public void trainDocuments(
InstanceList documents, int numTopics, int numIterations, double alpha, double beta) {
double alphaSum = alpha * numTopics;
lda = new ParallelTopicModel(numTopics, alphaSum, beta);
lda.addInstances(documents);
lda.setNumThreads(4);
lda.setNumIterations(numIterations);
lda.printLogLikelihood = false;
try {
lda.estimate();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
System.out.println("LDA parameter, alphaSum: " + lda.alphaSum + ", beta: " + lda.beta);
}
protected double queryVsmSimilarity(int qdocId, int targetDocId) {
// TODO Auto-generated method stub
double predSim = 0;
double[] v1 = lda.getTopicProbabilities(qdocId);
double[] v2 = testTopicDistribution[targetDocId];
predSim = rs.util.vlc.Util.cosineProduct(v1, v2);
return predSim;
}
public void generateTestInference() {
if (lda == null) {
System.out.println("Should run lda estimation first.");
System.exit(1);
return;
}
if (testTopicDistribution == null) testTopicDistribution = new double[test.size()][];
TopicInferencer infer = lda.getInferencer();
int iterations = 800;
int thinning = 5;
int burnIn = 100;
for (int ti = 0; ti < test.size(); ti++) {
testTopicDistribution[ti] =
infer.getSampledDistribution(test.get(ti), iterations, thinning, burnIn);
}
}
