from mmengine.config import read_base
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import MMLUProDataset
from opencompass.utils.text_postprocessors import match_answer_pattern

with read_base():
    from .mmlu_pro_categories import categories



QUERY_TEMPLATE = """
Answer the following multiple choice question. Your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of Options(e.g. one of ABCDEFGHIJKLMNOP). Please answer directly without additional explanations.

Question:\n
{question}

Options:\n
{options_str}

""".strip()

mmlu_pro_datasets = []

for category in categories:
    mmlu_pro_reader_cfg = dict(
        input_columns=['question', 'cot_content', 'options_str'],
        output_column='answer',
        train_split='validation',
        test_split='test',
    )
    mmlu_pro_infer_cfg = dict(
        prompt_template=dict(
            type=PromptTemplate,
            template=dict(
                round=[
                    dict(role='HUMAN',
                         prompt=QUERY_TEMPLATE),
                ],
            ),
        ),
        retriever=dict(type=ZeroRetriever),
        inferencer=dict(type=GenInferencer),
    )

    mmlu_pro_eval_cfg = dict(
        evaluator=dict(type=AccEvaluator),
        pred_postprocessor=dict(
            type=match_answer_pattern,
            answer_pattern=r'(?i)ANSWER\s*:\s*([A-P])')
    )

    mmlu_pro_datasets.append(
        dict(
            abbr=f'mmlu_pro_{category.replace(" ", "_")}',
            type=MMLUProDataset,
            path='opencompass/mmlu_pro',
            category=category,
            reader_cfg=mmlu_pro_reader_cfg,
            infer_cfg=mmlu_pro_infer_cfg,
            eval_cfg=mmlu_pro_eval_cfg,
        ))