def _compute()

in metrics/squad_v2/squad_v2.py [0:0]

• 19 lines of code
• 9 McCabe index (conditional complexity)

    def _compute(self, predictions, references, no_answer_threshold=1.0):
        no_answer_probabilities = {p["id"]: p["no_answer_probability"] for p in predictions}
        dataset = [{"paragraphs": [{"qas": references}]}]
        predictions = {p["id"]: p["prediction_text"] for p in predictions}

        qid_to_has_ans = make_qid_to_has_ans(dataset)  # maps qid to True/False
        has_ans_qids = [k for k, v in qid_to_has_ans.items() if v]
        no_ans_qids = [k for k, v in qid_to_has_ans.items() if not v]

        exact_raw, f1_raw = get_raw_scores(dataset, predictions)
        exact_thresh = apply_no_ans_threshold(exact_raw, no_answer_probabilities, qid_to_has_ans, no_answer_threshold)
        f1_thresh = apply_no_ans_threshold(f1_raw, no_answer_probabilities, qid_to_has_ans, no_answer_threshold)
        out_eval = make_eval_dict(exact_thresh, f1_thresh)

        if has_ans_qids:
            has_ans_eval = make_eval_dict(exact_thresh, f1_thresh, qid_list=has_ans_qids)
            merge_eval(out_eval, has_ans_eval, "HasAns")
        if no_ans_qids:
            no_ans_eval = make_eval_dict(exact_thresh, f1_thresh, qid_list=no_ans_qids)
            merge_eval(out_eval, no_ans_eval, "NoAns")
        find_all_best_thresh(out_eval, predictions, exact_raw, f1_raw, no_answer_probabilities, qid_to_has_ans)
        return dict(out_eval)