def make_precision_recall_eval()

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

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

def make_precision_recall_eval(scores, na_probs, num_true_pos, qid_to_has_ans, out_image=None, title=None):
    qid_list = sorted(na_probs, key=lambda k: na_probs[k])
    true_pos = 0.0
    cur_p = 1.0
    cur_r = 0.0
    precisions = [1.0]
    recalls = [0.0]
    avg_prec = 0.0
    for i, qid in enumerate(qid_list):
        if qid_to_has_ans[qid]:
            true_pos += scores[qid]
        cur_p = true_pos / float(i + 1)
        cur_r = true_pos / float(num_true_pos)
        if i == len(qid_list) - 1 or na_probs[qid] != na_probs[qid_list[i + 1]]:
            # i.e., if we can put a threshold after this point
            avg_prec += cur_p * (cur_r - recalls[-1])
            precisions.append(cur_p)
            recalls.append(cur_r)
    if out_image:
        plot_pr_curve(precisions, recalls, out_image, title)
    return {"ap": 100.0 * avg_prec}