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 String toString() {
StringBuffer sb = new StringBuffer();
for (int fsi = 0; fsi < length; fsi++) {
Object o = dictionary.lookupObject(features[fsi]);
sb.append(fsi);
sb.append(": ");
sb.append(o.toString());
sb.append(" (");
sb.append(features[fsi]);
sb.append(")\n");
}
return sb.toString();
}
public void printState(PrintWriter pw) {
Alphabet a = ilist.getDataAlphabet();
pw.println("#doc pos typeindex type topic");
for (int di = 0; di < topics.length; di++) {
FeatureSequence fs = (FeatureSequence) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(a.lookupObject(type));
pw.print(' ');
pw.print(topics[di][si]);
pw.println();
}
}
}
public void printCounts() {
Alphabet alphabet = instances.getDataAlphabet();
NumberFormat nf = NumberFormat.getInstance();
nf.setMinimumFractionDigits(0);
nf.setMaximumFractionDigits(6);
nf.setGroupingUsed(false);
for (int feature = 0; feature < numFeatures; feature++) {
Formatter formatter = new Formatter(new StringBuilder(), Locale.US);
formatter.format(
"%s\t%s\t%d",
alphabet.lookupObject(feature).toString(),
nf.format(featureCounts[feature]),
documentFrequencies[feature]);
System.out.println(formatter);
}
}
public void printState(PrintWriter pw) {
pw.println("#doc pos typeindex type bigrampossible? topic bigram");
for (int di = 0; di < topics.length; di++) {
FeatureSequenceWithBigrams fs = (FeatureSequenceWithBigrams) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(uniAlphabet.lookupObject(type));
pw.print(' ');
pw.print(fs.getBiIndexAtPosition(si) == -1 ? 0 : 1);
pw.print(' ');
pw.print(topics[di][si]);
pw.print(' ');
pw.print(grams[di][si]);
pw.println();
}
}
}
/**
* Remove features from the sequence that occur fewer than <code>cutoff</code> times in the
* corpus, as indicated by the provided counts. Also swap in the new, reduced alphabet. This
* method alters the instance in place; it is not appropriate if the original instance will be
* needed.
*/
public void prune(double[] counts, Alphabet newAlphabet, int cutoff) {
// The goal is to replace the sequence of features in place, by
// creating a new array and then swapping it in.
// First: figure out how long the new array will have to be
int newLength = 0;
for (int i = 0; i < length; i++) {
if (counts[features[i]] >= cutoff) {
newLength++;
}
}
// Second: allocate a new features array
int[] newFeatures = new int[newLength];
// Third: fill the new array
int newIndex = 0;
for (int i = 0; i < length; i++) {
if (counts[features[i]] >= cutoff) {
Object feature = dictionary.lookupObject(features[i]);
newFeatures[newIndex] = newAlphabet.lookupIndex(feature);
newIndex++;
}
}
// Fourth: swap out the arrays
features = newFeatures;
length = newLength;
dictionary = newAlphabet;
}
// xxx This method name seems a bit ambiguous?
public Object get(int pos) {
return dictionary.lookupObject(features[pos]);
}
public void printTopWords(int numWords, boolean useNewLines) {
class WordProb implements Comparable {
int wi;
double p;
public WordProb(int wi, double p) {
this.wi = wi;
this.p = p;
}
public final int compareTo(Object o2) {
if (p > ((WordProb) o2).p) return -1;
else if (p == ((WordProb) o2).p) return 0;
else return 1;
}
}
for (int ti = 0; ti < numTopics; ti++) {
// Unigrams
WordProb[] wp = new WordProb[numTypes];
for (int wi = 0; wi < numTypes; wi++)
wp[wi] = new WordProb(wi, (double) unitypeTopicCounts[wi][ti]);
Arrays.sort(wp);
int numToPrint = Math.min(wp.length, numWords);
if (useNewLines) {
System.out.println("\nTopic " + ti + " unigrams");
for (int i = 0; i < numToPrint; i++)
System.out.println(
uniAlphabet.lookupObject(wp[i].wi).toString() + " " + wp[i].p / tokensPerTopic[ti]);
} else {
System.out.print("Topic " + ti + ": ");
for (int i = 0; i < numToPrint; i++)
System.out.print(uniAlphabet.lookupObject(wp[i].wi).toString() + " ");
}
// Bigrams
/*
wp = new WordProb[numBitypes];
int bisum = 0;
for (int wi = 0; wi < numBitypes; wi++) {
wp[wi] = new WordProb (wi, ((double)bitypeTopicCounts[wi][ti]));
bisum += bitypeTopicCounts[wi][ti];
}
Arrays.sort (wp);
numToPrint = Math.min(wp.length, numWords);
if (useNewLines) {
System.out.println ("\nTopic "+ti+" bigrams");
for (int i = 0; i < numToPrint; i++)
System.out.println (biAlphabet.lookupObject(wp[i].wi).toString() + " " + wp[i].p/bisum);
} else {
System.out.print (" ");
for (int i = 0; i < numToPrint; i++)
System.out.print (biAlphabet.lookupObject(wp[i].wi).toString() + " ");
System.out.println();
}
*/
// Ngrams
AugmentableFeatureVector afv = new AugmentableFeatureVector(new Alphabet(), 10000, false);
for (int di = 0; di < topics.length; di++) {
FeatureSequenceWithBigrams fs = (FeatureSequenceWithBigrams) ilist.get(di).getData();
for (int si = topics[di].length - 1; si >= 0; si--) {
if (topics[di][si] == ti && grams[di][si] == 1) {
String gramString = uniAlphabet.lookupObject(fs.getIndexAtPosition(si)).toString();
while (grams[di][si] == 1 && --si >= 0)
gramString =
uniAlphabet.lookupObject(fs.getIndexAtPosition(si)).toString() + "_" + gramString;
afv.add(gramString, 1.0);
}
}
}
// System.out.println ("pre-sorting");
int numNgrams = afv.numLocations();
// System.out.println ("post-sorting "+numNgrams);
wp = new WordProb[numNgrams];
int ngramSum = 0;
for (int loc = 0; loc < numNgrams; loc++) {
wp[loc] = new WordProb(afv.indexAtLocation(loc), afv.valueAtLocation(loc));
ngramSum += wp[loc].p;
}
Arrays.sort(wp);
int numUnitypeTokens = 0, numBitypeTokens = 0, numUnitypeTypes = 0, numBitypeTypes = 0;
for (int fi = 0; fi < numTypes; fi++) {
numUnitypeTokens += unitypeTopicCounts[fi][ti];
if (unitypeTopicCounts[fi][ti] != 0) numUnitypeTypes++;
}
for (int fi = 0; fi < numBitypes; fi++) {
numBitypeTokens += bitypeTopicCounts[fi][ti];
if (bitypeTopicCounts[fi][ti] != 0) numBitypeTypes++;
}
if (useNewLines) {
System.out.println(
"\nTopic "
+ ti
+ " unigrams "
+ numUnitypeTokens
+ "/"
+ numUnitypeTypes
+ " bigrams "
+ numBitypeTokens
+ "/"
+ numBitypeTypes
+ " phrases "
+ Math.round(afv.oneNorm())
+ "/"
+ numNgrams);
for (int i = 0; i < Math.min(numNgrams, numWords); i++)
System.out.println(
afv.getAlphabet().lookupObject(wp[i].wi).toString() + " " + wp[i].p / ngramSum);
} else {
System.out.print(
" (unigrams "
+ numUnitypeTokens
+ "/"
+ numUnitypeTypes
+ " bigrams "
+ numBitypeTokens
+ "/"
+ numBitypeTypes
+ " phrases "
+ Math.round(afv.oneNorm())
+ "/"
+ numNgrams
+ ")\n ");
// System.out.print (" (unique-ngrams="+numNgrams+"
// ngram-count="+Math.round(afv.oneNorm())+")\n ");
for (int i = 0; i < Math.min(numNgrams, numWords); i++)
System.out.print(afv.getAlphabet().lookupObject(wp[i].wi).toString() + " ");
System.out.println();
}
}
}