{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.multioutput import MultiOutputRegressor\n",
    "import xgboost as xgb\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.metrics import mean_absolute_error, mean_squared_error, mean_absolute_percentage_error, r2_score\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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>机组编号</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "      <th>煤种</th>\n",
       "      <th>所处地区</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5740</th>\n",
       "      <td>榆能榆神热电有限公司</td>\n",
       "      <td>2</td>\n",
       "      <td>350.0</td>\n",
       "      <td>抽凝式</td>\n",
       "      <td>超临界</td>\n",
       "      <td>间接空冷</td>\n",
       "      <td>25514.0</td>\n",
       "      <td>38.84</td>\n",
       "      <td>7.28</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>陕西省</td>\n",
       "      <td>109.820265</td>\n",
       "      <td>38.304383</td>\n",
       "      <td>1151</td>\n",
       "      <td>0.661759</td>\n",
       "      <td>0.091483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            企业名称  机组编号  铭牌容量 (MW) 机组类型 参数分类 冷凝器型式  入炉煤低位热值(kJ/kg)  \\\n",
       "5740  榆能榆神热电有限公司     2      350.0  抽凝式  超临界  间接空冷         25514.0   \n",
       "\n",
       "      燃煤挥发份Var(%)  燃煤灰份Aar(%)  煤种 所处地区   longitude   latitude  altitude  \\\n",
       "5740        38.84        7.28  烟煤  陕西省  109.820265  38.304383      1151   \n",
       "\n",
       "      发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)  \n",
       "5740         0.661759        0.091483  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total_data = pd.read_excel('train_data.xlsx')\n",
    "total_data.tail(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['企业名称', '机组编号', '铭牌容量 (MW)', '机组类型', '参数分类', '冷凝器型式', '入炉煤低位热值(kJ/kg)',\n",
       "       '燃煤挥发份Var(%)', '燃煤灰份Aar(%)', '煤种', '所处地区', 'longitude', 'latitude',\n",
       "       'altitude', '发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total_data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "num_cols = ['铭牌容量 (MW)', '入炉煤低位热值(kJ/kg)', '燃煤挥发份Var(%)', '燃煤灰份Aar(%)', 'longitude', 'latitude', 'altitude', '发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)']\n",
    "# object_cols = ['所处地区', '类型', '机组参数', '冷却型式']\n",
    "object_cols = ['所处地区', '机组类型', '参数分类', '冷凝器型式']\n",
    "# object_cols = ['所处地区', '机组类型', '参数分类', '冷凝器型式', '煤种']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def change_str(x):\n",
    "    if '空冷' in x:\n",
    "        return '空冷'\n",
    "    if '水冷' in x:\n",
    "        return '水冷'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "total_data = total_data[total_data['发电碳排放因子(kg/kWh)'] <= 0.9].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['所处地区',\n",
       " '机组类型',\n",
       " '参数分类',\n",
       " '冷凝器型式',\n",
       " '铭牌容量 (MW)',\n",
       " '入炉煤低位热值(kJ/kg)',\n",
       " '燃煤挥发份Var(%)',\n",
       " '燃煤灰份Aar(%)',\n",
       " 'longitude',\n",
       " 'latitude',\n",
       " 'altitude']"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "use_cols = object_cols + [x for x in num_cols if '因子' not in x]\n",
    "use_cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "total_data = total_data[~total_data['供热碳排放因子(kg/MJ)'].isna()].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5732, 16)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1092, 14)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total_data.groupby(['企业名称', '机组编号']).count().shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "total_data['入炉煤低位热值(kJ/kg)'] = total_data['入炉煤低位热值(kJ/kg)'].apply(lambda x: x * 1000 if x < 100 else x * 1)\n",
    "total_data['燃煤灰份Aar(%)'] = total_data['燃煤灰份Aar(%)'].apply(lambda x: x / 1000 if x > 10000 else x * 1)\n",
    "total_data['燃煤挥发份Var(%)'] = total_data['燃煤挥发份Var(%)'].apply(lambda x: x / 1000 if x > 10000 else x * 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "total_data.altitude = total_data.altitude.apply(lambda x: 0 if x < 0 else x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5629, 16)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "use_data = total_data[(total_data['供热碳排放因子(kg/MJ)'] > 0.01)&(total_data['供热碳排放因子(kg/MJ)'] < 0.1)].copy()\n",
    "use_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    5629.000000\n",
       "mean        0.070915\n",
       "std         0.009967\n",
       "min         0.010464\n",
       "25%         0.065467\n",
       "50%         0.071533\n",
       "75%         0.077513\n",
       "max         0.099905\n",
       "Name: 供热碳排放因子(kg/MJ), dtype: float64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "use_data['供热碳排放因子(kg/MJ)'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\miniconda3\\envs\\py37\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "train_data = use_data.groupby(use_cols)['发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'].mean().reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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>所处地区</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>18366.00</td>\n",
       "      <td>26.05</td>\n",
       "      <td>15.70</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>18426.00</td>\n",
       "      <td>26.05</td>\n",
       "      <td>15.70</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3</td>\n",
       "      <td>0.545516</td>\n",
       "      <td>0.072476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>19507.00</td>\n",
       "      <td>26.40</td>\n",
       "      <td>14.95</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3</td>\n",
       "      <td>0.595849</td>\n",
       "      <td>0.064745</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>19599.00</td>\n",
       "      <td>26.78</td>\n",
       "      <td>11.58</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3</td>\n",
       "      <td>0.584432</td>\n",
       "      <td>0.068390</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>20125.00</td>\n",
       "      <td>24.92</td>\n",
       "      <td>14.90</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3</td>\n",
       "      <td>0.605369</td>\n",
       "      <td>0.066996</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3961</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>200.0</td>\n",
       "      <td>15941.21</td>\n",
       "      <td>23.83</td>\n",
       "      <td>14.73</td>\n",
       "      <td>126.575647</td>\n",
       "      <td>45.918566</td>\n",
       "      <td>118</td>\n",
       "      <td>0.500172</td>\n",
       "      <td>0.064200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3962</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>210.0</td>\n",
       "      <td>15355.00</td>\n",
       "      <td>42.00</td>\n",
       "      <td>36.70</td>\n",
       "      <td>131.695864</td>\n",
       "      <td>46.580444</td>\n",
       "      <td>91</td>\n",
       "      <td>0.518301</td>\n",
       "      <td>0.063249</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3963</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>背压式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷-开式循环</td>\n",
       "      <td>200.0</td>\n",
       "      <td>13396.00</td>\n",
       "      <td>23.39</td>\n",
       "      <td>15.66</td>\n",
       "      <td>123.639146</td>\n",
       "      <td>47.210696</td>\n",
       "      <td>151</td>\n",
       "      <td>0.224312</td>\n",
       "      <td>0.053770</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3964</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>背压式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷-闭式循环</td>\n",
       "      <td>215.0</td>\n",
       "      <td>15753.00</td>\n",
       "      <td>36.29</td>\n",
       "      <td>42.40</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250</td>\n",
       "      <td>0.290814</td>\n",
       "      <td>0.068027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3965</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>背压式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷-闭式循环</td>\n",
       "      <td>215.0</td>\n",
       "      <td>16471.11</td>\n",
       "      <td>30.10</td>\n",
       "      <td>38.67</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3966 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      所处地区 机组类型 参数分类    冷凝器型式  铭牌容量 (MW)  入炉煤低位热值(kJ/kg)  燃煤挥发份Var(%)  \\\n",
       "0      上海市  供热式  亚临界       水冷      300.0        18366.00        26.05   \n",
       "1      上海市  供热式  亚临界       水冷      300.0        18426.00        26.05   \n",
       "2      上海市  供热式  亚临界       水冷      300.0        19507.00        26.40   \n",
       "3      上海市  供热式  亚临界       水冷      300.0        19599.00        26.78   \n",
       "4      上海市  供热式  亚临界       水冷      300.0        20125.00        24.92   \n",
       "...    ...  ...  ...      ...        ...             ...          ...   \n",
       "3961  黑龙江省  纯凝式  超高压       水冷      200.0        15941.21        23.83   \n",
       "3962  黑龙江省  纯凝式  超高压       水冷      210.0        15355.00        42.00   \n",
       "3963  黑龙江省  背压式  超高压  水冷-开式循环      200.0        13396.00        23.39   \n",
       "3964  黑龙江省  背压式  超高压  水冷-闭式循环      215.0        15753.00        36.29   \n",
       "3965  黑龙江省  背压式  超高压  水冷-闭式循环      215.0        16471.11        30.10   \n",
       "\n",
       "      燃煤灰份Aar(%)   longitude   latitude  altitude  发电碳排放因子(kg/kWh)  \\\n",
       "0          15.70  121.471140  31.065113         3         0.537574   \n",
       "1          15.70  121.471140  31.065113         3         0.545516   \n",
       "2          14.95  121.471140  31.065113         3         0.595849   \n",
       "3          11.58  121.471140  31.065113         3         0.584432   \n",
       "4          14.90  121.471140  31.065113         3         0.605369   \n",
       "...          ...         ...        ...       ...              ...   \n",
       "3961       14.73  126.575647  45.918566       118         0.500172   \n",
       "3962       36.70  131.695864  46.580444        91         0.518301   \n",
       "3963       15.66  123.639146  47.210696       151         0.224312   \n",
       "3964       42.40  129.604803  44.608202       250         0.290814   \n",
       "3965       38.67  129.604803  44.608202       250         0.321635   \n",
       "\n",
       "      供热碳排放因子(kg/MJ)  \n",
       "0           0.070992  \n",
       "1           0.072476  \n",
       "2           0.064745  \n",
       "3           0.068390  \n",
       "4           0.066996  \n",
       "...              ...  \n",
       "3961        0.064200  \n",
       "3962        0.063249  \n",
       "3963        0.053770  \n",
       "3964        0.068027  \n",
       "3965        0.067798  \n",
       "\n",
       "[3966 rows x 13 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "for col in num_cols:\n",
    "    if '因子' not in col:\n",
    "        train_data[col] = np.log1p(train_data[col])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "train_data = train_data[train_data['供热碳排放因子(kg/MJ)']<=0.1].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "train_data = pd.get_dummies(train_data, columns=object_cols).dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "for col in train_data.columns:\n",
    "    train_data[col] = train_data[col].astype(float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "feature_cols = [x for x in train_data.columns if '因子' not in x]\n",
    "target_cols = [x for x in train_data.columns if '因子' in x]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "train_data.to_csv('./train_data_processed.csv', encoding='utf-8-sig', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "train, test = train_test_split(train_data.dropna(), test_size=0.1, shuffle=True, random_state=666)\n",
    "train, valid = train_test_split(train, test_size=0.2, shuffle=True, random_state=666)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "train_X, train_y = train[feature_cols], train[target_cols]\n",
    "valid_X, valid_y = valid[feature_cols], valid[target_cols]\n",
    "test_X, test_y = test[feature_cols], test[target_cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "from xgboost import XGBRegressor\n",
    "from bayes_opt import BayesianOptimization"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### 供电建模"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "params_xgb = {'objective': 'reg:squarederror',\n",
    "              'booster': 'gbtree',\n",
    "              'eta': 0.01,\n",
    "              'max_depth': 60,\n",
    "              'subsample': 0.85,\n",
    "              'colsample_bytree': 0.85,\n",
    "              'min_child_weight': 10,\n",
    "              'seed': 10}\n",
    "\n",
    "num_boost_round = 2000\n",
    "\n",
    "dtrain = xgb.DMatrix(train_X, train_y.values[:, 0])\n",
    "dvalid = xgb.DMatrix(valid_X, valid_y.values[:, 0])\n",
    "watchlist = [(dtrain, 'train'), (dvalid, 'eval')]\n",
    "\n",
    "gb_model = xgb.train(params_xgb, dtrain, num_boost_round, evals=watchlist,\n",
    "                early_stopping_rounds=200, verbose_eval=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "y_pred_xgb = gb_model.predict(xgb.DMatrix(test_X))\n",
    "y_true_xgb = test_y.values[:, 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MSE: 5.5E-04\n",
      "RMSE: 0.0235\n",
      "MAE: 0.0145\n",
      "MAPE: 2.99 %\n",
      "R_2: 0.9011\n"
     ]
    }
   ],
   "source": [
    "MSE = mean_squared_error(y_true_xgb, y_pred_xgb)\n",
    "RMSE = np.sqrt(mean_squared_error(y_true_xgb, y_pred_xgb))\n",
    "MAE = mean_absolute_error(y_true_xgb, y_pred_xgb)\n",
    "MAPE = mean_absolute_percentage_error(y_true_xgb, y_pred_xgb)\n",
    "R_2 = r2_score(y_true_xgb, y_pred_xgb)\n",
    "print('MSE:', format(MSE, '.1E'))\n",
    "print('RMSE:', round(RMSE, 4))\n",
    "print('MAE:', round(MAE, 4))\n",
    "print('MAPE:', round(MAPE*100, 2), '%')\n",
    "print('R_2:', round(R_2, 4))  #R方为负就说明拟合效果比平均值差a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "power_eva_df = pd.DataFrame.from_records([y_true_xgb, y_pred_xgb]).T\n",
    "power_eva_df.to_csv('./发电测试结果.csv', index=False, encoding='utf-8-sig')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "gb_model.save_model('./models/power_model.txt')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### 发热建模"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "def xgb_cv(max_depth, learning_rate, min_child_weight, subsample, colsample_bytree, reg_alpha, gamma):\n",
    "    val = cross_val_score(estimator=XGBRegressor(max_depth=int(max_depth),\n",
    "                                                 learning_rate=learning_rate,\n",
    "                                                 n_estimators=2000,\n",
    "                                                 min_child_weight=min_child_weight,\n",
    "                                                 subsample=max(min(subsample, 1), 0),\n",
    "                                                 colsample_bytree=max(min(colsample_bytree, 1), 0),\n",
    "                                                 reg_alpha=max(reg_alpha, 0), gamma=gamma, objective='reg:squarederror',\n",
    "                                                 booster='gbtree',\n",
    "                                                 seed=10), X=train[feature_cols], y=train['供热碳排放因子(kg/MJ)'], scoring='r2',\n",
    "                          cv=10).max()\n",
    "    return val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "params_xgb = {'objective': 'reg:squarederror',\n",
    "              'booster': 'gbtree',\n",
    "              'eta': 0.01,\n",
    "              'max_depth': 30,\n",
    "              'subsample': 0.8,\n",
    "              'colsample_bytree': 0.9,\n",
    "              'min_child_weight': 10,\n",
    "              'seed': 108}\n",
    "\n",
    "num_boost_round = 2000\n",
    "\n",
    "dtrain = xgb.DMatrix(train_X, train_y.values[:, 1])\n",
    "dvalid = xgb.DMatrix(valid_X, valid_y.values[:, 1])\n",
    "watchlist = [(dtrain, 'train'), (dvalid, 'eval')]\n",
    "\n",
    "gb_model_heat = xgb.train(params_xgb, dtrain, num_boost_round, evals=watchlist,\n",
    "                early_stopping_rounds=200, verbose_eval=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "y_pred_heat = gb_model_heat.predict(xgb.DMatrix(test_X))\n",
    "y_true_heat = test_y.values[:, 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MSE: 2.9E-05\n",
      "RMSE: 0.0054\n",
      "MAE: 0.0024\n",
      "MAPE: 5.19 %\n",
      "R_2: 0.7392\n"
     ]
    }
   ],
   "source": [
    "MSE = mean_squared_error(y_true_heat, y_pred_heat)\n",
    "RMSE = np.sqrt(mean_squared_error(y_true_heat, y_pred_heat))\n",
    "MAE = mean_absolute_error(y_true_heat, y_pred_heat)\n",
    "MAPE = mean_absolute_percentage_error(y_true_heat, y_pred_heat)\n",
    "R_2 = r2_score(y_true_heat, y_pred_heat)\n",
    "print('MSE:', format(MSE, '.1E'))\n",
    "print('RMSE:', round(RMSE, 4))\n",
    "print('MAE:', round(MAE, 4))\n",
    "print('MAPE:', round(MAPE*100, 2), '%')\n",
    "print('R_2:', round(R_2, 4))  #R方为负就说明拟合效果比平均值差a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "pd.DataFrame.from_records([y_true_heat, y_pred_heat]).T.to_csv('./供热测试结果.csv', index=False, encoding='utf-8-sig')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "gb_model_heat.save_model('./models/heat_model.txt')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### 煤种标准化工程"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\miniconda3\\envs\\py37\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    }
   ],
   "source": [
    "new_values = use_data.groupby(['煤种', '入炉煤低位热值(kJ/kg)', '燃煤挥发份Var(%)', '燃煤灰份Aar(%)'])['发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>煤种</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>无烟煤</th>\n",
       "      <th>19827.00</th>\n",
       "      <th>11.18</th>\n",
       "      <th>2539.00</th>\n",
       "      <td>0.561424</td>\n",
       "      <td>0.087794</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">烟煤</th>\n",
       "      <th>16733.00</th>\n",
       "      <th>22.53</th>\n",
       "      <th>27.46</th>\n",
       "      <td>0.441511</td>\n",
       "      <td>0.064259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">16740.00</th>\n",
       "      <th>18.99</th>\n",
       "      <th>37.00</th>\n",
       "      <td>0.487225</td>\n",
       "      <td>0.064535</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27.93</th>\n",
       "      <th>24.43</th>\n",
       "      <td>0.418457</td>\n",
       "      <td>0.064747</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16741.00</th>\n",
       "      <th>26.69</th>\n",
       "      <th>25.92</th>\n",
       "      <td>0.433679</td>\n",
       "      <td>0.061822</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">贫煤</th>\n",
       "      <th>22149.00</th>\n",
       "      <th>12.43</th>\n",
       "      <th>25.10</th>\n",
       "      <td>0.629733</td>\n",
       "      <td>0.082772</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22272.51</th>\n",
       "      <th>11.83</th>\n",
       "      <th>22.97</th>\n",
       "      <td>0.627877</td>\n",
       "      <td>0.083234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22475.97</th>\n",
       "      <th>8.90</th>\n",
       "      <th>23.98</th>\n",
       "      <td>0.620331</td>\n",
       "      <td>0.086574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23215.00</th>\n",
       "      <th>11.00</th>\n",
       "      <th>19.31</th>\n",
       "      <td>0.682221</td>\n",
       "      <td>0.080249</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23791.00</th>\n",
       "      <th>11.00</th>\n",
       "      <th>19.31</th>\n",
       "      <td>0.701795</td>\n",
       "      <td>0.082240</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3936 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                           发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)\n",
       "煤种  入炉煤低位热值(kJ/kg) 燃煤挥发份Var(%) 燃煤灰份Aar(%)                                 \n",
       "无烟煤 19827.00       11.18       2539.00            0.561424        0.087794\n",
       "烟煤  16733.00       22.53       27.46              0.441511        0.064259\n",
       "    16740.00       18.99       37.00              0.487225        0.064535\n",
       "                   27.93       24.43              0.418457        0.064747\n",
       "    16741.00       26.69       25.92              0.433679        0.061822\n",
       "...                                                    ...             ...\n",
       "贫煤  22149.00       12.43       25.10              0.629733        0.082772\n",
       "    22272.51       11.83       22.97              0.627877        0.083234\n",
       "    22475.97       8.90        23.98              0.620331        0.086574\n",
       "    23215.00       11.00       19.31              0.682221        0.080249\n",
       "    23791.00       11.00       19.31              0.701795        0.082240\n",
       "\n",
       "[3936 rows x 2 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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>煤种</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>无烟煤</td>\n",
       "      <td>19827.00</td>\n",
       "      <td>11.18</td>\n",
       "      <td>2539.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>烟煤</td>\n",
       "      <td>16733.00</td>\n",
       "      <td>22.53</td>\n",
       "      <td>27.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>烟煤</td>\n",
       "      <td>16740.00</td>\n",
       "      <td>18.99</td>\n",
       "      <td>37.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>烟煤</td>\n",
       "      <td>16740.00</td>\n",
       "      <td>27.93</td>\n",
       "      <td>24.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>烟煤</td>\n",
       "      <td>16741.00</td>\n",
       "      <td>26.69</td>\n",
       "      <td>25.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3931</th>\n",
       "      <td>贫煤</td>\n",
       "      <td>22149.00</td>\n",
       "      <td>12.43</td>\n",
       "      <td>25.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3932</th>\n",
       "      <td>贫煤</td>\n",
       "      <td>22272.51</td>\n",
       "      <td>11.83</td>\n",
       "      <td>22.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3933</th>\n",
       "      <td>贫煤</td>\n",
       "      <td>22475.97</td>\n",
       "      <td>8.90</td>\n",
       "      <td>23.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3934</th>\n",
       "      <td>贫煤</td>\n",
       "      <td>23215.00</td>\n",
       "      <td>11.00</td>\n",
       "      <td>19.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3935</th>\n",
       "      <td>贫煤</td>\n",
       "      <td>23791.00</td>\n",
       "      <td>11.00</td>\n",
       "      <td>19.31</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3936 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       煤种  入炉煤低位热值(kJ/kg)  燃煤挥发份Var(%)  燃煤灰份Aar(%)\n",
       "0     无烟煤        19827.00        11.18     2539.00\n",
       "1      烟煤        16733.00        22.53       27.46\n",
       "2      烟煤        16740.00        18.99       37.00\n",
       "3      烟煤        16740.00        27.93       24.43\n",
       "4      烟煤        16741.00        26.69       25.92\n",
       "...   ...             ...          ...         ...\n",
       "3931   贫煤        22149.00        12.43       25.10\n",
       "3932   贫煤        22272.51        11.83       22.97\n",
       "3933   贫煤        22475.97         8.90       23.98\n",
       "3934   贫煤        23215.00        11.00       19.31\n",
       "3935   贫煤        23791.00        11.00       19.31\n",
       "\n",
       "[3936 rows x 4 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "coal_df = new_values.reset_index().drop(columns=['发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'])\n",
    "coal_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "coal_params_dict = dict()\n",
    "for coal_type in coal_df['煤种'].unique().tolist():\n",
    "    options = coal_df[coal_df['煤种']==coal_type][['入炉煤低位热值(kJ/kg)', '燃煤挥发份Var(%)', '燃煤灰份Aar(%)']].values\n",
    "    coal_params_dict[coal_type] = options"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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>电厂名称</th>\n",
       "      <th>机组编号</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "      <th>煤种</th>\n",
       "      <th>所处地区</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>江苏利港电力有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>21602.05000</td>\n",
       "      <td>26.09</td>\n",
       "      <td>16.80</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>江苏省</td>\n",
       "      <td>120.096620</td>\n",
       "      <td>31.942361</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.586990</td>\n",
       "      <td>0.076843</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>江苏利港电力有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>21926.81000</td>\n",
       "      <td>26.68</td>\n",
       "      <td>15.41</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>江苏省</td>\n",
       "      <td>120.096620</td>\n",
       "      <td>31.942361</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.632859</td>\n",
       "      <td>0.077676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>江苏利港电力有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>21261.93062</td>\n",
       "      <td>26.46</td>\n",
       "      <td>15.18</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>江苏省</td>\n",
       "      <td>120.096620</td>\n",
       "      <td>31.942361</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.609196</td>\n",
       "      <td>0.074823</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>江苏利港电力有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>20840.00000</td>\n",
       "      <td>26.43</td>\n",
       "      <td>14.55</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>江苏省</td>\n",
       "      <td>120.096620</td>\n",
       "      <td>31.942361</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.602178</td>\n",
       "      <td>0.081628</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>江苏利港电力有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>20706.00000</td>\n",
       "      <td>26.43</td>\n",
       "      <td>14.96</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>江苏省</td>\n",
       "      <td>120.096620</td>\n",
       "      <td>31.942361</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.590254</td>\n",
       "      <td>0.081103</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5736</th>\n",
       "      <td>浙江浙能电力股份有限公司台州发电厂</td>\n",
       "      <td>8</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21973.00000</td>\n",
       "      <td>37.43</td>\n",
       "      <td>17.12</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>浙江省</td>\n",
       "      <td>121.465840</td>\n",
       "      <td>28.704623</td>\n",
       "      <td>73.0</td>\n",
       "      <td>0.628300</td>\n",
       "      <td>0.078776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5737</th>\n",
       "      <td>浙江浙能电力股份有限公司台州发电厂</td>\n",
       "      <td>8</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21372.00000</td>\n",
       "      <td>39.87</td>\n",
       "      <td>18.01</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>浙江省</td>\n",
       "      <td>121.465840</td>\n",
       "      <td>28.704623</td>\n",
       "      <td>73.0</td>\n",
       "      <td>0.595019</td>\n",
       "      <td>0.076622</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5738</th>\n",
       "      <td>浙江浙能电力股份有限公司台州发电厂</td>\n",
       "      <td>8</td>\n",
       "      <td>350.0</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20856.00000</td>\n",
       "      <td>39.32</td>\n",
       "      <td>19.74</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>浙江省</td>\n",
       "      <td>121.465840</td>\n",
       "      <td>28.704623</td>\n",
       "      <td>73.0</td>\n",
       "      <td>0.565718</td>\n",
       "      <td>0.074772</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5739</th>\n",
       "      <td>榆能榆神热电有限公司</td>\n",
       "      <td>1</td>\n",
       "      <td>350.0</td>\n",
       "      <td>供热式</td>\n",
       "      <td>超临界</td>\n",
       "      <td>间接空冷</td>\n",
       "      <td>25514.00000</td>\n",
       "      <td>38.84</td>\n",
       "      <td>7.28</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>陕西省</td>\n",
       "      <td>109.820265</td>\n",
       "      <td>38.304383</td>\n",
       "      <td>1151.0</td>\n",
       "      <td>0.664456</td>\n",
       "      <td>0.091482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5740</th>\n",
       "      <td>榆能榆神热电有限公司</td>\n",
       "      <td>2</td>\n",
       "      <td>350.0</td>\n",
       "      <td>供热式</td>\n",
       "      <td>超临界</td>\n",
       "      <td>间接空冷</td>\n",
       "      <td>25514.00000</td>\n",
       "      <td>38.84</td>\n",
       "      <td>7.28</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>陕西省</td>\n",
       "      <td>109.820265</td>\n",
       "      <td>38.304383</td>\n",
       "      <td>1151.0</td>\n",
       "      <td>0.661759</td>\n",
       "      <td>0.091483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5629 rows × 16 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                   电厂名称  机组编号  铭牌容量 (MW) 机组类型 参数分类 冷凝器型式  入炉煤低位热值(kJ/kg)  \\\n",
       "0            江苏利港电力有限公司     1      350.0  纯凝式  亚临界    水冷     21602.05000   \n",
       "1            江苏利港电力有限公司     1      350.0  纯凝式  亚临界    水冷     21926.81000   \n",
       "2            江苏利港电力有限公司     1      350.0  纯凝式  亚临界    水冷     21261.93062   \n",
       "3            江苏利港电力有限公司     1      350.0  纯凝式  亚临界    水冷     20840.00000   \n",
       "4            江苏利港电力有限公司     1      350.0  纯凝式  亚临界    水冷     20706.00000   \n",
       "...                 ...   ...        ...  ...  ...   ...             ...   \n",
       "5736  浙江浙能电力股份有限公司台州发电厂     8      350.0  纯凝式  亚临界   NaN     21973.00000   \n",
       "5737  浙江浙能电力股份有限公司台州发电厂     8      350.0  纯凝式  亚临界   NaN     21372.00000   \n",
       "5738  浙江浙能电力股份有限公司台州发电厂     8      350.0  纯凝式  亚临界   NaN     20856.00000   \n",
       "5739         榆能榆神热电有限公司     1      350.0  供热式  超临界  间接空冷     25514.00000   \n",
       "5740         榆能榆神热电有限公司     2      350.0  供热式  超临界  间接空冷     25514.00000   \n",
       "\n",
       "      燃煤挥发份Var(%)  燃煤灰份Aar(%)  煤种 所处地区   longitude   latitude  altitude  \\\n",
       "0           26.09       16.80  烟煤  江苏省  120.096620  31.942361       1.0   \n",
       "1           26.68       15.41  烟煤  江苏省  120.096620  31.942361       1.0   \n",
       "2           26.46       15.18  烟煤  江苏省  120.096620  31.942361       1.0   \n",
       "3           26.43       14.55  烟煤  江苏省  120.096620  31.942361       1.0   \n",
       "4           26.43       14.96  烟煤  江苏省  120.096620  31.942361       1.0   \n",
       "...           ...         ...  ..  ...         ...        ...       ...   \n",
       "5736        37.43       17.12  烟煤  浙江省  121.465840  28.704623      73.0   \n",
       "5737        39.87       18.01  烟煤  浙江省  121.465840  28.704623      73.0   \n",
       "5738        39.32       19.74  烟煤  浙江省  121.465840  28.704623      73.0   \n",
       "5739        38.84        7.28  烟煤  陕西省  109.820265  38.304383    1151.0   \n",
       "5740        38.84        7.28  烟煤  陕西省  109.820265  38.304383    1151.0   \n",
       "\n",
       "      发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)  \n",
       "0            0.586990        0.076843  \n",
       "1            0.632859        0.077676  \n",
       "2            0.609196        0.074823  \n",
       "3            0.602178        0.081628  \n",
       "4            0.590254        0.081103  \n",
       "...               ...             ...  \n",
       "5736         0.628300        0.078776  \n",
       "5737         0.595019        0.076622  \n",
       "5738         0.565718        0.074772  \n",
       "5739         0.664456        0.091482  \n",
       "5740         0.661759        0.091483  \n",
       "\n",
       "[5629 rows x 16 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "use_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\miniconda3\\envs\\py37\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    },
    {
     "data": {
      "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>所处地区</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>煤种</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>0.545516</td>\n",
       "      <td>0.072476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>0.595849</td>\n",
       "      <td>0.064745</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>0.584432</td>\n",
       "      <td>0.068390</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>烟煤</td>\n",
       "      <td>0.605369</td>\n",
       "      <td>0.066996</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>3075</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>200.0</td>\n",
       "      <td>126.575647</td>\n",
       "      <td>45.918566</td>\n",
       "      <td>118.0</td>\n",
       "      <td>褐煤</td>\n",
       "      <td>0.500172</td>\n",
       "      <td>0.064200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3076</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>200.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>褐煤</td>\n",
       "      <td>0.378298</td>\n",
       "      <td>0.069663</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3077</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>210.0</td>\n",
       "      <td>131.695864</td>\n",
       "      <td>46.580444</td>\n",
       "      <td>91.0</td>\n",
       "      <td>褐煤</td>\n",
       "      <td>0.518301</td>\n",
       "      <td>0.063249</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3078</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>褐煤</td>\n",
       "      <td>0.290814</td>\n",
       "      <td>0.068027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>褐煤</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3080 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      所处地区 机组类型 参数分类 冷凝器型式  铭牌容量 (MW)   longitude   latitude  altitude  煤种  \\\n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0  烟煤   \n",
       "1      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0  烟煤   \n",
       "2      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0  烟煤   \n",
       "3      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0  烟煤   \n",
       "4      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0  烟煤   \n",
       "...    ...  ...  ...   ...        ...         ...        ...       ...  ..   \n",
       "3075  黑龙江省  纯凝式  超高压    水冷      200.0  126.575647  45.918566     118.0  褐煤   \n",
       "3076  黑龙江省  纯凝式  超高压    水冷      200.0  129.604803  44.608202     250.0  褐煤   \n",
       "3077  黑龙江省  纯凝式  超高压    水冷      210.0  131.695864  46.580444      91.0  褐煤   \n",
       "3078  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0  褐煤   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0  褐煤   \n",
       "\n",
       "      发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)  \n",
       "0            0.537574        0.070992  \n",
       "1            0.545516        0.072476  \n",
       "2            0.595849        0.064745  \n",
       "3            0.584432        0.068390  \n",
       "4            0.605369        0.066996  \n",
       "...               ...             ...  \n",
       "3075         0.500172        0.064200  \n",
       "3076         0.378298        0.069663  \n",
       "3077         0.518301        0.063249  \n",
       "3078         0.290814        0.068027  \n",
       "3079         0.321635        0.067798  \n",
       "\n",
       "[3080 rows x 11 columns]"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_use_data = use_data.groupby(use_cols+['煤种'])['发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'].mean().reset_index().drop(columns=['入炉煤低位热值(kJ/kg)', '燃煤挥发份Var(%)', '燃煤灰份Aar(%)'])\n",
    "new_use_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "new_use_data['coal_params'] = new_use_data['煤种'].apply(lambda x: coal_params_dict.get(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "new_use_data.drop(columns='煤种', inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "new_data = new_use_data.explode(column='coal_params')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "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>所处地区</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "      <th>coal_params</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>[16733.0, 22.53, 27.46]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>[16740.0, 18.99, 37.0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>[16740.0, 27.93, 24.43]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>[16741.0, 26.69, 25.92]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.471140</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>[16741.51, 19.51, 35.62]</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>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "      <td>[16723.0, 40.63, 39.94]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "      <td>[16725.0, 26.36, 28.51]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "      <td>[16725.19, 34.59, 37.71]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "      <td>[16725.85, 43.2, 12.0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>215.0</td>\n",
       "      <td>129.604803</td>\n",
       "      <td>44.608202</td>\n",
       "      <td>250.0</td>\n",
       "      <td>0.321635</td>\n",
       "      <td>0.067798</td>\n",
       "      <td>[16729.0, 51.42, 17.33]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7151079 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      所处地区 机组类型 参数分类 冷凝器型式  铭牌容量 (MW)   longitude   latitude  altitude  \\\n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0   \n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0   \n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0   \n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0   \n",
       "0      上海市  供热式  亚临界    水冷      300.0  121.471140  31.065113       3.0   \n",
       "...    ...  ...  ...   ...        ...         ...        ...       ...   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷      215.0  129.604803  44.608202     250.0   \n",
       "\n",
       "      发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)               coal_params  \n",
       "0            0.537574        0.070992   [16733.0, 22.53, 27.46]  \n",
       "0            0.537574        0.070992    [16740.0, 18.99, 37.0]  \n",
       "0            0.537574        0.070992   [16740.0, 27.93, 24.43]  \n",
       "0            0.537574        0.070992   [16741.0, 26.69, 25.92]  \n",
       "0            0.537574        0.070992  [16741.51, 19.51, 35.62]  \n",
       "...               ...             ...                       ...  \n",
       "3079         0.321635        0.067798   [16723.0, 40.63, 39.94]  \n",
       "3079         0.321635        0.067798   [16725.0, 26.36, 28.51]  \n",
       "3079         0.321635        0.067798  [16725.19, 34.59, 37.71]  \n",
       "3079         0.321635        0.067798    [16725.85, 43.2, 12.0]  \n",
       "3079         0.321635        0.067798   [16729.0, 51.42, 17.33]  \n",
       "\n",
       "[7151079 rows x 11 columns]"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "new_data['入炉煤低位热值(kJ/kg)'] = new_data.coal_params.apply(lambda x: x[0]).values\n",
    "new_data['燃煤挥发份Var(%)'] = new_data.coal_params.apply(lambda x: x[1]).values\n",
    "new_data['燃煤灰份Aar(%)'] = new_data.coal_params.apply(lambda x: x[2]).values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "norm_data = new_data.drop(columns='coal_params')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>所处地区</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>发电碳排放因子(kg/kWh)</th>\n",
       "      <th>供热碳排放因子(kg/MJ)</th>\n",
       "      <th>入炉煤低位热值(kJ/kg)</th>\n",
       "      <th>燃煤挥发份Var(%)</th>\n",
       "      <th>燃煤灰份Aar(%)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.47114</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>16733.00</td>\n",
       "      <td>22.53</td>\n",
       "      <td>27.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.47114</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>16740.00</td>\n",
       "      <td>18.99</td>\n",
       "      <td>37.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.47114</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>16740.00</td>\n",
       "      <td>27.93</td>\n",
       "      <td>24.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.47114</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>16741.00</td>\n",
       "      <td>26.69</td>\n",
       "      <td>25.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>300.0</td>\n",
       "      <td>121.47114</td>\n",
       "      <td>31.065113</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.537574</td>\n",
       "      <td>0.070992</td>\n",
       "      <td>16741.51</td>\n",
       "      <td>19.51</td>\n",
       "      <td>35.62</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  所处地区 机组类型 参数分类 冷凝器型式  铭牌容量 (MW)  longitude   latitude  altitude  \\\n",
       "0  上海市  供热式  亚临界    水冷      300.0  121.47114  31.065113       3.0   \n",
       "0  上海市  供热式  亚临界    水冷      300.0  121.47114  31.065113       3.0   \n",
       "0  上海市  供热式  亚临界    水冷      300.0  121.47114  31.065113       3.0   \n",
       "0  上海市  供热式  亚临界    水冷      300.0  121.47114  31.065113       3.0   \n",
       "0  上海市  供热式  亚临界    水冷      300.0  121.47114  31.065113       3.0   \n",
       "\n",
       "   发电碳排放因子(kg/kWh)  供热碳排放因子(kg/MJ)  入炉煤低位热值(kJ/kg)  燃煤挥发份Var(%)  燃煤灰份Aar(%)  \n",
       "0         0.537574        0.070992        16733.00        22.53       27.46  \n",
       "0         0.537574        0.070992        16740.00        18.99       37.00  \n",
       "0         0.537574        0.070992        16740.00        27.93       24.43  \n",
       "0         0.537574        0.070992        16741.00        26.69       25.92  \n",
       "0         0.537574        0.070992        16741.51        19.51       35.62  "
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "norm_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "for col in num_cols:\n",
    "    norm_data[col] = np.log1p(norm_data[col])\n",
    "    # total_data[col] = (total_data[col] - total_data[col].min()) / (total_data[col].max() - total_data[col].min())\n",
    "norm_data_dummpy = pd.get_dummies(norm_data, columns=object_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "norm_data_dummpy.drop(columns=['发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "new_xgb_data = xgb.DMatrix(norm_data_dummpy[feature_cols])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "norm_data['power_co2_factor'] = gb_model.predict(new_xgb_data)\n",
    "norm_data['heat_co2_factor'] = gb_model_heat.predict(new_xgb_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "normaled_data = norm_data.drop(columns=['入炉煤低位热值(kJ/kg)', '燃煤挥发份Var(%)', '燃煤灰份Aar(%)', '发电碳排放因子(kg/kWh)', '供热碳排放因子(kg/MJ)'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>所处地区</th>\n",
       "      <th>机组类型</th>\n",
       "      <th>参数分类</th>\n",
       "      <th>冷凝器型式</th>\n",
       "      <th>铭牌容量 (MW)</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>altitude</th>\n",
       "      <th>power_co2_factor</th>\n",
       "      <th>heat_co2_factor</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.707110</td>\n",
       "      <td>4.807875</td>\n",
       "      <td>3.467769</td>\n",
       "      <td>1.386294</td>\n",
       "      <td>0.492558</td>\n",
       "      <td>0.064411</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.707110</td>\n",
       "      <td>4.807875</td>\n",
       "      <td>3.467769</td>\n",
       "      <td>1.386294</td>\n",
       "      <td>0.474082</td>\n",
       "      <td>0.062117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.707110</td>\n",
       "      <td>4.807875</td>\n",
       "      <td>3.467769</td>\n",
       "      <td>1.386294</td>\n",
       "      <td>0.489623</td>\n",
       "      <td>0.063859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.707110</td>\n",
       "      <td>4.807875</td>\n",
       "      <td>3.467769</td>\n",
       "      <td>1.386294</td>\n",
       "      <td>0.493615</td>\n",
       "      <td>0.064382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>上海市</td>\n",
       "      <td>供热式</td>\n",
       "      <td>亚临界</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.707110</td>\n",
       "      <td>4.807875</td>\n",
       "      <td>3.467769</td>\n",
       "      <td>1.386294</td>\n",
       "      <td>0.470883</td>\n",
       "      <td>0.062354</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.375278</td>\n",
       "      <td>4.872176</td>\n",
       "      <td>3.820088</td>\n",
       "      <td>5.525453</td>\n",
       "      <td>0.388912</td>\n",
       "      <td>0.067787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.375278</td>\n",
       "      <td>4.872176</td>\n",
       "      <td>3.820088</td>\n",
       "      <td>5.525453</td>\n",
       "      <td>0.388606</td>\n",
       "      <td>0.065639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.375278</td>\n",
       "      <td>4.872176</td>\n",
       "      <td>3.820088</td>\n",
       "      <td>5.525453</td>\n",
       "      <td>0.380971</td>\n",
       "      <td>0.068147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.375278</td>\n",
       "      <td>4.872176</td>\n",
       "      <td>3.820088</td>\n",
       "      <td>5.525453</td>\n",
       "      <td>0.401973</td>\n",
       "      <td>0.065844</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3079</th>\n",
       "      <td>黑龙江省</td>\n",
       "      <td>纯凝式</td>\n",
       "      <td>超高压</td>\n",
       "      <td>水冷</td>\n",
       "      <td>5.375278</td>\n",
       "      <td>4.872176</td>\n",
       "      <td>3.820088</td>\n",
       "      <td>5.525453</td>\n",
       "      <td>0.386369</td>\n",
       "      <td>0.065845</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7151079 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      所处地区 机组类型 参数分类 冷凝器型式  铭牌容量 (MW)  longitude  latitude  altitude  \\\n",
       "0      上海市  供热式  亚临界    水冷   5.707110   4.807875  3.467769  1.386294   \n",
       "0      上海市  供热式  亚临界    水冷   5.707110   4.807875  3.467769  1.386294   \n",
       "0      上海市  供热式  亚临界    水冷   5.707110   4.807875  3.467769  1.386294   \n",
       "0      上海市  供热式  亚临界    水冷   5.707110   4.807875  3.467769  1.386294   \n",
       "0      上海市  供热式  亚临界    水冷   5.707110   4.807875  3.467769  1.386294   \n",
       "...    ...  ...  ...   ...        ...        ...       ...       ...   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷   5.375278   4.872176  3.820088  5.525453   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷   5.375278   4.872176  3.820088  5.525453   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷   5.375278   4.872176  3.820088  5.525453   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷   5.375278   4.872176  3.820088  5.525453   \n",
       "3079  黑龙江省  纯凝式  超高压    水冷   5.375278   4.872176  3.820088  5.525453   \n",
       "\n",
       "      power_co2_factor  heat_co2_factor  \n",
       "0             0.492558         0.064411  \n",
       "0             0.474082         0.062117  \n",
       "0             0.489623         0.063859  \n",
       "0             0.493615         0.064382  \n",
       "0             0.470883         0.062354  \n",
       "...                ...              ...  \n",
       "3079          0.388912         0.067787  \n",
       "3079          0.388606         0.065639  \n",
       "3079          0.380971         0.068147  \n",
       "3079          0.401973         0.065844  \n",
       "3079          0.386369         0.065845  \n",
       "\n",
       "[7151079 rows x 10 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "normaled_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "target_cols = ['power_co2_factor', 'heat_co2_factor']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "save_data = normaled_data.groupby([x for x in normaled_data.columns if x not in target_cols])[target_cols].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "save_data.reset_index().to_csv('./results/去煤种化数据.csv', encoding='utf-8-sig', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}