SequenceVectors.Builder

java.lang.Object
- org.deeplearning4j.models.sequencevectors.SequenceVectors.Builder<T>

Direct Known Subclasses:

Glove.Builder, Node2Vec.Builder, Word2Vec.Builder

Enclosing class:

SequenceVectors<T extends SequenceElement>
```
public static class SequenceVectors.Builder<T extends SequenceElement>
extends java.lang.Object
```

Field Summary

Fields
Modifier and Type	Field and Description
`protected int`	`batchSize`
`protected VectorsConfiguration`	`configuration`
`protected ElementsLearningAlgorithm<T>`	`elementsLearningAlgorithm`
`protected boolean`	`enableScavenger`
`protected WordVectors`	`existingVectors`
`protected boolean`	`hugeModelExpected`
`protected int`	`iterations`
`protected SequenceIterator<T>`	`iterator`
`protected int`	`layerSize`
`protected double`	`learningRate`
`protected int`	`learningRateDecayWords`
`protected WeightLookupTable<T>`	`lookupTable`
`protected double`	`minLearningRate`
`protected int`	`minWordFrequency`
`protected ModelUtils<T>`	`modelUtils`
`protected double`	`negative`
`protected int`	`numEpochs`
`protected boolean`	`preciseWeightInit`
`protected boolean`	`resetModel`
`protected double`	`sampling`
`protected long`	`seed`
`protected SequenceLearningAlgorithm<T>`	`sequenceLearningAlgorithm`
`protected java.lang.String`	`STOP`
`protected java.util.Collection<java.lang.String>`	`stopWords`
`protected boolean`	`trainElementsVectors`
`protected boolean`	`trainSequenceVectors`
`protected java.lang.String`	`UNK`
`protected T`	`unknownElement`
`protected boolean`	`useAdaGrad`
`protected boolean`	`useHierarchicSoftmax`
`protected boolean`	`useUnknown`
`protected int[]`	`variableWindows`
`protected java.util.Set<VectorsListener<T>>`	`vectorsListeners`
`protected VocabCache<T>`	`vocabCache`
`protected int`	`window`
`protected int`	`workers`

Constructor Summary

Constructors
Constructor and Description

Builder()

Builder(VectorsConfiguration configuration)

Constructors
Constructor and Description
`Builder()`
`Builder(VectorsConfiguration configuration)`

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`SequenceVectors.Builder<T>`	`batchSize(int batchSize)` This method defines batchSize option, viable only if iterations > 1
`SequenceVectors<T>`	`build()` Build SequenceVectors instance with defined settings/options
`SequenceVectors.Builder<T>`	`elementsLearningAlgorithm(ElementsLearningAlgorithm<T> algorithm)` * Sets specific LearningAlgorithm as Elements Learning Algorithm
`SequenceVectors.Builder<T>`	`elementsLearningAlgorithm(java.lang.String algoName)` * Sets specific LearningAlgorithm as Elements Learning Algorithm
`SequenceVectors.Builder<T>`	`enableScavenger(boolean reallyEnable)` This method ebables/disables periodical vocab truncation during construction Default value: disabled
`SequenceVectors.Builder<T>`	`epochs(int numEpochs)` This method defines how much iterations should be done over whole training corpus during modelling
`SequenceVectors.Builder<T>`	`iterate(SequenceIterator<T> iterator)` This method defines SequenceIterator to be used for model building
`SequenceVectors.Builder<T>`	`iterations(int iterations)` This method defines how much iterations should be done over batched sequences.
`SequenceVectors.Builder<T>`	`layerSize(int layerSize)` This method defines number of dimensions for outcome vectors.
`SequenceVectors.Builder<T>`	`learningRate(double learningRate)` This method defines initial learning rate.
`SequenceVectors.Builder<T>`	`lookupTable(WeightLookupTable<T> lookupTable)` You can pass externally built WeightLookupTable, containing model weights and vocabulary.
`SequenceVectors.Builder<T>`	`minLearningRate(double minLearningRate)` This method defines minimum learning rate after decay being applied.
`SequenceVectors.Builder<T>`	`minWordFrequency(int minWordFrequency)` This method defines minimal element frequency for elements found in the training corpus.
`SequenceVectors.Builder<T>`	`modelUtils(ModelUtils<T> modelUtils)` ModelUtils implementation, that will be used to access model.
`SequenceVectors.Builder<T>`	`negativeSample(double negative)` This method defines negative sampling value for skip-gram algorithm.
`protected void`	`presetTables()` This method creates new WeightLookupTable and VocabCache if there were none set
`SequenceVectors.Builder<T>`	`resetModel(boolean reallyReset)` This method defines, should all model be reset before training.
`SequenceVectors.Builder<T>`	`sampling(double sampling)` This method defines sub-sampling threshold.
`SequenceVectors.Builder<T>`	`seed(long randomSeed)` Sets seed for random numbers generator.
`SequenceVectors.Builder<T>`	`sequenceLearningAlgorithm(SequenceLearningAlgorithm<T> algorithm)` Sets specific LearningAlgorithm as Sequence Learning Algorithm
`SequenceVectors.Builder<T>`	`sequenceLearningAlgorithm(java.lang.String algoName)` Sets specific LearningAlgorithm as Sequence Learning Algorithm
`SequenceVectors.Builder<T>`	`setVectorsListeners(java.util.Collection<VectorsListener<T>> listeners)` This method sets VectorsListeners for this SequenceVectors model
`SequenceVectors.Builder<T>`	`stopWords(java.util.Collection<T> stopList)` You can provide collection of objects to be ignored, and excluded out of model Please note: Object labels and hashCode will be used for filtering
`SequenceVectors.Builder<T>`	`stopWords(java.util.List<java.lang.String> stopList)` You can provide collection of objects to be ignored, and excluded out of model Please note: Object labels and hashCode will be used for filtering
`SequenceVectors.Builder<T>`	`trainElementsRepresentation(boolean trainElements)`
`SequenceVectors.Builder<T>`	`trainSequencesRepresentation(boolean trainSequences)`
`SequenceVectors.Builder<T>`	`unknownElement(T element)` This method allows you to specify SequenceElement that will be used as UNK element, if UNK is used
`SequenceVectors.Builder<T>`	`useAdaGrad(boolean reallyUse)` Deprecated.
`protected SequenceVectors.Builder<T>`	`useExistingWordVectors(WordVectors vec)` This method allows you to use pre-built WordVectors model (SkipGram or GloVe) for DBOW sequence learning.
`SequenceVectors.Builder<T>`	`useHierarchicSoftmax(boolean reallyUse)` Enable/disable hierarchic softmax
`SequenceVectors.Builder<T>`	`usePreciseWeightInit(boolean reallyUse)` If set to true, initial weights for elements/sequences will be derived from elements themself.
`SequenceVectors.Builder<T>`	`useUnknown(boolean reallyUse)` This method allows you to specify, if UNK word should be used internally
`SequenceVectors.Builder<T>`	`useVariableWindow(int... windows)` This method allows to use variable window size.
`SequenceVectors.Builder<T>`	`vocabCache(VocabCache<T> vocabCache)` You can pass externally built vocabCache object, containing vocabulary
`SequenceVectors.Builder<T>`	`windowSize(int windowSize)` Sets window size for skip-Gram training
`SequenceVectors.Builder<T>`	`workers(int numWorkers)` Sets number of worker threads to be used in calculations

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - vocabCache
```
protected VocabCache<T extends SequenceElement> vocabCache
```
  - lookupTable
```
protected WeightLookupTable<T extends SequenceElement> lookupTable
```
  - iterator
```
protected SequenceIterator<T extends SequenceElement> iterator
```
  - modelUtils
```
protected ModelUtils<T extends SequenceElement> modelUtils
```
  - existingVectors
```
protected WordVectors existingVectors
```
  - sampling
```
protected double sampling
```
  - negative
```
protected double negative
```
  - learningRate
```
protected double learningRate
```
  - minLearningRate
```
protected double minLearningRate
```
  - minWordFrequency
```
protected int minWordFrequency
```
  - iterations
```
protected int iterations
```
  - numEpochs
```
protected int numEpochs
```
  - layerSize
```
protected int layerSize
```
  - window
```
protected int window
```
  - hugeModelExpected
```
protected boolean hugeModelExpected
```
  - batchSize
```
protected int batchSize
```
  - learningRateDecayWords
```
protected int learningRateDecayWords
```
  - seed
```
protected long seed
```
  - useAdaGrad
```
protected boolean useAdaGrad
```
  - resetModel
```
protected boolean resetModel
```
  - workers
```
protected int workers
```
  - useUnknown
```
protected boolean useUnknown
```
  - useHierarchicSoftmax
```
protected boolean useHierarchicSoftmax
```
  - variableWindows
```
protected int[] variableWindows
```
  - trainSequenceVectors
```
protected boolean trainSequenceVectors
```
  - trainElementsVectors
```
protected boolean trainElementsVectors
```
  - preciseWeightInit
```
protected boolean preciseWeightInit
```
  - stopWords
```
protected java.util.Collection<java.lang.String> stopWords
```
  - configuration
```
protected VectorsConfiguration configuration
```
  - unknownElement
```
protected transient T extends SequenceElement unknownElement
```
  - UNK
```
protected java.lang.String UNK
```
  - STOP
```
protected java.lang.String STOP
```
  - enableScavenger
```
protected boolean enableScavenger
```
  - elementsLearningAlgorithm
```
protected ElementsLearningAlgorithm<T extends SequenceElement> elementsLearningAlgorithm
```
  - sequenceLearningAlgorithm
```
protected SequenceLearningAlgorithm<T extends SequenceElement> sequenceLearningAlgorithm
```
  - vectorsListeners
```
protected java.util.Set<VectorsListener<T extends SequenceElement>> vectorsListeners
```
- Constructor Detail
  - Builder
```
public Builder()
```
  - Builder
```
public Builder(@NonNull
               VectorsConfiguration configuration)
```
- Method Detail
  - useExistingWordVectors
```
protected SequenceVectors.Builder<T> useExistingWordVectors(@NonNull
                                                            WordVectors vec)
```
    This method allows you to use pre-built WordVectors model (SkipGram or GloVe) for DBOW sequence learning. Existing model will be transferred into new model before training starts. PLEASE NOTE: This model has no effect for elements learning algorithms. Only sequence learning is affected. PLEASE NOTE: Non-normalized model is recommended to use here.
    
    Parameters:
    
    vec - existing WordVectors model
    
    Returns:
  - iterate
```
public SequenceVectors.Builder<T> iterate(@NonNull
                                          SequenceIterator<T> iterator)
```
    This method defines SequenceIterator to be used for model building
    
    Parameters:
    
    iterator -
    
    Returns:
  - sequenceLearningAlgorithm
```
public SequenceVectors.Builder<T> sequenceLearningAlgorithm(@NonNull
                                                            java.lang.String algoName)
```
    Sets specific LearningAlgorithm as Sequence Learning Algorithm
    
    Parameters:
    
    algoName - fully qualified class name
    
    Returns:
  - sequenceLearningAlgorithm
```
public SequenceVectors.Builder<T> sequenceLearningAlgorithm(@NonNull
                                                            SequenceLearningAlgorithm<T> algorithm)
```
    Sets specific LearningAlgorithm as Sequence Learning Algorithm
    
    Parameters:
    
    algorithm - SequenceLearningAlgorithm implementation
    
    Returns:
  - elementsLearningAlgorithm
```
public SequenceVectors.Builder<T> elementsLearningAlgorithm(@NonNull
                                                            java.lang.String algoName)
```
    * Sets specific LearningAlgorithm as Elements Learning Algorithm
    
    Parameters:
    
    algoName - fully qualified class name
    
    Returns:
  - elementsLearningAlgorithm
```
public SequenceVectors.Builder<T> elementsLearningAlgorithm(@NonNull
                                                            ElementsLearningAlgorithm<T> algorithm)
```
    * Sets specific LearningAlgorithm as Elements Learning Algorithm
    
    Parameters:
    
    algorithm - ElementsLearningAlgorithm implementation
    
    Returns:
  - batchSize
```
public SequenceVectors.Builder<T> batchSize(int batchSize)
```
    This method defines batchSize option, viable only if iterations > 1
    
    Parameters:
    
    batchSize -
    
    Returns:
  - iterations
```
public SequenceVectors.Builder<T> iterations(int iterations)
```
    This method defines how much iterations should be done over batched sequences.
    
    Parameters:
    
    iterations -
    
    Returns:
  - epochs
```
public SequenceVectors.Builder<T> epochs(int numEpochs)
```
    This method defines how much iterations should be done over whole training corpus during modelling
    
    Parameters:
    
    numEpochs -
    
    Returns:
  - workers
```
public SequenceVectors.Builder<T> workers(int numWorkers)
```
    Sets number of worker threads to be used in calculations
    
    Parameters:
    
    numWorkers -
    
    Returns:
  - useHierarchicSoftmax
```
public SequenceVectors.Builder<T> useHierarchicSoftmax(boolean reallyUse)
```
    Enable/disable hierarchic softmax
    
    Parameters:
    
    reallyUse -
    
    Returns:
  - useAdaGrad
```
@Deprecated
public SequenceVectors.Builder<T> useAdaGrad(boolean reallyUse)
```
    Deprecated.
    
    This method defines if Adaptive Gradients should be used in calculations
    
    Parameters:
    
    reallyUse -
    
    Returns:
  - layerSize
```
public SequenceVectors.Builder<T> layerSize(int layerSize)
```
    This method defines number of dimensions for outcome vectors. Please note: This option has effect only if lookupTable wasn't defined during building process.
    
    Parameters:
    
    layerSize -
    
    Returns:
  - learningRate
```
public SequenceVectors.Builder<T> learningRate(double learningRate)
```
    This method defines initial learning rate. Default value is 0.025
    
    Parameters:
    
    learningRate -
    
    Returns:
  - minWordFrequency
```
public SequenceVectors.Builder<T> minWordFrequency(int minWordFrequency)
```
    This method defines minimal element frequency for elements found in the training corpus. All elements with frequency below this threshold will be removed before training. Please note: this method has effect only if vocabulary is built internally.
    
    Parameters:
    
    minWordFrequency -
    
    Returns:
  - minLearningRate
```
public SequenceVectors.Builder<T> minLearningRate(double minLearningRate)
```
    This method defines minimum learning rate after decay being applied. Default value is 0.01
    
    Parameters:
    
    minLearningRate -
    
    Returns:
  - resetModel
```
public SequenceVectors.Builder<T> resetModel(boolean reallyReset)
```
    This method defines, should all model be reset before training. If set to true, vocabulary and WeightLookupTable will be reset before training, and will be built from scratches
    
    Parameters:
    
    reallyReset -
    
    Returns:
  - vocabCache
```
public SequenceVectors.Builder<T> vocabCache(@NonNull
                                             VocabCache<T> vocabCache)
```
    You can pass externally built vocabCache object, containing vocabulary
    
    Parameters:
    
    vocabCache -
    
    Returns:
  - lookupTable
```
public SequenceVectors.Builder<T> lookupTable(@NonNull
                                              WeightLookupTable<T> lookupTable)
```
    You can pass externally built WeightLookupTable, containing model weights and vocabulary.
    
    Parameters:
    
    lookupTable -
    
    Returns:
  - sampling
```
public SequenceVectors.Builder<T> sampling(double sampling)
```
    This method defines sub-sampling threshold.
    
    Parameters:
    
    sampling -
    
    Returns:
  - negativeSample
```
public SequenceVectors.Builder<T> negativeSample(double negative)
```
    This method defines negative sampling value for skip-gram algorithm.
    
    Parameters:
    
    negative -
    
    Returns:
  - stopWords
```
public SequenceVectors.Builder<T> stopWords(@NonNull
                                            java.util.List<java.lang.String> stopList)
```
    You can provide collection of objects to be ignored, and excluded out of model Please note: Object labels and hashCode will be used for filtering
    
    Parameters:
    
    stopList -
    
    Returns:
  - trainElementsRepresentation
```
public SequenceVectors.Builder<T> trainElementsRepresentation(boolean trainElements)
```
    Parameters:
    
    trainElements -
    
    Returns:
  - trainSequencesRepresentation
```
public SequenceVectors.Builder<T> trainSequencesRepresentation(boolean trainSequences)
```
  - stopWords
```
public SequenceVectors.Builder<T> stopWords(@NonNull
                                            java.util.Collection<T> stopList)
```
    You can provide collection of objects to be ignored, and excluded out of model Please note: Object labels and hashCode will be used for filtering
    
    Parameters:
    
    stopList -
    
    Returns:
  - windowSize
```
public SequenceVectors.Builder<T> windowSize(int windowSize)
```
    Sets window size for skip-Gram training
    
    Parameters:
    
    windowSize -
    
    Returns:
  - seed
```
public SequenceVectors.Builder<T> seed(long randomSeed)
```
    Sets seed for random numbers generator. Please note: this has effect only if vocabulary and WeightLookupTable is built internally
    
    Parameters:
    
    randomSeed -
    
    Returns:
  - modelUtils
```
public SequenceVectors.Builder<T> modelUtils(@NonNull
                                             ModelUtils<T> modelUtils)
```
    ModelUtils implementation, that will be used to access model. Methods like: similarity, wordsNearest, accuracy are provided by user-defined ModelUtils
    
    Parameters:
    
    modelUtils - model utils to be used
    
    Returns:
  - useUnknown
```
public SequenceVectors.Builder<T> useUnknown(boolean reallyUse)
```
    This method allows you to specify, if UNK word should be used internally
    
    Parameters:
    
    reallyUse -
    
    Returns:
  - unknownElement
```
public SequenceVectors.Builder<T> unknownElement(@NonNull
                                                 T element)
```
    This method allows you to specify SequenceElement that will be used as UNK element, if UNK is used
    
    Parameters:
    
    element -
    
    Returns:
  - useVariableWindow
```
public SequenceVectors.Builder<T> useVariableWindow(int... windows)
```
    This method allows to use variable window size. In this case, every batch gets processed using one of predefined window sizes
    
    Parameters:
    
    windows -
    
    Returns:
  - usePreciseWeightInit
```
public SequenceVectors.Builder<T> usePreciseWeightInit(boolean reallyUse)
```
    If set to true, initial weights for elements/sequences will be derived from elements themself. However, this implies additional cycle through input iterator. Default value: FALSE
    
    Parameters:
    
    reallyUse -
    
    Returns:
  - presetTables
```
protected void presetTables()
```
    This method creates new WeightLookupTable and VocabCache if there were none set
  - setVectorsListeners
```
public SequenceVectors.Builder<T> setVectorsListeners(@NonNull
                                                      java.util.Collection<VectorsListener<T>> listeners)
```
    This method sets VectorsListeners for this SequenceVectors model
    
    Parameters:
    
    listeners -
    
    Returns:
  - enableScavenger
```
public SequenceVectors.Builder<T> enableScavenger(boolean reallyEnable)
```
    This method ebables/disables periodical vocab truncation during construction Default value: disabled
    
    Parameters:
    
    reallyEnable -
    
    Returns:
  - build
```
public SequenceVectors<T> build()
```
    Build SequenceVectors instance with defined settings/options
    
    Returns:

Class SequenceVectors.Builder<T extends SequenceElement>

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

vocabCache

lookupTable

iterator

modelUtils

existingVectors

sampling

negative

learningRate

minLearningRate

minWordFrequency

iterations

numEpochs

layerSize

window

hugeModelExpected

batchSize

learningRateDecayWords

seed

useAdaGrad

resetModel

workers

useUnknown

useHierarchicSoftmax

variableWindows

trainSequenceVectors

trainElementsVectors

preciseWeightInit

stopWords

configuration

unknownElement

UNK

STOP

enableScavenger

elementsLearningAlgorithm

sequenceLearningAlgorithm

vectorsListeners

Constructor Detail

Builder

Builder

Method Detail

useExistingWordVectors

iterate

sequenceLearningAlgorithm

sequenceLearningAlgorithm

elementsLearningAlgorithm

elementsLearningAlgorithm

batchSize

iterations

epochs

workers

useHierarchicSoftmax

useAdaGrad

layerSize

learningRate

minWordFrequency

minLearningRate

resetModel

vocabCache

lookupTable

sampling

negativeSample

stopWords

trainElementsRepresentation

trainSequencesRepresentation

stopWords

windowSize

seed

modelUtils

useUnknown

unknownElement

useVariableWindow

usePreciseWeightInit

presetTables

setVectorsListeners