org.deeplearning4j.text.sentenceiterator.BasicLineIterator Java Examples

public static void main(String[] args) throws IOException {
    SentenceIterator iterator = new BasicLineIterator(new ClassPathResource("raw_sentences.txt").getFile());
    int count=0;
    while(iterator.hasNext()){
       iterator.nextSentence();
       count++;
    }
    System.out.println("count = "+count);
    iterator.reset();
    SentenceDataPreProcessor.setPreprocessor(iterator);
    while(iterator.hasNext()){
        System.out.println(iterator.nextSentence());
    }
    

}
 

@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");
}
 

@Test
public void testHasNextDocument1() throws Exception {

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

@Test(timeout = 300000)
public void nextDocument() throws Exception {
    SentenceIterator sentence = new BasicLineIterator(Resources.asFile("big/raw_sentences.txt"));
    BasicLabelAwareIterator backed = new BasicLabelAwareIterator.Builder(sentence).build();

    int cnt = 0;
    while (backed.hasNextDocument()) {
        backed.nextDocument();
        cnt++;
    }
    assertEquals(97162, cnt);

    backed.reset();

    AsyncLabelAwareIterator iterator = new AsyncLabelAwareIterator(backed, 64);
    cnt = 0;
    while (iterator.hasNext()) {
        iterator.next();
        cnt++;

        if (cnt == 10)
            iterator.reset();
    }
    assertEquals(97172, cnt);
}
 

@Test(timeout = 300000)
public void hasNext() throws Exception {
    SentenceIterator iterator = new BasicLineIterator(Resources.asFile("big/raw_sentences.txt"));

    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);
}
 

@Test(timeout=5000)		// 5s timeout
public void testParallelTokenizationDisabled_Completes() throws Exception {
    File inputFile = Resources.asFile("big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile);

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

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

    VocabConstructor<VocabWord> constructor = new VocabConstructor.Builder<VocabWord>().addSource(sequenceIterator, 5)
            .allowParallelTokenization( false)
            .build();

    constructor.buildJointVocabulary(false, true);
}
 

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

    Set<String> set = new HashSet<>();
    int lines = 0;
    int cnt = 0;
    while (iter.hasNext()) {
        Tokenizer tok = t.create(iter.nextSentence());
        for (String token : tok.getTokens()) {
            if (token == null || token.isEmpty() || token.trim().isEmpty())
                continue;
            cnt++;

            if (!set.contains(token))
                set.add(token);
        }

        lines++;
    }

    log.info("Total number of tokens: [" + cnt + "], lines: [" + lines + "], set size: [" + set.size() + "]");
    log.info("Set:\n" + set);
}
 

@Ignore
@Test
public void testFindNamesFromText() throws IOException {
    SentenceIterator iter = new BasicLineIterator("src/test/resources/chineseName.txt");

    log.info("load is right!");
    TokenizerFactory tokenizerFactory = new ChineseTokenizerFactory();
    //tokenizerFactory.setTokenPreProcessor(new ChineseTokenizer());

    //Generates a word-vector from the dataset stored in resources folder
    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(2).iterations(5).layerSize(100).seed(42)
                    .learningRate(0.1).windowSize(20).iterate(iter).tokenizerFactory(tokenizerFactory).build();
    vec.fit();
    WordVectorSerializer.writeWordVectors(vec, new File("src/test/resources/chineseNameWordVector.txt"));

    //trains a model that can find out all names from news(Suffix txt),It uses word vector generated
    // WordVectors wordVectors;

    //test model,Whether the model find out name from unknow text;

}
 

public static void main(String[] args) throws IOException {
    SentenceIterator iterator = new BasicLineIterator(new ClassPathResource("raw_sentences.txt").getFile());
    int count=0;
    while(iterator.hasNext()){
       iterator.nextSentence();
       count++;
    }
    System.out.println("count = "+count);
    iterator.reset();
    SentenceDataPreProcessor.setPreprocessor(iterator);
    while(iterator.hasNext()){
        System.out.println(iterator.nextSentence());
    }
    

}
 

@Ignore
@Test
public void testWord2VecCBOWBig() throws Exception {
    SentenceIterator iter = new BasicLineIterator("/home/raver119/Downloads/corpus/namuwiki_raw.txt");
    //iter = new BasicLineIterator("/home/raver119/Downloads/corpus/ru_sentences.txt");
    //SentenceIterator iter = new BasicLineIterator("/ext/DATASETS/ru/Socials/ru_sentences.txt");

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

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(1).iterations(5).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)
                    .allowParallelTokenization(true).tokenizerFactory(t)
                    .elementsLearningAlgorithm(new CBOW<VocabWord>()).build();

    long time1 = System.currentTimeMillis();

    vec.fit();

    long time2 = System.currentTimeMillis();

    log.info("Total execution time: {}", (time2 - time1));
}
 

@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();
}
 

@Test
public void testWordVectorsPartiallyAbsentLabels() 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());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(10).useUnknown(true)
            .iterations(1).layerSize(100)
            .stopWords(new ArrayList<String>()).seed(42).learningRate(0.025).minLearningRate(0.001)
            .sampling(0).elementsLearningAlgorithm(new CBOW<VocabWord>()).epochs(1).windowSize(5)
            .useHierarchicSoftmax(true).allowParallelTokenization(true)
            .useUnknown(false)
            .modelUtils(new FlatModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();

    vec.fit();

    ArrayList<String> labels = new ArrayList<>();
    labels.add("fewfew");
    labels.add("day");
    labels.add("night");
    labels.add("week");

    INDArray matrix = vec.getWordVectors(labels);
    assertEquals(3, matrix.rows());
    assertEquals(matrix.getRow(0, true), vec.getWordVectorMatrix("day"));
    assertEquals(matrix.getRow(1, true), vec.getWordVectorMatrix("night"));
    assertEquals(matrix.getRow(2, true), vec.getWordVectorMatrix("week"));
}
 

@Test
public void testWordVectorsAbsentLabels() 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());
    // Split on white spaces in the line to get words
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(10).useUnknown(true)
            .iterations(1).layerSize(100)
            .stopWords(new ArrayList<String>()).seed(42).learningRate(0.025).minLearningRate(0.001)
            .sampling(0).elementsLearningAlgorithm(new CBOW<VocabWord>()).epochs(1).windowSize(5)
            .useHierarchicSoftmax(true).allowParallelTokenization(true)
            .useUnknown(false)
            .modelUtils(new FlatModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();

    vec.fit();

    ArrayList<String> labels = new ArrayList<>();
    labels.add("fewfew");

    INDArray matrix = vec.getWordVectors(labels);
    assertTrue(matrix.isEmpty());
}
 

@Test
public void testWordVectorsAbsentLabels_WithUnknown() 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());
    // 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(4)
            .modelUtils(new BasicModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t)
            .useUnknown(true).unknownElement(new VocabWord(1, "UNKOWN")).build();

    vec.fit();

    ArrayList<String> labels = new ArrayList<>();
    labels.add("bus");
    labels.add("car");

    INDArray matrix = vec.getWordVectors(labels);
    for (int i = 0; i < labels.size(); ++i)
        assertEquals(matrix.getRow(i, true), vec.getWordVectorMatrix("UNKNOWN"));
}
 

@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
public void testHasNextDocument2() throws Exception {

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

    iterator.reset();

    cnt = 0;
    while (iterator.hasNextDocument()) {
        iterator.nextDocument();
        cnt++;
    }

    assertEquals(97162, cnt);

    LabelsSource generator = iterator.getLabelsSource();

    // this is important moment. Iterator after reset should not increase number of labels attained
    assertEquals(97162, generator.getLabels().size());
    assertEquals("DOCZ_0", generator.getLabels().get(0));
}
 

@Test
public void orderIsStableForParallelTokenization() throws Exception {

    String[] stringsArray = new String[1000];
    String testStrings = "";
    for (int i = 0; i < 1000; ++i) {
        stringsArray[i] = Integer.toString(i);
        testStrings += Integer.toString(i) + "\n";
    }
    InputStream inputStream = IOUtils.toInputStream(testStrings, "UTF-8");
    SentenceIterator iterator = new BasicLineIterator(inputStream);

    SentenceTransformer transformer = new SentenceTransformer.Builder().iterator(iterator).allowMultithreading(true)
            .tokenizerFactory(factory).build();

    Iterator<Sequence<VocabWord>> iter = transformer.iterator();

    Sequence<VocabWord> sequence = null;
    int cnt = 0;
    while (iter.hasNext()) {
        sequence = iter.next();
        List<VocabWord> words = sequence.getElements();
        for (VocabWord word : words) {
            assertEquals(stringsArray[cnt], word.getWord());
            ++cnt;
        }
    }

}
 

@Test
public void testLoadIterator() throws FileNotFoundException {
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());
     FastText
            .builder()
            .supervised(true)
            .iterator(iter)
            .build()
            .loadIterator();
}
 

@Test
public void testCompletes_WhenIteratorHasOneElement() throws Exception {

    String testString = "";
    String[] stringsArray = new String[100];
    for (int i = 0; i < 100; ++i) {
        testString += Integer.toString(i) + " ";
        stringsArray[i] = Integer.toString(i);
    }
    InputStream inputStream = IOUtils.toInputStream(testString, "UTF-8");
    SentenceIterator iterator = new BasicLineIterator(inputStream);

    SentenceTransformer transformer = new SentenceTransformer.Builder().iterator(iterator).allowMultithreading(true)
            .tokenizerFactory(factory).build();

    Iterator<Sequence<VocabWord>> iter = transformer.iterator();

    Sequence<VocabWord> sequence = null;
    int cnt = 0;
    while (iter.hasNext()) {
        sequence = iter.next();
        List<VocabWord> words = sequence.getElements();
        for (VocabWord word : words) {
            assertEquals(stringsArray[cnt], word.getWord());
            ++cnt;
        }
    }

}
 

@Test
@Ignore // no adagrad these days
public void testWord2VecAdaGrad() throws Exception {
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

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

    Word2Vec vec = new Word2Vec.Builder().minWordFrequency(5).iterations(5).learningRate(0.025).layerSize(100)
                    .seed(42).batchSize(13500).sampling(0).negativeSample(0)
                    //.epochs(10)
                    .windowSize(5).modelUtils(new BasicModelUtils<VocabWord>()).useAdaGrad(false)
                    .useHierarchicSoftmax(true).iterate(iter).workers(4).tokenizerFactory(t).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"));
}
 

@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);
}
 

@Test
public void testBuildJointVocabulary1() throws Exception {
    File inputFile = Resources.asFile("big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile);

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

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


    /*
        And we pack that transformer into AbstractSequenceIterator
     */
    AbstractSequenceIterator<VocabWord> sequenceIterator =
                    new AbstractSequenceIterator.Builder<>(transformer).build();

    VocabConstructor<VocabWord> constructor = new VocabConstructor.Builder<VocabWord>()
                    .addSource(sequenceIterator, 0).useAdaGrad(false).setTargetVocabCache(cache).build();

    constructor.buildJointVocabulary(true, false);


    assertEquals(244, cache.numWords());

    assertEquals(0, cache.totalWordOccurrences());
}
 

public static void main(String[] args) throws Exception {
    ClassPathResource srcFile = new ClassPathResource("/raw_sentences.txt");
    File file = srcFile.getFile();
    SentenceIterator iter = new BasicLineIterator(file);
    
    TokenizerFactory tFact = new DefaultTokenizerFactory();
    tFact.setTokenPreProcessor(new CommonPreprocessor());

    LabelsSource labelFormat = new LabelsSource("LINE_");

    ParagraphVectors vec = new ParagraphVectors.Builder()
            .minWordFrequency(1)
            .iterations(5)
            .epochs(1)
            .layerSize(100)
            .learningRate(0.025)
            .labelsSource(labelFormat)
            .windowSize(5)
            .iterate(iter)
            .trainWordVectors(false)
            .tokenizerFactory(tFact)
            .sampling(0)
            .build();

    vec.fit();

    double similar1 = vec.similarity("LINE_9835", "LINE_12492");
    out.println("Comparing lines 9836 & 12493 ('This is my house .'/'This is my world .') Similarity = " + similar1);


    double similar2 = vec.similarity("LINE_3720", "LINE_16392");
    out.println("Comparing lines 3721 & 16393 ('This is my way .'/'This is my work .') Similarity = " + similar2);

    double similar3 = vec.similarity("LINE_6347", "LINE_3720");
    out.println("Comparing lines 6348 & 3721 ('This is my case .'/'This is my way .') Similarity = " + similar3);

    double dissimilar1 = vec.similarity("LINE_3720", "LINE_9852");
    out.println("Comparing lines 3721 & 9853 ('This is my way .'/'We now have one .') Similarity = " + dissimilar1);
    
    double dissimilar2 = vec.similarity("LINE_3720", "LINE_3719");
    out.println("Comparing lines 3721 & 3720 ('This is my way .'/'At first he says no .') Similarity = " + dissimilar2);
    
    
    
}
 

@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);
}
 

@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
@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 testUnknown1() 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
    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(10).useUnknown(true)
                    .unknownElement(new VocabWord(1.0, "PEWPEW")).iterations(1).layerSize(100)
                    .stopWords(new ArrayList<String>()).seed(42).learningRate(0.025).minLearningRate(0.001)
                    .sampling(0).elementsLearningAlgorithm(new CBOW<VocabWord>()).epochs(1).windowSize(5)
                    .useHierarchicSoftmax(true).allowParallelTokenization(true)
                    .modelUtils(new FlatModelUtils<VocabWord>()).iterate(iter).tokenizerFactory(t).build();

    vec.fit();

    assertTrue(vec.hasWord("PEWPEW"));
    assertTrue(vec.getVocab().containsWord("PEWPEW"));

    INDArray unk = vec.getWordVectorMatrix("PEWPEW");
    assertNotEquals(null, unk);

    File tempFile = File.createTempFile("temp", "file");
    tempFile.deleteOnExit();

    WordVectorSerializer.writeWord2VecModel(vec, tempFile);

    log.info("Original configuration: {}", vec.getConfiguration());

    Word2Vec restored = WordVectorSerializer.readWord2VecModel(tempFile);

    assertTrue(restored.hasWord("PEWPEW"));
    assertTrue(restored.getVocab().containsWord("PEWPEW"));
    INDArray unk_restored = restored.getWordVectorMatrix("PEWPEW");

    assertEquals(unk, unk_restored);



    // now we're getting some junk word
    INDArray random = vec.getWordVectorMatrix("hhsd7d7sdnnmxc_SDsda");
    INDArray randomRestored = restored.getWordVectorMatrix("hhsd7d7sdnnmxc_SDsda");

    log.info("Restored configuration: {}", restored.getConfiguration());

    assertEquals(unk, random);
    assertEquals(unk, randomRestored);
}
 

/**
 * Here we test basic vocab transfer, done WITHOUT labels
 * @throws Exception
 */
@Test
public void testMergedVocab1() throws Exception {
    AbstractCache<VocabWord> cacheSource = new AbstractCache.Builder<VocabWord>().build();

    AbstractCache<VocabWord> cacheTarget = 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);

    int sourceSize = cacheSource.numWords();
    log.info("Source Vocab size: " + sourceSize);


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

    vocabTransfer.buildMergedVocabulary(cacheSource, false);

    assertEquals(sourceSize, cacheTarget.numWords());
}
 

@Test
public void testBuildJointVocabulary2() throws Exception {
    File inputFile = Resources.asFile("big/raw_sentences.txt");
    SentenceIterator iter = new BasicLineIterator(inputFile);

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

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


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

    VocabConstructor<VocabWord> constructor = new VocabConstructor.Builder<VocabWord>()
                    .addSource(sequenceIterator, 5).useAdaGrad(false).setTargetVocabCache(cache).build();

    constructor.buildJointVocabulary(false, true);

    //        assertFalse(cache.hasToken("including"));

    assertEquals(242, cache.numWords());


    assertEquals("i", cache.wordAtIndex(1));
    assertEquals("it", cache.wordAtIndex(0));

    assertEquals(634303, cache.totalWordOccurrences());
}
 

@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);
}