{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [
    {
     "data": {
      "text/plain": "dict_keys(['浙江秀舟', '武乡西山', '邯郸东郊', '建投遵化'])"
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "daily_data = pd.read_excel('data/电厂日数据.xlsx', sheet_name=None)\n",
    "daily_data.keys()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [],
   "source": [
    "zjxz_daily = daily_data.get('浙江秀舟')\n",
    "wxxs_daily = daily_data.get('武乡西山')\n",
    "hddj_daily = daily_data.get('邯郸东郊')\n",
    "jtzh_daily = daily_data.get('建投遵化')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [
    {
     "data": {
      "text/plain": "         days  发电量（千瓦时）  供热量（吉焦）  燃料消耗量（吨）      流量 （m3/h）  氮氧化物浓度(mg/m3)  \\\n0  2018-10-01  156796.0  6536.83       323  162345.192917      24.515087   \n1  2018-10-02  133984.0  2484.64       218  140175.330833      18.829456   \n2  2018-10-03  134023.0  3020.83       212  154686.184167      20.891797   \n3  2018-10-04  124765.0  5599.23       223  120345.545833      18.641687   \n4  2018-10-05  134414.0  4702.65       243  162533.103542      22.031219   \n\n      含氧量（%）      温度（℃）  二氧化硫浓度(mg/m3)  烟尘浓度(mg/m3)  发电量（万千瓦时）  \n0   9.900000  51.250000       4.721475     0.176932    15.6796  \n1   9.400000  50.679167       3.698115     0.161356    13.3984  \n2   8.550000  52.808333       6.381178     0.117507    13.4023  \n3  10.202083  48.854167       2.393757     0.761287    12.4765  \n4  11.497917  45.783333       0.338422     1.842860    13.4414  ",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>days</th>\n      <th>发电量（千瓦时）</th>\n      <th>供热量（吉焦）</th>\n      <th>燃料消耗量（吨）</th>\n      <th>流量 （m3/h）</th>\n      <th>氮氧化物浓度(mg/m3)</th>\n      <th>含氧量（%）</th>\n      <th>温度（℃）</th>\n      <th>二氧化硫浓度(mg/m3)</th>\n      <th>烟尘浓度(mg/m3)</th>\n      <th>发电量（万千瓦时）</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2018-10-01</td>\n      <td>156796.0</td>\n      <td>6536.83</td>\n      <td>323</td>\n      <td>162345.192917</td>\n      <td>24.515087</td>\n      <td>9.900000</td>\n      <td>51.250000</td>\n      <td>4.721475</td>\n      <td>0.176932</td>\n      <td>15.6796</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2018-10-02</td>\n      <td>133984.0</td>\n      <td>2484.64</td>\n      <td>218</td>\n      <td>140175.330833</td>\n      <td>18.829456</td>\n      <td>9.400000</td>\n      <td>50.679167</td>\n      <td>3.698115</td>\n      <td>0.161356</td>\n      <td>13.3984</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2018-10-03</td>\n      <td>134023.0</td>\n      <td>3020.83</td>\n      <td>212</td>\n      <td>154686.184167</td>\n      <td>20.891797</td>\n      <td>8.550000</td>\n      <td>52.808333</td>\n      <td>6.381178</td>\n      <td>0.117507</td>\n      <td>13.4023</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2018-10-04</td>\n      <td>124765.0</td>\n      <td>5599.23</td>\n      <td>223</td>\n      <td>120345.545833</td>\n      <td>18.641687</td>\n      <td>10.202083</td>\n      <td>48.854167</td>\n      <td>2.393757</td>\n      <td>0.761287</td>\n      <td>12.4765</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2018-10-05</td>\n      <td>134414.0</td>\n      <td>4702.65</td>\n      <td>243</td>\n      <td>162533.103542</td>\n      <td>22.031219</td>\n      <td>11.497917</td>\n      <td>45.783333</td>\n      <td>0.338422</td>\n      <td>1.842860</td>\n      <td>13.4414</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zjxz_daily['发电量（万千瓦时）'] = zjxz_daily['发电量（千瓦时）'] / 10000\n",
    "zjxz_daily.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [],
   "source": [
    "zjxz_daily.rename(columns={'流量 （m3/h）': 'flow', '温度（℃）': 'temperature', '含氧量（%）': 'r_O2'}, inplace=True)\n",
    "zjxz_daily['c_smoke'] = zjxz_daily['flow'] * zjxz_daily['烟尘浓度(mg/m3)']\n",
    "zjxz_daily['c_NO2'] = zjxz_daily['flow'] * zjxz_daily['氮氧化物浓度(mg/m3)']\n",
    "zjxz_daily['c_SO2'] = zjxz_daily['flow'] * zjxz_daily['二氧化硫浓度(mg/m3)']\n",
    "zjxz_daily['企业名称'] = '浙江秀舟热电有限公司'"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "outputs": [],
   "source": [
    "zjxz_daily_final = zjxz_daily[\n",
    "    ['days', '企业名称', 'r_O2', 'temperature', '发电量（万千瓦时）', '供热量（吉焦）', 'c_smoke', 'c_NO2', 'c_SO2', 'flow', '燃料消耗量（吨）']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [],
   "source": [
    "wxxs_daily.rename(columns={'Unnamed: 0': 'days'}, inplace=True)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "outputs": [],
   "source": [
    "num_cols = [x for x in wxxs_daily.columns if x not in ['days', '企业名称', '机组1_状态', '机组2_状态']]"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [
    {
     "data": {
      "text/plain": "(112, 23)"
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wxxs_daily.dropna(inplace=True)\n",
    "wxxs_daily = wxxs_daily[~((wxxs_daily['机组1_状态'] == '停运') & (wxxs_daily['机组2_状态'] == '停运'))].copy()\n",
    "wxxs_daily.shape"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "outputs": [
    {
     "data": {
      "text/plain": "Index(['days', '发电量_1（万千瓦时）', '供热量_1（吉焦）', '燃料消耗量_1（吨）', '发电量_2（万千瓦时）',\n       '供热量_2（吉焦）', '燃料消耗量_2（吨）', '企业名称', '发电量（万千瓦时）', '供热量（吉焦）', '燃料消耗量（吨）',\n       '机组1_二氧化硫浓度(mg/m3)', '机组1_氮氧化物浓度(mg/m3)', '机组1_烟尘浓度(mg/m3)',\n       '机组1_流速(m/s)', '机组1_流量(m3/h)', '机组1_状态', '机组2_二氧化硫浓度(mg/m3)',\n       '机组2_氮氧化物浓度(mg/m3)', '机组2_烟尘浓度(mg/m3)', '机组2_流速(m/s)', '机组2_流量(m3/h)',\n       '机组2_状态'],\n      dtype='object')"
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wxxs_daily.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "outputs": [],
   "source": [
    "wxxs_unit_1 = wxxs_daily[['days', '企业名称']].copy()\n",
    "wxxs_unit_2 = wxxs_daily[['days', '企业名称']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "outputs": [],
   "source": [
    "wxxs_unit_1['c_smoke'] = wxxs_daily['机组1_流量(m3/h)'] * wxxs_daily['机组1_烟尘浓度(mg/m3)']\n",
    "wxxs_unit_1['c_NO2'] =  wxxs_daily['机组1_流量(m3/h)'] * wxxs_daily['机组1_氮氧化物浓度(mg/m3)']\n",
    "wxxs_unit_1['c_SO2'] =  wxxs_daily['机组1_流量(m3/h)'] * wxxs_daily['机组1_二氧化硫浓度(mg/m3)']\n",
    "wxxs_unit_1['flow'] = wxxs_daily['机组1_流量(m3/h)']\n",
    "wxxs_unit_1['r_O2'] = np.nan\n",
    "wxxs_unit_1['temperature'] = np.nan\n",
    "wxxs_unit_1['发电量（万千瓦时）'] = wxxs_daily['发电量_1（万千瓦时）']\n",
    "wxxs_unit_1['供热量（吉焦）'] = wxxs_daily['供热量_1（吉焦）']\n",
    "wxxs_unit_1['燃料消耗量（吨）'] = wxxs_daily['燃料消耗量_1（吨）']\n",
    "\n",
    "wxxs_unit_2['c_smoke'] = wxxs_daily['机组2_流量(m3/h)'] * wxxs_daily['机组2_烟尘浓度(mg/m3)']\n",
    "wxxs_unit_2['c_NO2'] =  wxxs_daily['机组2_流量(m3/h)'] * wxxs_daily['机组2_氮氧化物浓度(mg/m3)']\n",
    "wxxs_unit_2['c_SO2'] =  wxxs_daily['机组2_流量(m3/h)'] * wxxs_daily['机组2_二氧化硫浓度(mg/m3)']\n",
    "wxxs_unit_2['flow'] = wxxs_daily['机组2_流量(m3/h)']\n",
    "wxxs_unit_2['r_O2'] = np.nan\n",
    "wxxs_unit_2['temperature'] = np.nan\n",
    "wxxs_unit_2['发电量（万千瓦时）'] = wxxs_daily['发电量_2（万千瓦时）']\n",
    "wxxs_unit_2['供热量（吉焦）'] = wxxs_daily['供热量_2（吉焦）']\n",
    "wxxs_unit_2['燃料消耗量（吨）'] = wxxs_daily['燃料消耗量_2（吨）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "outputs": [],
   "source": [
    "wxxs_daily_final = pd.concat([wxxs_unit_1, wxxs_unit_2], axis=0)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "outputs": [
    {
     "data": {
      "text/plain": "(59, 28)"
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_daily.rename(columns={'Unnamed: 0': 'days'}, inplace=True)\n",
    "hddj_daily.shape"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "outputs": [
    {
     "data": {
      "text/plain": "Index(['days', '发电量_1（万千瓦时）', '供热量_1（吉焦）', '燃料消耗量_1（吨）', '发电量_2（万千瓦时）',\n       '供热量_2（吉焦）', '燃料消耗量_2（吨）', '企业名称', '机组1_流量 （m3/h）', '机组1_NOx浓度(mg/m3)',\n       '机组1_SO2浓度(mg/m3)', '机组1_烟尘浓度(mg/m3)', '机组1_含氧量（%）', '机组1_温度（℃）',\n       '机组1_烟气湿度（%）', '机组1_烟气压力（千帕）', '机组1_烟气流速（m/s）', '机组1_状态',\n       '机组2_流量 （m3/h）', '机组2_NOx浓度(mg/m3)', '机组2_SO2浓度(mg/m3)',\n       '机组2_烟尘浓度(mg/m3)', '机组2_含氧量（%）', '机组2_温度（℃）', '机组2_烟气湿度（%）',\n       '机组2_烟气压力（千帕）', '机组2_烟气流速（m/s）', '机组2_状态'],\n      dtype='object')"
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_daily.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "outputs": [],
   "source": [
    "hddj_unit_1 = hddj_daily[['days', '企业名称']].copy()\n",
    "hddj_unit_2 = hddj_daily[['days', '企业名称']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "outputs": [],
   "source": [
    "hddj_unit_1['c_smoke'] = hddj_daily['机组1_流量 （m3/h）'] * hddj_daily['机组1_烟尘浓度(mg/m3)']\n",
    "hddj_unit_1['c_NO2'] = hddj_daily['机组1_流量 （m3/h）'] * hddj_daily['机组1_NOx浓度(mg/m3)']\n",
    "hddj_unit_1['c_SO2'] = hddj_daily['机组1_流量 （m3/h）'] * hddj_daily['机组1_SO2浓度(mg/m3)']\n",
    "hddj_unit_1['flow'] = hddj_daily['机组1_流量 （m3/h）']\n",
    "hddj_unit_1['r_O2'] = hddj_daily['机组1_含氧量（%）']\n",
    "hddj_unit_1['发电量（万千瓦时）'] = hddj_daily['发电量_1（万千瓦时）']\n",
    "hddj_unit_1['供热量（吉焦）'] = hddj_daily['供热量_1（吉焦）']\n",
    "hddj_unit_1['temperature'] = hddj_daily['机组1_温度（℃）']\n",
    "hddj_unit_1['燃料消耗量（吨）'] = hddj_daily['燃料消耗量_1（吨）']\n",
    "\n",
    "hddj_unit_2['c_smoke'] = hddj_daily['机组2_流量 （m3/h）'] * hddj_daily['机组2_烟尘浓度(mg/m3)']\n",
    "hddj_unit_2['c_NO2'] = hddj_daily['机组2_流量 （m3/h）'] * hddj_daily['机组2_NOx浓度(mg/m3)']\n",
    "hddj_unit_2['c_SO2'] = hddj_daily['机组2_流量 （m3/h）'] * hddj_daily['机组2_SO2浓度(mg/m3)']\n",
    "hddj_unit_2['flow'] = hddj_daily['机组2_流量 （m3/h）']\n",
    "hddj_unit_2['r_O2'] = hddj_daily['机组2_含氧量（%）']\n",
    "hddj_unit_2['发电量（万千瓦时）'] = hddj_daily['发电量_2（万千瓦时）']\n",
    "hddj_unit_2['供热量（吉焦）'] = hddj_daily['供热量_2（吉焦）']\n",
    "hddj_unit_2['temperature'] = hddj_daily['机组2_温度（℃）']\n",
    "hddj_unit_2['燃料消耗量（吨）'] = hddj_daily['燃料消耗量_2（吨）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "outputs": [],
   "source": [
    "hddj_daily_final = pd.concat([hddj_unit_1, hddj_unit_2], axis=0)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "outputs": [
    {
     "data": {
      "text/plain": "(31, 26)"
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jtzh_daily.rename(columns={'Unnamed: 0': 'days'}, inplace=True)\n",
    "jtzh_daily['机组1_状态'] = (jtzh_daily['机组1_状态'] == '正常运行') * 1\n",
    "jtzh_daily['机组2_状态'] = (jtzh_daily['机组2_状态'] == '正常运行') * 1\n",
    "jtzh_daily.shape"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "outputs": [
    {
     "data": {
      "text/plain": "Index(['days', '发电量_1（万千瓦时）', '供热量_1（吉焦）', '燃料消耗量_1（吨）', '发电量_2（万千瓦时）',\n       '供热量_2（吉焦）', '燃料消耗量_2（吨）', '企业名称', '机组1_流量 （m3/h）', '机组1_NOx浓度(mg/m3)',\n       '机组1_SO2浓度(mg/m3)', '机组1_烟尘浓度(mg/m3)', '机组1_含氧量（%）', '机组1_温度（℃）',\n       '机组1_烟气湿度（%）', '机组1_烟气流速（m/s）', '机组1_状态', '机组2_流量 （m3/h）',\n       '机组2_NOx浓度(mg/m3)', '机组2_SO2浓度(mg/m3)', '机组2_烟尘浓度(mg/m3)', '机组2_含氧量（%）',\n       '机组2_温度（℃）', '机组2_烟气湿度（%）', '机组2_烟气流速（m/s）', '机组2_状态'],\n      dtype='object')"
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jtzh_daily.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "outputs": [],
   "source": [
    "jtzh_unit_1 = jtzh_daily[['days', '企业名称']].copy()\n",
    "jtzh_unit_2 = jtzh_daily[['days', '企业名称']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "outputs": [],
   "source": [
    "jtzh_unit_1['c_smoke'] = jtzh_daily['机组1_流量 （m3/h）'] * jtzh_daily['机组1_烟尘浓度(mg/m3)']\n",
    "jtzh_unit_1['c_NO2'] = jtzh_daily['机组1_流量 （m3/h）'] * jtzh_daily['机组1_NOx浓度(mg/m3)']\n",
    "jtzh_unit_1['c_SO2'] = jtzh_daily['机组1_流量 （m3/h）'] * jtzh_daily['机组1_SO2浓度(mg/m3)']\n",
    "jtzh_unit_1['flow'] = jtzh_daily['机组1_流量 （m3/h）']\n",
    "jtzh_unit_1['r_O2'] = jtzh_daily['机组1_含氧量（%）']\n",
    "jtzh_unit_1['temperature'] = jtzh_daily['机组1_温度（℃）']\n",
    "jtzh_unit_1['发电量（万千瓦时）'] = jtzh_daily['发电量_2（万千瓦时）']\n",
    "jtzh_unit_1['供热量（吉焦）'] = jtzh_daily['供热量_2（吉焦）']\n",
    "jtzh_unit_1['燃料消耗量（吨）'] = jtzh_daily['燃料消耗量_1（吨）']\n",
    "\n",
    "jtzh_unit_2['c_smoke'] = jtzh_daily['机组2_流量 （m3/h）'] * jtzh_daily['机组2_烟尘浓度(mg/m3)']\n",
    "jtzh_unit_2['c_NO2'] = jtzh_daily['机组2_流量 （m3/h）'] * jtzh_daily['机组2_NOx浓度(mg/m3)']\n",
    "jtzh_unit_2['c_SO2'] = jtzh_daily['机组2_流量 （m3/h）'] * jtzh_daily['机组2_SO2浓度(mg/m3)']\n",
    "jtzh_unit_2['flow'] = jtzh_daily['机组2_流量 （m3/h）']\n",
    "jtzh_unit_2['r_O2'] = jtzh_daily['机组2_含氧量（%）']\n",
    "jtzh_unit_2['temperature'] = jtzh_daily['机组2_温度（℃）']\n",
    "jtzh_unit_2['发电量（万千瓦时）'] = jtzh_daily['发电量_2（万千瓦时）']\n",
    "jtzh_unit_2['供热量（吉焦）'] = jtzh_daily['供热量_2（吉焦）']\n",
    "jtzh_unit_2['燃料消耗量（吨）'] = jtzh_daily['燃料消耗量_2（吨）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "outputs": [
    {
     "data": {
      "text/plain": "          days          企业名称       c_smoke         c_NO2         c_SO2  \\\n0   2022-05-01  建投遵化热电有限责任公司  1.467475e+06  1.063321e+07  1.055453e+07   \n1   2022-05-02  建投遵化热电有限责任公司  1.558803e+06  1.328556e+07  1.074905e+07   \n2   2022-05-03  建投遵化热电有限责任公司  1.427659e+06  1.111851e+07  9.591219e+06   \n3   2022-05-04  建投遵化热电有限责任公司  1.499975e+06  1.164537e+07  1.007516e+07   \n4   2022-05-05  建投遵化热电有限责任公司  1.724199e+06  1.227060e+07  1.193453e+07   \n..         ...           ...           ...           ...           ...   \n26  2022-05-27  建投遵化热电有限责任公司  1.020390e+06  1.173919e+07  1.101318e+07   \n27  2022-05-28  建投遵化热电有限责任公司  1.169393e+06  1.393048e+07  1.335698e+07   \n28  2022-05-29  建投遵化热电有限责任公司  1.124243e+06  1.267043e+07  1.129934e+07   \n29  2022-05-30  建投遵化热电有限责任公司  1.296293e+06  1.442430e+07  1.434195e+07   \n30  2022-05-31  建投遵化热电有限责任公司  1.554891e+06  1.758048e+07  1.593381e+07   \n\n      flow      r_O2  temperature  发电量（万千瓦时）  供热量（吉焦）  燃料消耗量（吨）  \n0   820965  7.795833    52.320833      0.000        0      1889  \n1   907380  7.295833    53.145833      0.000        0      2622  \n2   771360  7.650000    51.841667      0.000        0      2233  \n3   780390  7.462500    51.808333      0.000        0      2203  \n4   870075  7.195833    52.354167      0.000        0      2524  \n..     ...       ...          ...        ...      ...       ...  \n26  836100  6.329167    44.741667    467.106        0      2401  \n27  895515  6.183333    45.587500    504.900        0      2611  \n28  837945  6.425000    45.545833    462.822        0      2846  \n29  915030  6.162500    45.175000    528.960        0      2981  \n30  992220  5.570833    46.100000    672.180        0      3560  \n\n[62 rows x 11 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>days</th>\n      <th>企业名称</th>\n      <th>c_smoke</th>\n      <th>c_NO2</th>\n      <th>c_SO2</th>\n      <th>flow</th>\n      <th>r_O2</th>\n      <th>temperature</th>\n      <th>发电量（万千瓦时）</th>\n      <th>供热量（吉焦）</th>\n      <th>燃料消耗量（吨）</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2022-05-01</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.467475e+06</td>\n      <td>1.063321e+07</td>\n      <td>1.055453e+07</td>\n      <td>820965</td>\n      <td>7.795833</td>\n      <td>52.320833</td>\n      <td>0.000</td>\n      <td>0</td>\n      <td>1889</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2022-05-02</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.558803e+06</td>\n      <td>1.328556e+07</td>\n      <td>1.074905e+07</td>\n      <td>907380</td>\n      <td>7.295833</td>\n      <td>53.145833</td>\n      <td>0.000</td>\n      <td>0</td>\n      <td>2622</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2022-05-03</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.427659e+06</td>\n      <td>1.111851e+07</td>\n      <td>9.591219e+06</td>\n      <td>771360</td>\n      <td>7.650000</td>\n      <td>51.841667</td>\n      <td>0.000</td>\n      <td>0</td>\n      <td>2233</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2022-05-04</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.499975e+06</td>\n      <td>1.164537e+07</td>\n      <td>1.007516e+07</td>\n      <td>780390</td>\n      <td>7.462500</td>\n      <td>51.808333</td>\n      <td>0.000</td>\n      <td>0</td>\n      <td>2203</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2022-05-05</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.724199e+06</td>\n      <td>1.227060e+07</td>\n      <td>1.193453e+07</td>\n      <td>870075</td>\n      <td>7.195833</td>\n      <td>52.354167</td>\n      <td>0.000</td>\n      <td>0</td>\n      <td>2524</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>26</th>\n      <td>2022-05-27</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.020390e+06</td>\n      <td>1.173919e+07</td>\n      <td>1.101318e+07</td>\n      <td>836100</td>\n      <td>6.329167</td>\n      <td>44.741667</td>\n      <td>467.106</td>\n      <td>0</td>\n      <td>2401</td>\n    </tr>\n    <tr>\n      <th>27</th>\n      <td>2022-05-28</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.169393e+06</td>\n      <td>1.393048e+07</td>\n      <td>1.335698e+07</td>\n      <td>895515</td>\n      <td>6.183333</td>\n      <td>45.587500</td>\n      <td>504.900</td>\n      <td>0</td>\n      <td>2611</td>\n    </tr>\n    <tr>\n      <th>28</th>\n      <td>2022-05-29</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.124243e+06</td>\n      <td>1.267043e+07</td>\n      <td>1.129934e+07</td>\n      <td>837945</td>\n      <td>6.425000</td>\n      <td>45.545833</td>\n      <td>462.822</td>\n      <td>0</td>\n      <td>2846</td>\n    </tr>\n    <tr>\n      <th>29</th>\n      <td>2022-05-30</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.296293e+06</td>\n      <td>1.442430e+07</td>\n      <td>1.434195e+07</td>\n      <td>915030</td>\n      <td>6.162500</td>\n      <td>45.175000</td>\n      <td>528.960</td>\n      <td>0</td>\n      <td>2981</td>\n    </tr>\n    <tr>\n      <th>30</th>\n      <td>2022-05-31</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>1.554891e+06</td>\n      <td>1.758048e+07</td>\n      <td>1.593381e+07</td>\n      <td>992220</td>\n      <td>5.570833</td>\n      <td>46.100000</td>\n      <td>672.180</td>\n      <td>0</td>\n      <td>3560</td>\n    </tr>\n  </tbody>\n</table>\n<p>62 rows × 11 columns</p>\n</div>"
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jtzh_daily_final = pd.concat([jtzh_unit_1, jtzh_unit_2], axis=0)\n",
    "jtzh_daily_final"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "outputs": [],
   "source": [
    "all_daily_data = pd.concat([zjxz_daily_final, wxxs_daily_final, hddj_daily_final, jtzh_daily_final])"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "outputs": [],
   "source": [
    "unit_features = pd.read_excel('data/电厂特征表.xlsx', header=None).T"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "outputs": [
    {
     "data": {
      "text/plain": "               企业名称                地址   省份            经度            纬度  \\\n1        浙江秀舟热电有限公司         嘉兴市南湖区凤桥镇  浙江省  120°51′5.54″  30°39′14.76″   \n2      武乡西山发电有限责任公司      山西省武乡县丰州镇下城村  山西省    112°51′11″      36°50′0″   \n3  国电电力邯郸东郊热电有限责任公司  河北肥乡经济开发区光明西路11号  河北省     114°39'0\"      36°34'0\"   \n4      建投遵化热电有限责任公司    河北省遵化市新店子镇程庄子村  河北省    117°58'40\"      40°4'33\"   \n\n  烟囱高度（m）           脱硝工艺 脱硝剂名称 脱硝设备数量       脱硫工艺  ... 发电机组1_单机容量（MW）  \\\n1      80       SNCR SCR    氨水      3   石灰石-石膏湿法  ...             15   \n2     240            SCR    尿素      2  石灰石--石膏湿法  ...            600   \n3     NaN  采用高效低氮燃烧器＋SCR   NaN    NaN   石灰石-石膏湿法  ...            350   \n4     NaN  采用高效低氮燃烧器＋SCR   NaN    NaN   石灰石-石膏湿法  ...            350   \n\n            发电机组1_投产日期 发电机组1_汽轮机类型 发电机组1_压力参数 发电机组1_冷却方式 发电机组2_单机容量（MW）  \\\n1  2014-07-01 00:00:00         背压式         高压    水冷-闭式循环             15   \n2  2006-10-07 00:00:00         抽凝式        亚临界    空冷-直接空冷            600   \n3  2019-06-08 00:00:00         抽凝式       超超临界    水冷-闭式循环            350   \n4  2019-07-09 00:00:00         抽凝式        超临界    水冷-闭式循环            350   \n\n            发电机组2_投产日期 发电机组2_汽轮机类型 发电机组2_压力参数 发电机组2_冷却方式  \n1  2018-08-01 00:00:00         抽背式         高压    水冷-闭式循环  \n2  2007-01-07 00:00:00         抽凝式        亚临界    空冷-直接空冷  \n3  2019-06-08 00:00:00         抽凝式       超超临界    水冷-闭式循环  \n4  2020-05-02 00:00:00         抽凝式        超临界    水冷-闭式循环  \n\n[4 rows x 33 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>企业名称</th>\n      <th>地址</th>\n      <th>省份</th>\n      <th>经度</th>\n      <th>纬度</th>\n      <th>烟囱高度（m）</th>\n      <th>脱硝工艺</th>\n      <th>脱硝剂名称</th>\n      <th>脱硝设备数量</th>\n      <th>脱硫工艺</th>\n      <th>...</th>\n      <th>发电机组1_单机容量（MW）</th>\n      <th>发电机组1_投产日期</th>\n      <th>发电机组1_汽轮机类型</th>\n      <th>发电机组1_压力参数</th>\n      <th>发电机组1_冷却方式</th>\n      <th>发电机组2_单机容量（MW）</th>\n      <th>发电机组2_投产日期</th>\n      <th>发电机组2_汽轮机类型</th>\n      <th>发电机组2_压力参数</th>\n      <th>发电机组2_冷却方式</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1</th>\n      <td>浙江秀舟热电有限公司</td>\n      <td>嘉兴市南湖区凤桥镇</td>\n      <td>浙江省</td>\n      <td>120°51′5.54″</td>\n      <td>30°39′14.76″</td>\n      <td>80</td>\n      <td>SNCR SCR</td>\n      <td>氨水</td>\n      <td>3</td>\n      <td>石灰石-石膏湿法</td>\n      <td>...</td>\n      <td>15</td>\n      <td>2014-07-01 00:00:00</td>\n      <td>背压式</td>\n      <td>高压</td>\n      <td>水冷-闭式循环</td>\n      <td>15</td>\n      <td>2018-08-01 00:00:00</td>\n      <td>抽背式</td>\n      <td>高压</td>\n      <td>水冷-闭式循环</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>武乡西山发电有限责任公司</td>\n      <td>山西省武乡县丰州镇下城村</td>\n      <td>山西省</td>\n      <td>112°51′11″</td>\n      <td>36°50′0″</td>\n      <td>240</td>\n      <td>SCR</td>\n      <td>尿素</td>\n      <td>2</td>\n      <td>石灰石--石膏湿法</td>\n      <td>...</td>\n      <td>600</td>\n      <td>2006-10-07 00:00:00</td>\n      <td>抽凝式</td>\n      <td>亚临界</td>\n      <td>空冷-直接空冷</td>\n      <td>600</td>\n      <td>2007-01-07 00:00:00</td>\n      <td>抽凝式</td>\n      <td>亚临界</td>\n      <td>空冷-直接空冷</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>国电电力邯郸东郊热电有限责任公司</td>\n      <td>河北肥乡经济开发区光明西路11号</td>\n      <td>河北省</td>\n      <td>114°39'0\"</td>\n      <td>36°34'0\"</td>\n      <td>NaN</td>\n      <td>采用高效低氮燃烧器＋SCR</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>石灰石-石膏湿法</td>\n      <td>...</td>\n      <td>350</td>\n      <td>2019-06-08 00:00:00</td>\n      <td>抽凝式</td>\n      <td>超超临界</td>\n      <td>水冷-闭式循环</td>\n      <td>350</td>\n      <td>2019-06-08 00:00:00</td>\n      <td>抽凝式</td>\n      <td>超超临界</td>\n      <td>水冷-闭式循环</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>建投遵化热电有限责任公司</td>\n      <td>河北省遵化市新店子镇程庄子村</td>\n      <td>河北省</td>\n      <td>117°58'40\"</td>\n      <td>40°4'33\"</td>\n      <td>NaN</td>\n      <td>采用高效低氮燃烧器＋SCR</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>石灰石-石膏湿法</td>\n      <td>...</td>\n      <td>350</td>\n      <td>2019-07-09 00:00:00</td>\n      <td>抽凝式</td>\n      <td>超临界</td>\n      <td>水冷-闭式循环</td>\n      <td>350</td>\n      <td>2020-05-02 00:00:00</td>\n      <td>抽凝式</td>\n      <td>超临界</td>\n      <td>水冷-闭式循环</td>\n    </tr>\n  </tbody>\n</table>\n<p>4 rows × 33 columns</p>\n</div>"
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unit_features = unit_features.rename(columns=unit_features.iloc[0]).drop(unit_features.index[0])\n",
    "unit_features.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "outputs": [],
   "source": [
    "unit_features.to_excel('data/机组特征表.xlsx')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "outputs": [],
   "source": [
    "unit_features_used = unit_features[['企业名称', '生产设备类型', '燃料类型', '低位发热量（GJ/t）']].copy()\n",
    "unit_features_used['汽轮机类型'] = unit_features['发电机组1_汽轮机类型']\n",
    "unit_features_used['冷却方式'] = unit_features['发电机组1_冷却方式']\n",
    "unit_features_used['额定蒸发量'] = unit_features['锅炉1额定蒸发量 t/h'] + unit_features['锅炉2额定蒸发量 t/h']\n",
    "unit_features_used['压力参数'] = unit_features['发电机组1_压力参数']\n",
    "unit_features_used['单机容量'] = unit_features['发电机组1_单机容量（MW）'] + unit_features['发电机组2_单机容量（MW）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "outputs": [],
   "source": [
    "for i in range(2, 5):\n",
    "    unit_features_used.loc[i, '额定蒸发量'] = unit_features_used.loc[i, '额定蒸发量'] / 2\n",
    "    unit_features_used.loc[i, '单机容量'] = unit_features_used.loc[i, '单机容量'] / 2"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "outputs": [
    {
     "data": {
      "text/plain": "               企业名称       生产设备类型     燃料类型 低位发热量（GJ/t） 汽轮机类型     冷却方式   额定蒸发量  \\\n1        浙江秀舟热电有限公司  高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   \n2      武乡西山发电有限责任公司         煤粉锅炉       褐煤      18.643   抽凝式  空冷-直接空冷  2080.0   \n3  国电电力邯郸东郊热电有限责任公司         煤粉锅炉   低挥发分烟煤      19.087   抽凝式  水冷-闭式循环  1125.0   \n4      建投遵化热电有限责任公司         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0   \n\n   压力参数   单机容量  \n1    高压     30  \n2   亚临界  600.0  \n3  超超临界  350.0  \n4   超临界  350.0  ",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>企业名称</th>\n      <th>生产设备类型</th>\n      <th>燃料类型</th>\n      <th>低位发热量（GJ/t）</th>\n      <th>汽轮机类型</th>\n      <th>冷却方式</th>\n      <th>额定蒸发量</th>\n      <th>压力参数</th>\n      <th>单机容量</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1</th>\n      <td>浙江秀舟热电有限公司</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>武乡西山发电有限责任公司</td>\n      <td>煤粉锅炉</td>\n      <td>褐煤</td>\n      <td>18.643</td>\n      <td>抽凝式</td>\n      <td>空冷-直接空冷</td>\n      <td>2080.0</td>\n      <td>亚临界</td>\n      <td>600.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>国电电力邯郸东郊热电有限责任公司</td>\n      <td>煤粉锅炉</td>\n      <td>低挥发分烟煤</td>\n      <td>19.087</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1125.0</td>\n      <td>超超临界</td>\n      <td>350.0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>建投遵化热电有限责任公司</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unit_features_used"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "outputs": [],
   "source": [
    "final_data = all_daily_data.merge(unit_features_used, how='left', on='企业名称')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "outputs": [],
   "source": [
    "import datetime as dt"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "outputs": [],
   "source": [
    "def cal_timedelta(x):\n",
    "    date = dt.datetime.strptime(x, '%Y-%m-%d')\n",
    "    date = dt.date(date.year, date.month, date.day)\n",
    "    start_date = dt.date(date.year, 1, 1)\n",
    "    time_delta = (date - start_date).days\n",
    "    return time_delta"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "outputs": [],
   "source": [
    "final_data['day_of_year'] = final_data.days.apply(cal_timedelta)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "outputs": [],
   "source": [
    "final_data['week_of_year'] = final_data['day_of_year'] // 7"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "outputs": [
    {
     "data": {
      "text/plain": "            days          企业名称       r_O2  temperature  发电量（万千瓦时）  供热量（吉焦）  \\\n0     2018-10-01    浙江秀舟热电有限公司   9.900000    51.250000    15.6796  6536.83   \n1     2018-10-02    浙江秀舟热电有限公司   9.400000    50.679167    13.3984  2484.64   \n2     2018-10-03    浙江秀舟热电有限公司   8.550000    52.808333    13.4023  3020.83   \n3     2018-10-04    浙江秀舟热电有限公司  10.202083    48.854167    12.4765  5599.23   \n4     2018-10-05    浙江秀舟热电有限公司  11.497917    45.783333    13.4414  4702.65   \n...          ...           ...        ...          ...        ...      ...   \n1486  2022-05-27  建投遵化热电有限责任公司   6.329167    44.741667   467.1060     0.00   \n1487  2022-05-28  建投遵化热电有限责任公司   6.183333    45.587500   504.9000     0.00   \n1488  2022-05-29  建投遵化热电有限责任公司   6.425000    45.545833   462.8220     0.00   \n1489  2022-05-30  建投遵化热电有限责任公司   6.162500    45.175000   528.9600     0.00   \n1490  2022-05-31  建投遵化热电有限责任公司   5.570833    46.100000   672.1800     0.00   \n\n           c_smoke         c_NO2         c_SO2           flow  ...  \\\n0     2.872405e+04  3.979907e+06  7.665088e+05  162345.192917  ...   \n1     2.261807e+04  2.639425e+06  5.183845e+05  140175.330833  ...   \n2     1.817677e+04  3.231672e+06  9.870800e+05  154686.184167  ...   \n3     9.161746e+04  2.243444e+06  2.880779e+05  120345.545833  ...   \n4     2.995257e+05  3.580802e+06  5.500482e+04  162533.103542  ...   \n...            ...           ...           ...            ...  ...   \n1486  1.020390e+06  1.173919e+07  1.101318e+07  836100.000000  ...   \n1487  1.169393e+06  1.393048e+07  1.335698e+07  895515.000000  ...   \n1488  1.124243e+06  1.267043e+07  1.129934e+07  837945.000000  ...   \n1489  1.296293e+06  1.442430e+07  1.434195e+07  915030.000000  ...   \n1490  1.554891e+06  1.758048e+07  1.593381e+07  992220.000000  ...   \n\n           生产设备类型     燃料类型 低位发热量（GJ/t） 汽轮机类型     冷却方式   额定蒸发量 压力参数   单机容量  \\\n0     高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   高压     30   \n1     高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   高压     30   \n2     高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   高压     30   \n3     高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   高压     30   \n4     高温高压循环流化床锅炉  中高挥发分烟煤      20.501   背压式  水冷-闭式循环     230   高压     30   \n...           ...      ...         ...   ...      ...     ...  ...    ...   \n1486         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0  超临界  350.0   \n1487         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0  超临界  350.0   \n1488         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0  超临界  350.0   \n1489         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0  超临界  350.0   \n1490         煤粉锅炉     一般烟煤      14.682   抽凝式  水冷-闭式循环  1172.0  超临界  350.0   \n\n     day_of_year  week_of_year  \n0            273            39  \n1            274            39  \n2            275            39  \n3            276            39  \n4            277            39  \n...          ...           ...  \n1486         146            20  \n1487         147            21  \n1488         148            21  \n1489         149            21  \n1490         150            21  \n\n[1491 rows x 21 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>days</th>\n      <th>企业名称</th>\n      <th>r_O2</th>\n      <th>temperature</th>\n      <th>发电量（万千瓦时）</th>\n      <th>供热量（吉焦）</th>\n      <th>c_smoke</th>\n      <th>c_NO2</th>\n      <th>c_SO2</th>\n      <th>flow</th>\n      <th>...</th>\n      <th>生产设备类型</th>\n      <th>燃料类型</th>\n      <th>低位发热量（GJ/t）</th>\n      <th>汽轮机类型</th>\n      <th>冷却方式</th>\n      <th>额定蒸发量</th>\n      <th>压力参数</th>\n      <th>单机容量</th>\n      <th>day_of_year</th>\n      <th>week_of_year</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2018-10-01</td>\n      <td>浙江秀舟热电有限公司</td>\n      <td>9.900000</td>\n      <td>51.250000</td>\n      <td>15.6796</td>\n      <td>6536.83</td>\n      <td>2.872405e+04</td>\n      <td>3.979907e+06</td>\n      <td>7.665088e+05</td>\n      <td>162345.192917</td>\n      <td>...</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n      <td>273</td>\n      <td>39</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2018-10-02</td>\n      <td>浙江秀舟热电有限公司</td>\n      <td>9.400000</td>\n      <td>50.679167</td>\n      <td>13.3984</td>\n      <td>2484.64</td>\n      <td>2.261807e+04</td>\n      <td>2.639425e+06</td>\n      <td>5.183845e+05</td>\n      <td>140175.330833</td>\n      <td>...</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n      <td>274</td>\n      <td>39</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2018-10-03</td>\n      <td>浙江秀舟热电有限公司</td>\n      <td>8.550000</td>\n      <td>52.808333</td>\n      <td>13.4023</td>\n      <td>3020.83</td>\n      <td>1.817677e+04</td>\n      <td>3.231672e+06</td>\n      <td>9.870800e+05</td>\n      <td>154686.184167</td>\n      <td>...</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n      <td>275</td>\n      <td>39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2018-10-04</td>\n      <td>浙江秀舟热电有限公司</td>\n      <td>10.202083</td>\n      <td>48.854167</td>\n      <td>12.4765</td>\n      <td>5599.23</td>\n      <td>9.161746e+04</td>\n      <td>2.243444e+06</td>\n      <td>2.880779e+05</td>\n      <td>120345.545833</td>\n      <td>...</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n      <td>276</td>\n      <td>39</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2018-10-05</td>\n      <td>浙江秀舟热电有限公司</td>\n      <td>11.497917</td>\n      <td>45.783333</td>\n      <td>13.4414</td>\n      <td>4702.65</td>\n      <td>2.995257e+05</td>\n      <td>3.580802e+06</td>\n      <td>5.500482e+04</td>\n      <td>162533.103542</td>\n      <td>...</td>\n      <td>高温高压循环流化床锅炉</td>\n      <td>中高挥发分烟煤</td>\n      <td>20.501</td>\n      <td>背压式</td>\n      <td>水冷-闭式循环</td>\n      <td>230</td>\n      <td>高压</td>\n      <td>30</td>\n      <td>277</td>\n      <td>39</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>1486</th>\n      <td>2022-05-27</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>6.329167</td>\n      <td>44.741667</td>\n      <td>467.1060</td>\n      <td>0.00</td>\n      <td>1.020390e+06</td>\n      <td>1.173919e+07</td>\n      <td>1.101318e+07</td>\n      <td>836100.000000</td>\n      <td>...</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n      <td>146</td>\n      <td>20</td>\n    </tr>\n    <tr>\n      <th>1487</th>\n      <td>2022-05-28</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>6.183333</td>\n      <td>45.587500</td>\n      <td>504.9000</td>\n      <td>0.00</td>\n      <td>1.169393e+06</td>\n      <td>1.393048e+07</td>\n      <td>1.335698e+07</td>\n      <td>895515.000000</td>\n      <td>...</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n      <td>147</td>\n      <td>21</td>\n    </tr>\n    <tr>\n      <th>1488</th>\n      <td>2022-05-29</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>6.425000</td>\n      <td>45.545833</td>\n      <td>462.8220</td>\n      <td>0.00</td>\n      <td>1.124243e+06</td>\n      <td>1.267043e+07</td>\n      <td>1.129934e+07</td>\n      <td>837945.000000</td>\n      <td>...</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n      <td>148</td>\n      <td>21</td>\n    </tr>\n    <tr>\n      <th>1489</th>\n      <td>2022-05-30</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>6.162500</td>\n      <td>45.175000</td>\n      <td>528.9600</td>\n      <td>0.00</td>\n      <td>1.296293e+06</td>\n      <td>1.442430e+07</td>\n      <td>1.434195e+07</td>\n      <td>915030.000000</td>\n      <td>...</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n      <td>149</td>\n      <td>21</td>\n    </tr>\n    <tr>\n      <th>1490</th>\n      <td>2022-05-31</td>\n      <td>建投遵化热电有限责任公司</td>\n      <td>5.570833</td>\n      <td>46.100000</td>\n      <td>672.1800</td>\n      <td>0.00</td>\n      <td>1.554891e+06</td>\n      <td>1.758048e+07</td>\n      <td>1.593381e+07</td>\n      <td>992220.000000</td>\n      <td>...</td>\n      <td>煤粉锅炉</td>\n      <td>一般烟煤</td>\n      <td>14.682</td>\n      <td>抽凝式</td>\n      <td>水冷-闭式循环</td>\n      <td>1172.0</td>\n      <td>超临界</td>\n      <td>350.0</td>\n      <td>150</td>\n      <td>21</td>\n    </tr>\n  </tbody>\n</table>\n<p>1491 rows × 21 columns</p>\n</div>"
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_data"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "outputs": [],
   "source": [
    "final_data.to_csv('data/unit_train_data.csv', encoding='utf-8-sig', index=False)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}