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);
}
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);
}
public EvaluationResult Evaluate(IClassifier classifier, TextDocument[] testSet, string targetTag)
{
var results = testSet
.Select(x => new BusinessObjects.Evaluation
{
DocumentId = x.Id,
Result = classifier.Classify(x),
ExpectedClass = x.Tags.Contains(targetTag) ? 1 : 0,
})
.ToArray();
var total = results.Length;
var errors = Get(results, r => r.Result.PredictedClass != r.ExpectedClass);
var truePositives = Get(results, r => r.Result.PredictedClass == 1 && r.ExpectedClass == 1);
var falsePositives = Get(results, r => r.Result.PredictedClass == 1 && r.ExpectedClass == 0);
var falseNegatives = Get(results, r => r.Result.PredictedClass == 0 && r.ExpectedClass == 1);
var trueNegatives = Get(results, r => r.Result.PredictedClass == 0 && r.ExpectedClass == 0);
var accuracy = (total - errors.Length) * 1.0 / total;
var precision = truePositives.Length * 1.0 / (truePositives.Length + falsePositives.Length);
var recall = truePositives.Length * 1.0 / (truePositives.Length + falseNegatives.Length);
var fscore = 2.0 * precision * recall / (precision + recall);
if (double.IsNaN(fscore))
{
fscore = 0.0;
}
return new EvaluationResult
{
Accuracy = accuracy,
Precision = precision,
Recall = recall,
FScore = fscore,
TruePositives = truePositives,
FalsePositives = falsePositives,
TrueNegatives = trueNegatives,
FalseNegatives = falseNegatives,
Errors = errors,
};
}