Examples with BasicLineIterator org.deeplearning4j.text.sentenceiterator.BasicLineIterator used on opensource projects

Example 1 with BasicLineIterator

use of org.deeplearning4j.text.sentenceiterator.BasicLineIterator in project deeplearning4j by deeplearning4j.

the class WordVectorSerializer method loadFullModel.

/**
     * This method loads full w2v model, previously saved with writeFullMethod call
     *
     * Deprecation note: Please, consider using readWord2VecModel() or loadStaticModel() method instead
     *
     * @param path - path to previously stored w2v json model
     * @return - Word2Vec instance
     */
@Deprecated
public static Word2Vec loadFullModel(@NonNull String path) throws FileNotFoundException {
    /*
            // TODO: implementation is in process
            We need to restore:
                     1. WeightLookupTable, including syn0 and syn1 matrices
                     2. VocabCache + mark it as SPECIAL, to avoid accidental word removals
         */
    BasicLineIterator iterator = new BasicLineIterator(new File(path));
    // first 3 lines should be processed separately
    String confJson = iterator.nextSentence();
    log.info("Word2Vec conf. JSON: " + confJson);
    VectorsConfiguration configuration = VectorsConfiguration.fromJson(confJson);
    // actually we dont need expTable, since it produces exact results on subsequent runs untill you dont modify expTable size :)
    String eTable = iterator.nextSentence();
    double[] expTable;
    String nTable = iterator.nextSentence();
    if (configuration.getNegative() > 0) {
    // TODO: we probably should parse negTable, but it's not required until vocab changes are introduced. Since on the predefined vocab it will produce exact nTable, the same goes for expTable btw.
    }
    /*
                Since we're restoring vocab from previously serialized model, we can expect minWordFrequency appliance in its vocabulary, so it should NOT be truncated.
                That's why i'm setting minWordFrequency to configuration value, but applying SPECIAL to each word, to avoid truncation
         */
    VocabularyHolder holder = new VocabularyHolder.Builder().minWordFrequency(configuration.getMinWordFrequency()).hugeModelExpected(configuration.isHugeModelExpected()).scavengerActivationThreshold(configuration.getScavengerActivationThreshold()).scavengerRetentionDelay(configuration.getScavengerRetentionDelay()).build();
    AtomicInteger counter = new AtomicInteger(0);
    AbstractCache<VocabWord> vocabCache = new AbstractCache.Builder<VocabWord>().build();
    while (iterator.hasNext()) {
        //    log.info("got line: " + iterator.nextSentence());
        String wordJson = iterator.nextSentence();
        VocabularyWord word = VocabularyWord.fromJson(wordJson);
        word.setSpecial(true);
        VocabWord vw = new VocabWord(word.getCount(), word.getWord());
        vw.setIndex(counter.getAndIncrement());
        vw.setIndex(word.getHuffmanNode().getIdx());
        vw.setCodeLength(word.getHuffmanNode().getLength());
        vw.setPoints(arrayToList(word.getHuffmanNode().getPoint(), word.getHuffmanNode().getLength()));
        vw.setCodes(arrayToList(word.getHuffmanNode().getCode(), word.getHuffmanNode().getLength()));
        vocabCache.addToken(vw);
        vocabCache.addWordToIndex(vw.getIndex(), vw.getLabel());
        vocabCache.putVocabWord(vw.getWord());
    }
    // at this moment vocab is restored, and it's time to rebuild Huffman tree
    // since word counters are equal, huffman tree will be equal too
    //holder.updateHuffmanCodes();
    // we definitely don't need UNK word in this scenarion
    //        holder.transferBackToVocabCache(vocabCache, false);
    // now, it's time to transfer syn0/syn1/syn1 neg values
    InMemoryLookupTable lookupTable = (InMemoryLookupTable) new InMemoryLookupTable.Builder().negative(configuration.getNegative()).useAdaGrad(configuration.isUseAdaGrad()).lr(configuration.getLearningRate()).cache(vocabCache).vectorLength(configuration.getLayersSize()).build();
    // we create all arrays
    lookupTable.resetWeights(true);
    iterator.reset();
    // we should skip 3 lines from file
    iterator.nextSentence();
    iterator.nextSentence();
    iterator.nextSentence();
    // now, for each word from vocabHolder we'll just transfer actual values
    while (iterator.hasNext()) {
        String wordJson = iterator.nextSentence();
        VocabularyWord word = VocabularyWord.fromJson(wordJson);
        // syn0 transfer
        INDArray syn0 = lookupTable.getSyn0().getRow(vocabCache.indexOf(word.getWord()));
        syn0.assign(Nd4j.create(word.getSyn0()));
        // syn1 transfer
        // syn1 values are being accessed via tree points, but since our goal is just deserialization - we can just push it row by row
        INDArray syn1 = lookupTable.getSyn1().getRow(vocabCache.indexOf(word.getWord()));
        syn1.assign(Nd4j.create(word.getSyn1()));
        // syn1Neg transfer
        if (configuration.getNegative() > 0) {
            INDArray syn1Neg = lookupTable.getSyn1Neg().getRow(vocabCache.indexOf(word.getWord()));
            syn1Neg.assign(Nd4j.create(word.getSyn1Neg()));
        }
    }
    Word2Vec vec = new Word2Vec.Builder(configuration).vocabCache(vocabCache).lookupTable(lookupTable).resetModel(false).build();
    vec.setModelUtils(new BasicModelUtils());
    return vec;
}

Example 2 with BasicLineIterator

use of org.deeplearning4j.text.sentenceiterator.BasicLineIterator in project deeplearning4j by deeplearning4j.

the class Word2VecTests method testWord2VecCBOW.

@Test
public void testWord2VecCBOW() throws Exception {
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).iterations(5).learningRate(0.025).layerSize(150).seed(42).sampling(0).negativeSample(0).useHierarchicSoftmax(true).windowSize(5).modelUtils(new BasicModelUtils<VocabWord>()).useAdaGrad(false).iterate(iter).workers(8).tokenizerFactory(t).elementsLearningAlgorithm(new CBOW<VocabWord>()).build();
    vec.fit();
    Collection<String> lst = vec.wordsNearest("day", 10);
    log.info(Arrays.toString(lst.toArray()));
    //   assertEquals(10, lst.size());
    double sim = vec.similarity("day", "night");
    log.info("Day/night similarity: " + sim);
    assertTrue(lst.contains("week"));
    assertTrue(lst.contains("night"));
    assertTrue(lst.contains("year"));
    assertTrue(sim > 0.65f);
}

Example 3 with BasicLineIterator

use of org.deeplearning4j.text.sentenceiterator.BasicLineIterator in project deeplearning4j by deeplearning4j.

the class Word2VecTests method testW2VnegativeOnRestore.

@Test
public void testW2VnegativeOnRestore() throws Exception {
    // Strip white space before and after for each line
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).iterations(3).batchSize(64).layerSize(100).stopWords(new ArrayList<String>()).seed(42).learningRate(0.025).minLearningRate(0.001).sampling(0).elementsLearningAlgorithm(new SkipGram<VocabWord>()).negativeSample(10).epochs(1).windowSize(5).useHierarchicSoftmax(false).allowParallelTokenization(true).modelUtils(new FlatModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();
    assertEquals(false, vec.getConfiguration().isUseHierarchicSoftmax());
    log.info("Fit 1");
    vec.fit();
    File tmpFile = File.createTempFile("temp", "file");
    tmpFile.deleteOnExit();
    WordVectorSerializer.writeWord2VecModel(vec, tmpFile);
    iter.reset();
    Word2Vec restoredVec = WordVectorSerializer.readWord2VecModel(tmpFile, true);
    restoredVec.setTokenizerFactory(t);
    restoredVec.setSentenceIterator(iter);
    assertEquals(false, restoredVec.getConfiguration().isUseHierarchicSoftmax());
    assertTrue(restoredVec.getModelUtils() instanceof FlatModelUtils);
    assertTrue(restoredVec.getConfiguration().isAllowParallelTokenization());
    log.info("Fit 2");
    restoredVec.fit();
    iter.reset();
    restoredVec = WordVectorSerializer.readWord2VecModel(tmpFile, false);
    restoredVec.setTokenizerFactory(t);
    restoredVec.setSentenceIterator(iter);
    assertEquals(false, restoredVec.getConfiguration().isUseHierarchicSoftmax());
    assertTrue(restoredVec.getModelUtils() instanceof BasicModelUtils);
    log.info("Fit 3");
    restoredVec.fit();
}

Example 4 with BasicLineIterator

use of org.deeplearning4j.text.sentenceiterator.BasicLineIterator in project deeplearning4j by deeplearning4j.

the class Word2VecTests method testUnknown1.

@Test
public void testUnknown1() throws Exception {
    // Strip white space before and after for each line
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(10).useUnknown(true).unknownElement(new VocabWord(1.0, "PEWPEW")).iterations(1).layerSize(100).stopWords(new ArrayList<String>()).seed(42).learningRate(0.025).minLearningRate(0.001).sampling(0).elementsLearningAlgorithm(new CBOW<VocabWord>()).epochs(1).windowSize(5).useHierarchicSoftmax(true).allowParallelTokenization(true).modelUtils(new FlatModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();
    vec.fit();
    assertTrue(vec.hasWord("PEWPEW"));
    assertTrue(vec.getVocab().containsWord("PEWPEW"));
    INDArray unk = vec.getWordVectorMatrix("PEWPEW");
    assertNotEquals(null, unk);
    File tempFile = File.createTempFile("temp", "file");
    tempFile.deleteOnExit();
    WordVectorSerializer.writeWord2VecModel(vec, tempFile);
    log.info("Original configuration: {}", vec.getConfiguration());
    Word2Vec restored = WordVectorSerializer.readWord2VecModel(tempFile);
    assertTrue(restored.hasWord("PEWPEW"));
    assertTrue(restored.getVocab().containsWord("PEWPEW"));
    INDArray unk_restored = restored.getWordVectorMatrix("PEWPEW");
    assertEquals(unk, unk_restored);
    // now we're getting some junk word
    INDArray random = vec.getWordVectorMatrix("hhsd7d7sdnnmxc_SDsda");
    INDArray randomRestored = restored.getWordVectorMatrix("hhsd7d7sdnnmxc_SDsda");
    log.info("Restored configuration: {}", restored.getConfiguration());
    assertEquals(unk, random);
    assertEquals(unk, randomRestored);
}

Example 5 with BasicLineIterator

use of org.deeplearning4j.text.sentenceiterator.BasicLineIterator in project deeplearning4j by deeplearning4j.

the class PerformanceTests method testWord2VecCBOWBig.

@Ignore
@Test
public void testWord2VecCBOWBig() throws Exception {
    SentenceIterator iter = new BasicLineIterator("/home/raver119/Downloads/corpus/namuwiki_raw.txt");
    //iter = new BasicLineIterator("/home/raver119/Downloads/corpus/ru_sentences.txt");
    //SentenceIterator iter = new BasicLineIterator("/ext/DATASETS/ru/Socials/ru_sentences.txt");
    TokenizerFactory t = new KoreanTokenizerFactory();
    //t = new DefaultTokenizerFactory();
    //t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).iterations(5).learningRate(0.025).layerSize(150).seed(42).sampling(0).negativeSample(0).useHierarchicSoftmax(true).windowSize(5).modelUtils(new BasicModelUtils<VocabWord>()).useAdaGrad(false).iterate(iter).workers(8).allowParallelTokenization(true).tokenizerFactory(t).elementsLearningAlgorithm(new CBOW<VocabWord>()).build();
    long time1 = System.currentTimeMillis();
    vec.fit();
    long time2 = System.currentTimeMillis();
    log.info("Total execution time: {}", (time2 - time1));
}