Examples with VocabWord org.deeplearning4j.models.word2vec.VocabWord used on opensource projects

Example 6 with VocabWord

use of org.deeplearning4j.models.word2vec.VocabWord in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method readWord2VecFromText.

/**
     * This method allows you to read ParagraphVectors from externaly originated vectors and syn1.
     * So, technically this method is compatible with any other w2v implementation
     *
     * @param vectors   text file with words and their wieghts, aka Syn0
     * @param hs    text file HS layers, aka Syn1
     * @param h_codes   text file with Huffman tree codes
     * @param h_points  text file with Huffman tree points
     * @return
     */
public static Word2Vec readWord2VecFromText(@NonNull File vectors, @NonNull File hs, @NonNull File h_codes, @NonNull File h_points, @NonNull VectorsConfiguration configuration) throws IOException {
    // first we load syn0
    Pair<InMemoryLookupTable, VocabCache> pair = loadTxt(vectors);
    InMemoryLookupTable lookupTable = pair.getFirst();
    lookupTable.setNegative(configuration.getNegative());
    if (configuration.getNegative() > 0)
        lookupTable.initNegative();
    VocabCache<VocabWord> vocab = (VocabCache<VocabWord>) pair.getSecond();
    // now we load syn1
    BufferedReader reader = new BufferedReader(new FileReader(hs));
    String line = null;
    List<INDArray> rows = new ArrayList<>();
    while ((line = reader.readLine()) != null) {
        String[] split = line.split(" ");
        double[] array = new double[split.length];
        for (int i = 0; i < split.length; i++) {
            array[i] = Double.parseDouble(split[i]);
        }
        rows.add(Nd4j.create(array));
    }
    reader.close();
    // it's possible to have full model without syn1
    if (rows.size() > 0) {
        INDArray syn1 = Nd4j.vstack(rows);
        lookupTable.setSyn1(syn1);
    }
    // now we transform mappings into huffman tree points
    reader = new BufferedReader(new FileReader(h_points));
    while ((line = reader.readLine()) != null) {
        String[] split = line.split(" ");
        VocabWord word = vocab.wordFor(decodeB64(split[0]));
        List<Integer> points = new ArrayList<>();
        for (int i = 1; i < split.length; i++) {
            points.add(Integer.parseInt(split[i]));
        }
        word.setPoints(points);
    }
    reader.close();
    // now we transform mappings into huffman tree codes
    reader = new BufferedReader(new FileReader(h_codes));
    while ((line = reader.readLine()) != null) {
        String[] split = line.split(" ");
        VocabWord word = vocab.wordFor(decodeB64(split[0]));
        List<Byte> codes = new ArrayList<>();
        for (int i = 1; i < split.length; i++) {
            codes.add(Byte.parseByte(split[i]));
        }
        word.setCodes(codes);
        word.setCodeLength((short) codes.size());
    }
    reader.close();
    Word2Vec.Builder builder = new Word2Vec.Builder(configuration).vocabCache(vocab).lookupTable(lookupTable).resetModel(false);
    TokenizerFactory factory = getTokenizerFactory(configuration);
    if (factory != null)
        builder.tokenizerFactory(factory);
    Word2Vec w2v = builder.build();
    return w2v;
}

Example 7 with VocabWord

use of org.deeplearning4j.models.word2vec.VocabWord in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method readWord2Vec.

/**
     * This method restores Word2Vec model previously saved with writeWord2VecModel
     *
     * PLEASE NOTE: This method loads FULL model, so don't use it if you're only going to use weights.
     *
     * @param file
     * @return
     * @throws IOException
     */
@Deprecated
public static Word2Vec readWord2Vec(File file) throws IOException {
    File tmpFileSyn0 = File.createTempFile("word2vec", "0");
    File tmpFileSyn1 = File.createTempFile("word2vec", "1");
    File tmpFileC = File.createTempFile("word2vec", "c");
    File tmpFileH = File.createTempFile("word2vec", "h");
    File tmpFileF = File.createTempFile("word2vec", "f");
    tmpFileSyn0.deleteOnExit();
    tmpFileSyn1.deleteOnExit();
    tmpFileH.deleteOnExit();
    tmpFileC.deleteOnExit();
    tmpFileF.deleteOnExit();
    int originalFreq = Nd4j.getMemoryManager().getOccasionalGcFrequency();
    boolean originalPeriodic = Nd4j.getMemoryManager().isPeriodicGcActive();
    if (originalPeriodic)
        Nd4j.getMemoryManager().togglePeriodicGc(false);
    Nd4j.getMemoryManager().setOccasionalGcFrequency(50000);
    try {
        ZipFile zipFile = new ZipFile(file);
        ZipEntry syn0 = zipFile.getEntry("syn0.txt");
        InputStream stream = zipFile.getInputStream(syn0);
        Files.copy(stream, Paths.get(tmpFileSyn0.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        ZipEntry syn1 = zipFile.getEntry("syn1.txt");
        stream = zipFile.getInputStream(syn1);
        Files.copy(stream, Paths.get(tmpFileSyn1.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        ZipEntry codes = zipFile.getEntry("codes.txt");
        stream = zipFile.getInputStream(codes);
        Files.copy(stream, Paths.get(tmpFileC.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        ZipEntry huffman = zipFile.getEntry("huffman.txt");
        stream = zipFile.getInputStream(huffman);
        Files.copy(stream, Paths.get(tmpFileH.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        ZipEntry config = zipFile.getEntry("config.json");
        stream = zipFile.getInputStream(config);
        StringBuilder builder = new StringBuilder();
        try (BufferedReader reader = new BufferedReader(new InputStreamReader(stream))) {
            String line;
            while ((line = reader.readLine()) != null) {
                builder.append(line);
            }
        }
        VectorsConfiguration configuration = VectorsConfiguration.fromJson(builder.toString().trim());
        // we read first 4 files as w2v model
        Word2Vec w2v = readWord2VecFromText(tmpFileSyn0, tmpFileSyn1, tmpFileC, tmpFileH, configuration);
        // we read frequencies from frequencies.txt, however it's possible that we might not have this file
        ZipEntry frequencies = zipFile.getEntry("frequencies.txt");
        if (frequencies != null) {
            stream = zipFile.getInputStream(frequencies);
            try (BufferedReader reader = new BufferedReader(new InputStreamReader(stream))) {
                String line;
                while ((line = reader.readLine()) != null) {
                    String[] split = line.split(" ");
                    VocabWord word = w2v.getVocab().tokenFor(decodeB64(split[0]));
                    word.setElementFrequency((long) Double.parseDouble(split[1]));
                    word.setSequencesCount((long) Double.parseDouble(split[2]));
                }
            }
        }
        ZipEntry zsyn1Neg = zipFile.getEntry("syn1Neg.txt");
        if (zsyn1Neg != null) {
            stream = zipFile.getInputStream(zsyn1Neg);
            try (InputStreamReader isr = new InputStreamReader(stream);
                BufferedReader reader = new BufferedReader(isr)) {
                String line = null;
                List<INDArray> rows = new ArrayList<>();
                while ((line = reader.readLine()) != null) {
                    String[] split = line.split(" ");
                    double[] array = new double[split.length];
                    for (int i = 0; i < split.length; i++) {
                        array[i] = Double.parseDouble(split[i]);
                    }
                    rows.add(Nd4j.create(array));
                }
                // it's possible to have full model without syn1Neg
                if (rows.size() > 0) {
                    INDArray syn1Neg = Nd4j.vstack(rows);
                    ((InMemoryLookupTable) w2v.getLookupTable()).setSyn1Neg(syn1Neg);
                }
            }
        }
        return w2v;
    } finally {
        if (originalPeriodic)
            Nd4j.getMemoryManager().togglePeriodicGc(true);
        Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
    }
}

Example 8 with VocabWord

use of org.deeplearning4j.models.word2vec.VocabWord in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method readWord2VecModel.

/**
     * This method
     * 1) Binary model, either compressed or not. Like well-known Google Model
     * 2) Popular CSV word2vec text format
     * 3) DL4j compressed format
     *
     * Please note: if extended data isn't available, only weights will be loaded instead.
     *
     * @param file
     * @param extendedModel if TRUE, we'll try to load HS states & Huffman tree info, if FALSE, only weights will be loaded
     * @return
     */
public static Word2Vec readWord2VecModel(@NonNull File file, boolean extendedModel) {
    InMemoryLookupTable<VocabWord> lookupTable = new InMemoryLookupTable<>();
    AbstractCache<VocabWord> vocabCache = new AbstractCache<>();
    Word2Vec vec;
    INDArray syn0 = null;
    VectorsConfiguration configuration = new VectorsConfiguration();
    if (!file.exists() || !file.isFile())
        throw new ND4JIllegalStateException("File [" + file.getAbsolutePath() + "] doesn't exist");
    int originalFreq = Nd4j.getMemoryManager().getOccasionalGcFrequency();
    boolean originalPeriodic = Nd4j.getMemoryManager().isPeriodicGcActive();
    if (originalPeriodic)
        Nd4j.getMemoryManager().togglePeriodicGc(false);
    Nd4j.getMemoryManager().setOccasionalGcFrequency(50000);
    // try to load zip format
    try {
        if (extendedModel) {
            log.debug("Trying full model restoration...");
            if (originalPeriodic)
                Nd4j.getMemoryManager().togglePeriodicGc(true);
            Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
            return readWord2Vec(file);
        } else {
            log.debug("Trying simplified model restoration...");
            File tmpFileSyn0 = File.createTempFile("word2vec", "syn");
            File tmpFileConfig = File.createTempFile("word2vec", "config");
            // we don't need full model, so we go directly to syn0 file
            ZipFile zipFile = new ZipFile(file);
            ZipEntry syn = zipFile.getEntry("syn0.txt");
            InputStream stream = zipFile.getInputStream(syn);
            Files.copy(stream, Paths.get(tmpFileSyn0.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
            // now we're restoring configuration saved earlier
            ZipEntry config = zipFile.getEntry("config.json");
            if (config != null) {
                stream = zipFile.getInputStream(config);
                StringBuilder builder = new StringBuilder();
                try (BufferedReader reader = new BufferedReader(new InputStreamReader(stream))) {
                    String line;
                    while ((line = reader.readLine()) != null) {
                        builder.append(line);
                    }
                }
                configuration = VectorsConfiguration.fromJson(builder.toString().trim());
            }
            ZipEntry ve = zipFile.getEntry("frequencies.txt");
            if (ve != null) {
                stream = zipFile.getInputStream(ve);
                AtomicInteger cnt = new AtomicInteger(0);
                try (BufferedReader reader = new BufferedReader(new InputStreamReader(stream))) {
                    String line;
                    while ((line = reader.readLine()) != null) {
                        String[] split = line.split(" ");
                        VocabWord word = new VocabWord(Double.valueOf(split[1]), decodeB64(split[0]));
                        word.setIndex(cnt.getAndIncrement());
                        word.incrementSequencesCount(Long.valueOf(split[2]));
                        vocabCache.addToken(word);
                        vocabCache.addWordToIndex(word.getIndex(), word.getLabel());
                        Nd4j.getMemoryManager().invokeGcOccasionally();
                    }
                }
            }
            List<INDArray> rows = new ArrayList<>();
            // basically read up everything, call vstacl and then return model
            try (Reader reader = new CSVReader(tmpFileSyn0)) {
                AtomicInteger cnt = new AtomicInteger(0);
                while (reader.hasNext()) {
                    Pair<VocabWord, float[]> pair = reader.next();
                    VocabWord word = pair.getFirst();
                    INDArray vector = Nd4j.create(pair.getSecond());
                    if (ve != null) {
                        if (syn0 == null)
                            syn0 = Nd4j.create(vocabCache.numWords(), vector.length());
                        syn0.getRow(cnt.getAndIncrement()).assign(vector);
                    } else {
                        rows.add(vector);
                        vocabCache.addToken(word);
                        vocabCache.addWordToIndex(word.getIndex(), word.getLabel());
                    }
                    Nd4j.getMemoryManager().invokeGcOccasionally();
                }
            } catch (Exception e) {
                throw new RuntimeException(e);
            } finally {
                if (originalPeriodic)
                    Nd4j.getMemoryManager().togglePeriodicGc(true);
                Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
            }
            if (syn0 == null && vocabCache.numWords() > 0)
                syn0 = Nd4j.vstack(rows);
            if (syn0 == null) {
                log.error("Can't build syn0 table");
                throw new DL4JInvalidInputException("Can't build syn0 table");
            }
            lookupTable = new InMemoryLookupTable.Builder<VocabWord>().cache(vocabCache).vectorLength(syn0.columns()).useHierarchicSoftmax(false).useAdaGrad(false).build();
            lookupTable.setSyn0(syn0);
            try {
                tmpFileSyn0.delete();
                tmpFileConfig.delete();
            } catch (Exception e) {
            //
            }
        }
    } catch (Exception e) {
        // let's try to load this file as csv file
        try {
            log.debug("Trying CSV model restoration...");
            Pair<InMemoryLookupTable, VocabCache> pair = loadTxt(file);
            lookupTable = pair.getFirst();
            vocabCache = (AbstractCache<VocabWord>) pair.getSecond();
        } catch (Exception ex) {
            // we fallback to trying binary model instead
            try {
                log.debug("Trying binary model restoration...");
                if (originalPeriodic)
                    Nd4j.getMemoryManager().togglePeriodicGc(true);
                Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
                vec = loadGoogleModel(file, true, true);
                return vec;
            } catch (Exception ey) {
                // try to load without linebreaks
                try {
                    if (originalPeriodic)
                        Nd4j.getMemoryManager().togglePeriodicGc(true);
                    Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
                    vec = loadGoogleModel(file, true, false);
                    return vec;
                } catch (Exception ez) {
                    throw new RuntimeException("Unable to guess input file format. Please use corresponding loader directly");
                }
            }
        }
    }
    Word2Vec.Builder builder = new Word2Vec.Builder(configuration).lookupTable(lookupTable).useAdaGrad(false).vocabCache(vocabCache).layerSize(lookupTable.layerSize()).useHierarchicSoftmax(false).resetModel(false);
    /*
            Trying to restore TokenizerFactory & TokenPreProcessor
         */
    TokenizerFactory factory = getTokenizerFactory(configuration);
    if (factory != null)
        builder.tokenizerFactory(factory);
    vec = builder.build();
    return vec;
}

Example 9 with VocabWord

use of org.deeplearning4j.models.word2vec.VocabWord in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method readParagraphVectors.

/**
     * This method restores ParagraphVectors model previously saved with writeParagraphVectors()
     *
     * @return
     */
public static ParagraphVectors readParagraphVectors(File file) throws IOException {
    File tmpFileL = File.createTempFile("paravec", "l");
    tmpFileL.deleteOnExit();
    Word2Vec w2v = readWord2Vec(file);
    // and "convert" it to ParaVec model + optionally trying to restore labels information
    ParagraphVectors vectors = new ParagraphVectors.Builder(w2v.getConfiguration()).vocabCache(w2v.getVocab()).lookupTable(w2v.getLookupTable()).resetModel(false).build();
    ZipFile zipFile = new ZipFile(file);
    // now we try to restore labels information
    ZipEntry labels = zipFile.getEntry("labels.txt");
    if (labels != null) {
        InputStream stream = zipFile.getInputStream(labels);
        Files.copy(stream, Paths.get(tmpFileL.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        try (BufferedReader reader = new BufferedReader(new FileReader(tmpFileL))) {
            String line;
            while ((line = reader.readLine()) != null) {
                VocabWord word = vectors.getVocab().tokenFor(decodeB64(line.trim()));
                if (word != null) {
                    word.markAsLabel(true);
                }
            }
        }
    }
    vectors.extractLabels();
    return vectors;
}

Example 10 with VocabWord

use of org.deeplearning4j.models.word2vec.VocabWord in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method loadStaticModel.

/**
     * This method restores previously saved w2v model. File can be in one of the following formats:
     * 1) Binary model, either compressed or not. Like well-known Google Model
     * 2) Popular CSV word2vec text format
     * 3) DL4j compressed format
     *
     * In return you get StaticWord2Vec model, which might be used as lookup table only in multi-gpu environment.
     *
     * @param file File should point to previously saved w2v model
     * @return
     */
// TODO: this method needs better name :)
public static WordVectors loadStaticModel(File file) {
    if (!file.exists() || file.isDirectory())
        throw new RuntimeException(new FileNotFoundException("File [" + file.getAbsolutePath() + "] was not found"));
    int originalFreq = Nd4j.getMemoryManager().getOccasionalGcFrequency();
    boolean originalPeriodic = Nd4j.getMemoryManager().isPeriodicGcActive();
    if (originalPeriodic)
        Nd4j.getMemoryManager().togglePeriodicGc(false);
    Nd4j.getMemoryManager().setOccasionalGcFrequency(50000);
    CompressedRamStorage<Integer> storage = new CompressedRamStorage.Builder<Integer>().useInplaceCompression(false).setCompressor(new NoOp()).emulateIsAbsent(false).build();
    VocabCache<VocabWord> vocabCache = new AbstractCache.Builder<VocabWord>().build();
    // if zip - that's dl4j format
    try {
        log.debug("Trying DL4j format...");
        File tmpFileSyn0 = File.createTempFile("word2vec", "syn");
        ZipFile zipFile = new ZipFile(file);
        ZipEntry syn0 = zipFile.getEntry("syn0.txt");
        InputStream stream = zipFile.getInputStream(syn0);
        Files.copy(stream, Paths.get(tmpFileSyn0.getAbsolutePath()), StandardCopyOption.REPLACE_EXISTING);
        storage.clear();
        try (Reader reader = new CSVReader(tmpFileSyn0)) {
            while (reader.hasNext()) {
                Pair<VocabWord, float[]> pair = reader.next();
                VocabWord word = pair.getFirst();
                storage.store(word.getIndex(), pair.getSecond());
                vocabCache.addToken(word);
                vocabCache.addWordToIndex(word.getIndex(), word.getLabel());
                Nd4j.getMemoryManager().invokeGcOccasionally();
            }
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            if (originalPeriodic)
                Nd4j.getMemoryManager().togglePeriodicGc(true);
            Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
        }
    } catch (Exception e) {
        //
        try {
            // try to load file as text csv
            vocabCache = new AbstractCache.Builder<VocabWord>().build();
            storage.clear();
            log.debug("Trying CSVReader...");
            try (Reader reader = new CSVReader(file)) {
                while (reader.hasNext()) {
                    Pair<VocabWord, float[]> pair = reader.next();
                    VocabWord word = pair.getFirst();
                    storage.store(word.getIndex(), pair.getSecond());
                    vocabCache.addToken(word);
                    vocabCache.addWordToIndex(word.getIndex(), word.getLabel());
                    Nd4j.getMemoryManager().invokeGcOccasionally();
                }
            } catch (Exception ef) {
                // we throw away this exception, and trying to load data as binary model
                throw new RuntimeException(ef);
            } finally {
                if (originalPeriodic)
                    Nd4j.getMemoryManager().togglePeriodicGc(true);
                Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
            }
        } catch (Exception ex) {
            // otherwise it's probably google model. which might be compressed or not
            log.debug("Trying BinaryReader...");
            vocabCache = new AbstractCache.Builder<VocabWord>().build();
            storage.clear();
            try (Reader reader = new BinaryReader(file)) {
                while (reader.hasNext()) {
                    Pair<VocabWord, float[]> pair = reader.next();
                    VocabWord word = pair.getFirst();
                    storage.store(word.getIndex(), pair.getSecond());
                    vocabCache.addToken(word);
                    vocabCache.addWordToIndex(word.getIndex(), word.getLabel());
                    Nd4j.getMemoryManager().invokeGcOccasionally();
                }
            } catch (Exception ez) {
                throw new RuntimeException("Unable to guess input file format");
            } finally {
                if (originalPeriodic)
                    Nd4j.getMemoryManager().togglePeriodicGc(true);
                Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
            }
        } finally {
            if (originalPeriodic)
                Nd4j.getMemoryManager().togglePeriodicGc(true);
            Nd4j.getMemoryManager().setOccasionalGcFrequency(originalFreq);
        }
    }
    StaticWord2Vec word2Vec = new StaticWord2Vec.Builder(storage, vocabCache).build();
    return word2Vec;
}