public void doInference() {
try {
ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile));
TopicInferencer inferencer = model.getInferencer();
// TopicInferencer inferencer =
// TopicInferencer.read(new File(inferencerFile));
// InstanceList testing = readFile();
readFile();
InstanceList testing = generateInstanceList(); // readFile();
for (int i = 0; i < testing.size(); i++) {
StringBuilder probabilities = new StringBuilder();
double[] testProbabilities = inferencer.getSampledDistribution(testing.get(i), 10, 1, 5);
ArrayList probabilityList = new ArrayList();
for (int j = 0; j < testProbabilities.length; j++) {
probabilityList.add(new Pair<Integer, Double>(j, testProbabilities[j]));
}
Collections.sort(probabilityList, new CustomComparator());
for (int j = 0; j < testProbabilities.length && j < topN; j++) {
if (j > 0) probabilities.append(" ");
probabilities.append(
((Pair<Integer, Double>) probabilityList.get(j)).getFirst().toString()
+ ","
+ ((Pair<Integer, Double>) probabilityList.get(j)).getSecond().toString());
}
System.out.println(docIds.get(i) + "," + probabilities.toString());
}
} catch (Exception e) {
e.printStackTrace();
System.err.println(e.getMessage());
}
}
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 void run() {
try {
if (!isFinished) {
System.out.println("already running!");
return;
}
isFinished = false;
// Initialize the smoothing-only sampling bucket
smoothingOnlyMass = 0;
smoothingOnlyLabelMass = 0;
// Initialize the cached coefficients, using only smoothing.
// These values will be selectively replaced in documents with
// non-zero counts in particular topics.
for (int topic = 0; topic < numTopics; topic++) {
smoothingOnlyMass += alpha[topic] * beta / (tokensPerTopic[topic] + betaSum);
if (ignoreLabels) {
// smoothingOnlyMass += alpha[topic] * beta / (tokensPerTopic[topic] + betaSum);
cachedCoefficients[topic] = alpha[topic] / (tokensPerTopic[topic] + betaSum);
} else {
// smoothingOnlyMass += (1 + lblWeight) * alpha[topic] * beta / (tokensPerTopic[topic] +
// betaSum);
cachedCoefficients[topic] =
(1 + lblWeight) * alpha[topic] / (tokensPerTopic[topic] + betaSum);
}
smoothingOnlyLabelMass += alpha[topic] * gamma / (labelsPerTopic[topic] + gammaSum);
if (ignoreLabels) {
// smoothingOnlyLabelMass += alpha[topic] * gamma / (labelsPerTopic[topic] + gammaSum);
cachedLabelCoefficients[topic] = alpha[topic] / (labelsPerTopic[topic] + gammaSum);
} else {
// smoothingOnlyLabelMass += (1 + 1 / lblWeight) * alpha[topic] * gamma /
// (labelsPerTopic[topic] + gammaSum);
cachedLabelCoefficients[topic] =
(1 + 1 / lblWeight) * alpha[topic] / (labelsPerTopic[topic] + gammaSum);
}
}
for (int doc = startDoc; doc < data.size() && doc < startDoc + numDocs; doc++) {
/*
if (doc % 10000 == 0) {
System.out.println("processing doc " + doc);
}
*/
/*
FeatureSequence tokenSequence =
(FeatureSequence) data.get(doc).instance.getData();
LabelSequence topicSequence =
(LabelSequence) data.get(doc).topicSequence;
LabelSequence lblTopicSequence =
(LabelSequence) data.get(doc).lblTopicSequence;
FeatureSequence labelSequence =
(FeatureSequence) data.get(doc).instance.getTarget();*/
sampleTopicsForOneDoc(data.get(doc));
// typeTopicCounts);
// , cachedCoefficients, tokensPerTopic, betaSum, beta, smoothingOnlyMass,
// lbltypeTopicCounts, cachedLabelCoefficients, labelsPerTopic, gammaSum, gamma,
// smoothingOnlyLabelMass);
// sampleTopicsForOneDoc(tokenSequence, topicSequence,
// true, typeTopicCounts, cachedCoefficients, tokensPerTopic, betaSum, beta,
// smoothingOnlyMass);
// homer sample labels now
// sampleTopicsForOneDoc(labelSequence, topicSequence,
// true, lbltypeTopicCounts, cachedLabelCoefficients, labelsPerTopic, gammaSum,
// gamma, smoothingOnlyLabelMass);
// homer
}
if (shouldBuildLocalCounts) {
buildLocalTypeTopicCounts();
}
shouldSaveState = false;
isFinished = true;
} catch (Exception e) {
e.printStackTrace();
}
}
