org.deeplearning4j.spark.models.embeddings.word2vec

Class Word2Vec

java.lang.Object

org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl<VocabWord>

org.deeplearning4j.spark.models.embeddings.word2vec.Word2Vec

All Implemented Interfaces:

Serializable, WordVectors, org.deeplearning4j.nn.weights.embeddings.EmbeddingInitializer

public class Word2Vec
extends WordVectorsImpl<VocabWord>
implements Serializable

Spark version of word2vec

Author:

Adam Gibson, raver119@gmail.com

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Word2Vec.Builder

Field Summary

Fields

Modifier and Type	Field and Description
protected VectorsConfiguration	configuration

Fields inherited from class org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl

batchSize, DEFAULT_UNK, layerSize, learningRate, learningRateDecayWords, lookupTable, minLearningRate, minWordFrequency, modelUtils, negative, numEpochs, numIterations, resetModel, sampling, stopWords, trainElementsVectors, trainSequenceVectors, useAdeGrad, variableWindows, vocab, window, workers

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	Word2Vec()
protected	Word2Vec(org.nd4j.linalg.api.ndarray.INDArray trainedSyn1)

Method Summary

Modifier and Type	Method and Description
Map<String,Object>	getTokenizerVarMap()
Map<String,Object>	getWord2vecVarMap()
protected double[]	initExpTable()
void	train(org.apache.spark.api.java.JavaRDD<String> corpusRDD) Training word2vec model on a given text corpus

Methods inherited from class org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl

accuracy, getLayerSize, getLookupTable, getMinWordFrequency, getModelUtils, getStopWords, getUNK, getVocab, getWindow, getWordVector, getWordVectorMatrix, getWordVectorMatrixNormalized, getWordVectors, getWordVectorsMean, hasWord, indexOf, jsonSerializable, loadWeightsInto, lookupTable, outOfVocabularySupported, setLookupTable, setModelUtils, setUNK, setVocab, similarity, similarWordsInVocabTo, update, update, vectorSize, vocab, vocabSize, wordsNearest, wordsNearest, wordsNearest, wordsNearestSum, wordsNearestSum, wordsNearestSum

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

configuration

protected VectorsConfiguration configuration

Constructor Detail

Word2Vec

protected Word2Vec(org.nd4j.linalg.api.ndarray.INDArray trainedSyn1)

Word2Vec

protected Word2Vec()

Method Detail

initExpTable

protected double[] initExpTable()

getTokenizerVarMap

public Map<String,Object> getTokenizerVarMap()

getWord2vecVarMap

public Map<String,Object> getWord2vecVarMap()

train

public void train(org.apache.spark.api.java.JavaRDD<String> corpusRDD)
           throws Exception

Training word2vec model on a given text corpus

Parameters:

corpusRDD - training corpus

Throws:

Exception