weka.dl4j.iterators.instance.sequence.text.rnn

Class RnnTextFilesEmbeddingInstanceIterator

java.lang.Object

weka.dl4j.iterators.instance.AbstractInstanceIterator

weka.dl4j.iterators.instance.sequence.AbstractSequenceInstanceIterator

weka.dl4j.iterators.instance.sequence.text.AbstractTextEmbeddingIterator

weka.dl4j.iterators.instance.sequence.text.rnn.RnnTextEmbeddingInstanceIterator

weka.dl4j.iterators.instance.sequence.text.rnn.RnnTextFilesEmbeddingInstanceIterator

All Implemented Interfaces:

java.io.Serializable, weka.core.OptionHandler

public class RnnTextFilesEmbeddingInstanceIterator
extends RnnTextEmbeddingInstanceIterator

Converts the given Instances object into a DataSet and then constructs and returns a RnnTextEmbeddingInstanceIterator.

Assumes the instance object has the following two attributes:

• Path to text file
• Class

See Also:

Serialized Form

Field Summary

Fields inherited from class weka.dl4j.iterators.instance.sequence.text.AbstractTextEmbeddingIterator

wordVectors

Constructor Summary

Constructors

Constructor and Description
RnnTextFilesEmbeddingInstanceIterator()

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.dataset.api.iterator.DataSetIterator	getDataSetIterator(weka.core.Instances data, int seed, int batchSize) Returns the actual iterator.
java.lang.String[]	getOptions() Gets the current settings of the Classifier.
org.deeplearning4j.iterator.LabeledSentenceProvider	getSentenceProvider(weka.core.Instances data) Create a sentence provider from the given data.
java.io.File	getTextsLocation()
java.lang.String	globalInfo()
java.util.Enumeration<weka.core.Option>	listOptions() Returns an enumeration describing the available options.
void	setOptions(java.lang.String[] options) Parses a given list of options.
void	setTextsLocation(java.io.File textsLocation)
void	validate(weka.core.Instances data) Validates the input dataset

Methods inherited from class weka.dl4j.iterators.instance.sequence.text.rnn.RnnTextEmbeddingInstanceIterator

initialize

Methods inherited from class weka.dl4j.iterators.instance.sequence.text.AbstractTextEmbeddingIterator

getStopwords, getTokenizerFactory, getTokenPreProcess, getTruncateLength, getWordVectorLocation, getWordVectors, initWordVectors, setStopwords, setTokenizerFactory, setTokenPreProcess, setTruncateLength, setWordVectorLocation, setWordVectors

Methods inherited from class weka.dl4j.iterators.instance.AbstractInstanceIterator

getDataSetIterator, getTrainBatchSize, setTrainBatchSize

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

RnnTextFilesEmbeddingInstanceIterator

public RnnTextFilesEmbeddingInstanceIterator()

Method Detail

getDataSetIterator

public org.nd4j.linalg.dataset.api.iterator.DataSetIterator getDataSetIterator(weka.core.Instances data,
                                                                               int seed,
                                                                               int batchSize)
                                                                        throws InvalidInputDataException,
                                                                               java.io.IOException

Description copied from class: RnnTextEmbeddingInstanceIterator

Returns the actual iterator.

Overrides:

getDataSetIterator in class RnnTextEmbeddingInstanceIterator

Parameters:

data - the dataset to use

seed - the seed for the random number generator

batchSize - the batch size to use

Returns:

the DataSetIterator

Throws:

InvalidInputDataException

java.io.IOException

getSentenceProvider

public org.deeplearning4j.iterator.LabeledSentenceProvider getSentenceProvider(weka.core.Instances data)

Description copied from class: AbstractTextEmbeddingIterator

Create a sentence provider from the given data.

Overrides:

getSentenceProvider in class AbstractTextEmbeddingIterator

Parameters:

data - Data

Returns:

Sentence provider

validate

public void validate(weka.core.Instances data)
              throws InvalidInputDataException

Validates the input dataset

Overrides:

validate in class RnnTextEmbeddingInstanceIterator

Parameters:

data - the input dataset

Throws:

InvalidInputDataException - if validation is unsuccessful

getTextsLocation

@OptionMetadata(displayName="directory of text files",
                description="The directory containing the text files (default = user home).",
                commandLineParamName="textsLocation",
                commandLineParamSynopsis="-textsLocation <string>",
                displayOrder=3)
public java.io.File getTextsLocation()

setTextsLocation

public void setTextsLocation(java.io.File textsLocation)

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface weka.core.OptionHandler

Overrides:

listOptions in class RnnTextEmbeddingInstanceIterator

Returns:

an enumeration of all the available options.

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the Classifier.

Specified by:

getOptions in interface weka.core.OptionHandler

Overrides:

getOptions in class RnnTextEmbeddingInstanceIterator

Returns:

an array of strings suitable for passing to setOptions

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Specified by:

setOptions in interface weka.core.OptionHandler

Overrides:

setOptions in class RnnTextEmbeddingInstanceIterator

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

globalInfo

public java.lang.String globalInfo()

Overrides:

globalInfo in class RnnTextEmbeddingInstanceIterator