Examples with DefaultTokenizerFactory org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory used on opensource projects

Example 1 with DefaultTokenizerFactory

use of org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory in project deeplearning4j by deeplearning4j.

the class ParagraphVectorsTest method testParagraphVectorsDM.

@Test
public void testParagraphVectorsDM() throws Exception {
    ClassPathResource resource = new ClassPathResource("/big/raw_sentences.txt");
    File file = resource.getFile();
    SentenceIterator iter = new BasicLineIterator(file);
    AbstractCache<VocabWord> cache = new AbstractCache.Builder<VocabWord>().build();
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    LabelsSource source = new LabelsSource("DOC_");
    ParagraphVectors vec = new ParagraphVectors.Builder().minWordFrequency(1).iterations(2).seed(119).epochs(3).layerSize(100).learningRate(0.025).labelsSource(source).windowSize(5).iterate(iter).trainWordVectors(true).vocabCache(cache).tokenizerFactory(t).negativeSample(0).useHierarchicSoftmax(true).sampling(0).workers(1).usePreciseWeightInit(true).sequenceLearningAlgorithm(new DM<VocabWord>()).build();
    vec.fit();
    int cnt1 = cache.wordFrequency("day");
    int cnt2 = cache.wordFrequency("me");
    assertNotEquals(1, cnt1);
    assertNotEquals(1, cnt2);
    assertNotEquals(cnt1, cnt2);
    double simDN = vec.similarity("day", "night");
    log.info("day/night similariry: {}", simDN);
    double similarity1 = vec.similarity("DOC_9835", "DOC_12492");
    log.info("9835/12492 similarity: " + similarity1);
    //        assertTrue(similarity1 > 0.2d);
    double similarity2 = vec.similarity("DOC_3720", "DOC_16392");
    log.info("3720/16392 similarity: " + similarity2);
    //      assertTrue(similarity2 > 0.2d);
    double similarity3 = vec.similarity("DOC_6347", "DOC_3720");
    log.info("6347/3720 similarity: " + similarity3);
    //        assertTrue(similarity3 > 0.6d);
    double similarityX = vec.similarity("DOC_3720", "DOC_9852");
    log.info("3720/9852 similarity: " + similarityX);
    assertTrue(similarityX < 0.5d);
    // testing DM inference now
    INDArray original = vec.getWordVectorMatrix("DOC_16392").dup();
    INDArray inferredA1 = vec.inferVector("This is my work");
    INDArray inferredB1 = vec.inferVector("This is my work .");
    double cosAO1 = Transforms.cosineSim(inferredA1.dup(), original.dup());
    double cosAB1 = Transforms.cosineSim(inferredA1.dup(), inferredB1.dup());
    log.info("Cos O/A: {}", cosAO1);
    log.info("Cos A/B: {}", cosAB1);
}

Example 2 with DefaultTokenizerFactory

use of org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory in project deeplearning4j by deeplearning4j.

the class ParagraphVectorsTest method testGoogleModelForInference.

@Ignore
@Test
public void testGoogleModelForInference() throws Exception {
    WordVectors googleVectors = WordVectorSerializer.loadGoogleModelNonNormalized(new File("/ext/GoogleNews-vectors-negative300.bin.gz"), true, false);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    ParagraphVectors pv = new ParagraphVectors.Builder().tokenizerFactory(t).iterations(10).useHierarchicSoftmax(false).trainWordVectors(false).iterations(10).useExistingWordVectors(googleVectors).negativeSample(10).sequenceLearningAlgorithm(new DM<VocabWord>()).build();
    INDArray vec1 = pv.inferVector("This text is pretty awesome");
    INDArray vec2 = pv.inferVector("Fantastic process of crazy things happening inside just for history purposes");
    log.info("vec1/vec2: {}", Transforms.cosineSim(vec1, vec2));
}

Example 3 with DefaultTokenizerFactory

use of org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory in project deeplearning4j by deeplearning4j.

the class ParagraphVectorsTest method testParagraphVectorsWithWordVectorsModelling1.

@Test
public void testParagraphVectorsWithWordVectorsModelling1() throws Exception {
    ClassPathResource resource = new ClassPathResource("/big/raw_sentences.txt");
    File file = resource.getFile();
    SentenceIterator iter = new BasicLineIterator(file);
    //        InMemoryLookupCache cache = new InMemoryLookupCache(false);
    AbstractCache<VocabWord> cache = new AbstractCache.Builder<VocabWord>().build();
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    LabelsSource source = new LabelsSource("DOC_");
    ParagraphVectors vec = new ParagraphVectors.Builder().minWordFrequency(1).iterations(3).epochs(1).layerSize(100).learningRate(0.025).labelsSource(source).windowSize(5).iterate(iter).trainWordVectors(true).vocabCache(cache).tokenizerFactory(t).sampling(0).build();
    vec.fit();
    int cnt1 = cache.wordFrequency("day");
    int cnt2 = cache.wordFrequency("me");
    assertNotEquals(1, cnt1);
    assertNotEquals(1, cnt2);
    assertNotEquals(cnt1, cnt2);
    /*
            We have few lines that contain pretty close words invloved.
            These sentences should be pretty close to each other in vector space
         */
    // line 3721: This is my way .
    // line 6348: This is my case .
    // line 9836: This is my house .
    // line 12493: This is my world .
    // line 16393: This is my work .
    // this is special sentence, that has nothing common with previous sentences
    // line 9853: We now have one .
    assertTrue(vec.hasWord("DOC_3720"));
    double similarityD = vec.similarity("day", "night");
    log.info("day/night similarity: " + similarityD);
    double similarityW = vec.similarity("way", "work");
    log.info("way/work similarity: " + similarityW);
    double similarityH = vec.similarity("house", "world");
    log.info("house/world similarity: " + similarityH);
    double similarityC = vec.similarity("case", "way");
    log.info("case/way similarity: " + similarityC);
    double similarity1 = vec.similarity("DOC_9835", "DOC_12492");
    log.info("9835/12492 similarity: " + similarity1);
    //        assertTrue(similarity1 > 0.7d);
    double similarity2 = vec.similarity("DOC_3720", "DOC_16392");
    log.info("3720/16392 similarity: " + similarity2);
    //        assertTrue(similarity2 > 0.7d);
    double similarity3 = vec.similarity("DOC_6347", "DOC_3720");
    log.info("6347/3720 similarity: " + similarity3);
    //        assertTrue(similarity2 > 0.7d);
    // likelihood in this case should be significantly lower
    // however, since corpus is small, and weight initialization is random-based, sometimes this test CAN fail
    double similarityX = vec.similarity("DOC_3720", "DOC_9852");
    log.info("3720/9852 similarity: " + similarityX);
    assertTrue(similarityX < 0.5d);
    double sim119 = vec.similarityToLabel("This is my case .", "DOC_6347");
    double sim120 = vec.similarityToLabel("This is my case .", "DOC_3720");
    log.info("1/2: " + sim119 + "/" + sim120);
//assertEquals(similarity3, sim119, 0.001);
}

Example 4 with DefaultTokenizerFactory

use of org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory in project deeplearning4j by deeplearning4j.

the class ParagraphVectorsTest method testParagraphVectorsReducedLabels1.

/**
     * This test is not indicative.
     * there's no need in this test within travis, use it manually only for problems detection
     *
     * @throws Exception
     */
@Test
@Ignore
public void testParagraphVectorsReducedLabels1() throws Exception {
    ClassPathResource resource = new ClassPathResource("/labeled");
    File file = resource.getFile();
    LabelAwareIterator iter = new FileLabelAwareIterator.Builder().addSourceFolder(file).build();
    TokenizerFactory t = new DefaultTokenizerFactory();
    /**
         * Please note: text corpus is REALLY small, and some kind of "results" could be received with HIGH epochs number, like 30.
         * But there's no reason to keep at that high
         */
    ParagraphVectors vec = new ParagraphVectors.Builder().minWordFrequency(1).epochs(3).layerSize(100).stopWords(new ArrayList<String>()).windowSize(5).iterate(iter).tokenizerFactory(t).build();
    vec.fit();
    //WordVectorSerializer.writeWordVectors(vec, "vectors.txt");
    INDArray w1 = vec.lookupTable().vector("I");
    INDArray w2 = vec.lookupTable().vector("am");
    INDArray w3 = vec.lookupTable().vector("sad.");
    INDArray words = Nd4j.create(3, vec.lookupTable().layerSize());
    words.putRow(0, w1);
    words.putRow(1, w2);
    words.putRow(2, w3);
    INDArray mean = words.isMatrix() ? words.mean(0) : words;
    log.info("Mean" + Arrays.toString(mean.dup().data().asDouble()));
    log.info("Array" + Arrays.toString(vec.lookupTable().vector("negative").dup().data().asDouble()));
    double simN = Transforms.cosineSim(mean, vec.lookupTable().vector("negative"));
    log.info("Similarity negative: " + simN);
    double simP = Transforms.cosineSim(mean, vec.lookupTable().vector("neutral"));
    log.info("Similarity neutral: " + simP);
    double simV = Transforms.cosineSim(mean, vec.lookupTable().vector("positive"));
    log.info("Similarity positive: " + simV);
}

Example 5 with DefaultTokenizerFactory

use of org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory in project deeplearning4j by deeplearning4j.

the class SequenceVectorsTest method testInternalVocabConstruction.

@Test
public void testInternalVocabConstruction() throws Exception {
    ClassPathResource resource = new ClassPathResource("big/raw_sentences.txt");
    File file = resource.getFile();
    BasicLineIterator underlyingIterator = new BasicLineIterator(file);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    SentenceTransformer transformer = new SentenceTransformer.Builder().iterator(underlyingIterator).tokenizerFactory(t).build();
    AbstractSequenceIterator<VocabWord> sequenceIterator = new AbstractSequenceIterator.Builder<>(transformer).build();
    SequenceVectors<VocabWord> vectors = new SequenceVectors.Builder<VocabWord>(new VectorsConfiguration()).minWordFrequency(5).iterate(sequenceIterator).batchSize(250).iterations(1).epochs(1).resetModel(false).trainElementsRepresentation(true).build();
    logger.info("Fitting model...");
    vectors.fit();
    logger.info("Model ready...");
    double sim = vectors.similarity("day", "night");
    logger.info("Day/night similarity: " + sim);
    assertTrue(sim > 0.6d);
    Collection<String> labels = vectors.wordsNearest("day", 10);
    logger.info("Nearest labels to 'day': " + labels);
}