Java Code Examples for org.deeplearning4j.text.tokenization.tokenizerfactory.TokenizerFactory#setTokenPreProcessor()

@Test(timeout = 300000)
public void testWord2VecPlot() throws Exception {
    File inputFile = Resources.asFile("big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(5).iterations(2).batchSize(1000).learningRate(0.025)
                    .layerSize(100).seed(42).sampling(0).negativeSample(0).windowSize(5)
                    .modelUtils(new BasicModelUtils<VocabWord>()).useAdaGrad(false).iterate(iter).workers(10)
                    .tokenizerFactory(t).build();

    vec.fit();

    //        UiConnectionInfo connectionInfo = UiServer.getInstance().getConnectionInfo();

    //        vec.getLookupTable().plotVocab(100, connectionInfo);

    Thread.sleep(10000000000L);
    fail("Not implemented");
}
 

@Ignore
@Test
public void testGoogleModelForInference() throws Exception {
    WordVectors googleVectors = WordVectorSerializer.readWord2VecModel(new File("/ext/GoogleNews-vectors-negative300.bin.gz"));

    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));
}
 

@Ignore
@Test
public void testWord2VecGoogleModelUptraining() throws Exception {
    long time1 = System.currentTimeMillis();
    Word2Vec vec = WordVectorSerializer.readWord2VecModel(
                    new File("C:\\Users\\raver\\Downloads\\GoogleNews-vectors-negative300.bin.gz"), false);
    long time2 = System.currentTimeMillis();
    log.info("Model loaded in {} msec", time2 - time1);
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    vec.setTokenizerFactory(t);
    vec.setSentenceIterator(iter);
    vec.getConfiguration().setUseHierarchicSoftmax(false);
    vec.getConfiguration().setNegative(5.0);
    vec.setElementsLearningAlgorithm(new CBOW<VocabWord>());

    vec.fit();
}
 

public static void main(String[] args) throws Exception {
    final SentenceIterator iterator = new LineSentenceIterator(new ClassPathResource("raw_sentences_large.txt").getFile());
    SentenceDataPreProcessor.setPreprocessor(iterator);
    final TokenizerFactory tokenizerFactory = new DefaultTokenizerFactory();
    tokenizerFactory.setTokenPreProcessor(new EndingPreProcessor());

    final Word2Vec model = new Word2Vec.Builder()
                                    .iterate(iterator)
                                    .tokenizerFactory(tokenizerFactory)
                                    .minWordFrequency(5)
                                    .layerSize(100)
                                    .seed(42)
                                    .epochs(50)
                                    .windowSize(5)
                                    .build();
    log.info("Fitting Word2Vec model....");
    model.fit();

    final Collection<String> words = model.wordsNearest("season",10);
    for(final String word: words){
        System.out.println(word+ " ");
    }
    final double cosSimilarity = model.similarity("season","program");
    System.out.println(cosSimilarity);

    BarnesHutTsne tsne = new BarnesHutTsne.Builder()
            .setMaxIter(100)
            .theta(0.5)
            .normalize(false)
            .learningRate(500)
            .useAdaGrad(false)
            .build();


    //save word vectors for tSNE visualization.
    WordVectorSerializer.writeWordVectors(model.lookupTable(),new File("words.txt"));
    WordVectorSerializer.writeWord2VecModel(model, "model.zip");

}
 

@Ignore
@Test
public void testSparkW2VonBiggerCorpus() throws Exception {
    SparkConf sparkConf = new SparkConf().setMaster("local[8]").setAppName("sparktest")
            .set("spark.driver.host", "localhost")
                    .set("spark.driver.maxResultSize", "4g").set("spark.driver.memory", "8g")
                    .set("spark.executor.memory", "8g");

    // Set SparkContext
    JavaSparkContext sc = new JavaSparkContext(sparkConf);

    // Path of data part-00000
    //String dataPath = Resources.asFile("big/raw_sentences.txt").getAbsolutePath();
    //        String dataPath = "/ext/Temp/SampleRussianCorpus.txt";
    String dataPath = new ClassPathResource("spark_word2vec_test.txt").getFile().getAbsolutePath();

    // Read in data
    JavaRDD<String> corpus = sc.textFile(dataPath);

    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new LowCasePreProcessor());

    Word2Vec word2Vec = new Word2Vec.Builder().setNGrams(1)
                    //     .setTokenizer("org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory")
                    //     .setTokenPreprocessor("org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor")
                    //     .setRemoveStop(false)
                    .tokenizerFactory(t).seed(42L).negative(3).useAdaGrad(false).layerSize(100).windowSize(5)
                    .learningRate(0.025).minLearningRate(0.0001).iterations(1).batchSize(100).minWordFrequency(5)
                    .useUnknown(true).build();

    word2Vec.train(corpus);


    sc.stop();

    WordVectorSerializer.writeWordVectors(word2Vec.getLookupTable(), "/ext/Temp/sparkRuModel.txt");
}
 

public static void main(String[] args) throws Exception {

        // Gets Path to Text file
        String filePath = "c:/raw_sentences.txt";

        log.info("Load & Vectorize Sentences....");
        // Strip white space before and after for each line
        SentenceIterator iter = UimaSentenceIterator.createWithPath(filePath);
        // Split on white spaces in the line to get words
        TokenizerFactory t = new DefaultTokenizerFactory();
        t.setTokenPreProcessor(new CommonPreprocessor());

        InMemoryLookupCache cache = new InMemoryLookupCache();
        WeightLookupTable table = new InMemoryLookupTable.Builder()
                .vectorLength(100)
                .useAdaGrad(false)
                .cache(cache)
                .lr(0.025f).build();

        log.info("Building model....");
        Word2Vec vec = new Word2Vec.Builder()
                .minWordFrequency(5).iterations(1)
                .layerSize(100).lookupTable(table)
                .stopWords(new ArrayList<String>())
                .vocabCache(cache).seed(42)
                .windowSize(5).iterate(iter).tokenizerFactory(t).build();

        log.info("Fitting Word2Vec model....");
        vec.fit();

        log.info("Writing word vectors to text file....");
        // Write word
        WordVectorSerializer.writeWordVectors(vec, "word2vec.txt");

        log.info("Closest Words:");
        Collection<String> lst = vec.wordsNearest("man", 5); 
        System.out.println(lst);
        double cosSim = vec.similarity("cruise", "voyage");
        System.out.println(cosSim);
    }
 

@Test
public void testWord2VecCBOW() throws Exception {
    String backend = Nd4j.getExecutioner().getEnvironmentInformation().getProperty("backend");
    if(!isIntegrationTests() && "CUDA".equalsIgnoreCase(backend)) {
        skipUnlessIntegrationTests(); //AB 2020/02/06 Skip CUDA except for integration tests due to very slow test speed - > 5 minutes on Titan X
    }

    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).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(4)
                    .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);
}
 

public static void main(String[] args) throws Exception {
    final SentenceIterator iterator = new LineSentenceIterator(new ClassPathResource("raw_sentences_large.txt").getFile());
    SentenceDataPreProcessor.setPreprocessor(iterator);
    final TokenizerFactory tokenizerFactory = new DefaultTokenizerFactory();
    tokenizerFactory.setTokenPreProcessor(new EndingPreProcessor());

    final Word2Vec model = new Word2Vec.Builder()
                                    .iterate(iterator)
                                    .tokenizerFactory(tokenizerFactory)
                                    .minWordFrequency(5)
                                    .layerSize(100)
                                    .seed(42)
                                    .epochs(50)
                                    .windowSize(5)
                                    .build();
    log.info("Fitting Word2Vec model....");
    model.fit();

    final Collection<String> words = model.wordsNearest("season",10);
    for(final String word: words){
        System.out.println(word+ " ");
    }
    final double cosSimilarity = model.similarity("season","program");
    System.out.println(cosSimilarity);

    BarnesHutTsne tsne = new BarnesHutTsne.Builder()
            .setMaxIter(100)
            .theta(0.5)
            .normalize(false)
            .learningRate(500)
            .useAdaGrad(false)
            .build();


    //save word vectors for tSNE visualization.
    WordVectorSerializer.writeWordVectors(model.lookupTable(),new File("words.txt"));
    WordVectorSerializer.writeWord2VecModel(model, "model.zip");

}
 

/**
     * Basically all we want from this test - being able to finish without exceptions.
     */
    @Test
    public void testIterator1() throws Exception {

        File inputFile = Resources.asFile("big/raw_sentences.txt");
        SentenceIterator iter = ParagraphVectorsTest.getIterator(isIntegrationTests(), inputFile);
//        SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

        TokenizerFactory t = new DefaultTokenizerFactory();
        t.setTokenPreProcessor(new CommonPreprocessor());

        Word2Vec vec = new Word2Vec.Builder().minWordFrequency(10) // we make sure we'll have some missing words
                        .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();
        int count = 0;
        while (iterator.hasNext()) {
            DataSet ds = iterator.next();

            assertArrayEquals(array.shape(), ds.getFeatures().shape());

            if(!isIntegrationTests() && count++ > 20)
                break;  //raw_sentences.txt is 2.81 MB, takes quite some time to process. We'll only first 20 minibatches when doing unit tests
        }
    }
 

@Test
public void testWordsNearestSum() throws IOException {
    String backend = Nd4j.getExecutioner().getEnvironmentInformation().getProperty("backend");
    if(!isIntegrationTests() && "CUDA".equalsIgnoreCase(backend)) {
        skipUnlessIntegrationTests(); //AB 2020/02/06 Skip CUDA except for integration tests due to very slow test speed - > 5 minutes on Titan X
    }

    log.info("Load & Vectorize Sentences....");
    SentenceIterator iter = new BasicLineIterator(inputFile);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    log.info("Building model....");
    Word2Vec vec = new Word2Vec.Builder()
            .minWordFrequency(5)
            .iterations(1)
            .layerSize(100)
            .seed(42)
            .windowSize(5)
            .iterate(iter)
            .tokenizerFactory(t)
            .build();

    log.info("Fitting Word2Vec model....");
    vec.fit();
    log.info("Writing word vectors to text file....");
    log.info("Closest Words:");
    Collection<String> lst = vec.wordsNearestSum("day", 10);
    log.info("10 Words closest to 'day': {}", lst);
    assertTrue(lst.contains("week"));
    assertTrue(lst.contains("night"));
    assertTrue(lst.contains("year"));
    assertTrue(lst.contains("years"));
    assertTrue(lst.contains("time"));
}
 

@Test(timeout = 300000)
public void testParagraphVectorsWithWordVectorsModelling1() throws Exception {
    String backend = Nd4j.getExecutioner().getEnvironmentInformation().getProperty("backend");
    if(!isIntegrationTests() && "CUDA".equalsIgnoreCase(backend)) {
        skipUnlessIntegrationTests(); //Skip CUDA except for integration tests due to very slow test speed
    }

    File file = Resources.asFile("/big/raw_sentences.txt");
    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);
}
 

@Test
@Ignore("AB 2019/06/24 - Failing: Ignored to get to all passing baseline to prevent regressions via CI - see issue #7912")
public void testOutputStream() throws Exception {
    File file = File.createTempFile("tmp_ser", "ssa");
    file.deleteOnExit();

    File inputFile = Resources.asFile("big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile);
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    InMemoryLookupCache cache = new InMemoryLookupCache(false);
    WeightLookupTable table = new InMemoryLookupTable.Builder().vectorLength(100).useAdaGrad(false).negative(5.0)
                    .cache(cache).lr(0.025f).build();

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(5).iterations(1).epochs(1).layerSize(100)
                    .lookupTable(table).stopWords(new ArrayList<String>()).useAdaGrad(false).negativeSample(5)
                    .vocabCache(cache).seed(42)
                    //                .workers(6)
                    .windowSize(5).iterate(iter).tokenizerFactory(t).build();

    assertEquals(new ArrayList<String>(), vec.getStopWords());
    vec.fit();

    INDArray day1 = vec.getWordVectorMatrix("day");

    WordVectorSerializer.writeWordVectors(vec, new FileOutputStream(file));

    WordVectors vec2 = WordVectorSerializer.loadTxtVectors(file);

    INDArray day2 = vec2.getWordVectorMatrix("day");

    assertEquals(day1, day2);

    File tempFile = File.createTempFile("tetsts", "Fdfs");
    tempFile.deleteOnExit();

    WordVectorSerializer.writeWord2VecModel(vec, tempFile);

    Word2Vec vec3 = WordVectorSerializer.readWord2VecModel(tempFile);
}
 

@Test
public void testConcepts() throws Exception {
    // These are all default values for word2vec
    SparkConf sparkConf = new SparkConf().setMaster("local[8]")
            .set("spark.driver.host", "localhost")
            .setAppName("sparktest");

    // Set SparkContext
    JavaSparkContext sc = new JavaSparkContext(sparkConf);

    // Path of data part-00000
    String dataPath = new ClassPathResource("big/raw_sentences.txt").getFile().getAbsolutePath();
    //        dataPath = "/ext/Temp/part-00000";
    //        String dataPath = new ClassPathResource("spark_word2vec_test.txt").getFile().getAbsolutePath();

    // Read in data
    JavaRDD<String> corpus = sc.textFile(dataPath);

    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec word2Vec = new Word2Vec.Builder().setNGrams(1)
                    //     .setTokenizer("org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory")
                    //     .setTokenPreprocessor("org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor")
                    //     .setRemoveStop(false)
                    .tokenizerFactory(t).seed(42L).negative(10).useAdaGrad(false).layerSize(150).windowSize(5)
                    .learningRate(0.025).minLearningRate(0.0001).iterations(1).batchSize(100).minWordFrequency(5)
                    .stopWords(Arrays.asList("three")).useUnknown(true).build();

    word2Vec.train(corpus);

    //word2Vec.setModelUtils(new FlatModelUtils());

    System.out.println("UNK: " + word2Vec.getWordVectorMatrix("UNK"));

    InMemoryLookupTable<VocabWord> table = (InMemoryLookupTable<VocabWord>) word2Vec.lookupTable();

    double sim = word2Vec.similarity("day", "night");
    System.out.println("day/night similarity: " + sim);
    /*
    System.out.println("Hornjo: " + word2Vec.getWordVectorMatrix("hornjoserbsce"));
    System.out.println("carro: " + word2Vec.getWordVectorMatrix("carro"));
    
    Collection<String> portu = word2Vec.wordsNearest("carro", 10);
    printWords("carro", portu, word2Vec);
    
    portu = word2Vec.wordsNearest("davi", 10);
    printWords("davi", portu, word2Vec);
    
    System.out.println("---------------------------------------");
    */

    Collection<String> words = word2Vec.wordsNearest("day", 10);
    printWords("day", words, word2Vec);

    assertTrue(words.contains("night"));
    assertTrue(words.contains("week"));
    assertTrue(words.contains("year"));

    sim = word2Vec.similarity("two", "four");
    System.out.println("two/four similarity: " + sim);

    words = word2Vec.wordsNearest("two", 10);
    printWords("two", words, word2Vec);

    // three should be absent due to stopWords
    assertFalse(words.contains("three"));

    assertTrue(words.contains("five"));
    assertTrue(words.contains("four"));

    sc.stop();


    // test serialization
    File tempFile = testDir.newFile("temp" + System.currentTimeMillis() + ".tmp");

    int idx1 = word2Vec.vocab().wordFor("day").getIndex();

    INDArray array1 = word2Vec.getWordVectorMatrix("day").dup();

    VocabWord word1 = word2Vec.vocab().elementAtIndex(0);

    WordVectorSerializer.writeWordVectors(word2Vec.getLookupTable(), tempFile);

    WordVectors vectors = WordVectorSerializer.loadTxtVectors(tempFile);

    VocabWord word2 = ((VocabCache<VocabWord>) vectors.vocab()).elementAtIndex(0);
    VocabWord wordIT = ((VocabCache<VocabWord>) vectors.vocab()).wordFor("it");
    int idx2 = vectors.vocab().wordFor("day").getIndex();

    INDArray array2 = vectors.getWordVectorMatrix("day").dup();

    System.out.println("word 'i': " + word2);
    System.out.println("word 'it': " + wordIT);

    assertEquals(idx1, idx2);
    assertEquals(word1, word2);
    assertEquals(array1, array2);
}
 

@Test(timeout = 300000)
public void testParagraphVectorsDBOW() throws Exception {
    skipUnlessIntegrationTests();

    File file = Resources.asFile("/big/raw_sentences.txt");
    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(4)
                    .usePreciseWeightInit(true).sequenceLearningAlgorithm(new DBOW<VocabWord>()).build();

    vec.fit();

    assertFalse(((InMemoryLookupTable<VocabWord>)vec.getLookupTable()).getSyn0().isAttached());
    assertFalse(((InMemoryLookupTable<VocabWord>)vec.getLookupTable()).getSyn1().isAttached());

    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);

}
 

@Test
public void testRunWord2Vec() throws Exception {
    String backend = Nd4j.getExecutioner().getEnvironmentInformation().getProperty("backend");
    if(!isIntegrationTests() && "CUDA".equalsIgnoreCase(backend)) {
        skipUnlessIntegrationTests(); //AB 2020/02/06 Skip CUDA except for integration tests due to very slow test speed - > 5 minutes on Titan X
    }

    // Strip white space before and after for each line
    /*val shakespear = new ClassPathResource("big/rnj.txt");
    SentenceIterator iter = new BasicLineIterator(shakespear.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());


    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).iterations(1).batchSize(8192).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).allowParallelTokenization(true)
                    .workers(6)
                    .usePreciseMode(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, true), vec.getWordVectorMatrix("day"));
    assertEquals(matrix.getRow(1, true), vec.getWordVectorMatrix("night"));
    assertEquals(matrix.getRow(2, true), vec.getWordVectorMatrix("week"));

    WordVectorSerializer.writeWordVectors(vec, pathToWriteto);
}
 

@Test
public void reproducibleResults_ForMultipleRuns() throws Exception {
    String backend = Nd4j.getExecutioner().getEnvironmentInformation().getProperty("backend");
    if(!isIntegrationTests() && "CUDA".equalsIgnoreCase(backend)) {
        skipUnlessIntegrationTests(); //AB 2020/02/06 Skip CUDA except for integration tests due to very slow test speed - > 5 minutes on Titan X
    }

    log.info("reproducibleResults_ForMultipleRuns");
    val shakespear = new ClassPathResource("big/rnj.txt");
    val basic = new ClassPathResource("big/rnj.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile);
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec vec1 = new Word2Vec.Builder().minWordFrequency(1).iterations(1).batchSize(8192).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)
            .workers(1)
            .useHierarchicSoftmax(true)
            .modelUtils(new BasicModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();

    Word2Vec vec2 = new Word2Vec.Builder().minWordFrequency(1).iterations(1).batchSize(8192).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)
            .workers(1)
            .useHierarchicSoftmax(true)
            .modelUtils(new BasicModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();

    vec1.fit();

    iter.reset();

    vec2.fit();

    for (int e = 0; e < vec1.getVocab().numWords(); e++) {
        val w1 = vec1.getVocab().elementAtIndex(e);
        val w2 = vec2.getVocab().elementAtIndex(e);

        assertNotNull(w1);
        assertNotNull(w2);

        assertEquals(w1.getLabel(), w2.getLabel());

        assertArrayEquals("Failed for token [" + w1.getLabel() + "] at index [" + e + "]", Ints.toArray(w1.getPoints()), Ints.toArray(w2.getPoints()));
        assertArrayEquals("Failed for token [" + w1.getLabel() + "] at index [" + e + "]", Ints.toArray(w1.getCodes()), Ints.toArray(w2.getCodes()));
    }

    val syn0_from_vec1 = ((InMemoryLookupTable<VocabWord>) vec1.getLookupTable()).getSyn0();
    val syn0_from_vec2 = ((InMemoryLookupTable<VocabWord>) vec2.getLookupTable()).getSyn0();

    assertEquals(syn0_from_vec1, syn0_from_vec2);

    log.info("Day/night similarity: {}", vec1.similarity("day", "night"));
    val result = vec1.wordsNearest("day", 10);
    printWords("day", result, vec1);
}
 

/**
 * This test checks, how vocab is built using SentenceIterator provided, without labels.
 *
 * @throws Exception
 */
@Test(timeout = 2400000)
public void testParagraphVectorsVocabBuilding1() throws Exception {
    File file = Resources.asFile("/big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(file); //UimaSentenceIterator.createWithPath(file.getAbsolutePath());

    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)
                    //      .labelsGenerator(source)
                    .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());
}
 

@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);
}
 

@Test(timeout = 300000)
public void testConsumeOnEqualVocabs() throws Exception {
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    AbstractCache<VocabWord> cacheSource = new AbstractCache.Builder<VocabWord>().build();


    File resource = Resources.asFile("big/raw_sentences.txt");

    BasicLineIterator underlyingIterator = new BasicLineIterator(resource);


    SentenceTransformer transformer =
                    new SentenceTransformer.Builder().iterator(underlyingIterator).tokenizerFactory(t).build();

    AbstractSequenceIterator<VocabWord> sequenceIterator =
                    new AbstractSequenceIterator.Builder<>(transformer).build();

    VocabConstructor<VocabWord> vocabConstructor = new VocabConstructor.Builder<VocabWord>()
                    .addSource(sequenceIterator, 1).setTargetVocabCache(cacheSource).build();

    vocabConstructor.buildJointVocabulary(false, true);

    assertEquals(244, cacheSource.numWords());

    InMemoryLookupTable<VocabWord> mem1 =
                    (InMemoryLookupTable<VocabWord>) new InMemoryLookupTable.Builder<VocabWord>().vectorLength(100)
                                    .cache(cacheSource).seed(17).build();

    mem1.resetWeights(true);

    InMemoryLookupTable<VocabWord> mem2 =
                    (InMemoryLookupTable<VocabWord>) new InMemoryLookupTable.Builder<VocabWord>().vectorLength(100)
                                    .cache(cacheSource).seed(15).build();

    mem2.resetWeights(true);

    assertNotEquals(mem1.vector("day"), mem2.vector("day"));

    mem2.consume(mem1);

    assertEquals(mem1.vector("day"), mem2.vector("day"));

}
 

@Test(timeout = 300000)
public void testConsumeOnNonEqualVocabs() throws Exception {
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    AbstractCache<VocabWord> cacheSource = new AbstractCache.Builder<VocabWord>().build();


    File resource = Resources.asFile("big/raw_sentences.txt");

    BasicLineIterator underlyingIterator = new BasicLineIterator(resource);


    SentenceTransformer transformer =
                    new SentenceTransformer.Builder().iterator(underlyingIterator).tokenizerFactory(t).build();

    AbstractSequenceIterator<VocabWord> sequenceIterator =
                    new AbstractSequenceIterator.Builder<>(transformer).build();

    VocabConstructor<VocabWord> vocabConstructor = new VocabConstructor.Builder<VocabWord>()
                    .addSource(sequenceIterator, 1).setTargetVocabCache(cacheSource).build();

    vocabConstructor.buildJointVocabulary(false, true);

    assertEquals(244, cacheSource.numWords());

    InMemoryLookupTable<VocabWord> mem1 =
                    (InMemoryLookupTable<VocabWord>) new InMemoryLookupTable.Builder<VocabWord>().vectorLength(100)
                                    .cache(cacheSource).build();

    mem1.resetWeights(true);



    AbstractCache<VocabWord> cacheTarget = new AbstractCache.Builder<VocabWord>().build();


    val dir = testDir.newFolder();
    new ClassPathResource("/paravec/labeled/").copyDirectory(dir);

    FileLabelAwareIterator labelAwareIterator = new FileLabelAwareIterator.Builder()
                    .addSourceFolder(dir).build();

    transformer = new SentenceTransformer.Builder().iterator(labelAwareIterator).tokenizerFactory(t).build();

    sequenceIterator = new AbstractSequenceIterator.Builder<>(transformer).build();

    VocabConstructor<VocabWord> vocabTransfer = new VocabConstructor.Builder<VocabWord>()
                    .addSource(sequenceIterator, 1).setTargetVocabCache(cacheTarget).build();

    vocabTransfer.buildMergedVocabulary(cacheSource, true);

    // those +3 go for 3 additional entries in target VocabCache: labels
    assertEquals(cacheSource.numWords() + 3, cacheTarget.numWords());


    InMemoryLookupTable<VocabWord> mem2 =
                    (InMemoryLookupTable<VocabWord>) new InMemoryLookupTable.Builder<VocabWord>().vectorLength(100)
                                    .cache(cacheTarget).seed(18).build();

    mem2.resetWeights(true);

    assertNotEquals(mem1.vector("day"), mem2.vector("day"));

    mem2.consume(mem1);

    assertEquals(mem1.vector("day"), mem2.vector("day"));

    assertTrue(mem1.syn0.rows() < mem2.syn0.rows());

    assertEquals(mem1.syn0.rows() + 3, mem2.syn0.rows());
}