public TopicScores getDistanceFromUniform() {
int[] tokensPerTopic = model.tokensPerTopic;
TopicScores scores = new TopicScores("uniform_dist", numTopics, numTopWords);
scores.wordScoresDefined = true;
int numTypes = alphabet.size();
for (int topic = 0; topic < numTopics; topic++) {
double topicScore = 0.0;
int position = 0;
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
for (IDSorter info : sortedWords) {
int type = info.getID();
double count = info.getWeight();
double score =
(count / tokensPerTopic[topic]) * Math.log((count * numTypes) / tokensPerTopic[topic]);
if (position < numTopWords) {
scores.setTopicWordScore(topic, position, score);
}
topicScore += score;
position++;
}
scores.setTopicScore(topic, topicScore);
}
return scores;
}
/** Low-quality topics may have words that are also prominent in other topics. */
public TopicScores getExclusivity() {
int[] tokensPerTopic = model.tokensPerTopic;
TopicScores scores = new TopicScores("exclusivity", numTopics, numTopWords);
scores.wordScoresDefined = true;
double sumDefaultProbs = 0.0;
for (int topic = 0; topic < numTopics; topic++) {
sumDefaultProbs += model.beta / (model.betaSum + tokensPerTopic[topic]);
}
for (int topic = 0; topic < numTopics; topic++) {
double topicScore = 0.0;
int position = 0;
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
for (IDSorter info : sortedWords) {
int type = info.getID();
double count = info.getWeight();
double sumTypeProbs = sumDefaultProbs;
int[] topicCounts = model.typeTopicCounts[type];
int index = 0;
while (index < topicCounts.length && topicCounts[index] > 0) {
int otherTopic = topicCounts[index] & model.topicMask;
int otherCount = topicCounts[index] >> model.topicBits;
// We've already accounted for the smoothing parameter,
// now we need to add the actual count for the non-zero
// topics.
sumTypeProbs += ((double) otherCount) / (model.betaSum + tokensPerTopic[otherTopic]);
index++;
}
double score =
((model.beta + count) / (model.betaSum + tokensPerTopic[topic])) / sumTypeProbs;
scores.setTopicWordScore(topic, position, score);
topicScore += score;
position++;
if (position == numTopWords) {
break;
}
}
scores.setTopicScore(topic, topicScore / numTopWords);
}
return scores;
}
public TopicModelDiagnostics(ParallelTopicModel model, int numTopWords) {
numTopics = model.getNumTopics();
this.numTopWords = numTopWords;
this.model = model;
alphabet = model.getAlphabet();
topicSortedWords = model.getSortedWords();
topicTopWords = new String[numTopics][numTopWords];
numRank1Documents = new int[numTopics];
numNonZeroDocuments = new int[numTopics];
numDocumentsAtProportions = new int[numTopics][DEFAULT_DOC_PROPORTIONS.length];
sumCountTimesLogCount = new double[numTopics];
diagnostics = new ArrayList<TopicScores>();
for (int topic = 0; topic < numTopics; topic++) {
int position = 0;
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
// How many words should we report? Some topics may have fewer than
// the default number of words with non-zero weight.
int limit = numTopWords;
if (sortedWords.size() < numTopWords) {
limit = sortedWords.size();
}
Iterator<IDSorter> iterator = sortedWords.iterator();
for (int i = 0; i < limit; i++) {
IDSorter info = iterator.next();
topicTopWords[topic][i] = (String) alphabet.lookupObject(info.getID());
}
}
collectDocumentStatistics();
diagnostics.add(getTokensPerTopic(model.tokensPerTopic));
diagnostics.add(getDocumentEntropy(model.tokensPerTopic));
diagnostics.add(getWordLengthScores());
diagnostics.add(getCoherence());
diagnostics.add(getDistanceFromUniform());
diagnostics.add(getDistanceFromCorpus());
diagnostics.add(getEffectiveNumberOfWords());
diagnostics.add(getTokenDocumentDiscrepancies());
diagnostics.add(getRank1Percent());
diagnostics.add(getDocumentPercentRatio(FIFTY_PERCENT_INDEX, TWO_PERCENT_INDEX));
diagnostics.add(getDocumentPercent(5));
diagnostics.add(getExclusivity());
}
public TopicScores getTokenDocumentDiscrepancies() {
TopicScores scores = new TopicScores("token-doc-diff", numTopics, numTopWords);
scores.wordScoresDefined = true;
for (int topic = 0; topic < numTopics; topic++) {
int[][] matrix = topicCodocumentMatrices[topic];
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
double topicScore = 0.0;
double[] wordDistribution = new double[numTopWords];
double[] docDistribution = new double[numTopWords];
double wordSum = 0.0;
double docSum = 0.0;
int position = 0;
Iterator<IDSorter> iterator = sortedWords.iterator();
while (iterator.hasNext() && position < numTopWords) {
IDSorter info = iterator.next();
wordDistribution[position] = info.getWeight();
docDistribution[position] = matrix[position][position];
wordSum += wordDistribution[position];
docSum += docDistribution[position];
position++;
}
for (position = 0; position < numTopWords; position++) {
double p = wordDistribution[position] / wordSum;
double q = docDistribution[position] / docSum;
double meanProb = 0.5 * (p + q);
double score = 0.0;
if (p > 0) {
score += 0.5 * p * Math.log(p / meanProb);
}
if (q > 0) {
score += 0.5 * q * Math.log(q / meanProb);
}
scores.setTopicWordScore(topic, position, score);
topicScore += score;
}
scores.setTopicScore(topic, topicScore);
}
return scores;
}
/** Low-quality topics may be very similar to the global distribution. */
public TopicScores getDistanceFromCorpus() {
int[] tokensPerTopic = model.tokensPerTopic;
TopicScores scores = new TopicScores("corpus_dist", numTopics, numTopWords);
scores.wordScoresDefined = true;
for (int topic = 0; topic < numTopics; topic++) {
double coefficient = (double) numTokens / tokensPerTopic[topic];
double topicScore = 0.0;
int position = 0;
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
for (IDSorter info : sortedWords) {
int type = info.getID();
double count = info.getWeight();
double score =
(count / tokensPerTopic[topic]) * Math.log(coefficient * count / wordTypeCounts[type]);
if (position < numTopWords) {
// System.out.println(alphabet.lookupObject(type) + ": " + count + " * " + numTokens + " /
// " + wordTypeCounts[type] + " * " + tokensPerTopic[topic] + " = " + (coefficient * count
// / wordTypeCounts[type]));
scores.setTopicWordScore(topic, position, score);
}
topicScore += score;
position++;
}
scores.setTopicScore(topic, topicScore);
}
return scores;
}
public TopicScores getEffectiveNumberOfWords() {
int[] tokensPerTopic = model.tokensPerTopic;
TopicScores scores = new TopicScores("eff_num_words", numTopics, numTopWords);
int numTypes = alphabet.size();
for (int topic = 0; topic < numTopics; topic++) {
double sumSquaredProbabilities = 0.0;
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
for (IDSorter info : sortedWords) {
int type = info.getID();
double probability = info.getWeight() / tokensPerTopic[topic];
sumSquaredProbabilities += probability * probability;
}
scores.setTopicScore(topic, 1.0 / sumSquaredProbabilities);
}
return scores;
}
public String toXML() {
int[] tokensPerTopic = model.tokensPerTopic;
StringBuilder out = new StringBuilder();
Formatter formatter = new Formatter(out, Locale.US);
out.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n");
out.append("<model>\n");
for (int topic = 0; topic < numTopics; topic++) {
int[][] matrix = topicCodocumentMatrices[topic];
formatter.format("<topic id='%d'", topic);
for (TopicScores scores : diagnostics) {
formatter.format(" %s='%.4f'", scores.name, scores.scores[topic]);
}
out.append(">\n");
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
// How many words should we report? Some topics may have fewer than
// the default number of words with non-zero weight.
int limit = numTopWords;
if (sortedWords.size() < numTopWords) {
limit = sortedWords.size();
}
double cumulativeProbability = 0.0;
Iterator<IDSorter> iterator = sortedWords.iterator();
for (int position = 0; position < limit; position++) {
IDSorter info = iterator.next();
double probability = info.getWeight() / tokensPerTopic[topic];
cumulativeProbability += probability;
formatter.format(
"<word rank='%d' count='%.0f' prob='%.5f' cumulative='%.5f' docs='%d'",
position + 1,
info.getWeight(),
probability,
cumulativeProbability,
matrix[position][position]);
for (TopicScores scores : diagnostics) {
if (scores.wordScoresDefined) {
formatter.format(" %s='%.4f'", scores.name, scores.topicWordScores[topic][position]);
}
}
formatter.format(
">%s</word>\n",
topicTopWords[topic][position].replaceAll("&", "&").replaceAll("<", ">"));
}
out.append("</topic>\n");
}
out.append("</model>\n");
return out.toString();
}