/** This is (mostly) copied from CRF4.java */
public boolean[][] labelConnectionsIn(
Alphabet outputAlphabet, InstanceList trainingSet, String start) {
int numLabels = outputAlphabet.size();
boolean[][] connections = new boolean[numLabels][numLabels];
for (int i = 0; i < trainingSet.size(); i++) {
Instance instance = trainingSet.getInstance(i);
FeatureSequence output = (FeatureSequence) instance.getTarget();
for (int j = 1; j < output.size(); j++) {
int sourceIndex = outputAlphabet.lookupIndex(output.get(j - 1));
int destIndex = outputAlphabet.lookupIndex(output.get(j));
assert (sourceIndex >= 0 && destIndex >= 0);
connections[sourceIndex][destIndex] = true;
}
}
// Handle start state
if (start != null) {
int startIndex = outputAlphabet.lookupIndex(start);
for (int j = 0; j < outputAlphabet.size(); j++) {
connections[startIndex][j] = true;
}
}
return connections;
}
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;
}
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 void collectDocumentStatistics() {
topicCodocumentMatrices = new int[numTopics][numTopWords][numTopWords];
wordTypeCounts = new int[alphabet.size()];
numTokens = 0;
// This is an array of hash sets containing the words-of-interest for each topic,
// used for checking if the word at some position is one of those words.
IntHashSet[] topicTopWordIndices = new IntHashSet[numTopics];
// The same as the topic top words, but with int indices instead of strings,
// used for iterating over positions.
int[][] topicWordIndicesInOrder = new int[numTopics][numTopWords];
// This is an array of hash sets that will hold the words-of-interest present in a document,
// which will be cleared after every document.
IntHashSet[] docTopicWordIndices = new IntHashSet[numTopics];
int numDocs = model.getData().size();
// The count of each topic, again cleared after every document.
int[] topicCounts = new int[numTopics];
for (int topic = 0; topic < numTopics; topic++) {
IntHashSet wordIndices = new IntHashSet();
for (int i = 0; i < numTopWords; i++) {
if (topicTopWords[topic][i] != null) {
int type = alphabet.lookupIndex(topicTopWords[topic][i]);
topicWordIndicesInOrder[topic][i] = type;
wordIndices.add(type);
}
}
topicTopWordIndices[topic] = wordIndices;
docTopicWordIndices[topic] = new IntHashSet();
}
int doc = 0;
for (TopicAssignment document : model.getData()) {
FeatureSequence tokens = (FeatureSequence) document.instance.getData();
FeatureSequence topics = (FeatureSequence) document.topicSequence;
for (int position = 0; position < tokens.size(); position++) {
int type = tokens.getIndexAtPosition(position);
int topic = topics.getIndexAtPosition(position);
numTokens++;
wordTypeCounts[type]++;
topicCounts[topic]++;
if (topicTopWordIndices[topic].contains(type)) {
docTopicWordIndices[topic].add(type);
}
}
int docLength = tokens.size();
if (docLength > 0) {
int maxTopic = -1;
int maxCount = -1;
for (int topic = 0; topic < numTopics; topic++) {
if (topicCounts[topic] > 0) {
numNonZeroDocuments[topic]++;
if (topicCounts[topic] > maxCount) {
maxTopic = topic;
maxCount = topicCounts[topic];
}
sumCountTimesLogCount[topic] += topicCounts[topic] * Math.log(topicCounts[topic]);
double proportion =
(model.alpha[topic] + topicCounts[topic]) / (model.alphaSum + docLength);
for (int i = 0; i < DEFAULT_DOC_PROPORTIONS.length; i++) {
if (proportion < DEFAULT_DOC_PROPORTIONS[i]) {
break;
}
numDocumentsAtProportions[topic][i]++;
}
IntHashSet supportedWords = docTopicWordIndices[topic];
int[] indices = topicWordIndicesInOrder[topic];
for (int i = 0; i < numTopWords; i++) {
if (supportedWords.contains(indices[i])) {
for (int j = i; j < numTopWords; j++) {
if (i == j) {
// Diagonals are total number of documents with word W in topic T
topicCodocumentMatrices[topic][i][i]++;
} else if (supportedWords.contains(indices[j])) {
topicCodocumentMatrices[topic][i][j]++;
topicCodocumentMatrices[topic][j][i]++;
}
}
}
}
docTopicWordIndices[topic].clear();
topicCounts[topic] = 0;
}
}
if (maxTopic > -1) {
numRank1Documents[maxTopic]++;
}
}
doc++;
}
}
public void add(int featureIndex) {
growIfNecessary();
assert (featureIndex < dictionary.size());
features[length++] = featureIndex;
}
public void estimate(
InstanceList documents,
int numIterations,
int showTopicsInterval,
int outputModelInterval,
String outputModelFilename,
Randoms r) {
ilist = documents;
uniAlphabet = ilist.getDataAlphabet();
biAlphabet = ((FeatureSequenceWithBigrams) ilist.get(0).getData()).getBiAlphabet();
numTypes = uniAlphabet.size();
numBitypes = biAlphabet.size();
int numDocs = ilist.size();
topics = new int[numDocs][];
grams = new int[numDocs][];
docTopicCounts = new int[numDocs][numTopics];
typeNgramTopicCounts = new int[numTypes][2][numTopics];
unitypeTopicCounts = new int[numTypes][numTopics];
bitypeTopicCounts = new int[numBitypes][numTopics];
tokensPerTopic = new int[numTopics];
bitokensPerTopic = new int[numTypes][numTopics];
tAlpha = alpha * numTopics;
vBeta = beta * numTypes;
vGamma = gamma * numTypes;
long startTime = System.currentTimeMillis();
// Initialize with random assignments of tokens to topics
// and finish allocating this.topics and this.tokens
int topic, gram, seqLen, fi;
for (int di = 0; di < numDocs; di++) {
FeatureSequenceWithBigrams fs = (FeatureSequenceWithBigrams) ilist.get(di).getData();
seqLen = fs.getLength();
numTokens += seqLen;
topics[di] = new int[seqLen];
grams[di] = new int[seqLen];
// Randomly assign tokens to topics
int prevFi = -1, prevTopic = -1;
for (int si = 0; si < seqLen; si++) {
// randomly sample a topic for the word at position si
topic = r.nextInt(numTopics);
// if a bigram is allowed at position si, then sample a gram status for it.
gram = (fs.getBiIndexAtPosition(si) == -1 ? 0 : r.nextInt(2));
if (gram != 0) biTokens++;
topics[di][si] = topic;
grams[di][si] = gram;
docTopicCounts[di][topic]++;
fi = fs.getIndexAtPosition(si);
if (prevFi != -1) typeNgramTopicCounts[prevFi][gram][prevTopic]++;
if (gram == 0) {
unitypeTopicCounts[fi][topic]++;
tokensPerTopic[topic]++;
} else {
bitypeTopicCounts[fs.getBiIndexAtPosition(si)][topic]++;
bitokensPerTopic[prevFi][topic]++;
}
prevFi = fi;
prevTopic = topic;
}
}
for (int iterations = 0; iterations < numIterations; iterations++) {
sampleTopicsForAllDocs(r);
if (iterations % 10 == 0) System.out.print(iterations);
else System.out.print(".");
System.out.flush();
if (showTopicsInterval != 0 && iterations % showTopicsInterval == 0 && iterations > 0) {
System.out.println();
printTopWords(5, false);
}
if (outputModelInterval != 0 && iterations % outputModelInterval == 0 && iterations > 0) {
this.write(new File(outputModelFilename + '.' + iterations));
}
}
System.out.println(
"\nTotal time (sec): " + ((System.currentTimeMillis() - startTime) / 1000.0));
}