Class Word2Vec

constructor

• new Word2Vec(
      method: "CBOW" | "skip-gram",
      n: number,
      wordsOrNumber: number | string[],
      reduce_size: number,
      optimizer: string,
  ): Word2Vec

• Parameters

  • method: "CBOW" | "skip-gram"

    Method name
  • n: number

    Number of how many adjacent words to learn
  • wordsOrNumber: number | string[]

    Initial words or number of words
  • reduce_size: number

    Reduced dimension
  • optimizer: string

    Optimizer of the network

  Returns Word2Vec

_epoch

_layers

_method

_model

_n

_words

_wordsIdx

_wordsNumber

epoch

• get epoch(): number

• Epoch

  Returns number

fit

• fit(words: string[], iteration: number, rate: number, batch: number): number

• Fit model.

  Parameters

  • words: string[]

    Training data
  • iteration: number

    Iteration count
  • rate: number

    Learning rate
  • batch: number

    Batch size

  Returns number

  Loss value

predict

• predict(x: string[]): number[][]

• Returns predicted values.

  Parameters

  • x: string[]

    Sample data

  Returns number[][]

  Predicted values

reduce

• reduce(x: string[]): number[][]

• Returns reduced values.

  Parameters

  • x: string[]

    Sample data

  Returns number[][]

  Predicted values