ai.djl.basicdataset.utils

Class TextData

java.lang.Object

ai.djl.basicdataset.utils.TextData

public class TextData
extends java.lang.Object

TextData is a utility for managing textual data within a Dataset.

See TextDataset for an example.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	TextData.Configuration The configuration for creating a TextData value in a Dataset.

Constructor Summary

Constructors

Constructor and Description
TextData(TextData.Configuration config) Constructs a new TextData.

Method Summary

Modifier and Type	Method and Description
static TextData.Configuration	getDefaultConfiguration() Returns a good default TextData.Configuration to use for the constructor with defaults.
ai.djl.ndarray.NDArray	getEmbedding(ai.djl.ndarray.NDManager manager, long index) Gets the text embedding for the given index of the text input.
java.util.List<java.lang.String>	getProcessedText(long index) Gets the textual input after preprocessing.
java.lang.String	getRawText(long index) Gets the raw textual input.
int	getSize() Returns the size of the data.
ai.djl.modality.nlp.embedding.TextEmbedding	getTextEmbedding() Gets the TextEmbedding used to embed the data with.
ai.djl.modality.nlp.Vocabulary	getVocabulary() Gets the SimpleVocabulary built while preprocessing the text data.
void	preprocess(ai.djl.ndarray.NDManager manager, java.util.List<java.lang.String> newTextData) Preprocess the textData into NDArray by providing the data from the dataset.
void	setEmbeddingSize(int embeddingSize) Sets the embedding size.
void	setTextEmbedding(ai.djl.modality.nlp.embedding.TextEmbedding textEmbedding) Sets the textEmbedding to embed the data with.
void	setTextProcessors(java.util.List<ai.djl.modality.nlp.preprocess.TextProcessor> textProcessors) Sets the text processors.

Methods inherited from class java.lang.Object

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

Constructor Detail

TextData

public TextData(TextData.Configuration config)

Constructs a new TextData.

Parameters:

config - the configuration for the TextData

Method Detail

getDefaultConfiguration

public static TextData.Configuration getDefaultConfiguration()

Returns a good default TextData.Configuration to use for the constructor with defaults.

Returns:

a good default TextData.Configuration to use for the constructor with defaults

preprocess

public void preprocess(ai.djl.ndarray.NDManager manager,
                       java.util.List<java.lang.String> newTextData)
                throws ai.djl.modality.nlp.embedding.EmbeddingException

Preprocess the textData into NDArray by providing the data from the dataset.

Parameters:

manager - the

newTextData - the data from the dataset

Throws:

ai.djl.modality.nlp.embedding.EmbeddingException - if there is an error while embedding input

setTextProcessors

public void setTextProcessors(java.util.List<ai.djl.modality.nlp.preprocess.TextProcessor> textProcessors)

Sets the text processors.

Parameters:

textProcessors - the new textProcessors

setTextEmbedding

public void setTextEmbedding(ai.djl.modality.nlp.embedding.TextEmbedding textEmbedding)

Sets the textEmbedding to embed the data with.

Parameters:

textEmbedding - the textEmbedding

getTextEmbedding

public ai.djl.modality.nlp.embedding.TextEmbedding getTextEmbedding()

Gets the TextEmbedding used to embed the data with.

Returns:

the TextEmbedding

setEmbeddingSize

public void setEmbeddingSize(int embeddingSize)

Sets the embedding size.

Parameters:

embeddingSize - the embedding size

getVocabulary

public ai.djl.modality.nlp.Vocabulary getVocabulary()

Gets the SimpleVocabulary built while preprocessing the text data.

Returns:

the SimpleVocabulary

getEmbedding

public ai.djl.ndarray.NDArray getEmbedding(ai.djl.ndarray.NDManager manager,
                                           long index)

Gets the text embedding for the given index of the text input.

Parameters:

manager - the manager for the embedding array

index - the index of the text input

Returns:

the NDArray containing the text embedding

getRawText

public java.lang.String getRawText(long index)

Gets the raw textual input.

Parameters:

index - the index of the text input

Returns:

the raw text

getProcessedText

public java.util.List<java.lang.String> getProcessedText(long index)

Gets the textual input after preprocessing.

Parameters:

index - the index of the text input

Returns:

the list of processed tokens

getSize

public int getSize()

Returns the size of the data.

Returns:

the size of the data