// Just for testing. Recommend instead is mallet/bin/vectors2topics
public static void main(String[] args) {
InstanceList ilist = InstanceList.load(new File(args[0]));
int numIterations = args.length > 1 ? Integer.parseInt(args[1]) : 1000;
int numTopWords = args.length > 2 ? Integer.parseInt(args[2]) : 20;
System.out.println("Data loaded.");
TopicalNGrams tng = new TopicalNGrams(10);
tng.estimate(ilist, 200, 1, 0, null, new Randoms());
tng.printTopWords(60, true);
}
// Recommended to use mallet/bin/vectors2topics instead.
public static void main(String[] args) throws IOException {
InstanceList ilist = InstanceList.load(new File(args[0]));
int numIterations = args.length > 1 ? Integer.parseInt(args[1]) : 1000;
int numTopWords = args.length > 2 ? Integer.parseInt(args[2]) : 20;
System.out.println("Data loaded.");
LDA lda = new LDA(10);
lda.estimate(ilist, numIterations, 50, 0, null, new Randoms()); // should be 1100
lda.printTopWords(numTopWords, true);
lda.printDocumentTopics(new File(args[0] + ".lda"));
}
public static void main(String[] args) throws Exception {
CommandOption.setSummary(
FeatureCountTool.class,
"Print feature counts and instances per feature (eg document frequencies) in an instance list");
CommandOption.process(FeatureCountTool.class, args);
InstanceList instances = InstanceList.load(new File(inputFile.value));
FeatureCountTool counter = new FeatureCountTool(instances);
counter.count();
counter.printCounts();
}
public static void main(String[] args) {
// String malletFile = "dataset/vlc_lectures.all.en.f8.mallet";
// String simFile = "dataset/vlc/sim5p.csv";
// String solutionFile = "dataset/vlc/task1_solution.en.f8.lm.txt";
// String queryFile = "dataset/task1_query.en.f8.txt";
// String targetFile = "dataset/task1_target.en.f8.txt";
String malletFile = "dataset/vlc/folds/all.0.4189.mallet";
String trainMalletFile = "dataset/vlc/folds/training.0.mallet";
String testMalletFile = "dataset/vlc/folds/test.0.mallet";
String queryFile = "dataset/vlc/folds/query.0.csv";
String linkFile = "dataset/vlc/folds/trainingPairs.0.csv";
String targetFile = "dataset/vlc/folds/target.0.csv";
String solutionFile = "dataset/vlc/task1_solution.en.f8.lm.txt";
int numTopics = 160;
int numIterations = 200;
double alpha = 0.0016;
double beta = 0.0001;
InstanceList train = InstanceList.load(new File(trainMalletFile));
InstanceList test = InstanceList.load(new File(testMalletFile));
SeparateParallelLda spl = new SeparateParallelLda(train, test);
spl.trainDocuments(numTopics, numIterations, alpha, beta);
spl.generateTestInference();
spl.lda.printTopWords(System.out, 10, true);
BasicTask1Solution solver = new Task1SolutionWithSeparateData(spl);
double precision;
try {
solver.retrieveTask1Solution(queryFile, solutionFile);
precision = Task1Solution.evaluateResult(targetFile, solutionFile);
System.out.println(
String.format(
"SeparateParallelLda: iteration: %d, precisoion: %f", numIterations, precision));
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public static void main(String[] args) throws Exception {
InstanceList instances = InstanceList.load(new File(args[0]));
int numTopics = Integer.parseInt(args[1]);
ParallelTopicModel model = new ParallelTopicModel(numTopics, 5.0, 0.01);
model.addInstances(instances);
model.setNumIterations(1000);
model.estimate();
TopicModelDiagnostics diagnostics = new TopicModelDiagnostics(model, 20);
if (args.length == 3) {
PrintWriter out = new PrintWriter(args[2]);
out.println(diagnostics.toXML());
out.close();
}
}