{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " 读取文件/data/common/北京市科委/result/5U/20230514/part-00000-78a4fe44-ad5f-4ef9-935f-a6bb5fe03317-c000.csv\n",
      " 读取文件/data/common/北京市科委/result/5U/20230517/part-00000-70ef25e5-42c3-4c55-95b8-a39d3879afd9-c000.csv\n",
      " 读取文件/data/common/北京市科委/result/5U/20230520/part-00000-351b68a8-c075-4a99-979c-6dc10acf5d3b-c000.csv\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "base_dir = '/data/common/北京市科委/result'\n",
    "factorys = os.listdir(base_dir)\n",
    "factorys.sort()\n",
    "factorys=['5U']\n",
    "df_all=pd.DataFrame()\n",
    "for factory in factorys:\n",
    "    dates = os.listdir(os.path.join(base_dir, factory))\n",
    "    dates.sort()\n",
    "    for date in dates:\n",
    "        files =  os.listdir(os.path.join(base_dir, factory, date))\n",
    "        for f in files:\n",
    "            if f.endswith(\".csv\"):\n",
    "                file_path = os.path.join(base_dir, factory, date, f)\n",
    "                print(f\" 读取文件{file_path}\")\n",
    "                df = pd.read_csv(file_path)\n",
    "                if len(df_all)==0:\n",
    "                    df_all=df\n",
    "                else:\n",
    "                    df_all=df_all=df.append(df)\n",
    "            break\n",
    "df.columns=['cellid','equipmentid','operatorid','ChargingMetaInfoId','updateDatetime','cellStatus','doorStatus','errorcode','current','voltage',\n",
    "            'power','quantity','envTemperature','cirTemprature','residualCurrent','startChargeSwq','receivedByPlatformDatetime']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "xx=df['cellid'].drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_806639/1630412067.py:4: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df['flag'][df['current']>0.1]='c'\n"
     ]
    }
   ],
   "source": [
    "df=df.sort_values([\"cellid\",\"updateDatetime\"],ascending = [True, True])\n",
    "df['flag']='d'\n",
    "if len(df['current']>0.1):\n",
    "    df['flag'][df['current']>0.1]='c'\n",
    "df['flag_block']=(df[\"flag\"].shift(1) != df[\"flag\"]).astype(int).cumsum()\n",
    "df_c=df[df['flag']=='c']\n",
    "df_c_time_b=df_c[[\"updateDatetime\",\"cellid\",\"flag_block\"]].groupby([\"cellid\",\"flag_block\"]).first()\n",
    "df_c_time_e=df_c[[\"updateDatetime\",\"cellid\",\"flag_block\"]].groupby([\"cellid\",\"flag_block\"]).last()\n",
    "frames=[df_c_time_b,df_c_time_e]\n",
    "df_merge_c_choice = pd.concat(frames, axis=1, join='inner')\n",
    "df_merge_c_choice=df_merge_c_choice.reset_index()\n",
    "df_merge_c_choice.columns=[\"cellid\",\"charge_block\",\"time_first\",\"time_last\"]\n",
    "df_merge_c_choice[\"order_delta\"]=pd.to_timedelta(pd.to_datetime(df_merge_c_choice[\"time_last\"])-pd.to_datetime(df_merge_c_choice[\"time_first\"])).dt.total_seconds()\n",
    "df_merge_c_choice[\"order_delta_h\"]=round(df_merge_c_choice[\"order_delta\"]/3600,2)\n",
    "df_merge_c_choice_result1=df_merge_c_choice[df_merge_c_choice[\"order_delta\"]>=300]\n",
    "df_merge_c21=df_c[(df_c[\"cellid\"].isin(df_merge_c_choice_result1[\"cellid\"]))&(df_c[\"flag_block\"].isin(df_merge_c_choice_result1[\"charge_block\"]))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zz=df_merge_c21['flag_block'].drop_duplicates()\n",
    "len(zz)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py3916",
   "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": "3.9.16"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}