Home Reference Source Test
public class | source

CausalNetEmbedding

You can directly use an instance of this class. causalNetEmbedding

Extends:

* → CausalNetEmbedding

This CausalNetEmbedding provide methods for transform raw tokenized sentence into its single vector representation mixWith: [ StorageMixins, MemCacheMixins, TokenLookUpMixins, ChunkLookUpMixins, WordEmbeddingMixins ])}

Example:

import { causalNetEmbedding } from 'causal-net.representation';
import { termLogger } from 'causal-net.log';
(async ()=>{
    const configLink = '../../datasets/WordVec_EN/';
    await causalNetEmbedding.connect(configLink, true);
    //first time transform will find on storage cache
    let vecs = await causalNetEmbedding.transform(['this', 'is', 'test']);
    for(let vec of vecs){
        termLogger.log({ vec });
    }
    //second time transform will find on memory cache
    vecs = await causalNetEmbedding.transform(['this', 'is', 'test']);
    for(let vec of vecs){
        termLogger.log({ vec });
    }
    //return the tensor representing sentence
    let sentVec = await causalNetEmbedding.sentenceEncode([ ['this', 'is', 'test'] ]);
    sentVec.print();
})().catch(err=>{
    console.error(err);
});

Test:

Constructor Summary

Public Constructor
public

Member Summary

Public Members
public

F: *

public
public

R: *

public

Storage: *

public
public get

VecSize: *

Return veczie in positive number
public
public
public
public
public

fetch: *

public

vecsize: *

Method Summary

Public Methods
public

async connect(link: URL | FilePath , refresh: boolean ): Promise

Load configure of pretrained vector from either local folder or remote server.
Private Methods
private

async getDescription(forceFecth: boolean): *

This method is called by connect
private

async query(link: *): *

fetch or read configure depends on provied link format
private

async queryDescription(): Object

query the description json

Public Constructors

public constructor() source

Public Members

public F: * source

public MemCache: * source

public R: * source

public Storage: * source

public TokenChunkIdMapper: * source

public get VecSize: * source

Return veczie in positive number

public description: * source

public embeddingDescriptionPath: * source

public embeddingSavePath: string source

public fetch: * source

public vecsize: * source

Public Methods

public async connect(link: URL | FilePath , refresh: boolean ): Promise source

Load configure of pretrained vector from either local folder or remote server. After connect, the result is cached for next time init.

Params:

NameTypeAttributeDescription
link URL | FilePath

link to load
refresh boolean
  • optional
  • default: false

force to discard local cache

Return:

Promise

Private Methods

private async getDescription(forceFecth: boolean): * source

This method is called by connect

Params:

NameTypeAttributeDescription
forceFecth boolean
  • optional
  • default: false

Return:

*

private async query(link: *): * source

fetch or read configure depends on provied link format

Params:

NameTypeAttributeDescription
link *

Return:

*

private async queryDescription(): Object source

query the description json

Return:

Object

description json object