public static void SaveTab(string[] featureNames, LabeledDataset <BlogMetaData, SparseVector <double> > dataset, ClassType classType, string fileName)
{
using (StreamWriter w = new StreamWriter(fileName, /*append=*/ false, Encoding.ASCII))
{
for (int i = 0; i < featureNames.Length; i++)
{
w.Write(featureNames[i] + "\t");
}
w.WriteLine("author");
for (int i = 0; i < featureNames.Length; i++)
{
w.Write("c\t");
}
w.WriteLine("d");
for (int i = 0; i < featureNames.Length; i++)
{
w.Write("\t");
}
w.WriteLine("class");
foreach (LabeledExample <BlogMetaData, SparseVector <double> > lblEx in dataset)
{
foreach (string lblStr in AnalysisUtils.GetLabel(lblEx.Label, classType).Split(','))
{
if (lblStr != "")
{
foreach (IdxDat <double> item in lblEx.Example)
{
w.Write(item.Dat + "\t");
}
w.WriteLine(lblStr);
}
}
}
}
}
public static void SaveArff(string[] featureNames, LabeledDataset <BlogMetaData, SparseVector <double> > dataset, ClassType classType, string fileName)
{
using (StreamWriter w = new StreamWriter(fileName, /*append=*/ false, Encoding.ASCII))
{
w.WriteLine("@RELATION r" + Guid.NewGuid().ToString("N"));
w.WriteLine();
foreach (string featureName in featureNames)
{
w.WriteLine("@ATTRIBUTE " + featureName + " NUMERIC");
}
w.Write("@ATTRIBUTE class ");
ArrayList <string> classes = new ArrayList <string>();
((IEnumerable <LabeledExample <BlogMetaData, SparseVector <double> > >)dataset).ToList().ForEach(
x => classes.AddRange(AnalysisUtils.GetLabel(x.Label, classType).Split(',')));
classes = new ArrayList <string>(classes.Distinct());
w.WriteLine(classes.ToString().Replace("( ", "{").Replace(" )", "}").Replace(" ", ","));
w.WriteLine();
w.WriteLine("@DATA");
foreach (LabeledExample <BlogMetaData, SparseVector <double> > lblEx in dataset)
{
foreach (string lblStr in AnalysisUtils.GetLabel(lblEx.Label, classType).Split(','))
{
if (lblStr != "")
{
foreach (IdxDat <double> item in lblEx.Example)
{
w.Write(item.Dat + ",");
}
w.WriteLine(lblStr);
}
}
}
}
}
static LabeledDataset <string, SparseVector <double> > CreateSingleFeatureDataset(LabeledDataset <BlogMetaData, SparseVector <double> > srcDataset, ClassType classType, int fIdx)
{
SparseVector <double> minValues, maxValues;
GetExtremes(srcDataset, out minValues, out maxValues);
LabeledDataset <string, SparseVector <double> > dataset = new LabeledDataset <string, SparseVector <double> >();
((IEnumerable <LabeledExample <BlogMetaData, SparseVector <double> > >)srcDataset).ToList()
.ForEach(x => dataset.Add(new LabeledExample <string, SparseVector <double> >(AnalysisUtils.GetLabel(x.Label, classType),
new SparseVector <double>(
new double[] { (x.Example[fIdx] - minValues[fIdx]) / (maxValues[fIdx] - minValues[fIdx]) } // simple normalization
))));
return(dataset);
}