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

Example 31 with SentenceIterator

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

the class ParallelTransformerIteratorTest method hasNext.

@Test
public void hasNext() throws Exception {
    SentenceIterator iterator = new BasicLineIterator(new ClassPathResource("/big/raw_sentences.txt").getFile());
    SentenceTransformer transformer = new SentenceTransformer.Builder().iterator(iterator).allowMultithreading(true).tokenizerFactory(factory).build();
    Iterator<Sequence<VocabWord>> iter = transformer.iterator();
    int cnt = 0;
    Sequence<VocabWord> sequence = null;
    while (iter.hasNext()) {
        sequence = iter.next();
        assertNotEquals("Failed on [" + cnt + "] iteration", null, sequence);
        assertNotEquals("Failed on [" + cnt + "] iteration", 0, sequence.size());
        cnt++;
    }
    //   log.info("Last element: {}", sequence.asLabels());
    assertEquals(97162, cnt);
}

Example 32 with SentenceIterator

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

the class Word2VecDataSetIteratorTest method testIterator1.

/**
     * Basically all we want from this test - being able to finish without exceptions.
     */
@Test
public void testIterator1() throws Exception {
    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec vec = // we make sure we'll have some missing words
    new Word2Vec.Builder().minWordFrequency(10).iterations(1).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();
    List<String> labels = new ArrayList<>();
    labels.add("positive");
    labels.add("negative");
    Word2VecDataSetIterator iterator = new Word2VecDataSetIterator(vec, getLASI(iter, labels), labels, 1);
    INDArray array = iterator.next().getFeatures();
    while (iterator.hasNext()) {
        DataSet ds = iterator.next();
        assertArrayEquals(array.shape(), ds.getFeatureMatrix().shape());
    }
}

Example 33 with SentenceIterator

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

the class BasicLabelAwareIteratorTest method testHasNextDocument1.

@Test
public void testHasNextDocument1() throws Exception {
    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    BasicLabelAwareIterator iterator = new BasicLabelAwareIterator.Builder(iter).setLabelTemplate("DOCZ_").build();
    int cnt = 0;
    while (iterator.hasNextDocument()) {
        iterator.nextDocument();
        cnt++;
    }
    assertEquals(97162, cnt);
    LabelsSource generator = iterator.getLabelsSource();
    assertEquals(97162, generator.getLabels().size());
    assertEquals("DOCZ_0", generator.getLabels().get(0));
}