// public static void main(String[] args) {
// List examples = new ArrayList();
// String leftLight = "leftLight";
// String rightLight = "rightLight";
// String broken = "BROKEN";
// String ok = "OK";
// Counter c1 = new ClassicCounter<>();
// c1.incrementCount(leftLight, 0);
// c1.incrementCount(rightLight, 0);
// RVFDatum d1 = new RVFDatum(c1, broken);
// examples.add(d1);
// Counter c2 = new ClassicCounter<>();
// c2.incrementCount(leftLight, 1);
// c2.incrementCount(rightLight, 1);
// RVFDatum d2 = new RVFDatum(c2, ok);
// examples.add(d2);
// Counter c3 = new ClassicCounter<>();
// c3.incrementCount(leftLight, 0);
// c3.incrementCount(rightLight, 1);
// RVFDatum d3 = new RVFDatum(c3, ok);
// examples.add(d3);
// Counter c4 = new ClassicCounter<>();
// c4.incrementCount(leftLight, 1);
// c4.incrementCount(rightLight, 0);
// RVFDatum d4 = new RVFDatum(c4, ok);
// examples.add(d4);
// Dataset data = new Dataset(examples.size());
// data.addAll(examples);
// NaiveBayesClassifier classifier = (NaiveBayesClassifier)
// new NaiveBayesClassifierFactory(200, 200, 1.0,
// LogPrior.LogPriorType.QUADRATIC.ordinal(),
// NaiveBayesClassifierFactory.CL)
// .trainClassifier(data);
// classifier.print();
// //now classifiy
// for (int i = 0; i < examples.size(); i++) {
// RVFDatum d = (RVFDatum) examples.get(i);
// Counter scores = classifier.scoresOf(d);
// System.out.println("for datum " + d + " scores are " + scores.toString());
// System.out.println(" class is " + Counters.topKeys(scores, 1));
// System.out.println(" class should be " + d.label());
// }
// }
// String trainFile = args[0];
// String testFile = args[1];
// NominalDataReader nR = new NominalDataReader();
// Map<Integer, Index<String>> indices = Generics.newHashMap();
// List<RVFDatum<String, Integer>> train = nR.readData(trainFile, indices);
// List<RVFDatum<String, Integer>> test = nR.readData(testFile, indices);
// System.out.println("Constrained conditional likelihood no prior :");
// for (int j = 0; j < 100; j++) {
// NaiveBayesClassifier<String, Integer> classifier = new NaiveBayesClassifierFactory<String, Integer>(0.1, 0.01, 0.6, LogPrior.LogPriorType.NULL.ordinal(), NaiveBayesClassifierFactory.CL).trainClassifier(train);
// classifier.print();
// //now classifiy
//
// float accTrain = classifier.accuracy(train.iterator());
// log.info("training accuracy " + accTrain);
// float accTest = classifier.accuracy(test.iterator());
// log.info("test accuracy " + accTest);
//
// }
// System.out.println("Unconstrained conditional likelihood no prior :");
// for (int j = 0; j < 100; j++) {
// NaiveBayesClassifier<String, Integer> classifier = new NaiveBayesClassifierFactory<String, Integer>(0.1, 0.01, 0.6, LogPrior.LogPriorType.NULL.ordinal(), NaiveBayesClassifierFactory.UCL).trainClassifier(train);
// classifier.print();
// //now classify
//
// float accTrain = classifier.accuracy(train.iterator());
// log.info("training accuracy " + accTrain);
// float accTest = classifier.accuracy(test.iterator());
// log.info("test accuracy " + accTest);
// }
// }
public virtual NaiveBayesClassifier <L, F> TrainClassifier(GeneralDataset <L, F> dataset)
{
if (dataset is RVFDataset)
{
throw new Exception("Not sure if RVFDataset runs correctly in this method. Please update this code if it does.");
}
return(TrainClassifier(dataset.GetDataArray(), dataset.labels, dataset.NumFeatures(), dataset.NumClasses(), dataset.labelIndex, dataset.featureIndex));
}
public GeneralizedExpectationObjectiveFunction(GeneralDataset <L, F> labeledDataset, IList <IDatum <L, F> > unlabeledDataList, IList <F> geFeatures)
{
System.Console.Out.WriteLine("Number of labeled examples:" + labeledDataset.size + "\nNumber of unlabeled examples:" + unlabeledDataList.Count);
System.Console.Out.WriteLine("Number of GE features:" + geFeatures.Count);
this.numFeatures = labeledDataset.NumFeatures();
this.numClasses = labeledDataset.NumClasses();
this.labeledDataset = labeledDataset;
this.unlabeledDataList = unlabeledDataList;
this.geFeatures = geFeatures;
this.classifier = new LinearClassifier <L, F>(null, labeledDataset.featureIndex, labeledDataset.labelIndex);
ComputeEmpiricalStatistics(geFeatures);
}
public virtual MultinomialLogisticClassifier <L, F> TrainClassifier(GeneralDataset <L, F> dataset)
{
numClasses = dataset.NumClasses();
numFeatures = dataset.NumFeatures();
data = dataset.GetDataArray();
if (dataset is RVFDataset <object, object> )
{
dataValues = dataset.GetValuesArray();
}
else
{
dataValues = LogisticUtils.InitializeDataValues(data);
}
AugmentFeatureMatrix(data, dataValues);
labels = dataset.GetLabelsArray();
return(new MultinomialLogisticClassifier <L, F>(TrainWeights(), dataset.featureIndex, dataset.labelIndex));
}
public BiasedLogConditionalObjectiveFunction(GeneralDataset <object, object> dataset, double[][] confusionMatrix, LogPrior prior)
: this(dataset.NumFeatures(), dataset.NumClasses(), dataset.GetDataArray(), dataset.GetLabelsArray(), confusionMatrix, prior)
{
}