Example usage for org.deeplearning4j.models.word2vec Word2Vec Word2Vec

Introduction

In this page you can find the example usage for org.deeplearning4j.models.word2vec Word2Vec Word2Vec.

Prototype

Word2Vec

Source Link

Usage

From source file:de.mpii.docsimilarity.mr.utils.io.WordVectorSerializer.java

License:Apache License

/**
 * @param modelFile/*www . j ava2 s  . co m*/
 * @return
 * @throws FileNotFoundException
 * @throws IOException
 * @throws NumberFormatException
 */
private static Word2Vec readTextModel(File modelFile) throws IOException, NumberFormatException {
    InMemoryLookupTable lookupTable;
    VocabCache cache;
    INDArray syn0;
    Word2Vec ret = new Word2Vec();
    try (BufferedReader reader = new BufferedReader(
            new InputStreamReader(GzipUtils.isCompressedFilename(modelFile.getName())
                    ? new GZIPInputStream(new FileInputStream(modelFile))
                    : new FileInputStream(modelFile)))) {
        String line = reader.readLine();
        String[] initial = line.split(" ");
        int words = Integer.parseInt(initial[0]);
        int layerSize = Integer.parseInt(initial[1]);
        syn0 = Nd4j.create(words, layerSize);

        cache = new InMemoryLookupCache(false);

        int currLine = 0;
        while ((line = reader.readLine()) != null) {
            String[] split = line.split(" ");
            assert split.length == layerSize + 1;
            String word = split[0];

            float[] vector = new float[split.length - 1];
            for (int i = 1; i < split.length; i++) {
                vector[i - 1] = Float.parseFloat(split[i]);
            }

            syn0.putRow(currLine, Transforms.unitVec(Nd4j.create(vector)));

            cache.addWordToIndex(cache.numWords(), word);
            cache.addToken(new VocabWord(1, word));
            cache.putVocabWord(word);

            currLine++;
        }

        lookupTable = (InMemoryLookupTable) new InMemoryLookupTable.Builder().cache(cache)
                .vectorLength(layerSize).build();
        lookupTable.setSyn0(syn0);

        ret.setVocab(cache);
        ret.setLookupTable(lookupTable);
    }
    return ret;
}

---

From source file:de.mpii.docsimilarity.mr.utils.io.WordVectorSerializer.java

License:Apache License

/**
 * Read a binary word2vec file./*w  w w .ja  v  a2  s .com*/
 *
 * @param modelFile
 *            the File to read
 * @param linebreaks
 *            if true, the reader expects each word/vector to be in a separate line, terminated
 *            by a line break
 * @return a {@link Word2Vec model}
 * @throws NumberFormatException
 * @throws IOException
 * @throws FileNotFoundException
 */
private static Word2Vec readBinaryModel(File modelFile, boolean linebreaks)
        throws NumberFormatException, IOException {
    InMemoryLookupTable lookupTable;
    VocabCache cache;
    INDArray syn0;
    int words, size;
    try (BufferedInputStream bis = new BufferedInputStream(GzipUtils.isCompressedFilename(modelFile.getName())
            ? new GZIPInputStream(new FileInputStream(modelFile))
            : new FileInputStream(modelFile)); DataInputStream dis = new DataInputStream(bis)) {
        words = Integer.parseInt(readString(dis));
        size = Integer.parseInt(readString(dis));
        syn0 = Nd4j.create(words, size);
        cache = new InMemoryLookupCache(false);
        lookupTable = (InMemoryLookupTable) new InMemoryLookupTable.Builder().cache(cache).vectorLength(size)
                .build();

        String word;
        for (int i = 0; i < words; i++) {

            word = readString(dis);
            log.trace("Loading " + word + " with word " + i);

            float[] vector = new float[size];

            for (int j = 0; j < size; j++) {
                vector[j] = readFloat(dis);
            }

            syn0.putRow(i, Transforms.unitVec(Nd4j.create(vector)));

            cache.addWordToIndex(cache.numWords(), word);
            cache.addToken(new VocabWord(1, word));
            cache.putVocabWord(word);

            if (linebreaks) {
                dis.readByte(); // line break
            }
        }
    }

    Word2Vec ret = new Word2Vec();

    lookupTable.setSyn0(syn0);
    ret.setVocab(cache);
    ret.setLookupTable(lookupTable);
    return ret;

}

---

From source file:de.mpii.docsimilarity.mr.utils.io.WordVectorSerializer.java

License:Apache License

/**
 * Read a binary word2vec file.// w w w.  ja  va2 s.c  o  m
 *
 * @param modelFile
 *            the File to read
 * @return a {@link Word2Vec model}
 * @throws NumberFormatException
 * @throws IOException
 * @throws FileNotFoundException
 */
public static Word2Vec readBinaryModel(String modelFile, FSDataInputStream modelstream,
        Set<String> requiredTerms) throws NumberFormatException, IOException {
    boolean linebreaks = DEFAULT_LINEBREAKS;
    InMemoryLookupTable lookupTable;
    VocabCache cache;
    INDArray syn0;
    int words, size;
    int count = 0;
    try (BufferedInputStream bis = new BufferedInputStream(
            GzipUtils.isCompressedFilename(modelFile) ? new GZIPInputStream(modelstream) : modelstream);
            DataInputStream dis = new DataInputStream(bis)) {
        words = Integer.parseInt(readString(dis));
        size = Integer.parseInt(readString(dis));
        System.out.println("words " + words + ", size " + size);
        syn0 = Nd4j.create(words, size);
        cache = new InMemoryLookupCache(false);
        lookupTable = (InMemoryLookupTable) new InMemoryLookupTable.Builder().cache(cache).vectorLength(size)
                .build();

        String word;

        for (int i = 0; i < words; i++) {

            word = readString(dis);

            log.trace("Loading " + word + " with word " + i);

            float[] vector = new float[size];

            for (int j = 0; j < size; j++) {
                vector[j] = readFloat(dis);
            }
            if (requiredTerms.contains(word)) {
                syn0.putRow(i, Transforms.unitVec(Nd4j.create(vector)));
                cache.addWordToIndex(cache.numWords(), word);
                cache.addToken(new VocabWord(1, word));
                cache.putVocabWord(word);
                count++;
            }

            if (linebreaks) {
                dis.readByte(); // line break
            }
        }
    }

    Word2Vec ret = new Word2Vec();

    lookupTable.setSyn0(syn0);
    ret.setVocab(cache);
    ret.setLookupTable(lookupTable);
    System.out.println("Load " + count + " terms in word2vec.");
    return ret;

}

---

From source file:org.knime.ext.textprocessing.dl4j.util.WordVectorPortObjectUtils.java

License:Open Source License

/**
 * Converts wordVectors to {@link Word2Vec}. Sets {@link WeightLookupTable} and {@link VocabCache}. Depending on
 * specified word vector type this may lead to information loss. E.g. labels for {@link ParagraphVectors}.
 *
 * @param wordVectors/* w w  w.  j ava2s. c o  m*/
 * @return Word2Vec containing vocab and lookup table
 */
public static Word2Vec wordVectorsToWord2Vec(final WordVectors wordVectors) {
    final Word2Vec w2v = new Word2Vec();
    w2v.setLookupTable(wordVectors.lookupTable());
    w2v.setVocab(wordVectors.vocab());
    return w2v;
}

---