public ClassifierBuildResult Build(TextDocument[] trainingSet, ClassifierParams classifierParams)
{
var targetTag = classifierParams.TargetTag;
var featuredWords = featureSelector.Select(trainingSet, classifierParams.FeatureSelectionParams).FeaturedWords.Select(x => x.Word).ToArray();
var trainingExamples = trainingSet.Select(textDocument => textDocumentConverter.ConvertToTrainingExample(textDocument, targetTag, featuredWords)).ToArray();
var oversampledExamples = sampler.OverSample(trainingExamples, classifierParams.SamplingParams);
var algorithmBuildResult = classificationAlgorithmBuilder.Build(oversampledExamples, classifierParams.ClassificationAlgorithmParams);
var result = new SimpleClassifier(algorithmBuildResult.ClassificationAlgorithm, textDocumentConverter, targetTag, featuredWords);
return ClassifierBuildResult.Create(result, algorithmBuildResult.Error);
}
private WeightedClassifier Build(TextDocument[] trainingSet, BaggingParams baggingParams, ClassifierParams classifierParams)
{
var underSampledSet = baggingParams.NeedUnderSampling
? trainingSet.RandomShuffle().Take(trainingSet.Length*85/100).ToArray()
: trainingSet;
return new WeightedClassifier
{
Classifier = classifierBuilder.Build(underSampledSet, classifierParams).Classifier,
Weight = 1.0
};
}
public ClassifierBuildResult Build(TextDocument[] trainingSet, ClassifierParams classifierParams)
{
return builders.First(x => x.Type == classifierParams.Type).Build(trainingSet, classifierParams);
}
