How to use the @tensorflow/tfjs-node.oneHot function in @tensorflow/tfjs-node

private *predictInternal(functionDecl: string) {
    const { ast: astTokens, comments: commentTokens } = this.tokenizers;
    const {
      max_ast_len,
      max_comment_len,
      ast_vocab_size,
      comment_vocab_size,
      character_tokenizer
    } = this.tokenizers.params;

    const ast = this.ast(functionDecl);
    const astVector = ast
      .split(' ')
      .slice(0, max_ast_len)
      .map((token) => (token in astTokens ? astTokens[token] : astTokens['UNK']));
    const inputSeq = tf
      .oneHot(astVector, ast_vocab_size)
      .pad([[0, max_ast_len - astVector.length], [0, 0]])
      .expandDims();
    let statesValues = this.encoderModel.predict(inputSeq) as tf.Tensor[];

    const startToken = character_tokenizer ? '/' : '';
    const startTokenValue = parseInt(
      Object.keys(commentTokens).find((k) => commentTokens[k] === startToken)!,
      10
    );
    if (character_tokenizer) {
      yield startToken;
    }

    // Populate the first character of target sequence with the start character.
    let targetSeq = tf.oneHot([startTokenValue], comment_vocab_size).expandDims();

function convertToTensors(featuresData, labelData, testSplit) {
  if (featuresData.length !== labelData.length) {
    throw new Error('features set and labels set have different numbers of examples');
  }

  const [shuffledFeatures, shuffledLabels] = shuffleData(featuresData, labelData);

  const featuresTensor = tf.tensor2d(shuffledFeatures, [numSamplesPerGesture, totalNumDataPerFile]);

  // Create a 1D `tf.Tensor` to hold the labels, and convert the number label
  // from the set {0, 1, 2} into one-hot encoding (.e.g., 0 --> [1, 0, 0]).
  const labelsTensor = tf.oneHot(tf.tensor1d(shuffledLabels).toInt(), numClasses);

  return split(featuresTensor, labelsTensor, testSplit);
}

yield nextWord;
      } else if (nextWord == '' || nextWord === '') {
        yield '\n';
        firstInLine = true;
      } else if (nextWord[0] === '>') {
        const space = firstInLine || prevWord[0] === '>' ? '' : ' ';
        yield space + nextWord[1];
        firstInLine = false;
      } else {
        const space = firstInLine ? '' : ' ';
        yield space + nextWord;
        firstInLine = false;
      }
      prevWord = nextWord;

      targetSeq = tf.oneHot([sampled_token_index], comment_vocab_size).expandDims();
      statesValues = [h, c];
    }
  }