def run_precision_recall_analysis()

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

• 34 lines of code
• 7 McCabe index (conditional complexity)

def run_precision_recall_analysis(main_eval, exact_raw, f1_raw, na_probs, qid_to_has_ans, out_image_dir):
    if out_image_dir and not os.path.exists(out_image_dir):
        os.makedirs(out_image_dir)
    num_true_pos = sum(1 for v in qid_to_has_ans.values() if v)
    if num_true_pos == 0:
        return
    pr_exact = make_precision_recall_eval(
        exact_raw,
        na_probs,
        num_true_pos,
        qid_to_has_ans,
        out_image=os.path.join(out_image_dir, "pr_exact.png"),
        title="Precision-Recall curve for Exact Match score",
    )
    pr_f1 = make_precision_recall_eval(
        f1_raw,
        na_probs,
        num_true_pos,
        qid_to_has_ans,
        out_image=os.path.join(out_image_dir, "pr_f1.png"),
        title="Precision-Recall curve for F1 score",
    )
    oracle_scores = {k: float(v) for k, v in qid_to_has_ans.items()}
    pr_oracle = make_precision_recall_eval(
        oracle_scores,
        na_probs,
        num_true_pos,
        qid_to_has_ans,
        out_image=os.path.join(out_image_dir, "pr_oracle.png"),
        title="Oracle Precision-Recall curve (binary task of HasAns vs. NoAns)",
    )
    merge_eval(main_eval, pr_exact, "pr_exact")
    merge_eval(main_eval, pr_f1, "pr_f1")
    merge_eval(main_eval, pr_oracle, "pr_oracle")