Data.Example(metadata, exampleIndex, values.ToArray(), label);
return(example);
}
public static Data.Dataset LoadDatasetFromArff(string filePath)
{
StreamReader reader = new StreamReader(filePath);
string datasetName = null;
Data.Metadata metadata = null;
Data.Dataset dataset = null;
List <Data.Attribute> attributes = new List <Data.Attribute>();
List <Data.Example> examples = new List <Data.Example>();
string[] target = null;
int attributeIndex = 0;
int exampleIndex = 0;
List <int> nominalAttributesIndexes = new List <int>();
int aindex = 0;
List <string> exampleLines = new List <string>();
while (!reader.EndOfStream)
{
string line = reader.ReadLine();
if (!string.IsNullOrEmpty(line))
{
if (line.Contains("%"))
{
continue;
}
if (line.Contains("@relation"))
{
datasetName = line.Substring(line.IndexOf(' ')).Trim();
datasetName = datasetName.Contains("-weka") ? datasetName.Substring(0, datasetName.IndexOf("-weka")) : datasetName;
}
else if (line.Contains("@attribute"))
{
if (line.ToUpper().Contains("CLASS"))
{
target = ParseClassAttributeLine(line);
}
else
{
Data.Attribute [] currentAttributes = ParseAttributeLine(line, attributeIndex);
attributeIndex += currentAttributes.Length;
attributes.AddRange(currentAttributes);
if (currentAttributes.Length > 1 || !line.Contains(currentAttributes[0].Name))
{
nominalAttributesIndexes.Add(aindex);
}
aindex++;
}
}
else if (line.Contains("@data"))
{
metadata = new Data.Metadata(datasetName, attributes.ToArray(), target);
dataset = new Data.Dataset(metadata);
}
else
{
if (exampleLines.Contains(line))
{
continue;
}
Data.Example example = ParseExampleLine(exampleIndex, line, dataset.Metadata, nominalAttributesIndexes);
exampleIndex++;
examples.Add(example);
exampleLines.Add(line);
}
}
}
dataset.SetExamples(examples.ToArray());
return(dataset);
}
