Modifier and Type | Method and Description |
---|---|
InvertedIndex<VocabWord> |
TextVectorizer.index()
Inverted index
|
Modifier and Type | Field and Description |
---|---|
protected Queue<Pair<Integer,List<Pair<VocabWord,VocabWord>>>> |
LegacyGlove.jobQueue
Deprecated.
|
protected Queue<Pair<Integer,List<Pair<VocabWord,VocabWord>>>> |
LegacyGlove.jobQueue
Deprecated.
|
Modifier and Type | Method and Description |
---|---|
Iterator<Pair<VocabWord,VocabWord>> |
CoOccurrences.coOccurrenceIteratorVocab() |
Iterator<Pair<VocabWord,VocabWord>> |
CoOccurrences.coOccurrenceIteratorVocab() |
Iterator<List<Pair<VocabWord,VocabWord>>> |
CoOccurrences.coOccurrenceIteratorVocabBatch(int batchSize) |
Iterator<List<Pair<VocabWord,VocabWord>>> |
CoOccurrences.coOccurrenceIteratorVocabBatch(int batchSize) |
List<Pair<VocabWord,VocabWord>> |
CoOccurrences.CoOccurrenceBatchIterator.next() |
List<Pair<VocabWord,VocabWord>> |
CoOccurrences.CoOccurrenceBatchIterator.next() |
Pair<VocabWord,VocabWord> |
CoOccurrences.CoOccurrenceIterator.next() |
Pair<VocabWord,VocabWord> |
CoOccurrences.CoOccurrenceIterator.next() |
Modifier and Type | Method and Description |
---|---|
Glove.Builder |
Glove.Builder.iterate(SequenceIterator<VocabWord> iterator) |
Glove.Builder |
Glove.Builder.lookupTable(WeightLookupTable<VocabWord> lookupTable) |
Glove.Builder |
Glove.Builder.stopWords(Collection<VocabWord> stopList) |
Glove.Builder |
Glove.Builder.vocabCache(VocabCache<VocabWord> vocabCache) |
Modifier and Type | Method and Description |
---|---|
ParagraphVectors.Builder |
ParagraphVectors.Builder.index(InvertedIndex<VocabWord> index) |
ParagraphVectors.Builder |
ParagraphVectors.Builder.iterate(SequenceIterator<VocabWord> iterator)
This method used to feed SequenceIterator, that contains training corpus, into ParagraphVectors
|
ParagraphVectors.Builder |
ParagraphVectors.Builder.lookupTable(WeightLookupTable<VocabWord> lookupTable)
This method allows to define external WeightLookupTable to be used
|
String |
ParagraphVectors.predict(List<VocabWord> document)
Predict several based on the document.
|
Counter<String> |
ParagraphVectors.predictSeveral(List<VocabWord> document)
Predict several based on the document.
|
ParagraphVectors.Builder |
ParagraphVectors.Builder.stopWords(Collection<VocabWord> stopList)
This method defines stop words that should be ignored during training
|
ParagraphVectors.Builder |
ParagraphVectors.Builder.vocabCache(VocabCache<VocabWord> vocabCache)
This method allows to define external VocabCache to be used
|
Modifier and Type | Method and Description |
---|---|
RNTN.Builder |
RNTN.Builder.setFeatureVectors(WeightLookupTable<VocabWord> featureVectors) |
Modifier and Type | Field and Description |
---|---|
protected VocabCache<VocabWord> |
SentenceTransformer.Builder.vocabCache |
Modifier and Type | Method and Description |
---|---|
Iterator<Sequence<VocabWord>> |
SentenceTransformer.iterator() |
Sequence<VocabWord> |
SentenceTransformer.transformToSequence(String object) |
Modifier and Type | Method and Description |
---|---|
static VocabWord |
VocabWord.none() |
Modifier and Type | Method and Description |
---|---|
Word2Vec.Builder |
Word2Vec.Builder.index(InvertedIndex<VocabWord> index)
Deprecated.
|
Word2Vec.Builder |
Word2Vec.Builder.iterate(SequenceIterator<VocabWord> iterator)
This method used to feed SequenceIterator, that contains training corpus, into ParagraphVectors
|
Word2Vec.Builder |
Word2Vec.Builder.lookupTable(WeightLookupTable<VocabWord> lookupTable)
This method allows to define external WeightLookupTable to be used
|
Word2Vec.Builder |
Word2Vec.Builder.stopWords(Collection<VocabWord> stopList)
This method defines stop words that should be ignored during training
|
Word2Vec.Builder |
Word2Vec.Builder.vocabCache(VocabCache<VocabWord> vocabCache)
This method allows to define external VocabCache to be used
|
Modifier and Type | Method and Description |
---|---|
List<VocabWord> |
SkipGramMessage.getSentence() |
Modifier and Type | Method and Description |
---|---|
void |
SkipGramMessage.setSentence(List<VocabWord> sentence) |
Constructor and Description |
---|
SkipGramMessage(int i,
int b,
List<VocabWord> sentence) |
Modifier and Type | Field and Description |
---|---|
Map<String,VocabWord> |
InMemoryLookupCache.tokens |
Map<String,VocabWord> |
InMemoryLookupCache.vocabs |
Modifier and Type | Method and Description |
---|---|
VocabWord |
InMemoryLookupCache.elementAtIndex(int index) |
VocabWord |
InMemoryLookupCache.tokenFor(String word) |
VocabWord |
InMemoryLookupCache.wordFor(String word) |
Modifier and Type | Method and Description |
---|---|
Map<String,VocabWord> |
InMemoryLookupCache.getTokens() |
Map<String,VocabWord> |
InMemoryLookupCache.getVocabs() |
Collection<VocabWord> |
InMemoryLookupCache.tokens() |
Collection<VocabWord> |
InMemoryLookupCache.vocabWords()
Returns all of the vocab word nodes
|
Modifier and Type | Method and Description |
---|---|
void |
InMemoryLookupCache.addToken(VocabWord word) |
void |
InMemoryLookupCache.removeElement(VocabWord element) |
Modifier and Type | Method and Description |
---|---|
void |
InMemoryLookupCache.importVocabulary(VocabCache<VocabWord> vocabCache) |
void |
InMemoryLookupCache.setTokens(Map<String,VocabWord> tokens) |
void |
InMemoryLookupCache.setVocabs(Map<String,VocabWord> vocabs) |
Modifier and Type | Method and Description |
---|---|
List<Pair<VocabWord,VocabWord>> |
GloveWork.getCoOccurrences() |
List<Pair<VocabWord,VocabWord>> |
GloveWork.getCoOccurrences() |
Map<Integer,VocabWord> |
GloveWork.getIndexes() |
Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> |
GloveWork.getVectors() |
Modifier and Type | Method and Description |
---|---|
double |
GlovePerformer.iterateSample(GloveWork work,
VocabWord w1,
VocabWord w2,
double score)
glove iteration
|
Modifier and Type | Method and Description |
---|---|
void |
GloveWork.setCoOccurrences(List<Pair<VocabWord,VocabWord>> coOccurrences) |
void |
GloveWork.setCoOccurrences(List<Pair<VocabWord,VocabWord>> coOccurrences) |
void |
GloveWork.setIndexes(Map<Integer,VocabWord> indexes) |
void |
GloveWork.setVectors(Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> vectors) |
Constructor and Description |
---|
GloveWork(GloveWeightLookupTable table,
List<Pair<VocabWord,VocabWord>> coOccurrences) |
GloveWork(GloveWeightLookupTable table,
List<Pair<VocabWord,VocabWord>> coOccurrences) |
Constructor and Description |
---|
GloveJobIterator(Iterator<List<List<VocabWord>>> sentenceIterator,
GloveWeightLookupTable table,
VocabCache cache,
StateTracker stateTracker) |
GloveJobIterator(Iterator<List<List<VocabWord>>> sentenceIterator,
GloveWeightLookupTable table,
VocabCache cache,
StateTracker stateTracker,
int batchSize) |
Modifier and Type | Method and Description |
---|---|
Map<Integer,VocabWord> |
Word2VecWork.getIndexes() |
Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> |
Word2VecWork.getNegativeVectors() |
List<List<VocabWord>> |
Word2VecWork.getSentences() |
Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> |
Word2VecWork.getVectors() |
Modifier and Type | Method and Description |
---|---|
void |
Word2VecPerformer.iterateSample(Word2VecWork work,
VocabWord w1,
VocabWord w2,
double alpha)
Iterate on the given 2 vocab words
|
Modifier and Type | Method and Description |
---|---|
void |
Word2VecWork.setIndexes(Map<Integer,VocabWord> indexes) |
void |
Word2VecWork.setNegativeVectors(Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> negativeVectors) |
void |
Word2VecWork.setSentences(List<List<VocabWord>> sentences) |
void |
Word2VecWork.setVectors(Map<String,Pair<VocabWord,org.nd4j.linalg.api.ndarray.INDArray>> vectors) |
void |
Word2VecPerformer.skipGram(int i,
List<VocabWord> sentence,
int b,
Word2VecWork work,
double alpha)
Train via skip gram
|
void |
Word2VecPerformer.trainSentence(List<VocabWord> sentence,
Word2VecWork work,
double alpha)
Train on a list of vocab words
|
Constructor and Description |
---|
Word2VecWork(InMemoryLookupTable<VocabWord> table,
InMemoryLookupCache cache,
List<List<VocabWord>> sentences) |
Word2VecWork(InMemoryLookupTable<VocabWord> table,
InMemoryLookupCache cache,
List<List<VocabWord>> sentences) |
Constructor and Description |
---|
Word2VecJobIterator(Iterator<List<List<VocabWord>>> sentenceIterator,
WeightLookupTable table,
VocabCache cache,
StateTracker stateTracker) |
Word2VecJobIterator(Iterator<List<List<VocabWord>>> sentenceIterator,
WeightLookupTable table,
VocabCache cache,
StateTracker stateTracker,
int batchSize) |
Copyright © 2016. All Rights Reserved.