/// <summary>
/// Trains a POS tag maximum entropy model
/// </summary>
/// <param name="trainingFile">filepath to the training data</param>
/// <param name="iterations">number of training iterations to perform</param>
/// <param name="cutoff">Cutoff value to use for the data indexer</param>
/// <returns>Trained GIS model</returns>
public static SharpEntropy.GisModel TrainModel(string trainingFile, int iterations, int cutoff)
{
#if DNF
SharpEntropy.ITrainingEventReader eventReader = new PosEventReader(new StreamReader(trainingFile));
#else
SharpEntropy.ITrainingEventReader eventReader = new PosEventReader(new StreamReader(new FileStream(trainingFile, FileMode.OpenOrCreate, FileAccess.Read)));
#endif
return(Train(eventReader, iterations, cutoff));
}
public virtual void LocalEvaluate(SharpEntropy.IMaximumEntropyModel posModel, StreamReader reader, out double accuracy, out double sentenceAccuracy)
{
this.PosModel = posModel;
float total = 0, correct = 0, sentences = 0, sentencesCorrect = 0;
var sentenceReader = new StreamReader(reader.BaseStream, System.Text.Encoding.UTF7);
string line;
while ((object)(line = sentenceReader.ReadLine()) != null)
{
sentences++;
var annotatedPair = PosEventReader.ConvertAnnotatedString(line);
var words = annotatedPair.Item1;
var outcomes = annotatedPair.Item2;
var tags = new ArrayList(Beam.BestSequence(words.ToArray(), null).Outcomes);
int count = 0;
bool isSentenceOk = true;
for (IEnumerator tagIndex = tags.GetEnumerator(); tagIndex.MoveNext(); count++)
{
total++;
var tag = (string)tagIndex.Current;
if (tag == (string)outcomes[count])
{
correct++;
}
else
{
isSentenceOk = false;
}
}
if (isSentenceOk)
{
sentencesCorrect++;
}
}
accuracy = correct / total;
sentenceAccuracy = sentencesCorrect / sentences;
}
public virtual void LocalEvaluate(SharpEntropy.IMaximumEntropyModel posModel, System.IO.StreamReader reader, out double accuracy, out double sentenceAccuracy)
{
mPosModel = posModel;
float total = 0, correct = 0, sentences = 0, sentencesCorrect = 0;
System.IO.StreamReader sentenceReader = new System.IO.StreamReader(reader.BaseStream, System.Text.Encoding.UTF7);
string line;
while ((object)(line = sentenceReader.ReadLine()) != null)
{
sentences++;
Util.Pair <ArrayList, ArrayList> annotatedPair = PosEventReader.ConvertAnnotatedString(line);
ArrayList words = annotatedPair.FirstValue;
ArrayList outcomes = annotatedPair.SecondValue;
ArrayList tags = new ArrayList(Beam.BestSequence(words, null).Outcomes);
int count = 0;
bool isSentenceOK = true;
for (System.Collections.IEnumerator tagIndex = tags.GetEnumerator(); tagIndex.MoveNext(); count++)
{
total++;
string tag = (string)tagIndex.Current;
if (tag == (string)outcomes[count])
{
correct++;
}
else
{
isSentenceOK = false;
}
}
if (isSentenceOK)
{
sentencesCorrect++;
}
}
accuracy = correct / total;
sentenceAccuracy = sentencesCorrect / sentences;
}
/// <summary>
/// Trains a POS tag maximum entropy model.
/// </summary>
/// <param name="trainingFile">
/// filepath to the training data.
/// </param>
/// <param name="iterations">
/// number of training iterations to perform.
/// </param>
/// <param name="cutoff">
/// Cutoff value to use for the data indexer.
/// </param>
/// <returns>
/// Trained GIS model.
/// </returns>
public static SharpEntropy.GisModel TrainModel(string trainingFile, int iterations, int cutoff)
{
SharpEntropy.ITrainingEventReader eventReader = new PosEventReader(new System.IO.StreamReader(trainingFile));
return Train(eventReader, iterations, cutoff);
}
/// <summary>
/// Trains a POS tag maximum entropy model
/// </summary>
/// <param name="trainingFile">filepath to the training data</param>
/// <param name="iterations">number of training iterations to perform</param>
/// <param name="cutoff">Cutoff value to use for the data indexer</param>
/// <returns>Trained GIS model</returns>
public static SharpEntropy.GisModel TrainModel(string trainingFile, int iterations, int cutoff)
{
SharpEntropy.ITrainingEventReader eventReader = new PosEventReader(new StreamReader(trainingFile));
return(Train(eventReader, iterations, cutoff));
}
