/// <summary>A helper function for dumping the accuracy of the trained classifier.</summary>
/// <param name="classifier">The classifier to evaluate.</param>
/// <param name="dataset">The dataset to evaluate the classifier on.</param>
public static void DumpAccuracy(IClassifier <ClauseSplitter.ClauseClassifierLabel, string> classifier, GeneralDataset <ClauseSplitter.ClauseClassifierLabel, string> dataset)
{
DecimalFormat df = new DecimalFormat("0.00%");
Redwood.Log("size: " + dataset.Size());
Redwood.Log("split count: " + StreamSupport.Stream(dataset.Spliterator(), false).Filter(null).Collect(Collectors.ToList()).Count);
Redwood.Log("interm count: " + StreamSupport.Stream(dataset.Spliterator(), false).Filter(null).Collect(Collectors.ToList()).Count);
Pair <double, double> pr = classifier.EvaluatePrecisionAndRecall(dataset, ClauseSplitter.ClauseClassifierLabel.ClauseSplit);
Redwood.Log("p (split): " + df.Format(pr.first));
Redwood.Log("r (split): " + df.Format(pr.second));
Redwood.Log("f1 (split): " + df.Format(2 * pr.first * pr.second / (pr.first + pr.second)));
pr = classifier.EvaluatePrecisionAndRecall(dataset, ClauseSplitter.ClauseClassifierLabel.ClauseInterm);
Redwood.Log("p (interm): " + df.Format(pr.first));
Redwood.Log("r (interm): " + df.Format(pr.second));
Redwood.Log("f1 (interm): " + df.Format(2 * pr.first * pr.second / (pr.first + pr.second)));
}