Class TextData

lstm-text-generation/data.js:53–237

 *   models and obtaining the seed text for model-based text generation.
 */
export class TextData {
  /**
   * Constructor of TextData.
   *
   * @param {string} dataIdentifier An identifier for this instance of TextData.
   * @param {string} textString The training text data.
   * @param {number} sampleLen Length of each training example, i.e., the input
   *   sequence length expected by the LSTM model.
   * @param {number} sampleStep How many characters to skip when going from one
   *   example of the training data (in `textString`) to the next.
   */
  constructor(dataIdentifier, textString, sampleLen, sampleStep) {
    tf.util.assert(
        sampleLen > 0,
        `Expected sampleLen to be a positive integer, but got ${sampleLen}`);
    tf.util.assert(
        sampleStep > 0,
        `Expected sampleStep to be a positive integer, but got ${sampleStep}`);

    if (!dataIdentifier) {
      throw new Error('Model identifier is not provided.');
    }

    this.dataIdentifier_ = dataIdentifier;

    this.textString_ = textString;
    this.textLen_ = textString.length;
    this.sampleLen_ = sampleLen;
    this.sampleStep_ = sampleStep;

    this.getCharSet_();
    this.convertAllTextToIndices_();
  }

  /**
   * Get data identifier.
   *
   * @returns {string} The data identifier.
   */
  dataIdentifier() {
    return this.dataIdentifier_;
  }

  /**
   * Get length of the training text data.
   *
   * @returns {number} Length of training text data.
   */
  textLen() {
    return this.textLen_;
  }

  /**
   * Get the length of each training example.
   */
  sampleLen() {
    return this.sampleLen_;
  }