How to use the simpletransformers.ner.ner_utils.read_examples_from_file function in simpletransformers

evaluate (optional): Indicates whether the examples are for evaluation or for training.
            no_cache (optional): Force feature conversion and prevent caching. I.e. Ignore cached features even if present.

        """

        process_count = self.args["process_count"]

        tokenizer = self.tokenizer
        output_mode = "classification"
        args = self.args

        mode = "dev" if evaluate else "train"

        if not to_predict:
            if isinstance(data, str):
                examples = read_examples_from_file(data, mode)
            else:
                examples = get_examples_from_df(data)
        else:
            examples = to_predict
            no_cache = True

        cached_features_file = os.path.join(args["cache_dir"], "cached_{}_{}_{}_{}_{}".format(mode, args["model_type"], args["max_seq_length"], self.num_labels, len(examples)))

        if not os.path.isdir(self.args["cache_dir"]):
            os.mkdir(self.args["cache_dir"])

        if os.path.exists(cached_features_file) and not args["reprocess_input_data"] and not no_cache:
            features = torch.load(cached_features_file)
            print(f"Features loaded from cache at {cached_features_file}")
        else:
            print(f"Converting to features started.")