nlp/com.londogard.nlp.embeddings/LightWordEmbeddings

LightWordEmbeddings

public final class LightWordEmbeddings implements Embeddings

Retrieves vectors from disc ad-hoc and caches the maxWordCount results in memory based on most active cache keys. Works very well in constrained environments like a Raspberry Pi.

Constructors

LightWordEmbeddings

public LightWordEmbeddings LightWordEmbeddings( Path filePath, Integer dimensions, Character delimiter, Integer maxWordCount)

Functions

addWords

public final Unit addWords(Set<String> words)

contains

public Boolean contains(String word)

Check if the word has an embedding.

cosineDistance

public Float cosineDistance(String w1, String w2)

euclideanDistance

public Float euclideanDistance(String w1, String w2)

getDelimiter

public Character getDelimiter()

getDimensions

public Integer getDimensions()

getEmbeddings

public Map<String, NDArray<Float, D1>> getEmbeddings()

getFilePath

public Path getFilePath()

getVocabulary

public Set<String> getVocabulary()

traverseVectors

public List<NDArray<Float, D1>> traverseVectors(List<String> words)

traverseVectorsOrNull

public List<NDArray<Float, D1>> traverseVectorsOrNull(List<String> words)

vector

public NDArray<Float, D1> vector(String word)

Fetches Embedding if it exists for word

Properties

delimiter

private final Character delimiter

dimensions

private final Integer dimensions

embeddings

private final Map<String, NDArray<Float, D1>> embeddings

filePath

private final Path filePath

vocabulary

private final Set<String> vocabulary