ML

//Code excerpts
final SentenceIterator it1 = loadData(fileName);
final TokenizerFactory tf = tokenizeData();

final int layerSize = 100;
final long seed = 5;
final int windowSize = 50;
final int minWordFrequency = 2;
final Word2Vec vec = trainModel(it1, tf, layerSize, seed, windowSize, minWordFrequency);

  //////////////////////////////////////////////////////////////////////////////////////////////////
  SentenceIterator loadData(final String fileName) {
    SentenceIterator sentenceIterator = null;
    try {
      final String filePath = new ClassPathResource(fileName).getFile().getAbsolutePath();

      // strip white space before & after
      sentenceIterator = new BasicLineIterator(filePath);

    } catch (final IOException e1) {
      logger.error(e1.getMessage());
      e1.printStackTrace();
    }
    return sentenceIterator;
  }
  //////////////////////////////////////////////////////////////////////////////////////////////////
  TokenizerFactory tokenizeData() {

    // Split on white spaces in the line to get words
    final TokenizerFactory tokenizerFactory = new DefaultTokenizerFactory();
    tokenizerFactory.setTokenPreProcessor(new CommonPreprocessor());
    return tokenizerFactory;
  }
  //////////////////////////////////////////////////////////////////////////////////////////////////
  Word2Vec trainModel( final SentenceIterator iterator,
      final TokenizerFactory tokenizerFactory, final int layerSize, final long seed,
      final int windowSize, final int minWordFrequency) {

      final Word2Vec vec =
        new Word2Vec.Builder().minWordFrequency(minWordFrequency).layerSize(layerSize).seed(seed)
            .windowSize(windowSize).iterate(iterator).tokenizerFactory(tokenizerFactory).build();
    vec.fit();
    return vec;
  }
  //////////////////////////////////////////////////////////////////////////////////////////////////


TEST RESULT (EXCEPTION)
12:21:31.770 [main] INFO com.yoochoose.ml.word2vec.Word2VecRaw - Load & Vectorize Sentences
12:21:31.773 [main] INFO com.yoochoose.ml.word2vec.Word2VecRaw - Tokenizing data...
12:21:31.774 [main] INFO com.yoochoose.ml.word2vec.Word2VecRaw - Building model...
12:21:31.811 [main] INFO org.nd4j.linalg.factory.Nd4jBackend - Loaded [CpuBackend] backend
12:21:32.455 [main] INFO org.nd4j.nativeblas.NativeOpsHolder - Number of threads used for NativeOps: 4
12:21:32.589 [main] INFO org.nd4j.nativeblas.Nd4jBlas - Number of threads used for BLAS: 4
12:21:32.593 [main] INFO org.nd4j.linalg.api.ops.executioner.DefaultOpExecutioner - Backend used: [CPU]; OS: [Linux]
12:21:32.593 [main] INFO org.nd4j.linalg.api.ops.executioner.DefaultOpExecutioner - Cores: [4]; Memory: [0.9GB];
12:21:32.593 [main] INFO org.nd4j.linalg.api.ops.executioner.DefaultOpExecutioner - Blas vendor: [OPENBLAS]
12:21:32.763 [main] INFO com.yoochoose.ml.word2vec.Word2VecRaw - Fitting Word2Vec model...
12:21:32.780 [main] INFO org.deeplearning4j.models.sequencevectors.SequenceVectors - Starting vocabulary building...
12:21:32.780 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Target vocab size before building: [0]
12:21:32.843 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Trying source iterator: [0]
12:21:32.843 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Target vocab size before building: [0]
12:21:35.983 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Waiting till all processes stop...
12:21:35.985 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Vocab size before truncation: [0],  NumWords: [0], sequences parsed: [10000], counter: [0]
12:21:35.985 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Scavenger: Words before: 0; Words after: 0;
12:21:35.985 [main] DEBUG org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Vocab size after truncation: [0],  NumWords: [0], sequences parsed: [10000], counter: [0]
12:21:36.035 [main] INFO org.deeplearning4j.models.word2vec.wordstore.VocabConstructor - Sequences checked: [10000], Current vocabulary size: [0]; Sequences/sec: [3073.14];
12:21:36.051 [main] INFO org.deeplearning4j.models.embeddings.loader.WordVectorSerializer - Projected memory use for model: [0.00 MB]
[Utils] Attempting to create /work/ebx/applications/ml/test-output/Default suite/Default test.html
[Utils]   Directory /work/ebx/applications/ml/test-output/Default suite exists: true
[Utils] Attempting to create /work/ebx/applications/ml/test-output/Default suite/Default test.xml
[Utils]   Directory /work/ebx/applications/ml/test-output/Default suite exists: true
FAILED: testX
java.lang.IllegalStateException: You can't fit() model with empty Vocabulary or WeightLookupTable
	at org.deeplearning4j.models.sequencevectors.SequenceVectors.fit(SequenceVectors.java:220)
	at com.yoochoose.ml.word2vec.Word2VecRaw.trainModel(Word2VecRaw.java:202)
	at com.yoochoose.ml.word2vec.Word2VecRaw.findInFileNWordsCloserTo_New(Word2VecRaw.java:76)
	at com.yoochoose.ml.word2vec.Word2VecRawTest.testX(Word2VecRawTest.java:116)