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

Example 21 with BasicLineIterator

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

the class GloveTest method testGloVe1.

@Ignore
@Test
public void testGloVe1() throws Exception {
    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Glove glove = new Glove.Builder().iterate(iter).tokenizerFactory(t).alpha(0.75).learningRate(0.1).epochs(45).xMax(100).shuffle(true).symmetric(true).build();
    glove.fit();
    double simD = glove.similarity("day", "night");
    double simP = glove.similarity("best", "police");
    log.info("Day/night similarity: " + simD);
    log.info("Best/police similarity: " + simP);
    Collection<String> words = glove.wordsNearest("day", 10);
    log.info("Nearest words to 'day': " + words);
    assertTrue(simD > 0.7);
    // actually simP should be somewhere at 0
    assertTrue(simP < 0.5);
    assertTrue(words.contains("night"));
    assertTrue(words.contains("year"));
    assertTrue(words.contains("week"));
    File tempFile = File.createTempFile("glove", "temp");
    tempFile.deleteOnExit();
    INDArray day1 = glove.getWordVectorMatrix("day").dup();
    WordVectorSerializer.writeWordVectors(glove, tempFile);
    WordVectors vectors = WordVectorSerializer.loadTxtVectors(tempFile);
    INDArray day2 = vectors.getWordVectorMatrix("day").dup();
    assertEquals(day1, day2);
    tempFile.delete();
}

Example 22 with BasicLineIterator

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

the class ParagraphVectorsTest method testDirectInference.

@Test
public void testDirectInference() throws Exception {
    ClassPathResource resource_sentences = new ClassPathResource("/big/raw_sentences.txt");
    ClassPathResource resource_mixed = new ClassPathResource("/paravec");
    SentenceIterator iter = new AggregatingSentenceIterator.Builder().addSentenceIterator(new BasicLineIterator(resource_sentences.getFile())).addSentenceIterator(new FileSentenceIterator(resource_mixed.getFile())).build();
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    Word2Vec wordVectors = new Word2Vec.Builder().minWordFrequency(1).batchSize(250).iterations(1).epochs(3).learningRate(0.025).layerSize(150).minLearningRate(0.001).elementsLearningAlgorithm(new SkipGram<VocabWord>()).useHierarchicSoftmax(true).windowSize(5).iterate(iter).tokenizerFactory(t).build();
    wordVectors.fit();
    ParagraphVectors pv = new ParagraphVectors.Builder().tokenizerFactory(t).iterations(10).useHierarchicSoftmax(true).trainWordVectors(true).useExistingWordVectors(wordVectors).negativeSample(0).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 23 with BasicLineIterator

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

the class ParagraphVectorsTest method testParagraphVectorsDBOW.

@Test
public void testParagraphVectorsDBOW() 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(5).seed(119).epochs(1).layerSize(100).learningRate(0.025).labelsSource(source).windowSize(5).iterate(iter).trainWordVectors(true).vocabCache(cache).tokenizerFactory(t).negativeSample(0).allowParallelTokenization(true).useHierarchicSoftmax(true).sampling(0).workers(2).usePreciseWeightInit(true).sequenceLearningAlgorithm(new DBOW<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 .");
    INDArray inferredC1 = vec.inferVector("This is my day");
    INDArray inferredD1 = vec.inferVector("This is my night");
    log.info("A: {}", Arrays.toString(inferredA1.data().asFloat()));
    log.info("C: {}", Arrays.toString(inferredC1.data().asFloat()));
    assertNotEquals(inferredA1, inferredC1);
    double cosAO1 = Transforms.cosineSim(inferredA1.dup(), original.dup());
    double cosAB1 = Transforms.cosineSim(inferredA1.dup(), inferredB1.dup());
    double cosAC1 = Transforms.cosineSim(inferredA1.dup(), inferredC1.dup());
    double cosCD1 = Transforms.cosineSim(inferredD1.dup(), inferredC1.dup());
    log.info("Cos O/A: {}", cosAO1);
    log.info("Cos A/B: {}", cosAB1);
    log.info("Cos A/C: {}", cosAC1);
    log.info("Cos C/D: {}", cosCD1);
}

Example 24 with BasicLineIterator

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

the class ParagraphVectorsTest method testParagraphVectorsVocabBuilding1.

/*
    @Test
    public void testWord2VecRunThroughVectors() throws Exception {
        ClassPathResource resource = new ClassPathResource("/big/raw_sentences.txt");
        File file = resource.getFile().getParentFile();
        LabelAwareSentenceIterator iter = LabelAwareUimaSentenceIterator.createWithPath(file.getAbsolutePath());
    
    
        TokenizerFactory t = new UimaTokenizerFactory();
    
    
        ParagraphVectors vec = new ParagraphVectors.Builder()
                .minWordFrequency(1).iterations(5).labels(Arrays.asList("label1", "deeple"))
                .layerSize(100)
                .stopWords(new ArrayList<String>())
                .windowSize(5).iterate(iter).tokenizerFactory(t).build();
    
        assertEquals(new ArrayList<String>(), vec.getStopWords());
    
    
        vec.fit();
        double sim = vec.similarity("day","night");
        log.info("day/night similarity: " + sim);
        new File("cache.ser").delete();
    
    }
    */
/**
     * This test checks, how vocab is built using SentenceIterator provided, without labels.
     *
     * @throws Exception
     */
@Test
public void testParagraphVectorsVocabBuilding1() throws Exception {
    ClassPathResource resource = new ClassPathResource("/big/raw_sentences.txt");
    //.getParentFile();
    File file = resource.getFile();
    //UimaSentenceIterator.createWithPath(file.getAbsolutePath());
    SentenceIterator iter = new BasicLineIterator(file);
    int numberOfLines = 0;
    while (iter.hasNext()) {
        iter.nextSentence();
        numberOfLines++;
    }
    iter.reset();
    InMemoryLookupCache cache = new InMemoryLookupCache(false);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    // LabelsSource source = new LabelsSource("DOC_");
    ParagraphVectors vec = new ParagraphVectors.Builder().minWordFrequency(1).iterations(5).layerSize(100).windowSize(5).iterate(iter).vocabCache(cache).tokenizerFactory(t).build();
    vec.buildVocab();
    LabelsSource source = vec.getLabelsSource();
    //VocabCache cache = vec.getVocab();
    log.info("Number of lines in corpus: " + numberOfLines);
    assertEquals(numberOfLines, source.getLabels().size());
    assertEquals(97162, source.getLabels().size());
    assertNotEquals(null, cache);
    assertEquals(97406, cache.numWords());
    // proper number of words for minWordsFrequency = 1 is 244
    assertEquals(244, cache.numWords() - source.getLabels().size());
}

Example 25 with BasicLineIterator

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

the class ParagraphVectorsTest method testParagraphVectorsModelling1.

/**
     * This test doesn't really cares about actual results. We only care about equality between live model & restored models
     *
     * @throws Exception
     */
@Test
public void testParagraphVectorsModelling1() throws Exception {
    ClassPathResource resource = new ClassPathResource("/big/raw_sentences.txt");
    File file = resource.getFile();
    SentenceIterator iter = new BasicLineIterator(file);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    LabelsSource source = new LabelsSource("DOC_");
    ParagraphVectors vec = new ParagraphVectors.Builder().minWordFrequency(1).iterations(5).seed(119).epochs(1).layerSize(150).learningRate(0.025).labelsSource(source).windowSize(5).sequenceLearningAlgorithm(new DM<VocabWord>()).iterate(iter).trainWordVectors(true).tokenizerFactory(t).workers(4).sampling(0).build();
    vec.fit();
    VocabCache<VocabWord> cache = vec.getVocab();
    File fullFile = File.createTempFile("paravec", "tests");
    fullFile.deleteOnExit();
    INDArray originalSyn1_17 = ((InMemoryLookupTable) vec.getLookupTable()).getSyn1().getRow(17).dup();
    WordVectorSerializer.writeParagraphVectors(vec, fullFile);
    int cnt1 = cache.wordFrequency("day");
    int cnt2 = cache.wordFrequency("me");
    assertNotEquals(1, cnt1);
    assertNotEquals(1, cnt2);
    assertNotEquals(cnt1, cnt2);
    assertEquals(97406, cache.numWords());
    assertTrue(vec.hasWord("DOC_16392"));
    assertTrue(vec.hasWord("DOC_3720"));
    List<String> result = new ArrayList<>(vec.nearestLabels(vec.getWordVectorMatrix("DOC_16392"), 10));
    System.out.println("nearest labels: " + result);
    for (String label : result) {
        System.out.println(label + "/DOC_16392: " + vec.similarity(label, "DOC_16392"));
    }
    assertTrue(result.contains("DOC_16392"));
    //assertTrue(result.contains("DOC_21383"));
    /*
            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 .
    double similarityD = vec.similarity("day", "night");
    log.info("day/night similarity: " + similarityD);
    if (similarityD < 0.0) {
        log.info("Day: " + Arrays.toString(vec.getWordVectorMatrix("day").dup().data().asDouble()));
        log.info("Night: " + Arrays.toString(vec.getWordVectorMatrix("night").dup().data().asDouble()));
    }
    List<String> labelsOriginal = vec.labelsSource.getLabels();
    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
    double similarityX = vec.similarity("DOC_3720", "DOC_9852");
    log.info("3720/9852 similarity: " + similarityX);
    assertTrue(similarityX < 0.5d);
    File tempFile = File.createTempFile("paravec", "ser");
    tempFile.deleteOnExit();
    INDArray day = vec.getWordVectorMatrix("day").dup();
    /*
            Testing txt serialization
         */
    File tempFile2 = File.createTempFile("paravec", "ser");
    tempFile2.deleteOnExit();
    WordVectorSerializer.writeWordVectors(vec, tempFile2);
    ParagraphVectors vec3 = WordVectorSerializer.readParagraphVectorsFromText(tempFile2);
    INDArray day3 = vec3.getWordVectorMatrix("day").dup();
    List<String> labelsRestored = vec3.labelsSource.getLabels();
    assertEquals(day, day3);
    assertEquals(labelsOriginal.size(), labelsRestored.size());
    /*
         Testing binary serialization
        */
    SerializationUtils.saveObject(vec, tempFile);
    ParagraphVectors vec2 = (ParagraphVectors) SerializationUtils.readObject(tempFile);
    INDArray day2 = vec2.getWordVectorMatrix("day").dup();
    List<String> labelsBinary = vec2.labelsSource.getLabels();
    assertEquals(day, day2);
    tempFile.delete();
    assertEquals(labelsOriginal.size(), labelsBinary.size());
    INDArray original = vec.getWordVectorMatrix("DOC_16392").dup();
    INDArray originalPreserved = original.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);
    //        assertTrue(cosAO1 > 0.45);
    assertTrue(cosAB1 > 0.95);
    //assertArrayEquals(inferredA.data().asDouble(), inferredB.data().asDouble(), 0.01);
    ParagraphVectors restoredVectors = WordVectorSerializer.readParagraphVectors(fullFile);
    restoredVectors.setTokenizerFactory(t);
    INDArray restoredSyn1_17 = ((InMemoryLookupTable) restoredVectors.getLookupTable()).getSyn1().getRow(17).dup();
    assertEquals(originalSyn1_17, restoredSyn1_17);
    INDArray originalRestored = vec.getWordVectorMatrix("DOC_16392").dup();
    assertEquals(originalPreserved, originalRestored);
    INDArray inferredA2 = restoredVectors.inferVector("This is my work .");
    INDArray inferredB2 = restoredVectors.inferVector("This is my work .");
    INDArray inferredC2 = restoredVectors.inferVector("world way case .");
    double cosAO2 = Transforms.cosineSim(inferredA2.dup(), original.dup());
    double cosAB2 = Transforms.cosineSim(inferredA2.dup(), inferredB2.dup());
    double cosAAX = Transforms.cosineSim(inferredA1.dup(), inferredA2.dup());
    double cosAC2 = Transforms.cosineSim(inferredC2.dup(), inferredA2.dup());
    log.info("Cos A2/B2: {}", cosAB2);
    log.info("Cos A1/A2: {}", cosAAX);
    log.info("Cos O/A2: {}", cosAO2);
    log.info("Cos C2/A2: {}", cosAC2);
    log.info("Vector: {}", Arrays.toString(inferredA1.data().asFloat()));
    log.info("cosAO2: {}", cosAO2);
    //  assertTrue(cosAO2 > 0.45);
    assertTrue(cosAB2 > 0.95);
    assertTrue(cosAAX > 0.95);
}