/// <summary>
/// Creates a new event reader based on the specified data reader using the specified context generator.
/// </summary>
/// <param name="dataReader">
/// The data reader for this event reader.
/// </param>
/// <param name="contextGenerator">
/// The context generator which should be used in the creation of events for this event stream.
/// </param>
public NameFinderEventReader(SharpEntropy.ITrainingDataReader <string> dataReader, INameContextGenerator contextGenerator)
{
mDataReader = dataReader;
mContextGenerator = contextGenerator;
mEventIndex = 0;
mPreviousTags = new Dictionary <string, string>();
//prime events with first line of data stream.
if (mDataReader.HasNext())
{
mLine = mDataReader.NextToken();
if (mLine.Length == 0)
{
mPreviousTags.Clear();
}
else
{
AddEvents(mLine);
}
}
else
{
mEvents = new SharpEntropy.TrainingEvent[0];
}
}
/// <summary>
/// Creates a new event reader based on the specified data reader using the specified context generator.
/// </summary>
/// <param name="dataReader">
/// The data reader for this event reader.
/// </param>
/// <param name="contextGenerator">
/// The context generator which should be used in the creation of events for this event stream.
/// </param>
public NameFinderEventReader(SharpEntropy.ITrainingDataReader<string> dataReader, INameContextGenerator contextGenerator)
{
mDataReader = dataReader;
mContextGenerator = contextGenerator;
mEventIndex = 0;
mPreviousTags = new Dictionary<string, string>();
//prime events with first line of data stream.
if (mDataReader.HasNext())
{
mLine = mDataReader.NextToken();
if (mLine.Length == 0)
{
mPreviousTags.Clear();
}
else
{
AddEvents(mLine);
}
}
else
{
mEvents = new SharpEntropy.TrainingEvent[0];
}
}
/// <summary>
/// Initializes a new instance of the <see cref="NameSampleSequenceStream"/> class.
/// </summary>
/// <param name="psi">The sample stream.</param>
/// <param name="pcg">The context generator.</param>
/// <param name="useOutcomes">if set to <c>true</c> will be used in the samples.</param>
/// <param name="seqCodec">The sequence codec.</param>
public NameSampleSequenceStream(IObjectStream<NameSample> psi, INameContextGenerator pcg, bool useOutcomes,
ISequenceCodec<string> seqCodec) {
this.psi = psi;
this.useOutcomes = useOutcomes;
this.pcg = pcg;
this.seqCodec = seqCodec;
}
public NameSampleSequenceStream(IObjectStream <NameSample> psi, INameContextGenerator pcg, bool useOutcomes, ISequenceCodec <string> seqCodec)
{
this.psi = psi;
this.useOutcomes = useOutcomes;
this.pcg = pcg;
this.seqCodec = seqCodec;
}
public NameFinderEventStream(IObjectStream <NameSample> dataStream, string type, INameContextGenerator contextGenerator, ISequenceCodec <string> codec) : base(dataStream)
{
this.codec = codec ?? new BioCodec();
additionalContextFeatureGenerator = new AdditionalContextFeatureGenerator();
this.contextGenerator = contextGenerator;
this.contextGenerator.AddFeatureGenerator(new WindowFeatureGenerator(additionalContextFeatureGenerator, 8, 8));
// TODO: How to make the type really do something?!
// Type = type ?? "default";
}
/// <summary>
/// Initializes a new instance of the <see cref="NameFinderME"/> using the given <see cref="TokenNameFinderModel"/>.
/// </summary>
/// <param name="model">The model.</param>
/// <exception cref="System.ArgumentNullException">model</exception>
public NameFinderME(TokenNameFinderModel model)
{
if (model == null)
{
throw new ArgumentNullException(nameof(model));
}
sequenceCodec = model.Factory.CreateSequenceCodec();
sequenceValidator = sequenceCodec.CreateSequenceValidator();
this.model = model.NameFinderSequenceModel;
contextGenerator = model.Factory.CreateContextGenerator();
// TODO: We should deprecate this. And come up with a better solution!
additionalContextFeatureGenerator = new AdditionalContextFeatureGenerator();
contextGenerator.AddFeatureGenerator(
new WindowFeatureGenerator(additionalContextFeatureGenerator, 8, 8));
}
/// <summary>
/// Initializes a new instance of the <see cref="NameSampleSequenceStream"/> class.
/// </summary>
/// <param name="psi">The sample stream.</param>
/// <param name="pcg">The context generator.</param>
public NameSampleSequenceStream(IObjectStream<NameSample> psi, INameContextGenerator pcg)
: this(psi, pcg, true) {}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
public MaximumEntropyNameFinder(SharpEntropy.IMaximumEntropyModel model, INameContextGenerator contextGenerator) :
this(model, contextGenerator, 10)
{
}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
/// <param name="beamSize">
/// The size of the beam to be used in decoding this model.
/// </param>
public MaximumEntropyNameFinder(SharpEntropy.IMaximumEntropyModel model, INameContextGenerator contextGenerator, int beamSize)
{
mModel = model;
mContextGenerator = contextGenerator;
mBeam = new NameBeamSearch(this, beamSize, contextGenerator, model, beamSize);
}
/// <summary>
/// Initializes a new instance of the <see cref="NameSampleSequenceStream"/> class using the <seealso cref="BioCodec"/> as sequence codec.
/// </summary>
/// <param name="psi">The sample stream.</param>
/// <param name="pcg">The context generator.</param>
/// <param name="useOutcomes">if set to <c>true</c> will be used in the samples.</param>
public NameSampleSequenceStream(IObjectStream <NameSample> psi, INameContextGenerator pcg, bool useOutcomes)
: this(psi, pcg, useOutcomes, new BioCodec())
{
}
/// <summary>
/// Creates a beam seach of the specified size using the specified model with the specified context generator.
/// </summary>
/// <param name="nameFinder">
/// The associated MaximumEntropyNameFinder instance.
/// </param>
/// <param name="size">
/// The size of the beam.
/// </param>
/// <param name="contextGenerator">
/// The context generator used with the specified model.
/// </param>
/// <param name="model">
/// The model used to determine names.
/// </param>
/// <param name="beamSize">
/// The size of the beam to use in searching.
/// </param>
public NameBeamSearch(MaximumEntropyNameFinder nameFinder, int size, INameContextGenerator contextGenerator, SharpEntropy.IMaximumEntropyModel model, int beamSize) :
base(size, contextGenerator, model, beamSize)
{
_nameFinder = nameFinder;
}
internal static List <Event> GenerateEvents(String[] sentence, String[] outcomes, INameContextGenerator cg)
{
var events = new List <Event>(outcomes.Length);
for (int i = 0; i < outcomes.Length; i++)
{
events.Add(new Event(outcomes[i], cg.GetContext(i, sentence, outcomes, null)));
}
cg.UpdateAdaptiveData(sentence, outcomes);
return(events);
}
/// <summary>
/// Initializes a new instance of the <see cref="NameSampleSequenceStream"/> class.
/// </summary>
/// <param name="psi">The sample stream.</param>
/// <param name="pcg">The context generator.</param>
public NameSampleSequenceStream(IObjectStream <NameSample> psi, INameContextGenerator pcg)
: this(psi, pcg, true)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="NameSampleSequenceStream"/> class using the <seealso cref="BioCodec"/> as sequence codec.
/// </summary>
/// <param name="psi">The sample stream.</param>
/// <param name="pcg">The context generator.</param>
/// <param name="useOutcomes">if set to <c>true</c> will be used in the samples.</param>
public NameSampleSequenceStream(IObjectStream<NameSample> psi, INameContextGenerator pcg, bool useOutcomes)
: this(psi, pcg, useOutcomes, new BioCodec()) {}
/// <summary>
/// Initializes a new instance of the <see cref="NameFinderME"/> using the given <see cref="TokenNameFinderModel"/>.
/// </summary>
/// <param name="model">The model.</param>
/// <exception cref="System.ArgumentNullException">model</exception>
public NameFinderME(TokenNameFinderModel model) {
if (model == null)
throw new ArgumentNullException("model");
sequenceCodec = model.Factory.CreateSequenceCodec();
sequenceValidator = sequenceCodec.CreateSequenceValidator();
this.model = model.NameFinderSequenceModel;
contextGenerator = model.Factory.CreateContextGenerator();
// TODO: We should deprecate this. And come up with a better solution!
additionalContextFeatureGenerator = new AdditionalContextFeatureGenerator();
contextGenerator.AddFeatureGenerator(
new WindowFeatureGenerator(additionalContextFeatureGenerator, 8, 8));
}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
/// <param name="beamSize">
/// The size of the beam to be used in decoding this model.
/// </param>
public MaximumEntropyNameFinder(SharpEntropy.IMaximumEntropyModel model, INameContextGenerator contextGenerator, int beamSize)
{
mModel = model;
mContextGenerator = contextGenerator;
mBeam = new NameBeamSearch(this, beamSize, contextGenerator, model, beamSize);
}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
public MaximumEntropyNameFinder(SharpEntropy.IMaximumEntropyModel model, INameContextGenerator contextGenerator)
: this(model, contextGenerator, 10)
{
}
/// <summary>
/// Creates a beam seach of the specified size using the specified model with the specified context generator.
/// </summary>
/// <param name="nameFinder">
/// The associated MaximumEntropyNameFinder instance.
/// </param>
/// <param name="size">
/// The size of the beam.
/// </param>
/// <param name="contextGenerator">
/// The context generator used with the specified model.
/// </param>
/// <param name="model">
/// The model used to determine names.
/// </param>
/// <param name="beamSize">
/// The size of the beam to use in searching.
/// </param>
public NameBeamSearch(MaximumEntropyNameFinder nameFinder, int size, INameContextGenerator contextGenerator, SharpEntropy.IMaximumEntropyModel model, int beamSize)
: base(size, contextGenerator, model, beamSize)
{
mNameFinder = nameFinder;
}
