private InstanceList readFile() throws IOException {
String NL = System.getProperty("line.separator");
Scanner scanner = new Scanner(new FileInputStream(fileName), encoding);
ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}\\p{L}+")));
pipeList.add(new TokenSequence2FeatureSequence());
InstanceList testing = new InstanceList(new SerialPipes(pipeList));
try {
while (scanner.hasNextLine()) {
String text = scanner.nextLine();
text = text.replaceAll("\\x0d", "");
Pattern patten = Pattern.compile("^(.*?),(.*?),(.*)$");
Matcher matcher = patten.matcher(text);
if (matcher.find()) {
docIds.add(matcher.group(1));
testing.addThruPipe(new Instance(matcher.group(3), null, "test instance", null));
}
}
} finally {
scanner.close();
}
return testing;
}
private InstanceList generateInstanceList() throws Exception {
ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}\\p{L}+")));
pipeList.add(new TokenSequence2FeatureSequence());
Reader fileReader = new InputStreamReader(new FileInputStream(new File(fileName)), "UTF-8");
InstanceList instances = new InstanceList(new SerialPipes(pipeList));
instances.addThruPipe(
new CsvIterator(
fileReader,
Pattern.compile("^(\\S*)[\\s,]*(\\S*)[\\s,]*(.*)$"),
3,
2,
1)); // data, label, name fields
return instances;
}
public void doInference() {
try {
ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile));
TopicInferencer inferencer = model.getInferencer();
// TopicInferencer inferencer =
// TopicInferencer.read(new File(inferencerFile));
// InstanceList testing = readFile();
readFile();
InstanceList testing = generateInstanceList(); // readFile();
for (int i = 0; i < testing.size(); i++) {
StringBuilder probabilities = new StringBuilder();
double[] testProbabilities = inferencer.getSampledDistribution(testing.get(i), 10, 1, 5);
ArrayList probabilityList = new ArrayList();
for (int j = 0; j < testProbabilities.length; j++) {
probabilityList.add(new Pair<Integer, Double>(j, testProbabilities[j]));
}
Collections.sort(probabilityList, new CustomComparator());
for (int j = 0; j < testProbabilities.length && j < topN; j++) {
if (j > 0) probabilities.append(" ");
probabilities.append(
((Pair<Integer, Double>) probabilityList.get(j)).getFirst().toString()
+ ","
+ ((Pair<Integer, Double>) probabilityList.get(j)).getSecond().toString());
}
System.out.println(docIds.get(i) + "," + probabilities.toString());
}
} catch (Exception e) {
e.printStackTrace();
System.err.println(e.getMessage());
}
}
public void test() throws Exception {
ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile));
TopicInferencer inferencer = model.getInferencer();
ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}\\p{L}+")));
pipeList.add(new TokenSequence2FeatureSequence());
InstanceList instances = new InstanceList(new SerialPipes(pipeList));
Reader fileReader = new InputStreamReader(new FileInputStream(new File(fileName)), "UTF-8");
instances.addThruPipe(
new CsvIterator(
fileReader,
Pattern.compile("^(\\S*)[\\s,]*(\\S*)[\\s,]*(.*)$"),
3,
2,
1)); // data, label, name fields
double[] testProbabilities = inferencer.getSampledDistribution(instances.get(1), 10, 1, 5);
for (int i = 0; i < 1000; i++) System.out.println(i + ": " + testProbabilities[i]);
}
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 TestCRFPipe(String trainingFilename) throws IOException {
ArrayList<Pipe> pipes = new ArrayList<Pipe>();
PrintWriter out = new PrintWriter("test.out");
int[][] conjunctions = new int[3][];
conjunctions[0] = new int[] {-1};
conjunctions[1] = new int[] {1};
conjunctions[2] = new int[] {-2, -1};
pipes.add(new SimpleTaggerSentence2TokenSequence());
// pipes.add(new FeaturesInWindow("PREV-", -1, 1));
// pipes.add(new FeaturesInWindow("NEXT-", 1, 2));
pipes.add(new OffsetConjunctions(conjunctions));
pipes.add(new TokenTextCharSuffix("C1=", 1));
pipes.add(new TokenTextCharSuffix("C2=", 2));
pipes.add(new TokenTextCharSuffix("C3=", 3));
pipes.add(new RegexMatches("CAPITALIZED", Pattern.compile("^\\p{Lu}.*")));
pipes.add(new RegexMatches("STARTSNUMBER", Pattern.compile("^[0-9].*")));
pipes.add(new RegexMatches("HYPHENATED", Pattern.compile(".*\\-.*")));
pipes.add(new RegexMatches("DOLLARSIGN", Pattern.compile("\\$.*")));
pipes.add(new TokenFirstPosition("FIRSTTOKEN"));
pipes.add(new TokenSequence2FeatureVectorSequence());
pipes.add(new SequencePrintingPipe(out));
Pipe pipe = new SerialPipes(pipes);
InstanceList trainingInstances = new InstanceList(pipe);
trainingInstances.addThruPipe(
new LineGroupIterator(
new BufferedReader(
new InputStreamReader(new GZIPInputStream(new FileInputStream(trainingFilename)))),
Pattern.compile("^\\s*$"),
true));
out.close();
}
