/// <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));
}
public virtual RVFDatum <L, F> ScaleDatumGaussian(RVFDatum <L, F> datum)
{
// scale this dataset before scaling the datum
if (means == null || stdevs == null)
{
ScaleFeaturesGaussian();
}
ICounter <F> scaledFeatures = new ClassicCounter <F>();
foreach (F feature in datum.AsFeatures())
{
int fID = this.featureIndex.IndexOf(feature);
if (fID >= 0)
{
double oldVal = datum.AsFeaturesCounter().GetCount(feature);
double newVal;
if (stdevs[fID] != 0)
{
newVal = (oldVal - means[fID]) / stdevs[fID];
}
else
{
newVal = oldVal;
}
scaledFeatures.IncrementCount(feature, newVal);
}
}
return(new RVFDatum <L, F>(scaledFeatures, datum.Label()));
}
/// <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));
}
public virtual float Accuracy(IEnumerator <RVFDatum <L, F> > exampleIterator)
{
int correct = 0;
int total = 0;
for (; exampleIterator.MoveNext();)
{
RVFDatum <L, F> next = exampleIterator.Current;
L guess = ClassOf(next);
if (guess.Equals(next.Label()))
{
correct++;
}
total++;
}
logger.Info("correct " + correct + " out of " + total);
return(correct / (float)total);
}
private double ProbabilityOfRVFDatum(RVFDatum <L, F> example)
{
return(ProbabilityOf(example.AsFeaturesCounter(), example.Label()));
}