/// <summary>
/// Trains a name finder model.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="samples">The training samples.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder factory.</param>
/// <returns>the newly <see cref="TokenNameFinderModel"/> trained model.</returns>
public static TokenNameFinderModel Train(
string languageCode,
IObjectStream <NameSample> samples,
TrainingParameters parameters,
TokenNameFinderFactory factory)
{
return(Train(languageCode, DefaultType, samples, parameters, factory));
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderCrossValidator"/> class.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="type"><c>null</c> or an override type for all types in the training data.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="listeners">The listeners.</param>
public TokenNameFinderCrossValidator(string languageCode, string type, TrainingParameters parameters, params IEvaluationMonitor <NameSample>[] listeners)
{
this.languageCode = languageCode;
this.type = type;
this.parameters = parameters;
this.listeners = listeners;
factory = new TokenNameFinderFactory();
FMeasure = new FMeasure <Span>();
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderCrossValidator"/> class.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="type"><c>null</c> or an override type for all types in the training data.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder factory.</param>
/// <param name="listeners">The listeners.</param>
public TokenNameFinderCrossValidator(string languageCode, string type, TrainingParameters parameters, TokenNameFinderFactory factory, params IEvaluationMonitor<NameSample>[] listeners) {
if (factory == null)
throw new ArgumentNullException(nameof(factory));
this.languageCode = languageCode;
this.type = type;
this.parameters = parameters;
this.factory = factory;
this.listeners = listeners;
FMeasure = new FMeasure<Span>();
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderModel" /> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="nameFinderModel">The name finder model.</param>
/// <param name="generatorDescriptor">The generator descriptor.</param>
/// <param name="resources">The resources.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="seqCodec">The sequence codec.</param>
/// <param name="factory">The tool factory.</param>
/// <exception cref="InvalidOperationException">Model not compatible with name finder!</exception>
/// <exception cref="System.InvalidOperationException">Model not compatible with name finder!</exception>
public TokenNameFinderModel(
string languageCode,
ISequenceClassificationModel<string> nameFinderModel,
byte[] generatorDescriptor,
Dictionary<string, object> resources,
Dictionary<string, string> manifestInfoEntries,
ISequenceCodec<string> seqCodec,
TokenNameFinderFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory) {
Init(nameFinderModel, generatorDescriptor, resources, seqCodec);
if (!seqCodec.AreOutcomesCompatible(nameFinderModel.GetOutcomes())) {
throw new InvalidOperationException("Model not compatible with name finder!");
}
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderModel" /> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="nameFinderModel">The name finder model.</param>
/// <param name="generatorDescriptor">The generator descriptor.</param>
/// <param name="resources">The resources.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="seqCodec">The sequence codec.</param>
/// <param name="factory">The tool factory.</param>
/// <exception cref="InvalidOperationException">Model not compatible with name finder!</exception>
/// <exception cref="System.InvalidOperationException">Model not compatible with name finder!</exception>
public TokenNameFinderModel(
string languageCode,
ISequenceClassificationModel <string> nameFinderModel,
byte[] generatorDescriptor,
Dictionary <string, object> resources,
Dictionary <string, string> manifestInfoEntries,
ISequenceCodec <string> seqCodec,
TokenNameFinderFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory)
{
Init(nameFinderModel, generatorDescriptor, resources, seqCodec);
if (!seqCodec.AreOutcomesCompatible(nameFinderModel.GetOutcomes()))
{
throw new InvalidOperationException("Model not compatible with name finder!");
}
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderModel" /> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="nameFinderModel">The name finder model.</param>
/// <param name="beamSize">Size of the beam.</param>
/// <param name="generatorDescriptor">The generator descriptor.</param>
/// <param name="resources">The resources.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="sequenceCodec">The sequence codec.</param>
/// <param name="factory">The tool factory.</param>
/// <exception cref="InvalidOperationException">Model not compatible with name finder!</exception>
/// <exception cref="System.InvalidOperationException">Model not compatible with name finder!</exception>
public TokenNameFinderModel(
string languageCode,
IMaxentModel nameFinderModel,
int beamSize,
byte[] generatorDescriptor,
Dictionary <string, object> resources,
Dictionary <string, string> manifestInfoEntries,
ISequenceCodec <string> sequenceCodec,
TokenNameFinderFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory)
{
Manifest[Parameters.BeamSize] = beamSize.ToString(CultureInfo.InvariantCulture);
Init(nameFinderModel, generatorDescriptor, resources, sequenceCodec);
if (!IsModelValid(nameFinderModel))
{
throw new InvalidOperationException("Model not compatible with name finder!");
}
}
/// <summary>
/// Trains a name finder model with the given parameters.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="type">Overrides the type parameter in the provided samples. This value can be null.</param>
/// <param name="samples">The training samples.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder 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 newly <see cref="TokenNameFinderModel"/> trained model.</returns>
public static TokenNameFinderModel Train(string languageCode, string type, IObjectStream <NameSample> samples, TrainingParameters parameters, TokenNameFinderFactory factory, Monitor monitor)
{
var beamSize = parameters.Get(Parameters.BeamSize, DefaultBeamSize);
var manifestInfoEntries = new Dictionary <string, string>();
var trainerType = TrainerFactory.GetTrainerType(parameters);
IMaxentModel meModel = null;
ML.Model.ISequenceClassificationModel <string> seqModel = null;
switch (trainerType)
{
case TrainerType.EventModelTrainer:
var eventStream = new NameFinderEventStream(samples, type, factory.CreateContextGenerator(),
factory.CreateSequenceCodec());
var nfTrainer = TrainerFactory.GetEventTrainer(parameters, manifestInfoEntries, monitor);
meModel = nfTrainer.Train(eventStream);
break;
case TrainerType.EventModelSequenceTrainer:
var sampleStream = new NameSampleSequenceStream(samples, factory.CreateContextGenerator());
var nsTrainer = TrainerFactory.GetEventModelSequenceTrainer(parameters, manifestInfoEntries, monitor);
meModel = nsTrainer.Train(sampleStream);
break;
case TrainerType.SequenceTrainer:
var sequenceStream = new NameSampleSequenceStream(samples, factory.CreateContextGenerator());
var sqTrainer = TrainerFactory.GetSequenceModelTrainer(parameters, manifestInfoEntries, monitor);
seqModel = sqTrainer.Train(sequenceStream);
break;
default:
throw new InvalidOperationException("Unexpected trainer type!");
}
if (seqModel != null)
{
return(new TokenNameFinderModel(
languageCode,
seqModel,
factory.FeatureGenerator,
factory.Resources,
manifestInfoEntries,
factory.SequenceCodec,
factory));
}
return(new TokenNameFinderModel(
languageCode,
meModel,
beamSize,
factory.FeatureGenerator,
factory.Resources,
manifestInfoEntries,
factory.SequenceCodec,
factory));
}
/// <summary>
/// Trains a name finder model with the given parameters.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="type">Overrides the type parameter in the provided samples. This value can be null.</param>
/// <param name="samples">The training samples.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder 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 newly <see cref="TokenNameFinderModel"/> trained model.</returns>
public static TokenNameFinderModel Train(string languageCode, string type, IObjectStream<NameSample> samples, TrainingParameters parameters, TokenNameFinderFactory factory, Monitor monitor) {
var beamSize = parameters.Get(Parameters.BeamSize, DefaultBeamSize);
var manifestInfoEntries = new Dictionary<string, string>();
var trainerType = TrainerFactory.GetTrainerType(parameters);
IMaxentModel meModel = null;
ML.Model.ISequenceClassificationModel<string> seqModel = null;
switch (trainerType) {
case TrainerType.EventModelTrainer:
var eventStream = new NameFinderEventStream(samples, type, factory.CreateContextGenerator(),
factory.CreateSequenceCodec());
var nfTrainer = TrainerFactory.GetEventTrainer(parameters, manifestInfoEntries, monitor);
meModel = nfTrainer.Train(eventStream);
break;
case TrainerType.EventModelSequenceTrainer:
var sampleStream = new NameSampleSequenceStream(samples, factory.CreateContextGenerator());
var nsTrainer = TrainerFactory.GetEventModelSequenceTrainer(parameters, manifestInfoEntries, monitor);
meModel = nsTrainer.Train(sampleStream);
break;
case TrainerType.SequenceTrainer:
var sequenceStream = new NameSampleSequenceStream(samples, factory.CreateContextGenerator());
var sqTrainer = TrainerFactory.GetSequenceModelTrainer(parameters, manifestInfoEntries, monitor);
seqModel = sqTrainer.Train(sequenceStream);
break;
default:
throw new InvalidOperationException("Unexpected trainer type!");
}
if (seqModel != null) {
return new TokenNameFinderModel(
languageCode,
seqModel,
factory.FeatureGenerator,
factory.Resources,
manifestInfoEntries,
factory.SequenceCodec,
factory);
}
return new TokenNameFinderModel(
languageCode,
meModel,
beamSize,
factory.FeatureGenerator,
factory.Resources,
manifestInfoEntries,
factory.SequenceCodec,
factory);
}
/// <summary>
/// Trains a name finder model with the given parameters.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="type">Overrides the type parameter in the provided samples. This value can be null.</param>
/// <param name="samples">The training samples.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder factory.</param>
/// <returns>the newly <see cref="TokenNameFinderModel"/> trained model.</returns>
public static TokenNameFinderModel Train(
string languageCode,
string type,
IObjectStream<NameSample> samples,
TrainingParameters parameters,
TokenNameFinderFactory factory) {
return Train(languageCode, type, samples, parameters, factory, null);
}
/// <summary>
/// Trains a name finder model.
/// </summary>
/// <param name="languageCode">The language of the training data.</param>
/// <param name="samples">The training samples.</param>
/// <param name="parameters">The machine learning train parameters.</param>
/// <param name="factory">The name finder 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 newly <see cref="TokenNameFinderModel"/> trained model.</returns>
public static TokenNameFinderModel Train(string languageCode, IObjectStream<NameSample> samples, TrainingParameters parameters, TokenNameFinderFactory factory, Monitor monitor) {
return Train(languageCode, DefaultType, samples, parameters, factory, monitor);
}
/// <summary>
/// Initializes a new instance of the <see cref="TokenNameFinderModel" /> class.
/// </summary>
/// <param name="languageCode">The language code.</param>
/// <param name="nameFinderModel">The name finder model.</param>
/// <param name="beamSize">Size of the beam.</param>
/// <param name="generatorDescriptor">The generator descriptor.</param>
/// <param name="resources">The resources.</param>
/// <param name="manifestInfoEntries">The manifest information entries.</param>
/// <param name="sequenceCodec">The sequence codec.</param>
/// <param name="factory">The tool factory.</param>
/// <exception cref="InvalidOperationException">Model not compatible with name finder!</exception>
/// <exception cref="System.InvalidOperationException">Model not compatible with name finder!</exception>
public TokenNameFinderModel(
string languageCode,
IMaxentModel nameFinderModel,
int beamSize,
byte[] generatorDescriptor,
Dictionary<string, object> resources,
Dictionary<string, string> manifestInfoEntries,
ISequenceCodec<string> sequenceCodec,
TokenNameFinderFactory factory)
: base(ComponentName, languageCode, manifestInfoEntries, factory) {
Manifest[Parameters.BeamSize] = beamSize.ToString(CultureInfo.InvariantCulture);
Init(nameFinderModel, generatorDescriptor, resources, sequenceCodec);
if (!IsModelValid(nameFinderModel))
throw new InvalidOperationException("Model not compatible with name finder!");
}
