class TFRecordGenerator:
    def __init__(
        self,
        dataset_type,
        texts,
        tokenizer,
        labels=None,
        max_len=220,
        chunk_size=100000,
        f_name="train.tfrecord",
        out_path="/kaggle/working",
    ):

        # Set parameters
        self.dataset_type = str(dataset_type).upper()
        self.texts = texts
        self.labels = labels
        self.tokenizer = tokenizer
        self.max_len = max_len
        self.chunk_size = chunk_size
        self.tfrecord_file_path = os.path.join(out_path, f_name)
        self.data_size = len(self.texts)
        self._check_data()