public void printTopWords (PrintStream out, int numWords, boolean usingNewLines) { if (dmrParameters != null) { setAlphas(); } super.printTopWords(out, numWords, usingNewLines); }
public TopicScores getRank1Percent() { TopicScores scores = new TopicScores("rank_1_docs", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, (double) numRank1Documents[topic] / numNonZeroDocuments[topic]); } return scores; }
public NCRPNode getNewLeaf() { NCRPNode node = this; for (int l=level; l<numLevels - 1; l++) { node = node.addChild(); } return node; }
public static void main (String[] args) throws Exception { InstanceList instances = InstanceList.load(new File(args[0])); ParallelTopicModel model = new ParallelTopicModel(50, 5.0, 0.01); model.addInstances(instances); model.setNumIterations(100); model.estimate(); TopicReports reports = new JSONTopicReports(model); reports.printSummary(new File("summary.json"), 20); }
/** Return a tool for estimating topic distributions for new documents */ public TopicInferencer getInferencer(int language) { return new TopicInferencer(languageTypeTopicCounts[language], languageTokensPerTopic[language], alphabets[language], alpha, betas[language], betaSums[language]); }
/** Return a tool for evaluating the marginal probability of new documents * under this model */ public MarginalProbEstimator getProbEstimator() { return new MarginalProbEstimator(numTopics, alpha, alphaSum, beta, typeTopicCounts, tokensPerTopic); }
public void loadDocuments(InstanceList instances) { this.instances = instances; addInstances(instances); }
public TopicScores getRank1Percent() { TopicScores scores = new TopicScores("rank_1_docs", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, (double) numRank1Documents[topic] / numNonZeroDocuments[topic]); } return scores; }
public void printTopWords (PrintStream out, int numWords, boolean usingNewLines) { if (dmrParameters != null) { setAlphas(); } super.printTopWords(out, numWords, usingNewLines); }
public NCRPNode getNewLeaf() { NCRPNode node = this; for (int l=level; l<numLevels - 1; l++) { node = node.addChild(); } return node; }
/** Return a tool for estimating topic distributions for new documents */ public TopicInferencer getInferencer(int language) { return new TopicInferencer(languageTypeTopicCounts[language], languageTokensPerTopic[language], alphabets[language], alpha, betas[language], betaSums[language]); }
/** Return a tool for evaluating the marginal probability of new documents * under this model */ public MarginalProbEstimator getProbEstimator() { return new MarginalProbEstimator(numTopics, alpha, alphaSum, beta, typeTopicCounts, tokensPerTopic); }
public TopicScores getTokensPerTopic(int[] tokensPerTopic) { TopicScores scores = new TopicScores("tokens", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, tokensPerTopic[topic]); } return scores; }
public void printTopWords (PrintStream out, int numWords, boolean usingNewLines) { if (dmrParameters != null) { setAlphas(); } super.printTopWords(out, numWords, usingNewLines); }
public NCRPNode getNewLeaf() { NCRPNode node = this; for (int l=level; l<numLevels - 1; l++) { node = node.addChild(); } return node; }
/** Return a tool for estimating topic distributions for new documents */ public TopicInferencer getInferencer(int language) { return new TopicInferencer(languageTypeTopicCounts[language], languageTokensPerTopic[language], alphabets[language], alpha, betas[language], betaSums[language]); }
/** Return a tool for evaluating the marginal probability of new documents * under this model */ public MarginalProbEstimator getProbEstimator() { return new MarginalProbEstimator(numTopics, alpha, alphaSum, beta, typeTopicCounts, tokensPerTopic); }
public TopicScores getTokensPerTopic(int[] tokensPerTopic) { TopicScores scores = new TopicScores("tokens", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, tokensPerTopic[topic]); } return scores; }
public TopicScores getRank1Percent() { TopicScores scores = new TopicScores("rank_1_docs", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, (double) numRank1Documents[topic] / numNonZeroDocuments[topic]); } return scores; }
public TopicScores getTokensPerTopic(int[] tokensPerTopic) { TopicScores scores = new TopicScores("tokens", numTopics, numTopWords); for (int topic = 0; topic < numTopics; topic++) { scores.setTopicScore(topic, tokensPerTopic[topic]); } return scores; }