public ClassifierBuildResult Build(TextDocument[] trainingSet, EnsembleParams ensembleParams)
{
var classifiers = ensembleParams.ClassifiersParams.Select(x => Build(trainingSet, ensembleParams.BaggingParams, x)).ToArray();
var result = new ClassifiersEnsemble(classifiers);
return ClassifierBuildResult.Create(result, trainingSet, ensembleParams.TargetTag);
}
public ClassifierBuildResult Build(TextDocument[] trainingSet, EnsembleParams ensembleParams)
{
var weightedDocuments = trainingSet.Select((x, i) => new WeightedDocument { Document = x, Weight = 1.0 / trainingSet.Length }).ToArray();
var classifiers = new List<WeightedClassifier>();
var classifierParamses = ensembleParams.ClassifiersParams;
var targetTag = ensembleParams.TargetTag;
for (int iteration = 0; iteration < classifierParamses.Length; iteration++)
{
Console.WriteLine("Running {0}/{1} boosting iteration", iteration + 1, classifierParamses.Length);
var sampledTrainingSet = DoSampling(weightedDocuments);
var binaryClassifierBuildResult = classifierBuilder.Build(sampledTrainingSet, classifierParamses[iteration]);
var classifier = binaryClassifierBuildResult.Classifier;
var error = weightedDocuments.Sum(x => classifier.IsClassifierWrong(x.Document, targetTag) ? x.Weight : 0);
var alpha = 0.5 * Math.Log((1.0 - error) / error);
foreach (var weightedDocument in weightedDocuments)
{
if (classifier.IsClassifierWrong(weightedDocument.Document, targetTag))
weightedDocument.Weight *= Math.Exp(alpha);
else
weightedDocument.Weight *= Math.Exp(-alpha);
}
var z = weightedDocuments.Sum(x => x.Weight);
foreach (var weightedDocument in weightedDocuments)
{
weightedDocument.Weight /= z;
}
classifiers.Add(new WeightedClassifier { Classifier = classifier, Weight = alpha });
Console.WriteLine("Error (weighted) = {0}", error);
Console.WriteLine("Alpha = {0}", alpha);
var evaluationResult = classifierEvaluator.Evaluate(classifier, trainingSet, targetTag);
Console.WriteLine("FScore = {0}", evaluationResult.FScore);
}
var result = new ClassifiersEnsemble(classifiers);
return ClassifierBuildResult.Create(result, trainingSet, targetTag);
}