Java BasicLineIterator类代码示例

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@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;

}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testWord2VecPlot() throws Exception {
    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    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");
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testWord2VecMultiEpoch() throws Exception {
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

    TokenizerFactory 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).epochs(3)
                    .modelUtils(new BasicModelUtils<VocabWord>()).useAdaGrad(false).iterate(iter).workers(8)
                    .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"));
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@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();
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testVocab() throws Exception {
    File inputFile = new ClassPathResource("big/raw_sentences.txt").getFile();
    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);
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void hasNext() throws Exception {
    SentenceIterator iterator = new BasicLineIterator(new ClassPathResource("/big/raw_sentences.txt").getFile());

    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);
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void nextDocument() throws Exception {
    SentenceIterator sentence = new BasicLineIterator(new ClassPathResource("/big/raw_sentences.txt").getFile());
    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);
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testHasNextDocument1() throws Exception {

    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    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));
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
public void trainParagraghVecModel(String locationToSave) throws FileNotFoundException {
    ClassPathResource resource = new ClassPathResource("/paragraphVectors/paragraphVectorTraining.txt");
    File file = resource.getFile();
    SentenceIterator iter = new BasicLineIterator(file);
    AbstractCache<VocabWord> cache = new AbstractCache<VocabWord>();
    TokenizerFactory t = new DefaultTokenizerFactory();
    t.setTokenPreProcessor(new CommonPreprocessor());
    /*
         if you don't have LabelAwareIterator handy, you can use synchronized labels generator
          it will be used to label each document/sequence/line with it's own label.
          But if you have LabelAwareIterator ready, you can can provide it, for your in-house labels
    */
    LabelsSource source = new LabelsSource("DOC_");

    ParagraphVectors vec = new ParagraphVectors.Builder()
            .minWordFrequency(1)
            .iterations(100)
            .epochs(1)
            .layerSize(50)
            .learningRate(0.02)
            .labelsSource(source)
            .windowSize(5)
            .iterate(iter)
            .trainWordVectors(true)
            .vocabCache(cache)
            .tokenizerFactory(t)
            .sampling(0)
            .build();

    vec.fit();

    WordVectorSerializer.writeParagraphVectors(vec, locationToSave);
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
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"));
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testWord2VecCBOW() throws Exception {
    SentenceIterator iter = new BasicLineIterator(inputFile.getAbsolutePath());

    TokenizerFactory 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)
                    .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);
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
public ASCIICoOccurrenceReader(@NonNull File file, @NonNull VocabCache<T> vocabCache) {
    this.vocabCache = vocabCache;
    this.file = file;
    try {
        iterator = new PrefetchingSentenceIterator.Builder(new BasicLineIterator(file)).build();
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@Test
public void testHasNextDocument2() throws Exception {

    File inputFile = new ClassPathResource("/big/raw_sentences.txt").getFile();
    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));
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
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);
    
    
    
}
 

import org.deeplearning4j.text.sentenceiterator.BasicLineIterator; //导入依赖的package包/类
@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));
}