/** 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 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++;
}
}
