Examples with RuntimeIOException edu.stanford.nlp.io.RuntimeIOException used on opensource projects

Example 81 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class CoNLLDocumentReaderAndWriter method makeCoreLabel.

/**
 * This deals with the CoNLL files for different languages which have
 *  between 2 and 5 columns on non-blank lines.
 *
 *  @param line A line of CoNLL input
 *  @return The constructed token
 */
private CoreLabel makeCoreLabel(String line) {
    CoreLabel wi = new CoreLabel();
    // wi.line = line;
    String[] bits = line.split("\\s+");
    switch(bits.length) {
        case 0:
        case 1:
            wi.setWord(BOUNDARY);
            wi.set(CoreAnnotations.AnswerAnnotation.class, flags.backgroundSymbol);
            break;
        case 2:
            wi.setWord(bits[0]);
            wi.set(CoreAnnotations.AnswerAnnotation.class, bits[1]);
            break;
        case 3:
            wi.setWord(bits[0]);
            wi.setTag(bits[1]);
            wi.set(CoreAnnotations.AnswerAnnotation.class, bits[2]);
            break;
        case 4:
            wi.setWord(bits[0]);
            wi.setTag(bits[1]);
            wi.set(CoreAnnotations.ChunkAnnotation.class, bits[2]);
            wi.set(CoreAnnotations.AnswerAnnotation.class, bits[3]);
            break;
        case 5:
            if (flags.useLemmaAsWord) {
                wi.setWord(bits[1]);
            } else {
                wi.setWord(bits[0]);
            }
            wi.set(CoreAnnotations.LemmaAnnotation.class, bits[1]);
            wi.setTag(bits[2]);
            wi.set(CoreAnnotations.ChunkAnnotation.class, bits[3]);
            wi.set(CoreAnnotations.AnswerAnnotation.class, bits[4]);
            break;
        default:
            throw new RuntimeIOException("Unexpected input (many fields): " + line);
    }
    // Value annotation is used in a lot of place in corenlp so setting here as the word itself
    wi.set(CoreAnnotations.ValueAnnotation.class, wi.word());
    // The copy to GoldAnswerAnnotation is done before the recoding is done, and so it preserves the original coding.
    // This is important if the original coding is true, but the recoding is defective (like IOB2 to IO), since
    // it will allow correct evaluation later.
    wi.set(CoreAnnotations.GoldAnswerAnnotation.class, wi.get(CoreAnnotations.AnswerAnnotation.class));
    return wi;
}

Example 82 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class SentimentModel method loadSerialized.

public static SentimentModel loadSerialized(String path) {
    try {
        Timing timing = new Timing();
        SentimentModel model = IOUtils.readObjectFromURLOrClasspathOrFileSystem(path);
        timing.done(log, "Loading sentiment model " + path);
        return model;
    } catch (IOException | ClassNotFoundException e) {
        throw new RuntimeIOException(e);
    }
}

Example 83 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class AffixDictionary method readDict.

private static Set<String> readDict(String filename) {
    Set<String> a = Generics.newHashSet();
    try {
        /*
      if(filename.endsWith("in.as") ||filename.endsWith("in.city") ){
      	aDetectorReader = new BufferedReader(new InputStreamReader(new FileInputStream(filename), "Big5_HKSCS"));
      }else{ aDetectorReader = new BufferedReader(new InputStreamReader(new FileInputStream(filename), "GB18030"));
      }
      */
        BufferedReader aDetectorReader = IOUtils.readerFromString(filename, "UTF-8");
        // logger.debug("DEBUG: in affDict readDict");
        for (String aDetectorLine; (aDetectorLine = aDetectorReader.readLine()) != null; ) {
            // logger.debug("DEBUG: affDict: "+filename+" "+aDetectorLine);
            a.add(aDetectorLine);
        }
        aDetectorReader.close();
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
    // logger.info("XM:::readDict(filename: " + filename + ")");
    logger.info("Loading affix dictionary from " + filename + " [done].");
    return a;
}

Example 84 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class ChineseDictionary method serializeDictionary.

private void serializeDictionary(String serializePath) {
    logger.info("Serializing dictionaries to " + serializePath + " ... ");
    try {
        ObjectOutputStream oos = IOUtils.writeStreamFromString(serializePath);
        // oos.writeObject(MAX_LEXICON_LENGTH);
        oos.writeObject(words_);
        // oos.writeObject(cdtos_);
        oos.close();
        logger.info("done.");
    } catch (Exception e) {
        logger.error("Failed", e);
        throw new RuntimeIOException(e);
    }
}

Example 85 with RuntimeIOException

use of edu.stanford.nlp.io.RuntimeIOException in project CoreNLP by stanfordnlp.

the class KBPStatisticalExtractor method main.

public static void main(String[] args) throws IOException, ClassNotFoundException {
    // Disable SLF4J crap.
    RedwoodConfiguration.standard().apply();
    // Fill command-line options
    ArgumentParser.fillOptions(KBPStatisticalExtractor.class, args);
    // Load the test (or dev) data
    forceTrack("Test data");
    List<Pair<KBPInput, String>> testExamples = KBPRelationExtractor.readDataset(TEST_FILE);
    log.info("Read " + testExamples.size() + " examples");
    endTrack("Test data");
    // If we can't find an existing model, train one
    if (!IOUtils.existsInClasspathOrFileSystem(MODEL_FILE)) {
        forceTrack("Training data");
        List<Pair<KBPInput, String>> trainExamples = KBPRelationExtractor.readDataset(TRAIN_FILE);
        log.info("Read " + trainExamples.size() + " examples");
        log.info("" + trainExamples.stream().map(Pair::second).filter(NO_RELATION::equals).count() + " are " + NO_RELATION);
        endTrack("Training data");
        // Featurize + create the dataset
        forceTrack("Creating dataset");
        RVFDataset<String, String> dataset = new RVFDataset<>();
        final AtomicInteger i = new AtomicInteger(0);
        long beginTime = System.currentTimeMillis();
        trainExamples.stream().parallel().forEach(example -> {
            if (i.incrementAndGet() % 1000 == 0) {
                log.info("[" + Redwood.formatTimeDifference(System.currentTimeMillis() - beginTime) + "] Featurized " + i.get() + " / " + trainExamples.size() + " examples");
            }
            // This takes a while per example
            Counter<String> features = features(example.first);
            synchronized (dataset) {
                dataset.add(new RVFDatum<>(features, example.second));
            }
        });
        // Free up some memory
        trainExamples.clear();
        endTrack("Creating dataset");
        // Train the classifier
        log.info("Training classifier:");
        Classifier<String, String> classifier = trainMultinomialClassifier(dataset, FEATURE_THRESHOLD, SIGMA);
        // Free up some memory
        dataset.clear();
        // Save the classifier
        IOUtils.writeObjectToFile(new KBPStatisticalExtractor(classifier), MODEL_FILE);
    }
    // Read either a newly-trained or pre-trained model
    Object model = IOUtils.readObjectFromURLOrClasspathOrFileSystem(MODEL_FILE);
    KBPStatisticalExtractor classifier;
    if (model instanceof Classifier) {
        // noinspection unchecked
        classifier = new KBPStatisticalExtractor((Classifier<String, String>) model);
    } else {
        classifier = ((KBPStatisticalExtractor) model);
    }
    // Evaluate the model
    classifier.computeAccuracy(testExamples.stream(), PREDICTIONS.map(x -> {
        try {
            return "stdout".equalsIgnoreCase(x) ? System.out : new PrintStream(new FileOutputStream(x));
        } catch (IOException e) {
            throw new RuntimeIOException(e);
        }
    }));
}