def compute_finqa()

in utils/compute_score.py [0:0]

• 32 lines of code
• 6 McCabe index (conditional complexity)

def compute_finqa(file_path):
    references = []
    candidates = []

    sub_task_references = {}
    sub_task_candidates = {}

    with open(file_path, 'r', encoding='utf-8') as input_file:
        print("Reading\t" + file_path)
        sample_list = json.load(input_file)
        samples = pd.json_normalize(sample_list, 'outputs')
        for _, line in samples.iterrows():
            if line['__raw.task'] == '金融咨询':
                # compute all score
                if not line['response']:
                    line['response'] = 'None'
                references.append(" ".join(jieba.lcut(line['__raw.output'])))
                candidates.append(" ".join(jieba.lcut(line['response'])))

                # compute sub_task score
                sub_task = line['__raw.sub_task']
                if sub_task not in sub_task_references:
                    sub_task_references[sub_task] = []
                    sub_task_candidates[sub_task] = []
                sub_task_references[sub_task].append(" ".join(jieba.lcut(line['__raw.output'])))
                sub_task_candidates[sub_task].append(" ".join(jieba.lcut(line['response'])))

        # result
        print(f"task: 金融咨询")
        _, _, rougel = rouge_score(references, candidates)
        bert = bert_score(references, candidates)
        print('\n')

        sub_task_qa, sub_task_bert = {}, {}
        for sub_task, refs in sub_task_references.items():
            print(f"Sub-task: {sub_task}")
            candidates = sub_task_candidates[sub_task]
            _, _, rouge_l = rouge_score(refs, candidates)
            print('\n')
    return rougel, bert