import json

import csv



def convert_to_alpaca_format(input_file, output_file):
    """
    读取csv文件，提取其中的question和answer列的数据，并转换为 Alpaca 格式。

    输入csv格式:
    question,A,B,C,D,E,F,G,H,I,J,answer

    输出格式 (swift):
    {
        "system": "你是个优秀的论文分类师",
        "conversation": [
            {
                "human": "Based on the title...",
                "assistant": "D"
            }
        ]
    }
    """
    print(f"转换数据: {input_file} -> {output_file}")

    converted_data = []
    with open(input_file, "r", encoding="utf-8") as f:
        csv_reader = csv.DictReader(f)
        for row in csv_reader:
            try:
                # 检查必要的列是否存在
                if "question" not in row or "answer" not in row:
                    print(f"警告: 数据缺少必要列: {row}")
                    continue

                # 创建新的 swift 格式数据
                


                
                new_data = {
                    
                    "messages": [
                        {
                            "role": "assistant",
                            "content": "This is a paper titled " + row["question"][19:] 
                            #"assistant": row["answer"]
                        }
                    ]
                }
                converted_data.append(new_data)

            except Exception as e:
                print(f"处理行时发生错误: {str(e)}")

    # 写入输出文件
    with open(output_file, "w", encoding="utf-8") as f:
        for item in converted_data:
            f.write(json.dumps(item, ensure_ascii=False) + "\n")

    print(f"转换完成! 共转换 {len(converted_data)} 条数据")

if __name__ == "__main__":
    # parser = argparse.ArgumentParser(description="转换数据到Alpaca格式")
    # parser.add_argument(
    #     "--input",
    #     type=str,
    #     required=True,
    #     help="输入文件路径 (swift_formatted_sft_train_data.jsonl)",
    # )
    # parser.add_argument("--output", type=str, required=True, help="输出文件路径")

    # args = parser.parse_args()

    #input_file = "arxiv-metadata-oai-snapshot--random.json"   # 20000条原始数据文件路径
    input_file = "newformat_sft_test_data.csv"
    output_file = "newformat_sft_test_data--swift-pretrain.jsonl"  # 输出文件路径

    convert_to_alpaca_format(input_file, output_file)