private static Data.Attribute ParseAttributeLine(string line, int attributeIndex)
{
Data.Attribute attribute=null;
string[] parts = line.Split(' ');
string name=parts[1];
for (int i = 2; i < parts.Length - 1; i++)
name += parts[i];
if (string.Compare(parts[parts.Length - 1].Trim(), "numeric", true) == 0)
{
attribute = new Data.NumericAttribute(name, attributeIndex);
}
else
{
string[] values = line.Split(' ');
values = values[values.Length - 1].Trim('{', '}').Split(',');
attribute = new Data.NominalAttribute(name, attributeIndex, values);
}
return attribute;
}
private static Data.Example ParseExampleLine(int exampleIndex, string line, Data.Dataset dataset)
{
string[] parts = line.Split(',');
List<double> values = new List<double>();
int label = dataset.Metadata.Target.GetIndex(parts[parts.Length - 1]);
for (int index = 0; index < parts.Length - 1; index++)
{
if (dataset.Metadata.Attributes[index] is Data.NominalAttribute)
{
Data.NominalAttribute attribute = dataset.Metadata.Attributes[index] as Data.NominalAttribute;
string value = parts[index];
values.Add(attribute.GetIndex(value));
}
else
{
double value = double.NaN;
if (parts[index] != "?")
value = double.Parse(parts[index]);
values.Add(value);
}
}
Data.Example example = new Data.Example(dataset.Metadata, exampleIndex, values.ToArray(), label);
return example;
}
private static Data.Instance ParseHierarchicalinstanceLine(int instanceIndex, string line, Data.Dataset dataset, bool skipFirstAttribute)
{
string[] parts = line.Split(',');
List <double> values = new List <double>();
List <int> label = new List <int>();
string[] labelParts = parts[parts.Length - 1].Split(';');
foreach (string target in labelParts)
{
if (!string.IsNullOrWhiteSpace(target))
{
label.Add(dataset.Metadata.Target.GetIndex(target));
}
}
for (int index = 0; index < parts.Length - 1; index++)
{
if (dataset.Metadata.Attributes[index] is Data.NominalAttribute)
{
Data.NominalAttribute attribute = dataset.Metadata.Attributes[index] as Data.NominalAttribute;
string value = parts[index];
values.Add(attribute.GetIndex(value));
}
else
{
double value = double.NaN;
if (parts[index] != "?")
{
value = double.Parse(parts[index]);
}
values.Add(value);
}
}
Data.Instance instance = new Data.Instance(dataset.Metadata, instanceIndex, values.ToArray(), label);
return(instance);
}
private void UpdateValueCounts()
{
for (int attributeIndex = 0; attributeIndex < this._metadata.Attributes.Length; attributeIndex++)
{
if (this._metadata.Attributes[attributeIndex] is NominalAttribute)
{
Data.NominalAttribute currentAttribute = this._metadata.Attributes[attributeIndex] as NominalAttribute;
for (int valueIndex = 0; valueIndex < currentAttribute.Values.Length; valueIndex++)
{
currentAttribute.ValueCounts[valueIndex] = this.Filter(attributeIndex, valueIndex).Count;
}
for (int valueIndex = 0; valueIndex < this._metadata.Target.Values.Length; valueIndex++)
{
this._metadata.Target.ValueCounts[valueIndex] = this.Filter(valueIndex).Count;
}
}
}
this._metadata.Size = this._examples.Length;
}
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;
}
