Add Javadoc for all remaining undocumented public methods and fields.

Classification/Core/src/main/java/org/tribuo/classification/ensemble/ClassificationEnsembleOptions.java

@@ -55,15 +55,25 @@ public enum EnsembleType {
         RF
     }
 
-    @Option(longName="ensemble-type",usage="Ensemble method, options are {ADABOOST, BAGGING, RF}.")
+    /**
+     * Ensemble method, options are {ADABOOST, BAGGING, RF}.
+     */
+    @Option(longName = "ensemble-type", usage = "Ensemble method, options are {ADABOOST, BAGGING, RF}.")
     public EnsembleType type = EnsembleType.BAGGING;
-    @Option(longName="ensemble-size",usage="Number of base learners in the ensemble.")
+    /**
+     * Number of base learners in the ensemble.
+     */
+    @Option(longName = "ensemble-size", usage = "Number of base learners in the ensemble.")
     public int ensembleSize = -1;
-    @Option(longName="ensemble-seed",usage="RNG seed.")
+    /**
+     * RNG seed.
+     */
+    @Option(longName = "ensemble-seed", usage = "RNG seed.")
     public long seed = Trainer.DEFAULT_SEED;
 
     /**
      * Wraps the supplied trainer using the ensemble trainer described by these options.
+     *
      * @param trainer The trainer to wrap.
      * @return An ensemble trainer.
      */
@@ -72,21 +82,21 @@ public Trainer<Label> wrapTrainer(Trainer<Label> trainer) {
             switch (type) {
                 case ADABOOST:
                     logger.info("Using Adaboost with " + ensembleSize + " members.");
-                    return new AdaBoostTrainer(trainer,ensembleSize,seed);
+                    return new AdaBoostTrainer(trainer, ensembleSize, seed);
                 case BAGGING:
                     logger.info("Using Bagging with " + ensembleSize + " members.");
-                    return new BaggingTrainer<>(trainer,new VotingCombiner(),ensembleSize,seed);
+                    return new BaggingTrainer<>(trainer, new VotingCombiner(), ensembleSize, seed);
                 case EXTRA_TREES:
                     if (trainer instanceof DecisionTreeTrainer) {
                         logger.info("Using Extra Trees with " + ensembleSize + " members.");
-                        return new ExtraTreesTrainer<>((DecisionTreeTrainer<Label>)trainer,new VotingCombiner(),ensembleSize,seed);
+                        return new ExtraTreesTrainer<>((DecisionTreeTrainer<Label>) trainer, new VotingCombiner(), ensembleSize, seed);
                     } else {
                         throw new IllegalArgumentException("ExtraTreesTrainer requires a DecisionTreeTrainer");
                     }
                 case RF:
                     if (trainer instanceof DecisionTreeTrainer) {
                         logger.info("Using Random Forests with " + ensembleSize + " members.");
-                        return new RandomForestTrainer<>((DecisionTreeTrainer<Label>)trainer,new VotingCombiner(),ensembleSize,seed);
+                        return new RandomForestTrainer<>((DecisionTreeTrainer<Label>) trainer, new VotingCombiner(), ensembleSize, seed);
                     } else {
                         throw new IllegalArgumentException("RandomForestTrainer requires a DecisionTreeTrainer");
                     }

Classification/Core/src/main/java/org/tribuo/classification/evaluation/LabelEvaluationUtil.java

@@ -207,8 +207,17 @@ public TPFP(List<Integer> falsePos, List<Integer> truePos, List<Double> threshol
      * Not yet a record, but it will be one day.
      */
     public static class ROC {
+        /**
+         * The false positive rate at the corresponding threshold.
+         */
         public final double[] fpr;
+        /**
+         * The true positive rate at the corresponding threshold.
+         */
         public final double[] tpr;
+        /**
+         * The threshold values.
+         */
         public final double[] thresholds;
 
         /**
@@ -231,8 +240,17 @@ public ROC(double[] fpr, double[] tpr, double[] thresholds) {
      * Not yet a record, but it will be one day.
      */
     public static class PRCurve {
+        /**
+         * The precision at the corresponding threshold.
+         */
         public final double[] precision;
+        /**
+         * The recall at the corresponding threshold.
+         */
         public final double[] recall;
+        /**
+         * The threshold values.
+         */
         public final double[] thresholds;
 
         /**

Classification/Core/src/main/java/org/tribuo/classification/evaluation/LabelMetric.java

@@ -102,16 +102,30 @@ public static final class Context extends MetricContext<Label> {
 
         private final ConfusionMatrix<Label> cm;
 
+        /**
+         * Constructs a context and compute the confusion matrix using the specified model and predictions.
+         * @param model The model.
+         * @param predictions The predictions.
+         */
         public Context(Model<Label> model, List<Prediction<Label>> predictions) {
             super(model, predictions);
             this.cm = new LabelConfusionMatrix(model.getOutputIDInfo(), predictions);
         }
 
+        /**
+         * Constructs a context and compute the confusion matrix using the specified model and predictions.
+         * @param model The model.
+         * @param predictions The predictions.
+         */
         public Context(SequenceModel<Label> model, List<Prediction<Label>> predictions) {
             super(model, predictions);
             this.cm = new LabelConfusionMatrix(model.getOutputIDInfo(), predictions);
         }
 
+        /**
+         * Gets the confusion matrix.
+         * @return The confusion matrix.
+         */
         public ConfusionMatrix<Label> getCM() {
             return cm;
         }

Classification/Core/src/main/java/org/tribuo/classification/example/GaussianLabelDataSource.java

@@ -33,10 +33,10 @@
 public final class GaussianLabelDataSource extends DemoLabelDataSource {
 
     @Config(mandatory = true, description = "2d mean of the first Gaussian.")
-    public double[] firstMean;
+    private double[] firstMean;
 
     @Config(mandatory = true, description = "4 element covariance matrix of the first Gaussian.")
-    public double[] firstCovarianceMatrix;
+    private double[] firstCovarianceMatrix;
 
     @Config(mandatory = true, description = "2d mean of the second Gaussian.")
     private double[] secondMean;

Classification/Core/src/main/java/org/tribuo/classification/example/LabelledDataGenerator.java

@@ -40,6 +40,12 @@ private LabelledDataGenerator() {}
 
     private static final LabelFactory labelFactory = new LabelFactory();
 
+    /**
+     * Generates a train/test dataset pair which is dense in the features,
+     * each example has 4 features,{A,B,C,D}, and there are 4 classes,
+     * {Foo,Bar,Baz,Quux}.
+     * @return A pair of datasets.
+     */
     public static Pair<Dataset<Label>,Dataset<Label>> denseTrainTest() {
         return denseTrainTest(-1.0);
     }
@@ -99,6 +105,12 @@ public static Pair<Dataset<Label>,Dataset<Label>> denseTrainTest(double negate)
         return new Pair<>(train,test);
     }
 
+    /**
+     * Generates a pair of datasets, where the features are sparse,
+     * and unknown features appear in the test data. It has the same
+     * 4 classes {Foo,Bar,Baz,Quux}.
+     * @return A pair of train and test datasets.
+     */
     public static Pair<Dataset<Label>,Dataset<Label>> sparseTrainTest() {
         return sparseTrainTest(-1.0);
     }
@@ -173,6 +185,11 @@ public static Pair<Dataset<Label>,Dataset<Label>> sparseTrainTest(double negate)
         return new Pair<>(train,test);
     }
 
+    /**
+     * Generates a pair of datasets with sparse features and unknown features
+     * in the test data. Has binary labels {Foo,Bar}.
+     * @return A pair of train and test datasets.
+     */
     public static Pair<Dataset<Label>,Dataset<Label>> binarySparseTrainTest() {
         return binarySparseTrainTest(-1.0);
     }

Classification/Core/src/main/java/org/tribuo/classification/sequence/ConfidencePredictingSequenceModel.java

@@ -39,6 +39,13 @@
 public abstract class ConfidencePredictingSequenceModel extends SequenceModel<Label> {
     private static final long serialVersionUID = 1L;
 
+    /**
+     * Constructs a ConfidencePredictingSequenceModel with the supplied parameters.
+     * @param name The model name.
+     * @param description The model provenance.
+     * @param featureIDMap The feature domain.
+     * @param labelIDMap The output domain.
+     */
     protected ConfidencePredictingSequenceModel(String name, ModelProvenance description, ImmutableFeatureMap featureIDMap, ImmutableOutputInfo<Label> labelIDMap) {
         super(name,description,featureIDMap,labelIDMap);
     }
@@ -81,7 +88,13 @@ private static <SUB extends Subsequence> Double multiplyWeights(List<Prediction<
      */
     public static class Subsequence implements Serializable {
         private static final long serialVersionUID = 1L;
+        /**
+         * The subsequence start index.
+         */
         public final int begin;
+        /**
+         * The subsequence end index.
+         */
         public final int end;
 
         /**