/// <summary>The examples are assumed to be a list of RFVDatum.</summary>
/// <remarks>
/// The examples are assumed to be a list of RFVDatum.
/// The datums are assumed to not contain the zeroes and then they are added to each instance.
/// </remarks>
public virtual NaiveBayesClassifier <L, F> TrainClassifier(GeneralDataset <L, F> examples, ICollection <F> featureSet)
{
int numFeatures = featureSet.Count;
int[][] data = new int[][] { };
int[] labels = new int[examples.Size()];
labelIndex = new HashIndex <L>();
featureIndex = new HashIndex <F>();
foreach (F feat in featureSet)
{
featureIndex.Add(feat);
}
for (int d = 0; d < examples.Size(); d++)
{
RVFDatum <L, F> datum = examples.GetRVFDatum(d);
ICounter <F> c = datum.AsFeaturesCounter();
foreach (F feature in c.KeySet())
{
int fNo = featureIndex.IndexOf(feature);
int value = (int)c.GetCount(feature);
data[d][fNo] = value;
}
labelIndex.Add(datum.Label());
labels[d] = labelIndex.IndexOf(datum.Label());
}
int numClasses = labelIndex.Size();
return(TrainClassifier(data, labels, numFeatures, numClasses, labelIndex, featureIndex));
}
private void ComputeEmpiricalStatistics(IList <F> geFeatures)
{
//allocate memory to the containers and initialize them
geFeature2EmpiricalDist = new double[][] { };
geFeature2DatumList = new List <IList <int> >(geFeatures.Count);
IDictionary <F, int> geFeatureMap = Generics.NewHashMap();
ICollection <int> activeUnlabeledExamples = Generics.NewHashSet();
for (int n = 0; n < geFeatures.Count; n++)
{
F geFeature = geFeatures[n];
geFeature2DatumList.Add(new List <int>());
Arrays.Fill(geFeature2EmpiricalDist[n], 0);
geFeatureMap[geFeature] = n;
}
//compute the empirical label distribution for each GE feature
for (int i = 0; i < labeledDataset.Size(); i++)
{
IDatum <L, F> datum = labeledDataset.GetDatum(i);
int labelID = labeledDataset.labelIndex.IndexOf(datum.Label());
foreach (F feature in datum.AsFeatures())
{
if (geFeatureMap.Contains(feature))
{
int geFnum = geFeatureMap[feature];
geFeature2EmpiricalDist[geFnum][labelID]++;
}
}
}
//now normalize and smooth the label distribution for each feature.
for (int n_1 = 0; n_1 < geFeatures.Count; n_1++)
{
ArrayMath.Normalize(geFeature2EmpiricalDist[n_1]);
SmoothDistribution(geFeature2EmpiricalDist[n_1]);
}
//now build the inverted index from each GE feature to unlabeled datums that contain it.
for (int i_1 = 0; i_1 < unlabeledDataList.Count; i_1++)
{
IDatum <L, F> datum = unlabeledDataList[i_1];
foreach (F feature in datum.AsFeatures())
{
if (geFeatureMap.Contains(feature))
{
int geFnum = geFeatureMap[feature];
geFeature2DatumList[geFnum].Add(i_1);
activeUnlabeledExamples.Add(i_1);
}
}
}
System.Console.Out.WriteLine("Number of active unlabeled examples:" + activeUnlabeledExamples.Count);
}
/// <summary>Builds a sigmoid model to turn the classifier outputs into probabilities.</summary>
private LinearClassifier <L, L> FitSigmoid(SVMLightClassifier <L, F> classifier, GeneralDataset <L, F> dataset)
{
RVFDataset <L, L> plattDataset = new RVFDataset <L, L>();
for (int i = 0; i < dataset.Size(); i++)
{
RVFDatum <L, F> d = dataset.GetRVFDatum(i);
ICounter <L> scores = classifier.ScoresOf((IDatum <L, F>)d);
scores.IncrementCount(null);
plattDataset.Add(new RVFDatum <L, L>(scores, d.Label()));
}
LinearClassifierFactory <L, L> factory = new LinearClassifierFactory <L, L>();
factory.SetPrior(new LogPrior(LogPrior.LogPriorType.Null));
return(factory.TrainClassifier(plattDataset));
}