Examples with CommonPreprocessor org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor used on opensource projects

Example 16 with CommonPreprocessor

use of org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor in project deeplearning4j by deeplearning4j.

the class Word2VecTests method testRunWord2Vec.

@Test
public void testRunWord2Vec() 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>()).epochs(1).windowSize(5).allowParallelTokenization(true).modelUtils(new BasicModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();
    assertEquals(new ArrayList<String>(), vec.getStopWords());
    vec.fit();
    File tempFile = File.createTempFile("temp", "temp");
    tempFile.deleteOnExit();
    WordVectorSerializer.writeFullModel(vec, tempFile.getAbsolutePath());
    Collection<String> lst = vec.wordsNearest("day", 10);
    //log.info(Arrays.toString(lst.toArray()));
    printWords("day", lst, vec);
    assertEquals(10, lst.size());
    double sim = vec.similarity("day", "night");
    log.info("Day/night similarity: " + sim);
    assertTrue(sim < 1.0);
    assertTrue(sim > 0.4);
    assertTrue(lst.contains("week"));
    assertTrue(lst.contains("night"));
    assertTrue(lst.contains("year"));
    assertFalse(lst.contains(null));
    lst = vec.wordsNearest("day", 10);
    //log.info(Arrays.toString(lst.toArray()));
    printWords("day", lst, vec);
    assertTrue(lst.contains("week"));
    assertTrue(lst.contains("night"));
    assertTrue(lst.contains("year"));
    new File("cache.ser").delete();
    ArrayList<String> labels = new ArrayList<>();
    labels.add("day");
    labels.add("night");
    labels.add("week");
    INDArray matrix = vec.getWordVectors(labels);
    assertEquals(matrix.getRow(0), vec.getWordVectorMatrix("day"));
    assertEquals(matrix.getRow(1), vec.getWordVectorMatrix("night"));
    assertEquals(matrix.getRow(2), vec.getWordVectorMatrix("week"));
    WordVectorSerializer.writeWordVectors(vec, pathToWriteto);
}

Example 17 with CommonPreprocessor

use of org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor 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 18 with CommonPreprocessor

use of org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor 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 19 with CommonPreprocessor

use of org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor 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 20 with CommonPreprocessor

use of org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor 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());
}