private void doExport(string fpath, string opath)
{
var sample = new ClassifiedSample <string>();
using (var srcFile = File.Open(fpath, FileMode.Open, FileAccess.Read))
using (var srcReader = new StreamReader(srcFile))
{
var line = srcReader.ReadLine();
var segs = line.Split(SEPARATOR, StringSplitOptions.RemoveEmptyEntries);
var cls = m_Classes[segs[0]];
var doc = segs[1];
sample.Add(doc, cls);
}
var vocabulary = Alg.ExtractVocabulary(sample);
var dim = vocabulary.Count;
var builder = new StringBuilder();
using (var outFile = File.Open(opath, FileMode.CreateNew, FileAccess.Write))
using (var outWriter = new StreamWriter(outFile))
{
for (int i = 0; i < dim; i++)
{
builder.AppendFormat("{0},", vocabulary[i]);
}
builder.Append("_class,_value,_training");
outWriter.WriteLine(builder.ToString());
foreach (var pData in sample)
{
var doc = pData.Key;
var cls = pData.Value;
bool isEmpty;
var data = Alg.ExtractFeatureVector(doc, out isEmpty);
if (isEmpty)
{
continue;
}
builder.Clear();
for (int i = 0; i < dim; i++)
{
builder.AppendFormat("{0},", data[i]);
}
builder.AppendFormat("{0},{1},{2}", cls.Name, cls.Value, 1);
outWriter.WriteLine(builder.ToString());
}
}
}
