import os
import pandas as pd
from tqdm import tqdm

# 指定文件夹路径
folder_path = 'C:\\Users\\H610M-F\\Desktop\\MCServer\\logs\\RawBehaviorLog\\BehaviorLog-2023-1001-1031'

# 获取文件列表
file_list = os.listdir(folder_path)

# 创建一个空的字典用于存储每个游戏名字的符合条件的记录总数
total_records_dict = {}

# 遍历文件列表并加入进度条
for file_name in tqdm(file_list, desc='Processing files', unit='file'):
    if not file_name.endswith('.csv'):
        continue
    # 拼接文件路径
    file_path = os.path.join(folder_path, file_name)
    
    # 读取CSV文件
    df = pd.read_csv(file_path, on_bad_lines='skip')
    
    # 将时间列转换为 pandas 的 datetime 类型
    df['时间'] = pd.to_datetime(df['时间'], errors='coerce')

    # 筛选出事件为 '破坏方块' 且类型为 'minecraft:deepslate_diamond_ore' 的数据
    filtered_data = df[(df['事件'] == '破坏方块') & (df['目标'] == 'minecraft:ancient_debris')]

    # 对每个游戏名字进行计数，得到符合条件的记录总数
    for game_name in filtered_data['主体'].unique():
        total_records = filtered_data[filtered_data['主体'] == game_name].shape[0]
        
        # 更新字典中的记录总数统计
        if game_name in total_records_dict:
            total_records_dict[game_name] += total_records
        else:
            total_records_dict[game_name] = total_records

# 对记录总数进行排序
sorted_records = sorted(total_records_dict.items(), key=lambda x: x[1], reverse=True)

# 打印排序后的结果
for game_name, total_records in sorted_records:
    print(f"游戏名字为 '{game_name}'，事件为 '破坏方块' 且类型为 'minecraft:ancient_debris' 的记录总数为 {total_records}")