{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "map_file = r\"D:\\data\\mapping_ts_code_IH.csv\"    #主力合约统计表\n",
    "file_path = str(\"F:/2022_tickdata/marketdatacsv\") #csv文件绝对地址前缀\n",
    "\n",
    "header_file = r\"D:\\data\\fut_marketdata_head.csv\"  # 包含表头的 CSV 文件名\n",
    "# data_file = r\"D:\\combined_market_data.csv\"      # 包含数据的 CSV 文件名\n",
    "output_file = r\"D:\\IH888_up_2022.csv\"  # 合并后的输出文件名\n",
    "total_code = 'IH888'\n",
    "\n",
    "sp_chars = ['csv2022'] #'csv2021', 'csv2022',需要查找的主力年份文件"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(map_file, index_col=0, encoding='utf', low_memory=False)\n",
    "df['mapping_ts_code_new'] = df['mapping_ts_code'].apply(lambda x: x.split('.')[0])\n",
    "df['temp_path']= file_path\n",
    "df['final_path'] = df['temp_path'].astype(str) + df['trade_date'].astype(str)  + '/' + df['mapping_ts_code_new'] + '.csv'\n",
    "del df['mapping_ts_code_new'], df['temp_path']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import time as s_time\n",
    "import datetime\n",
    "import pandas as pd\n",
    "for sp_char in sp_chars:\n",
    "    csv_files = [sp_file for sp_file in df['final_path'] if sp_char in sp_file]\n",
    "    print(csv_files[:5])\n",
    "    print(csv_files[-5:])\n",
    "    dfs = pd.DataFrame()\n",
    "    for file_path in csv_files:\n",
    "        df_temp = pd.read_csv(file_path)   \n",
    "        print('读取%s成功'%(file_path))\n",
    "        # df_temp.columns = ['交易日','合约代码','最后修改时间','最后修改毫秒','最新价','数量','申买价一','申买量一','申卖价一','申卖量一','当日均价','成交金额','持仓量','涨停价','跌停价']\n",
    "        # df_temp['datetime'] = df_temp['交易日'].astype(str) + ' '+df_temp['最后修改时间'].astype(str) + '.' + df_temp['最后修改毫秒'].astype(str)\n",
    "        # df_temp['datetime'] = pd.to_datetime(df_temp['datetime'], errors='coerce', format='%Y-%m-%d %H:%M:%S.%f')\n",
    "        # df_temp['tmp_time'] = df_temp['datetime'].dt.strftime('%H:%M:%S.%f')\n",
    "        # df_temp['time'] = df_temp['tmp_time'].apply(lambda x: datetime.strptime(x, '%H:%M:%S.%f')).dt.time\n",
    "        # drop_index1 = df_temp.loc[(df_temp['time'] > s_time(11, 30, 0)) & (df_temp['time']  < s_time(13, 0, 0))].index\n",
    "        # drop_index2 = df_temp.loc[(df_temp['time']  > s_time(15, 0, 0)) | (df_temp['time']  < s_time(9, 30, 0))].index\n",
    "        # df_temp.drop(drop_index1, axis=0, inplace=True)\n",
    "        # df_temp.drop(drop_index2, axis=0, inplace=True)\n",
    "        # dfs.append(df_temp)\n",
    "        # df_temp.columns=['交易日','合约代码','最后修改时间','最后修改毫秒','最新价','数量','申买价一','申买量一','申卖价一','申卖量一','当日均价','成交金额','持仓量','涨停价','跌停价']\n",
    "        df_temp.columns = ['交易日','合约代码','最后修改时间','最后修改毫秒','最新价','数量','申买价一','申买量一','申卖价一','申卖量一','当日均价','成交金额','持仓量','涨停价','跌停价']\n",
    "        # print(df_temp.tail())\n",
    "        # # print(\"表头添加成功！\")\n",
    "        # dfs = pd.concat([dfs, df_temp],ignore_index=True, axis= 0)#  \n",
    "        # print(dfs.tail())\n",
    "        # dfs = pd.concat([df_temp, ignore_index=True)\n",
    "        dfs = pd.concat([dfs, df_temp], ignore_index=True)\n",
    "        \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfs.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfs.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df = dfs.sort_values(by = ['交易日', '最后修改时间', '最后修改毫秒'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df.insert(0,'统一代码', total_code)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined_df.to_csv(output_file, index=False)\n",
    "print(\"合并完成，并已导出到%s文件。\"%(output_file))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 以下为其他代码\n",
    "import pandas as pd\n",
    " \n",
    "try:\n",
    "    file_path = 'path/to/your/file.csv'  # 替换为你的文件路径\n",
    "    df = pd.read_csv(file_path)\n",
    "except FileNotFoundError:\n",
    "    print(f\"无法找到文件：{file_path}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "for k in ['2021']:# , '2023'\n",
    "    for v in [ 'IH', 'IF', 'IC', 'IM', 'T', 'TF', 'TL', 'TS']: \n",
    "        print('当前年份为:%s,品种为:%s'%(k,v))\n",
    "        map_file = 'D:/data/mapping_ts_code_%s.csv'%(v)    #v\n",
    "        file_path = 'F:/%s_tickdata/marketdatacsv'%(k) #csv文件绝对地址前缀\n",
    "        output_file = 'D:/%s888_up_%s.csv'%(v,k)  # 合并后的输出文件名\n",
    "        total_code = '%s888'%(v)\n",
    "        sp_chars = ['csv%s'%(k)] #'csv2021', 'csv2022',需要查找的主力年份文件\n",
    "\n",
    "        try:\n",
    "            df = pd.read_csv(map_file, index_col=0, encoding='utf', low_memory=False)\n",
    "        except FileNotFoundError:\n",
    "            raise ValueError(\"主力合约统计表文件不存在，请检查文件路径是否正确。\")\n",
    "        df['mapping_ts_code_new'] = df['mapping_ts_code'].apply(lambda x: x.split('.')[0])\n",
    "        df['temp_path']= file_path\n",
    "        df['final_path'] = df['temp_path'].astype(str) + df['trade_date'].astype(str)  + '/' + df['mapping_ts_code_new'] + '.csv'\n",
    "        del df['mapping_ts_code_new'], df['temp_path']\n",
    "\n",
    "        for sp_char in sp_chars:\n",
    "            csv_files = [sp_file for sp_file in df['final_path'] if sp_char in sp_file]\n",
    "            if csv_files:\n",
    "                print(csv_files[:5])\n",
    "                print(csv_files[-5:])\n",
    "                dfs = pd.DataFrame()\n",
    "                for path in csv_files:\n",
    "                    try:\n",
    "                        df_temp = pd.read_csv(path) \n",
    "                        # print('读取%s成功'%(path))\n",
    "                    except FileNotFoundError:\n",
    "                        raise ValueError(\"%s文件不存在，请检查文件路径是否正确。\"%(path))\n",
    "                        break\n",
    "                    df_temp.columns = ['交易日','合约代码','最后修改时间','最后修改毫秒','最新价','数量','申买价一','申买量一','申卖价一','申卖量一','当日均价','成交金额','持仓量','涨停价','跌停价']\n",
    "                    dfs = pd.concat([dfs, df_temp], ignore_index=True)\n",
    "                combined_df = dfs.sort_values(by = ['交易日', '最后修改时间', '最后修改毫秒'])\n",
    "                combined_df.insert(0,'统一代码', total_code)\n",
    "                combined_df.to_csv(output_file, index=False)\n",
    "                print(\"合并完成，并已导出到%s文件。\"%(output_file))\n",
    "            else:\n",
    "                print('品种%s在%s年无数据!'%(v,k))\n",
    "                continue\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}