protected static void randomLearn(String[] args) {
if (args.length != 3) {
System.out.println(
"Please specify the number of classes as the second argument "
+ "and the number of features as the third argument.");
} else {
final int numClassIndices = Integer.parseInt(args[1]);
final int maxFeatureIndex = Integer.parseInt(args[2]);
// Initialize the classifier to random parameters.
DiscretizingNaiveBayesClassifier classifier = new DiscretizingNaiveBayesClassifier();
classifier.initializeRandomly(
DiscretizingNaiveBayesClassifier.makeClassIndexSet(numClassIndices),
maxFeatureIndex,
new DiscretizingNaiveBayesClassifier.SimpleBinaryDiscretizer());
// Save the trained model.
saveTrainedModelFileData(classifier.toFileData());
}
}
protected static void semiSupervisedLearn(String[] args) {
if (args.length < 2) {
System.out.println(
"Please specify the path for the training data as the second argument. "
+ "(Optionally, you can give the number of EM iterations as the third argument.)");
} else {
final String trainingDataFilename = args[1];
int maxNumIterations;
if (args.length == 3) {
maxNumIterations = Integer.parseInt(args[2]);
} else {
maxNumIterations = Integer.MAX_VALUE;
}
try {
// Parse the sparse training data.
final Map.Entry<List<SparseLineAST>, Integer> instancesToMaxFeatureIndex =
SparseLineAST.parseSparseEncodingFromInputFilename(
trainingDataFilename,
new SparseLineAST.SemiSupervisedTrainingValidator(
new SparseLineAST.NumericValidator()));
final List<SparseLineAST> instances = instancesToMaxFeatureIndex.getKey();
final int maxFeatureIndex = instancesToMaxFeatureIndex.getValue();
// Initialize and train the classifier on the training data.
DiscretizingNaiveBayesClassifier classifier =
DiscretizingNaiveBayesClassifierEMTrainer.train(
getKForSmoothing().getSecond(),
instances,
maxFeatureIndex,
new DiscretizingNaiveBayesClassifier.SimpleBinaryDiscretizer(),
maxNumIterations);
// Save the trained model.
saveTrainedModelFileData(classifier.toFileData());
} catch (RuntimeException x) {
System.out.println(x.getMessage());
}
}
}
protected static void learn(String[] args) {
if (args.length != 2) {
System.out.println("Please specify the path for the training data as the second argument.");
} else {
final String trainingDataFilename = args[1];
try {
// Parse the sparse training data.
// Note: "u" outputs for training instances are accepted; they'll just be ignored.
final Map.Entry<List<SparseLineAST>, Integer> instancesToMaxFeatureIndex =
SparseLineAST.parseSparseEncodingFromInputFilename(
trainingDataFilename,
new SparseLineAST.SemiSupervisedTrainingValidator(
new SparseLineAST.NumericValidator()));
final List<SparseLineAST> instances = instancesToMaxFeatureIndex.getKey();
final int maxFeatureIndex = instancesToMaxFeatureIndex.getValue();
// Ignore unlabeled instances.
final List<SparseLineAST> labeledInstances = SparseLineAST.getLabeledInstances(instances);
// Initialize and train the classifier on the training data.
DiscretizingNaiveBayesClassifier classifier = new DiscretizingNaiveBayesClassifier();
classifier.initialize(getKForSmoothing().getSecond());
classifier.train(
labeledInstances,
maxFeatureIndex,
new DiscretizingNaiveBayesClassifier.SimpleBinaryDiscretizer());
// Save the trained model.
saveTrainedModelFileData(classifier.toFileData());
} catch (RuntimeException x) {
System.out.println(x.getMessage());
for (StackTraceElement element : x.getStackTrace()) {
System.out.println(element);
}
}
}
}
