/// <summary>
/// Trains a chunker model with the given parameters.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="samples">The data samples.</param>
/// <param name="factory">The sentence detector factory.</param>
/// <param name="parameters">The machine learnable parameters.</param>
/// <returns>The trained <see cref="ChunkerModel"/> object.</returns>
/// <exception cref="System.InvalidOperationException">The trainer was not specified.</exception>
/// <exception cref="System.NotSupportedException">Trainer type is not supported.</exception>
public static ChunkerModel Train(
string languageCode,
IObjectStream <ChunkSample> samples,
TrainingParameters parameters,
ChunkerFactory factory)
{
return(Train(languageCode, samples, parameters, factory, null));
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerCrossValidator"/> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="parameters">The parameters.</param>
/// <param name="factory">The factory.</param>
/// <param name="listeners">The listeners.</param>
public ChunkerCrossValidator(
string languageCode,
TrainingParameters parameters,
ChunkerFactory factory,
params IEvaluationMonitor <ChunkSample>[] listeners)
{
chunkerFactory = factory;
FMeasure = new FMeasure <Span>();
this.languageCode = languageCode;
this.parameters = parameters;
this.listeners = listeners;
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerCrossValidator"/> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="parameters">The parameters.</param>
/// <param name="factory">The factory.</param>
/// <param name="listeners">The listeners.</param>
public ChunkerCrossValidator(
string languageCode,
TrainingParameters parameters,
ChunkerFactory factory,
params IEvaluationMonitor<ChunkSample>[] listeners) {
chunkerFactory = factory;
FMeasure = new FMeasure<Span>();
this.languageCode = languageCode;
this.parameters = parameters;
this.listeners = listeners;
}
/// <summary>
/// Trains a chunker model with the given parameters.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="samples">The data samples.</param>
/// <param name="parameters">The machine learnable parameters.</param>
/// <param name="factory">The sentence detector factory.</param>
/// <param name="monitor">
/// A evaluation monitor that can be used to listen the messages during the training or it can cancel the training operation.
/// This argument can be a <c>null</c> value.</param>
/// <returns>The trained <see cref="ChunkerModel"/> object.</returns>
/// <exception cref="System.InvalidOperationException">The trainer was not specified.</exception>
/// <exception cref="System.NotSupportedException">Trainer type is not supported.</exception>
public static ChunkerModel Train(string languageCode, IObjectStream <ChunkSample> samples, TrainingParameters parameters, ChunkerFactory factory, Monitor monitor)
{
var trainerType = TrainerFactory.GetTrainerType(parameters);
if (!trainerType.HasValue)
{
throw new InvalidOperationException("The trainer was not specified.");
}
var manifestInfoEntries = new Dictionary <string, string>();
IMaxentModel chunkerModel = null;
ML.Model.ISequenceClassificationModel <string> seqChunkerModel = null;
switch (trainerType)
{
case TrainerType.SequenceTrainer:
var st = TrainerFactory.GetSequenceModelTrainer(parameters, manifestInfoEntries, monitor);
// TODO: This will probably cause issue, since the feature generator uses the outcomes array
var ss = new ChunkSampleSequenceStream(samples, factory.GetContextGenerator());
seqChunkerModel = st.Train(ss);
break;
case TrainerType.EventModelTrainer:
var es = new ChunkerEventStream(samples, factory.GetContextGenerator());
var et = TrainerFactory.GetEventTrainer(parameters, manifestInfoEntries, monitor);
chunkerModel = et.Train(es);
break;
default:
throw new NotSupportedException("Trainer type is not supported.");
}
var beamSize = parameters.Get(Parameters.BeamSize, DefaultBeamSize);
return(chunkerModel != null
? new ChunkerModel(languageCode, chunkerModel, beamSize, manifestInfoEntries, factory)
: new ChunkerModel(languageCode, seqChunkerModel, manifestInfoEntries, factory));
}
private static ChunkerModel TrainModel(ChunkerFactory factory) {
return ChunkerME.Train("en", ChunkerMETest.CreateSampleStream(), TrainingParameters.DefaultParameters(), factory);
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerModel"/> class with a specified <paramref name="beamSize"/> value.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="chunkerModel">The chunker model.</param>
/// <param name="beamSize">Size of the beam.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="factory">The chunker factory.</param>
public ChunkerModel(string languageCode, IMaxentModel chunkerModel, int beamSize, Dictionary <string, string> manifestInfoEntries, ChunkerFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory)
{
artifactMap[ChunkerEntry] = chunkerModel;
Manifest[Parameters.BeamSize] = beamSize.ToString(CultureInfo.InvariantCulture);
CheckArtifactMap();
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerModel"/> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="chunkerModel">The chunker model.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="factory">The chunker factory.</param>
public ChunkerModel(string languageCode, IMaxentModel chunkerModel, Dictionary <string, string> manifestInfoEntries, ChunkerFactory factory)
: this(languageCode, chunkerModel, ChunkerME.DefaultBeamSize, manifestInfoEntries, factory)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerModel"/> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="chunkerModel">The chunker model.</param>
/// <param name="factory">The chunker factory.</param>
public ChunkerModel(string languageCode, IMaxentModel chunkerModel, ChunkerFactory factory)
: this(languageCode, chunkerModel, ChunkerME.DefaultBeamSize, null, factory)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerModel"/> class using a <see cref="T:ISequenceClassificationModel{string}"/> as the chunker model.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="chunkerModel">The chunker model.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="factory">The chunker factory.</param>
public ChunkerModel(string languageCode, ISequenceClassificationModel <string> chunkerModel, Dictionary <string, string> manifestInfoEntries, ChunkerFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory)
{
artifactMap.Add(ChunkerEntry, chunkerModel);
CheckArtifactMap();
}
/// <summary>
/// Trains a chunker model with the given parameters.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="samples">The data samples.</param>
/// <param name="parameters">The machine learnable parameters.</param>
/// <param name="factory">The sentence detector factory.</param>
/// <param name="monitor">
/// A evaluation monitor that can be used to listen the messages during the training or it can cancel the training operation.
/// This argument can be a <c>null</c> value.</param>
/// <returns>The trained <see cref="ChunkerModel"/> object.</returns>
/// <exception cref="System.InvalidOperationException">The trainer was not specified.</exception>
/// <exception cref="System.NotSupportedException">Trainer type is not supported.</exception>
public static ChunkerModel Train(string languageCode, IObjectStream<ChunkSample> samples, TrainingParameters parameters, ChunkerFactory factory, Monitor monitor) {
var trainerType = TrainerFactory.GetTrainerType(parameters);
if (!trainerType.HasValue) {
throw new InvalidOperationException("The trainer was not specified.");
}
var manifestInfoEntries = new Dictionary<string, string>();
IMaxentModel chunkerModel = null;
ML.Model.ISequenceClassificationModel<string> seqChunkerModel = null;
switch (trainerType) {
case TrainerType.SequenceTrainer:
var st = TrainerFactory.GetSequenceModelTrainer(parameters, manifestInfoEntries, monitor);
// TODO: This will probably cause issue, since the feature generator uses the outcomes array
var ss = new ChunkSampleSequenceStream(samples, factory.GetContextGenerator());
seqChunkerModel = st.Train(ss);
break;
case TrainerType.EventModelTrainer:
var es = new ChunkerEventStream(samples, factory.GetContextGenerator());
var et = TrainerFactory.GetEventTrainer(parameters, manifestInfoEntries, monitor);
chunkerModel = et.Train(es);
break;
default:
throw new NotSupportedException("Trainer type is not supported.");
}
var beamSize = parameters.Get(Parameters.BeamSize, DefaultBeamSize);
return chunkerModel != null
? new ChunkerModel(languageCode, chunkerModel, beamSize, manifestInfoEntries, factory)
: new ChunkerModel(languageCode, seqChunkerModel, manifestInfoEntries, factory);
}
/// <summary>
/// Trains a chunker model with the given parameters.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="samples">The data samples.</param>
/// <param name="factory">The sentence detector factory.</param>
/// <param name="parameters">The machine learnable parameters.</param>
/// <returns>The trained <see cref="ChunkerModel"/> object.</returns>
/// <exception cref="System.InvalidOperationException">The trainer was not specified.</exception>
/// <exception cref="System.NotSupportedException">Trainer type is not supported.</exception>
public static ChunkerModel Train(
string languageCode,
IObjectStream<ChunkSample> samples,
TrainingParameters parameters,
ChunkerFactory factory) {
return Train(languageCode, samples, parameters, factory, null);
}
