@Override protected void setup(Context context) throws IOException, InterruptedException { log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing write model"); writeModel = modelWeight == 1 ? new TopicModel(numTopics, numTerms, eta, alpha, null, numUpdateThreads) : readModel; log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, writeModel, numTrainThreads, numTopics, numTerms); modelTrainer.start(); }
@Override protected void setup(Context context) throws IOException, InterruptedException { log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing write model"); writeModel = modelWeight == 1 ? new TopicModel(numTopics, numTerms, eta, alpha, null, numUpdateThreads) : readModel; log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, writeModel, numTrainThreads, numTopics, numTerms); modelTrainer.start(); }
@Override protected void setup(Context context) throws IOException, InterruptedException { log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing write model"); writeModel = modelWeight == 1 ? new TopicModel(numTopics, numTerms, eta, alpha, null, numUpdateThreads) : readModel; log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, writeModel, numTrainThreads, numTopics, numTerms); modelTrainer.start(); }
@Override protected void setup(Context context) throws IOException, InterruptedException { MemoryUtil.startMemoryLogger(5000); log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); random = RandomUtils.getRandom(seed); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); testFraction = conf.getFloat(CVB0Driver.TEST_SET_FRACTION, 0.1f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, null, numTrainThreads, numTopics, numTerms); log.info("Initializing topic vector"); topicVector = new DenseVector(new double[numTopics]); }
@Override protected void setup(Context context) throws IOException, InterruptedException { MemoryUtil.startMemoryLogger(5000); log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); random = RandomUtils.getRandom(seed); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); testFraction = conf.getFloat(CVB0Driver.TEST_SET_FRACTION, 0.1f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, null, numTrainThreads, numTopics, numTerms); log.info("Initializing topic vector"); topicVector = new DenseVector(new double[numTopics]); }
@Override protected void setup(Context context) throws IOException, InterruptedException { MemoryUtil.startMemoryLogger(5000); log.info("Retrieving configuration"); Configuration conf = context.getConfiguration(); float eta = conf.getFloat(CVB0Driver.TERM_TOPIC_SMOOTHING, Float.NaN); float alpha = conf.getFloat(CVB0Driver.DOC_TOPIC_SMOOTHING, Float.NaN); long seed = conf.getLong(CVB0Driver.RANDOM_SEED, 1234L); random = RandomUtils.getRandom(seed); numTopics = conf.getInt(CVB0Driver.NUM_TOPICS, -1); int numTerms = conf.getInt(CVB0Driver.NUM_TERMS, -1); int numUpdateThreads = conf.getInt(CVB0Driver.NUM_UPDATE_THREADS, 1); int numTrainThreads = conf.getInt(CVB0Driver.NUM_TRAIN_THREADS, 4); maxIters = conf.getInt(CVB0Driver.MAX_ITERATIONS_PER_DOC, 10); float modelWeight = conf.getFloat(CVB0Driver.MODEL_WEIGHT, 1.0f); testFraction = conf.getFloat(CVB0Driver.TEST_SET_FRACTION, 0.1f); log.info("Initializing read model"); Path[] modelPaths = CVB0Driver.getModelPaths(conf); if (modelPaths != null && modelPaths.length > 0) { readModel = new TopicModel(conf, eta, alpha, null, numUpdateThreads, modelWeight, modelPaths); } else { log.info("No model files found"); readModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(seed), null, numTrainThreads, modelWeight); } log.info("Initializing model trainer"); modelTrainer = new ModelTrainer(readModel, null, numTrainThreads, numTopics, numTerms); log.info("Initializing topic vector"); topicVector = new DenseVector(new double[numTopics]); }
private void initializeModel() { TopicModel topicModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(), terms, numUpdatingThreads, initialModelCorpusFraction == 0 ? 1 : initialModelCorpusFraction * totalCorpusWeight); topicModel.setConf(getConf()); TopicModel updatedModel = initialModelCorpusFraction == 0 ? new TopicModel(numTopics, numTerms, eta, alpha, null, terms, numUpdatingThreads, 1) : topicModel; updatedModel.setConf(getConf()); docTopicCounts = new DenseMatrix(numDocuments, numTopics); docTopicCounts.assign(1.0 / numTopics); modelTrainer = new ModelTrainer(topicModel, updatedModel, numTrainingThreads, numTopics, numTerms); }
private void initializeModel() { TopicModel topicModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(), terms, numUpdatingThreads, initialModelCorpusFraction == 0 ? 1 : initialModelCorpusFraction * totalCorpusWeight); topicModel.setConf(getConf()); TopicModel updatedModel = initialModelCorpusFraction == 0 ? new TopicModel(numTopics, numTerms, eta, alpha, null, terms, numUpdatingThreads, 1) : topicModel; updatedModel.setConf(getConf()); docTopicCounts = new DenseMatrix(numDocuments, numTopics); docTopicCounts.assign(1.0 / numTopics); modelTrainer = new ModelTrainer(topicModel, updatedModel, numTrainingThreads, numTopics, numTerms); }
private void initializeModel() { TopicModel topicModel = new TopicModel(numTopics, numTerms, eta, alpha, RandomUtils.getRandom(), terms, numUpdatingThreads, initialModelCorpusFraction == 0 ? 1 : initialModelCorpusFraction * totalCorpusWeight); topicModel.setConf(getConf()); TopicModel updatedModel = initialModelCorpusFraction == 0 ? new TopicModel(numTopics, numTerms, eta, alpha, null, terms, numUpdatingThreads, 1) : topicModel; updatedModel.setConf(getConf()); docTopicCounts = new DenseMatrix(numDocuments, numTopics); docTopicCounts.assign(1.0 / numTopics); modelTrainer = new ModelTrainer(topicModel, updatedModel, numTrainingThreads, numTopics, numTerms); }