{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "#新增加的两行\n",
    "from pylab import mpl\n",
    "\n",
    "# 设置显示中文字体\n",
    "mpl.rcParams[\"font.sans-serif\"] = [\"SimHei\"]\n",
    "\n",
    "mpl.rcParams[\"axes.unicode_minus\"] = False"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [
    {
     "data": {
      "text/plain": "          日期        企业名称         地址   省份            经度            纬度  烟囱高度（m）  \\\n0 2018-10-01  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″       80   \n1 2018-10-02  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″       80   \n2 2018-10-03  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″       80   \n3 2018-10-04  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″       80   \n4 2018-10-05  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″       80   \n\n       脱硝工艺 脱硝剂名称  脱硝设备数量  ...  供热量（吉焦） 产渣量（吨） 机组运行时间（小时）  硫分（%） 脱硫副产品产量（吨）  \\\n0  SNCR SCR    氨水       3  ...  6536.83    NaN       24.0   0.51        NaN   \n1  SNCR SCR    氨水       3  ...  2484.64    NaN       24.0   0.51        NaN   \n2  SNCR SCR    氨水       3  ...  3020.83    NaN       24.0   0.51        NaN   \n3  SNCR SCR    氨水       3  ...  5599.23    NaN       24.0   0.51      72.52   \n4  SNCR SCR    氨水       3  ...  4702.65    NaN       24.0   0.51        NaN   \n\n   脱硫剂使用量（吨）  脱硫设施运行时间（小时）  脱硝还原剂消耗量（吨）  脱硝运行时间（小时）  燃料消耗量（吨）  \n0       5.06          24.0         2.98        24.0       323  \n1       5.04          24.0         2.97        24.0       218  \n2       5.04          24.0         2.95        24.0       212  \n3       5.03          24.0         2.98        24.0       223  \n4       5.06          24.0         3.01        24.0       243  \n\n[5 rows x 44 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>日期</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>...</th>\n      <th>供热量（吉焦）</th>\n      <th>产渣量（吨）</th>\n      <th>机组运行时间（小时）</th>\n      <th>硫分（%）</th>\n      <th>脱硫副产品产量（吨）</th>\n      <th>脱硫剂使用量（吨）</th>\n      <th>脱硫设施运行时间（小时）</th>\n      <th>脱硝还原剂消耗量（吨）</th>\n      <th>脱硝运行时间（小时）</th>\n      <th>燃料消耗量（吨）</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>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>...</td>\n      <td>6536.83</td>\n      <td>NaN</td>\n      <td>24.0</td>\n      <td>0.51</td>\n      <td>NaN</td>\n      <td>5.06</td>\n      <td>24.0</td>\n      <td>2.98</td>\n      <td>24.0</td>\n      <td>323</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>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>...</td>\n      <td>2484.64</td>\n      <td>NaN</td>\n      <td>24.0</td>\n      <td>0.51</td>\n      <td>NaN</td>\n      <td>5.04</td>\n      <td>24.0</td>\n      <td>2.97</td>\n      <td>24.0</td>\n      <td>218</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>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>...</td>\n      <td>3020.83</td>\n      <td>NaN</td>\n      <td>24.0</td>\n      <td>0.51</td>\n      <td>NaN</td>\n      <td>5.04</td>\n      <td>24.0</td>\n      <td>2.95</td>\n      <td>24.0</td>\n      <td>212</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>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>...</td>\n      <td>5599.23</td>\n      <td>NaN</td>\n      <td>24.0</td>\n      <td>0.51</td>\n      <td>72.52</td>\n      <td>5.03</td>\n      <td>24.0</td>\n      <td>2.98</td>\n      <td>24.0</td>\n      <td>223</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>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>...</td>\n      <td>4702.65</td>\n      <td>NaN</td>\n      <td>24.0</td>\n      <td>0.51</td>\n      <td>NaN</td>\n      <td>5.06</td>\n      <td>24.0</td>\n      <td>3.01</td>\n      <td>24.0</td>\n      <td>243</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 44 columns</p>\n</div>"
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zjxz_daily = pd.read_excel('./data/机器学习样表.xlsx', sheet_name=0, header=[0, 1])\n",
    "old_cols = zjxz_daily.columns\n",
    "new_cols = [x[0].strip() if 'Unnamed' in x[1] else x[0] + '_' + x[1] for x in old_cols]\n",
    "zjxz_daily.columns = new_cols\n",
    "zjxz_daily.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [],
   "source": [
    "zjxz_daily_data = zjxz_daily[['日期', '企业名称', '发电量（千瓦时）', '供热量（吉焦）', '燃料消耗量（吨）']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "outputs": [
    {
     "data": {
      "text/plain": "Index(['企业名称', '地址', '省份', '经度', '纬度', '烟囱高度(m)', '机组数量', '单机容量（MW）', '生产设备类型',\n       '锅炉额定蒸发量 t/h ', '汽轮机类型', '压力参数', '冷却方式', '脱硝工艺', '脱硫工艺', '除尘工艺',\n       'Unnamed: 16', '日期', '机组编号', '投产日期', '燃煤干燥无灰基挥发分vda（%）',\n       '入炉煤低位发热量（GJ/t）', '入炉煤消耗量发电（吨）', '入炉煤消耗量供热（吨）', '脱硝还原剂使用量a侧（吨）',\n       '脱硝还原剂使用量b侧（吨）', '脱硝设施运行时间a侧（小时）', '脱硝设施运行时间b侧（小时）', '发电量', '供热量(吉焦)',\n       '机组运行时间', '硫分（%）', '脱硫副产品产量（吨）', '脱硫剂使用量（吨）', '脱硫设施运行时间（小时）',\n       '脱硝还原剂消耗量（吨）', '燃料消耗量（吨）', '石灰石总量（吨）', 'Unnamed: 38', 'Unnamed: 39',\n       '日期.1', '机组编号.1', '投产日期.1', '燃煤干燥无灰基挥发分vda（%）.1', '入炉煤低位发热量（GJ/t）.1',\n       '入炉煤消耗量发电（吨）.1', '入炉煤消耗量供热（吨）.1', '脱硝还原剂使用量a侧（吨）.1', '脱硝还原剂使用量b侧（吨）.1',\n       '脱硝设施运行时间a侧（小时）.1', '脱硝设施运行时间b侧（小时）.1', '发电量（万千瓦时）', '供热量（吉焦）',\n       '机组运行时间（小时）', '硫分（%）.1', '脱硫副产品产量（吨）.1', '脱硫剂使用量（吨）.1',\n       '脱硫设施运行时间（小时）.1', '脱硝还原剂消耗量（吨）.1', '燃料消耗量（吨）.1', '石灰石总量（吨）.1'],\n      dtype='object')"
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_daily = pd.read_excel('./data/机器学习样表.xlsx', sheet_name=3)\n",
    "xswx_daily.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "outputs": [
    {
     "data": {
      "text/plain": "          days  发电量_2（万千瓦时）  供热量_2（吉焦）  燃料消耗量_2（吨）\n149 2021-05-30         1033        0.0      4763.4\n150 2021-05-31          909        0.0      4516.5",
      "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_2（万千瓦时）</th>\n      <th>供热量_2（吉焦）</th>\n      <th>燃料消耗量_2（吨）</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>149</th>\n      <td>2021-05-30</td>\n      <td>1033</td>\n      <td>0.0</td>\n      <td>4763.4</td>\n    </tr>\n    <tr>\n      <th>150</th>\n      <td>2021-05-31</td>\n      <td>909</td>\n      <td>0.0</td>\n      <td>4516.5</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_daily_unit_1 = xswx_daily[xswx_daily['日期'] >= '2021-01-01'][['日期', '发电量', '供热量(吉焦)', '燃料消耗量（吨）']].copy()\n",
    "xswx_daily_unit_1.columns = ['days', \"发电量_1（万千瓦时）\", '供热量_1（吉焦）', '燃料消耗量_1（吨）']\n",
    "xswx_daily_unit_2 = xswx_daily[xswx_daily['日期.1'] >= '2021-01-01'][\n",
    "    ['日期.1', '发电量（万千瓦时）', '供热量（吉焦）', '燃料消耗量（吨）.1']].copy()\n",
    "xswx_daily_unit_2.columns = ['days', \"发电量_2（万千瓦时）\", '供热量_2（吉焦）', '燃料消耗量_2（吨）']\n",
    "xswx_daily_unit_2.tail(2)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "outputs": [
    {
     "data": {
      "text/plain": "DatetimeIndex(['2021-01-01', '2021-01-02', '2021-01-03', '2021-01-04',\n               '2021-01-05', '2021-01-06', '2021-01-07', '2021-01-08',\n               '2021-01-09', '2021-01-10',\n               ...\n               '2021-05-22', '2021-05-23', '2021-05-24', '2021-05-25',\n               '2021-05-26', '2021-05-27', '2021-05-28', '2021-05-29',\n               '2021-05-30', '2021-05-31'],\n              dtype='datetime64[ns]', length=151, freq='D')"
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min_start = min(xswx_daily_unit_1.days.min(), xswx_daily_unit_2.days.min())\n",
    "max_end = max(xswx_daily_unit_1.days.max(), xswx_daily_unit_2.days.max())\n",
    "date_range = pd.date_range(min_start, max_end, freq='D')\n",
    "date_range"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "outputs": [],
   "source": [
    "xswx_daily_unit_1 = xswx_daily_unit_1.set_index('days').reindex(date_range).fillna(0)\n",
    "xswx_daily_unit_2 = xswx_daily_unit_2.set_index('days').reindex(date_range).fillna(0)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "outputs": [],
   "source": [
    "xswx_daily_data = pd.concat([xswx_daily_unit_1, xswx_daily_unit_2], axis=1)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "outputs": [],
   "source": [
    "xswx_daily_data['企业名称'] = '武乡西山发电有限责任公司'\n",
    "xswx_daily_data['发电量（万千瓦时）'] = xswx_daily_data['发电量_1（万千瓦时）'] + xswx_daily_data['发电量_2（万千瓦时）']\n",
    "xswx_daily_data['供热量（吉焦）'] = xswx_daily_data['供热量_1（吉焦）'] + xswx_daily_data['供热量_2（吉焦）']\n",
    "xswx_daily_data['燃料消耗量（吨）'] = xswx_daily_data['燃料消耗量_1（吨）'] + xswx_daily_data['燃料消耗量_2（吨）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "outputs": [
    {
     "data": {
      "text/plain": "            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）  供热量_2（吉焦）  \\\n2021-01-01        952.0    11032.5      5478.8          893        0.0   \n2021-01-02       1127.0    11180.5      6125.4         1061        0.0   \n2021-01-03       1051.0    11197.7      5717.6         1053        0.0   \n2021-01-04       1179.0    11146.6      6172.5         1237        0.0   \n2021-01-05       1142.0    10922.4      6053.3         1082        0.0   \n...                 ...        ...         ...          ...        ...   \n2021-05-27          0.0        0.0         0.0         1192        0.0   \n2021-05-28          0.0        0.0         0.0         1159        0.0   \n2021-05-29          0.0        0.0         0.0          998        0.0   \n2021-05-30          0.0        0.0         0.0         1033        0.0   \n2021-05-31          0.0        0.0         0.0          909        0.0   \n\n            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）  \n2021-01-01      4689.7  武乡西山发电有限责任公司     1845.0  11032.5   10168.5  \n2021-01-02      5455.5  武乡西山发电有限责任公司     2188.0  11180.5   11580.9  \n2021-01-03      4060.5  武乡西山发电有限责任公司     2104.0  11197.7    9778.1  \n2021-01-04      5574.7  武乡西山发电有限责任公司     2416.0  11146.6   11747.2  \n2021-01-05      6363.9  武乡西山发电有限责任公司     2224.0  10922.4   12417.2  \n...                ...           ...        ...      ...       ...  \n2021-05-27      5684.3  武乡西山发电有限责任公司     1192.0      0.0    5684.3  \n2021-05-28      5349.3  武乡西山发电有限责任公司     1159.0      0.0    5349.3  \n2021-05-29      4851.2  武乡西山发电有限责任公司      998.0      0.0    4851.2  \n2021-05-30      4763.4  武乡西山发电有限责任公司     1033.0      0.0    4763.4  \n2021-05-31      4516.5  武乡西山发电有限责任公司      909.0      0.0    4516.5  \n\n[151 rows x 10 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>发电量_1（万千瓦时）</th>\n      <th>供热量_1（吉焦）</th>\n      <th>燃料消耗量_1（吨）</th>\n      <th>发电量_2（万千瓦时）</th>\n      <th>供热量_2（吉焦）</th>\n      <th>燃料消耗量_2（吨）</th>\n      <th>企业名称</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>2021-01-01</th>\n      <td>952.0</td>\n      <td>11032.5</td>\n      <td>5478.8</td>\n      <td>893</td>\n      <td>0.0</td>\n      <td>4689.7</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1845.0</td>\n      <td>11032.5</td>\n      <td>10168.5</td>\n    </tr>\n    <tr>\n      <th>2021-01-02</th>\n      <td>1127.0</td>\n      <td>11180.5</td>\n      <td>6125.4</td>\n      <td>1061</td>\n      <td>0.0</td>\n      <td>5455.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2188.0</td>\n      <td>11180.5</td>\n      <td>11580.9</td>\n    </tr>\n    <tr>\n      <th>2021-01-03</th>\n      <td>1051.0</td>\n      <td>11197.7</td>\n      <td>5717.6</td>\n      <td>1053</td>\n      <td>0.0</td>\n      <td>4060.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2104.0</td>\n      <td>11197.7</td>\n      <td>9778.1</td>\n    </tr>\n    <tr>\n      <th>2021-01-04</th>\n      <td>1179.0</td>\n      <td>11146.6</td>\n      <td>6172.5</td>\n      <td>1237</td>\n      <td>0.0</td>\n      <td>5574.7</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2416.0</td>\n      <td>11146.6</td>\n      <td>11747.2</td>\n    </tr>\n    <tr>\n      <th>2021-01-05</th>\n      <td>1142.0</td>\n      <td>10922.4</td>\n      <td>6053.3</td>\n      <td>1082</td>\n      <td>0.0</td>\n      <td>6363.9</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2224.0</td>\n      <td>10922.4</td>\n      <td>12417.2</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>2021-05-27</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1192</td>\n      <td>0.0</td>\n      <td>5684.3</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1192.0</td>\n      <td>0.0</td>\n      <td>5684.3</td>\n    </tr>\n    <tr>\n      <th>2021-05-28</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1159</td>\n      <td>0.0</td>\n      <td>5349.3</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1159.0</td>\n      <td>0.0</td>\n      <td>5349.3</td>\n    </tr>\n    <tr>\n      <th>2021-05-29</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>998</td>\n      <td>0.0</td>\n      <td>4851.2</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>998.0</td>\n      <td>0.0</td>\n      <td>4851.2</td>\n    </tr>\n    <tr>\n      <th>2021-05-30</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1033</td>\n      <td>0.0</td>\n      <td>4763.4</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1033.0</td>\n      <td>0.0</td>\n      <td>4763.4</td>\n    </tr>\n    <tr>\n      <th>2021-05-31</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>909</td>\n      <td>0.0</td>\n      <td>4516.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>909.0</td>\n      <td>0.0</td>\n      <td>4516.5</td>\n    </tr>\n  </tbody>\n</table>\n<p>151 rows × 10 columns</p>\n</div>"
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_daily_data"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "outputs": [
    {
     "data": {
      "text/plain": "    Unnamed: 0    Unnamed: 1     监控点名称  二氧化硫浓度(mg/m3)  氮氧化物浓度(mg/m3)  \\\n0     2021.1.1  武乡西山发电有限责任公司  1号炉废气排放口          20.15          31.49   \n1     2021.1.2  武乡西山发电有限责任公司  1号炉废气排放口          20.27          31.65   \n2     2021.1.3  武乡西山发电有限责任公司  1号炉废气排放口          19.72          31.68   \n3     2021.1.4  武乡西山发电有限责任公司  1号炉废气排放口          17.64          31.51   \n4     2021.1.5  武乡西山发电有限责任公司  1号炉废气排放口          18.66          31.72   \n..         ...           ...       ...            ...            ...   \n113  2021.4.26  武乡西山发电有限责任公司  1号炉废气排放口           0.22           0.01   \n114  2021.4.27  武乡西山发电有限责任公司  1号炉废气排放口           0.00           0.01   \n115  2021.4.28  武乡西山发电有限责任公司  1号炉废气排放口           0.01           0.00   \n116  2021.4.29  武乡西山发电有限责任公司  1号炉废气排放口           0.00           0.01   \n117  2021.4.30  武乡西山发电有限责任公司  1号炉废气排放口           0.00           0.02   \n\n     烟尘浓度(mg/m3)  流速(m/s)    流量(m3/h)  Unnamed: 8  Unnamed: 9  ...  \\\n0           2.49    11.24  1558502.96         NaN         NaN  ...   \n1           2.51    12.03  1648629.50         NaN         NaN  ...   \n2           2.50    12.11  1656682.63         NaN         NaN  ...   \n3           2.52    11.79  1610496.46         NaN         NaN  ...   \n4           2.50    11.97  1652330.08         NaN         NaN  ...   \n..           ...      ...         ...         ...         ...  ...   \n113         0.19     0.00        0.00         NaN         NaN  ...   \n114         0.21     0.00        0.00         NaN         NaN  ...   \n115         0.25     0.00        0.00         NaN         NaN  ...   \n116         0.26     0.00        0.00         NaN         NaN  ...   \n117         0.56     0.00        0.00         NaN         NaN  ...   \n\n      Unnamed: 14   监控点名称.1  二氧化硫浓度(mg/m3).1 氮氧化物浓度(mg/m3).1 烟尘浓度(mg/m3).1  \\\n0    武乡西山发电有限责任公司  2号炉废气排放口            22.00           33.09          2.25   \n1    武乡西山发电有限责任公司  2号炉废气排放口            20.45           34.37          2.37   \n2    武乡西山发电有限责任公司  2号炉废气排放口            19.82           33.55          2.38   \n3    武乡西山发电有限责任公司  2号炉废气排放口            20.18           32.47          2.39   \n4    武乡西山发电有限责任公司  2号炉废气排放口            21.07           33.73          2.42   \n..            ...       ...              ...             ...           ...   \n113  武乡西山发电有限责任公司  2号炉废气排放口            18.31           35.41          2.03   \n114  武乡西山发电有限责任公司  2号炉废气排放口             0.14            0.43          0.08   \n115  武乡西山发电有限责任公司  2号炉废气排放口             0.00            0.01          0.09   \n116  武乡西山发电有限责任公司  2号炉废气排放口             0.01            0.05          0.07   \n117  武乡西山发电有限责任公司  2号炉废气排放口             3.96           22.90          0.68   \n\n    流速(m/s).1  流量(m3/h).1  Unnamed: 21  Unnamed: 22  状态.1  \n0        5.00   731609.00          NaN          NaN  正常运行  \n1        9.18  1326387.42          NaN          NaN  正常运行  \n2        9.85  1417186.13          NaN          NaN  正常运行  \n3        9.07  1304455.88          NaN          NaN  正常运行  \n4        9.71  1390566.88          NaN          NaN  正常运行  \n..        ...         ...          ...          ...   ...  \n113      9.59  1316204.83          NaN          NaN  正常运行  \n114      1.44   193474.61          NaN          NaN    停运  \n115      2.69   467356.96          NaN          NaN    停运  \n116      2.30   401366.08          NaN          NaN    停运  \n117      6.09   932694.63          NaN          NaN    停运  \n\n[118 rows x 24 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>Unnamed: 0</th>\n      <th>Unnamed: 1</th>\n      <th>监控点名称</th>\n      <th>二氧化硫浓度(mg/m3)</th>\n      <th>氮氧化物浓度(mg/m3)</th>\n      <th>烟尘浓度(mg/m3)</th>\n      <th>流速(m/s)</th>\n      <th>流量(m3/h)</th>\n      <th>Unnamed: 8</th>\n      <th>Unnamed: 9</th>\n      <th>...</th>\n      <th>Unnamed: 14</th>\n      <th>监控点名称.1</th>\n      <th>二氧化硫浓度(mg/m3).1</th>\n      <th>氮氧化物浓度(mg/m3).1</th>\n      <th>烟尘浓度(mg/m3).1</th>\n      <th>流速(m/s).1</th>\n      <th>流量(m3/h).1</th>\n      <th>Unnamed: 21</th>\n      <th>Unnamed: 22</th>\n      <th>状态.1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2021.1.1</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>20.15</td>\n      <td>31.49</td>\n      <td>2.49</td>\n      <td>11.24</td>\n      <td>1558502.96</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>22.00</td>\n      <td>33.09</td>\n      <td>2.25</td>\n      <td>5.00</td>\n      <td>731609.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2021.1.2</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>20.27</td>\n      <td>31.65</td>\n      <td>2.51</td>\n      <td>12.03</td>\n      <td>1648629.50</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>20.45</td>\n      <td>34.37</td>\n      <td>2.37</td>\n      <td>9.18</td>\n      <td>1326387.42</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2021.1.3</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>19.72</td>\n      <td>31.68</td>\n      <td>2.50</td>\n      <td>12.11</td>\n      <td>1656682.63</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>19.82</td>\n      <td>33.55</td>\n      <td>2.38</td>\n      <td>9.85</td>\n      <td>1417186.13</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2021.1.4</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>17.64</td>\n      <td>31.51</td>\n      <td>2.52</td>\n      <td>11.79</td>\n      <td>1610496.46</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>20.18</td>\n      <td>32.47</td>\n      <td>2.39</td>\n      <td>9.07</td>\n      <td>1304455.88</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2021.1.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>18.66</td>\n      <td>31.72</td>\n      <td>2.50</td>\n      <td>11.97</td>\n      <td>1652330.08</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>21.07</td>\n      <td>33.73</td>\n      <td>2.42</td>\n      <td>9.71</td>\n      <td>1390566.88</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</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>113</th>\n      <td>2021.4.26</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>0.22</td>\n      <td>0.01</td>\n      <td>0.19</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>18.31</td>\n      <td>35.41</td>\n      <td>2.03</td>\n      <td>9.59</td>\n      <td>1316204.83</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>114</th>\n      <td>2021.4.27</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>0.00</td>\n      <td>0.01</td>\n      <td>0.21</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>0.14</td>\n      <td>0.43</td>\n      <td>0.08</td>\n      <td>1.44</td>\n      <td>193474.61</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>115</th>\n      <td>2021.4.28</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>0.01</td>\n      <td>0.00</td>\n      <td>0.25</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>0.00</td>\n      <td>0.01</td>\n      <td>0.09</td>\n      <td>2.69</td>\n      <td>467356.96</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>116</th>\n      <td>2021.4.29</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>0.00</td>\n      <td>0.01</td>\n      <td>0.26</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>0.01</td>\n      <td>0.05</td>\n      <td>0.07</td>\n      <td>2.30</td>\n      <td>401366.08</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>117</th>\n      <td>2021.4.30</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1号炉废气排放口</td>\n      <td>0.00</td>\n      <td>0.02</td>\n      <td>0.56</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2号炉废气排放口</td>\n      <td>3.96</td>\n      <td>22.90</td>\n      <td>0.68</td>\n      <td>6.09</td>\n      <td>932694.63</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>停运</td>\n    </tr>\n  </tbody>\n</table>\n<p>118 rows × 24 columns</p>\n</div>"
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_emiss_data = pd.read_excel('data/机器学习样表_单位换算.xlsx', sheet_name=2)\n",
    "xswx_emiss_data"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "outputs": [
    {
     "data": {
      "text/plain": "    Unnamed: 0  二氧化硫浓度(mg/m3)  氮氧化物浓度(mg/m3)  烟尘浓度(mg/m3)  流速(m/s)  \\\n0     2021.1.1          20.15          31.49         2.49    11.24   \n1     2021.1.2          20.27          31.65         2.51    12.03   \n2     2021.1.3          19.72          31.68         2.50    12.11   \n3     2021.1.4          17.64          31.51         2.52    11.79   \n4     2021.1.5          18.66          31.72         2.50    11.97   \n..         ...            ...            ...          ...      ...   \n113  2021.4.26           0.22           0.01         0.19     0.00   \n114  2021.4.27           0.00           0.01         0.21     0.00   \n115  2021.4.28           0.01           0.00         0.25     0.00   \n116  2021.4.29           0.00           0.01         0.26     0.00   \n117  2021.4.30           0.00           0.02         0.56     0.00   \n\n       流量(m3/h)    状态  \n0    1558502.96  正常运行  \n1    1648629.50  正常运行  \n2    1656682.63  正常运行  \n3    1610496.46  正常运行  \n4    1652330.08  正常运行  \n..          ...   ...  \n113        0.00    停运  \n114        0.00    停运  \n115        0.00    停运  \n116        0.00    停运  \n117        0.00    停运  \n\n[118 rows x 7 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>Unnamed: 0</th>\n      <th>二氧化硫浓度(mg/m3)</th>\n      <th>氮氧化物浓度(mg/m3)</th>\n      <th>烟尘浓度(mg/m3)</th>\n      <th>流速(m/s)</th>\n      <th>流量(m3/h)</th>\n      <th>状态</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2021.1.1</td>\n      <td>20.15</td>\n      <td>31.49</td>\n      <td>2.49</td>\n      <td>11.24</td>\n      <td>1558502.96</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2021.1.2</td>\n      <td>20.27</td>\n      <td>31.65</td>\n      <td>2.51</td>\n      <td>12.03</td>\n      <td>1648629.50</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2021.1.3</td>\n      <td>19.72</td>\n      <td>31.68</td>\n      <td>2.50</td>\n      <td>12.11</td>\n      <td>1656682.63</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2021.1.4</td>\n      <td>17.64</td>\n      <td>31.51</td>\n      <td>2.52</td>\n      <td>11.79</td>\n      <td>1610496.46</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2021.1.5</td>\n      <td>18.66</td>\n      <td>31.72</td>\n      <td>2.50</td>\n      <td>11.97</td>\n      <td>1652330.08</td>\n      <td>正常运行</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    </tr>\n    <tr>\n      <th>113</th>\n      <td>2021.4.26</td>\n      <td>0.22</td>\n      <td>0.01</td>\n      <td>0.19</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>114</th>\n      <td>2021.4.27</td>\n      <td>0.00</td>\n      <td>0.01</td>\n      <td>0.21</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>115</th>\n      <td>2021.4.28</td>\n      <td>0.01</td>\n      <td>0.00</td>\n      <td>0.25</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>116</th>\n      <td>2021.4.29</td>\n      <td>0.00</td>\n      <td>0.01</td>\n      <td>0.26</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>117</th>\n      <td>2021.4.30</td>\n      <td>0.00</td>\n      <td>0.02</td>\n      <td>0.56</td>\n      <td>0.00</td>\n      <td>0.00</td>\n      <td>停运</td>\n    </tr>\n  </tbody>\n</table>\n<p>118 rows × 7 columns</p>\n</div>"
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_emiss_data_1 = xswx_emiss_data[np.array(xswx_emiss_data.columns)[[0, 3, 4, 5, 6, 7, 10]]].copy()\n",
    "xswx_emiss_data_2 = xswx_emiss_data[np.array(xswx_emiss_data.columns)[[13, 16, 17, 18, 19, 20, 23]]].copy()\n",
    "xswx_emiss_data_1"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "outputs": [],
   "source": [
    "xswx_emiss_data_1.columns = ['days'] + xswx_emiss_data_1.columns[1:].tolist()\n",
    "xswx_emiss_data_2.columns = xswx_emiss_data_1.columns.tolist()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "outputs": [],
   "source": [
    "xswx_emiss_data_1.index = pd.to_datetime(xswx_emiss_data_1.days)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "outputs": [],
   "source": [
    "xswx_emiss_data_2.index = pd.to_datetime(xswx_emiss_data_2.days)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "outputs": [],
   "source": [
    "xswx_emiss_data_1.drop(columns=['days'], inplace=True)\n",
    "xswx_emiss_data_2.drop(columns=['days'], inplace=True)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "outputs": [],
   "source": [
    "xswx_emiss_data_1.columns = [f'机组1_{x}' for x in xswx_emiss_data_1.columns]\n",
    "xswx_emiss_data_2.columns = [f'机组2_{x}' for x in xswx_emiss_data_2.columns]"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "outputs": [
    {
     "data": {
      "text/plain": "2021-01-01    1\n2021-03-17    1\n2021-03-29    1\n2021-03-28    1\n2021-03-27    1\n             ..\n2021-02-05    1\n2021-02-04    1\n2021-02-03    1\n2021-02-02    1\n2021-04-30    1\nName: days, Length: 118, dtype: int64"
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xswx_emiss_data_1.reset_index().days.value_counts()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "outputs": [
    {
     "data": {
      "text/plain": "            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）  供热量_2（吉焦）  \\\n2021-01-01        952.0    11032.5      5478.8          893        0.0   \n2021-01-02       1127.0    11180.5      6125.4         1061        0.0   \n2021-01-03       1051.0    11197.7      5717.6         1053        0.0   \n2021-01-04       1179.0    11146.6      6172.5         1237        0.0   \n2021-01-05       1142.0    10922.4      6053.3         1082        0.0   \n...                 ...        ...         ...          ...        ...   \n2021-05-27          0.0        0.0         0.0         1192        0.0   \n2021-05-28          0.0        0.0         0.0         1159        0.0   \n2021-05-29          0.0        0.0         0.0          998        0.0   \n2021-05-30          0.0        0.0         0.0         1033        0.0   \n2021-05-31          0.0        0.0         0.0          909        0.0   \n\n            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）  ...  \\\n2021-01-01      4689.7  武乡西山发电有限责任公司     1845.0  11032.5   10168.5  ...   \n2021-01-02      5455.5  武乡西山发电有限责任公司     2188.0  11180.5   11580.9  ...   \n2021-01-03      4060.5  武乡西山发电有限责任公司     2104.0  11197.7    9778.1  ...   \n2021-01-04      5574.7  武乡西山发电有限责任公司     2416.0  11146.6   11747.2  ...   \n2021-01-05      6363.9  武乡西山发电有限责任公司     2224.0  10922.4   12417.2  ...   \n...                ...           ...        ...      ...       ...  ...   \n2021-05-27      5684.3  武乡西山发电有限责任公司     1192.0      0.0    5684.3  ...   \n2021-05-28      5349.3  武乡西山发电有限责任公司     1159.0      0.0    5349.3  ...   \n2021-05-29      4851.2  武乡西山发电有限责任公司      998.0      0.0    4851.2  ...   \n2021-05-30      4763.4  武乡西山发电有限责任公司     1033.0      0.0    4763.4  ...   \n2021-05-31      4516.5  武乡西山发电有限责任公司      909.0      0.0    4516.5  ...   \n\n            机组1_烟尘浓度(mg/m3)  机组1_流速(m/s)  机组1_流量(m3/h)  机组1_状态  \\\n2021-01-01             2.49        11.24    1558502.96    正常运行   \n2021-01-02             2.51        12.03    1648629.50    正常运行   \n2021-01-03             2.50        12.11    1656682.63    正常运行   \n2021-01-04             2.52        11.79    1610496.46    正常运行   \n2021-01-05             2.50        11.97    1652330.08    正常运行   \n...                     ...          ...           ...     ...   \n2021-05-27              NaN          NaN           NaN     NaN   \n2021-05-28              NaN          NaN           NaN     NaN   \n2021-05-29              NaN          NaN           NaN     NaN   \n2021-05-30              NaN          NaN           NaN     NaN   \n2021-05-31              NaN          NaN           NaN     NaN   \n\n            机组2_二氧化硫浓度(mg/m3) 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)  \\\n2021-01-01              22.00             33.09             2.25         5.00   \n2021-01-02              20.45             34.37             2.37         9.18   \n2021-01-03              19.82             33.55             2.38         9.85   \n2021-01-04              20.18             32.47             2.39         9.07   \n2021-01-05              21.07             33.73             2.42         9.71   \n...                       ...               ...              ...          ...   \n2021-05-27                NaN               NaN              NaN          NaN   \n2021-05-28                NaN               NaN              NaN          NaN   \n2021-05-29                NaN               NaN              NaN          NaN   \n2021-05-30                NaN               NaN              NaN          NaN   \n2021-05-31                NaN               NaN              NaN          NaN   \n\n            机组2_流量(m3/h)  机组2_状态  \n2021-01-01     731609.00    正常运行  \n2021-01-02    1326387.42    正常运行  \n2021-01-03    1417186.13    正常运行  \n2021-01-04    1304455.88    正常运行  \n2021-01-05    1390566.88    正常运行  \n...                  ...     ...  \n2021-05-27           NaN     NaN  \n2021-05-28           NaN     NaN  \n2021-05-29           NaN     NaN  \n2021-05-30           NaN     NaN  \n2021-05-31           NaN     NaN  \n\n[151 rows x 22 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>发电量_1（万千瓦时）</th>\n      <th>供热量_1（吉焦）</th>\n      <th>燃料消耗量_1（吨）</th>\n      <th>发电量_2（万千瓦时）</th>\n      <th>供热量_2（吉焦）</th>\n      <th>燃料消耗量_2（吨）</th>\n      <th>企业名称</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      <th>...</th>\n      <th>机组1_烟尘浓度(mg/m3)</th>\n      <th>机组1_流速(m/s)</th>\n      <th>机组1_流量(m3/h)</th>\n      <th>机组1_状态</th>\n      <th>机组2_二氧化硫浓度(mg/m3)</th>\n      <th>机组2_氮氧化物浓度(mg/m3)</th>\n      <th>机组2_烟尘浓度(mg/m3)</th>\n      <th>机组2_流速(m/s)</th>\n      <th>机组2_流量(m3/h)</th>\n      <th>机组2_状态</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2021-01-01</th>\n      <td>952.0</td>\n      <td>11032.5</td>\n      <td>5478.8</td>\n      <td>893</td>\n      <td>0.0</td>\n      <td>4689.7</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1845.0</td>\n      <td>11032.5</td>\n      <td>10168.5</td>\n      <td>...</td>\n      <td>2.49</td>\n      <td>11.24</td>\n      <td>1558502.96</td>\n      <td>正常运行</td>\n      <td>22.00</td>\n      <td>33.09</td>\n      <td>2.25</td>\n      <td>5.00</td>\n      <td>731609.00</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2021-01-02</th>\n      <td>1127.0</td>\n      <td>11180.5</td>\n      <td>6125.4</td>\n      <td>1061</td>\n      <td>0.0</td>\n      <td>5455.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2188.0</td>\n      <td>11180.5</td>\n      <td>11580.9</td>\n      <td>...</td>\n      <td>2.51</td>\n      <td>12.03</td>\n      <td>1648629.50</td>\n      <td>正常运行</td>\n      <td>20.45</td>\n      <td>34.37</td>\n      <td>2.37</td>\n      <td>9.18</td>\n      <td>1326387.42</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2021-01-03</th>\n      <td>1051.0</td>\n      <td>11197.7</td>\n      <td>5717.6</td>\n      <td>1053</td>\n      <td>0.0</td>\n      <td>4060.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2104.0</td>\n      <td>11197.7</td>\n      <td>9778.1</td>\n      <td>...</td>\n      <td>2.50</td>\n      <td>12.11</td>\n      <td>1656682.63</td>\n      <td>正常运行</td>\n      <td>19.82</td>\n      <td>33.55</td>\n      <td>2.38</td>\n      <td>9.85</td>\n      <td>1417186.13</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2021-01-04</th>\n      <td>1179.0</td>\n      <td>11146.6</td>\n      <td>6172.5</td>\n      <td>1237</td>\n      <td>0.0</td>\n      <td>5574.7</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2416.0</td>\n      <td>11146.6</td>\n      <td>11747.2</td>\n      <td>...</td>\n      <td>2.52</td>\n      <td>11.79</td>\n      <td>1610496.46</td>\n      <td>正常运行</td>\n      <td>20.18</td>\n      <td>32.47</td>\n      <td>2.39</td>\n      <td>9.07</td>\n      <td>1304455.88</td>\n      <td>正常运行</td>\n    </tr>\n    <tr>\n      <th>2021-01-05</th>\n      <td>1142.0</td>\n      <td>10922.4</td>\n      <td>6053.3</td>\n      <td>1082</td>\n      <td>0.0</td>\n      <td>6363.9</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>2224.0</td>\n      <td>10922.4</td>\n      <td>12417.2</td>\n      <td>...</td>\n      <td>2.50</td>\n      <td>11.97</td>\n      <td>1652330.08</td>\n      <td>正常运行</td>\n      <td>21.07</td>\n      <td>33.73</td>\n      <td>2.42</td>\n      <td>9.71</td>\n      <td>1390566.88</td>\n      <td>正常运行</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>2021-05-27</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1192</td>\n      <td>0.0</td>\n      <td>5684.3</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1192.0</td>\n      <td>0.0</td>\n      <td>5684.3</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2021-05-28</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1159</td>\n      <td>0.0</td>\n      <td>5349.3</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1159.0</td>\n      <td>0.0</td>\n      <td>5349.3</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2021-05-29</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>998</td>\n      <td>0.0</td>\n      <td>4851.2</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>998.0</td>\n      <td>0.0</td>\n      <td>4851.2</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2021-05-30</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>1033</td>\n      <td>0.0</td>\n      <td>4763.4</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>1033.0</td>\n      <td>0.0</td>\n      <td>4763.4</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2021-05-31</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>909</td>\n      <td>0.0</td>\n      <td>4516.5</td>\n      <td>武乡西山发电有限责任公司</td>\n      <td>909.0</td>\n      <td>0.0</td>\n      <td>4516.5</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>151 rows × 22 columns</p>\n</div>"
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([xswx_daily_data, xswx_emiss_data_1, xswx_emiss_data_2], axis=1)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "### 邯郸东郊"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "outputs": [
    {
     "data": {
      "text/plain": "Index(['企业名称', '地址', '省份', '经度', '纬度', '机组数量', '单机容量（MW）', '生产设备类型',\n       '锅炉额定蒸发量 t/h ', '汽轮机类型', '压力参数', '冷却方式', '脱硝工艺', '脱硫工艺', '除尘工艺', '日期',\n       '机组编号', '投产日期', '燃料类型', '低位发热量（GJ/t）', '产灰量（吨）', '发电量（万千瓦时）', '供热量',\n       '产渣量', '机组运行时间', '发电煤耗（克/千瓦时）', '燃料消耗量（吨）', 'Unnamed: 27', '日期.1',\n       '机组编号.1', '投产日期.1', '燃料类型.1', '低位发热量（GJ/t）.1', '产灰量（吨）.1',\n       '发电量（万千瓦时）.1', '供热量.1', '产渣量.1', '机组运行时间.1', '发电煤耗（克/千瓦时）.1',\n       '燃料消耗量（吨）.1'],\n      dtype='object')"
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_daily = pd.read_excel('data/机器学习样表_单位换算.xlsx', sheet_name=5)\n",
    "hddj_daily.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "outputs": [],
   "source": [
    "hddj_daily_1 = hddj_daily[['日期', '发电量（万千瓦时）', '供热量', '燃料消耗量（吨）']].copy()\n",
    "hddj_daily_1.columns = ['days', \"发电量_1（万千瓦时）\", '供热量_1（吉焦）', '燃料消耗量_1（吨）']\n",
    "hddj_daily_2 = hddj_daily[['日期.1', '发电量（万千瓦时）.1', '供热量.1', '燃料消耗量（吨）.1']].copy()\n",
    "hddj_daily_2.columns = ['days', \"发电量_2（万千瓦时）\", '供热量_2（吉焦）', '燃料消耗量_2（吨）']"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "outputs": [
    {
     "data": {
      "text/plain": "DatetimeIndex(['2022-01-01', '2022-01-02', '2022-01-03', '2022-01-04',\n               '2022-01-05', '2022-01-06', '2022-01-07', '2022-01-08',\n               '2022-01-09', '2022-01-10', '2022-01-11', '2022-01-12',\n               '2022-01-13', '2022-01-14', '2022-01-15', '2022-01-16',\n               '2022-01-17', '2022-01-18', '2022-01-19', '2022-01-20',\n               '2022-01-21', '2022-01-22', '2022-01-23', '2022-01-24',\n               '2022-01-25', '2022-01-26', '2022-01-27', '2022-01-28',\n               '2022-01-29', '2022-01-30', '2022-01-31', '2022-02-01',\n               '2022-02-02', '2022-02-03', '2022-02-04', '2022-02-05',\n               '2022-02-06', '2022-02-07', '2022-02-08', '2022-02-09',\n               '2022-02-10', '2022-02-11', '2022-02-12', '2022-02-13',\n               '2022-02-14', '2022-02-15', '2022-02-16', '2022-02-17',\n               '2022-02-18', '2022-02-19', '2022-02-20', '2022-02-21',\n               '2022-02-22', '2022-02-23', '2022-02-24', '2022-02-25',\n               '2022-02-26', '2022-02-27', '2022-02-28'],\n              dtype='datetime64[ns]', freq='D')"
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min_start = min(hddj_daily_1.days.min(), hddj_daily_2.days.min())\n",
    "max_end = max(hddj_daily_1.days.max(), hddj_daily_2.days.max())\n",
    "date_range = pd.date_range(min_start, max_end, freq='D')\n",
    "date_range"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "outputs": [],
   "source": [
    "hddj_daily_1 = hddj_daily_1.set_index('days').reindex(date_range).fillna(0)\n",
    "hddj_daily_2 = hddj_daily_2.set_index('days').reindex(date_range).fillna(0)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "outputs": [
    {
     "data": {
      "text/plain": "            发电量_1（万千瓦时）  供热量_1（吉焦）  燃料消耗量_1（吨）\n2022-01-01       494.20      30829        2861\n2022-01-02       554.30      32122        2536\n2022-01-03       558.30      33451        2911\n2022-01-04       529.70      33179        3023\n2022-01-05       563.90      29731        3191\n2022-01-06       561.00      32505        3357\n2022-01-07       570.00      33189        3231\n2022-01-08       526.80      31881        2765\n2022-01-09       517.10      30799        2574\n2022-01-10       512.80      29277        2512\n2022-01-11       521.20      32460        2757\n2022-01-12       543.32      33593        3132\n2022-01-13       512.52      33326        2950\n2022-01-14       495.42      31417        2755\n2022-01-15       500.06      32434        2834\n2022-01-16       527.93      31986        3182\n2022-01-17       496.50      32268        3121\n2022-01-18       529.31      31814        3241\n2022-01-19       552.01      30414        3274\n2022-01-20       544.00      32416        3594\n2022-01-21       561.29      34300        3891\n2022-01-22       574.00      38342        4276\n2022-01-23       534.94      37444        3767\n2022-01-24       543.91      34539        3175\n2022-01-25       538.31      36753        3860\n2022-01-26       529.59      34148        3749\n2022-01-27       525.88      33630        3725\n2022-01-28       545.06      34181        3866\n2022-01-29       522.68      30637        3395\n2022-01-30       509.69      34254        3101\n2022-01-31       516.51      32145        2985\n2022-02-01       500.46      25687        2662\n2022-02-02       477.03      29061        2821\n2022-02-03       439.93      29598        2779\n2022-02-04       452.76      28709        2523\n2022-02-05       508.35      30133        2884\n2022-02-06       485.41      27635        2902\n2022-02-07       469.75      28259        2939\n2022-02-08       452.87      26685        2556\n2022-02-09       470.87      26037        2691\n2022-02-10       490.75      25530        2901\n2022-02-11       467.50      24359        2790\n2022-02-12       446.31      24180        2766\n2022-02-13       466.12      25274        3054\n2022-02-14       464.96      29338        2533\n2022-02-15       466.40      27394        2611\n2022-02-16       493.26      27639        2905\n2022-02-17       495.53      30228        2894\n2022-02-18       524.59      28126        3030\n2022-02-19       466.49      27575        2470\n2022-02-20       503.46      27424        2799\n2022-02-21       521.02      26965        3098\n2022-02-22       528.08      26886        3317\n2022-02-23       533.95      25022        3174\n2022-02-24       505.76      26727        3079\n2022-02-25       445.43      21930        2580\n2022-02-26       491.01      16645        2733\n2022-02-27       465.33      17884        2862\n2022-02-28       487.21      15457        3029",
      "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>发电量_1（万千瓦时）</th>\n      <th>供热量_1（吉焦）</th>\n      <th>燃料消耗量_1（吨）</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2022-01-01</th>\n      <td>494.20</td>\n      <td>30829</td>\n      <td>2861</td>\n    </tr>\n    <tr>\n      <th>2022-01-02</th>\n      <td>554.30</td>\n      <td>32122</td>\n      <td>2536</td>\n    </tr>\n    <tr>\n      <th>2022-01-03</th>\n      <td>558.30</td>\n      <td>33451</td>\n      <td>2911</td>\n    </tr>\n    <tr>\n      <th>2022-01-04</th>\n      <td>529.70</td>\n      <td>33179</td>\n      <td>3023</td>\n    </tr>\n    <tr>\n      <th>2022-01-05</th>\n      <td>563.90</td>\n      <td>29731</td>\n      <td>3191</td>\n    </tr>\n    <tr>\n      <th>2022-01-06</th>\n      <td>561.00</td>\n      <td>32505</td>\n      <td>3357</td>\n    </tr>\n    <tr>\n      <th>2022-01-07</th>\n      <td>570.00</td>\n      <td>33189</td>\n      <td>3231</td>\n    </tr>\n    <tr>\n      <th>2022-01-08</th>\n      <td>526.80</td>\n      <td>31881</td>\n      <td>2765</td>\n    </tr>\n    <tr>\n      <th>2022-01-09</th>\n      <td>517.10</td>\n      <td>30799</td>\n      <td>2574</td>\n    </tr>\n    <tr>\n      <th>2022-01-10</th>\n      <td>512.80</td>\n      <td>29277</td>\n      <td>2512</td>\n    </tr>\n    <tr>\n      <th>2022-01-11</th>\n      <td>521.20</td>\n      <td>32460</td>\n      <td>2757</td>\n    </tr>\n    <tr>\n      <th>2022-01-12</th>\n      <td>543.32</td>\n      <td>33593</td>\n      <td>3132</td>\n    </tr>\n    <tr>\n      <th>2022-01-13</th>\n      <td>512.52</td>\n      <td>33326</td>\n      <td>2950</td>\n    </tr>\n    <tr>\n      <th>2022-01-14</th>\n      <td>495.42</td>\n      <td>31417</td>\n      <td>2755</td>\n    </tr>\n    <tr>\n      <th>2022-01-15</th>\n      <td>500.06</td>\n      <td>32434</td>\n      <td>2834</td>\n    </tr>\n    <tr>\n      <th>2022-01-16</th>\n      <td>527.93</td>\n      <td>31986</td>\n      <td>3182</td>\n    </tr>\n    <tr>\n      <th>2022-01-17</th>\n      <td>496.50</td>\n      <td>32268</td>\n      <td>3121</td>\n    </tr>\n    <tr>\n      <th>2022-01-18</th>\n      <td>529.31</td>\n      <td>31814</td>\n      <td>3241</td>\n    </tr>\n    <tr>\n      <th>2022-01-19</th>\n      <td>552.01</td>\n      <td>30414</td>\n      <td>3274</td>\n    </tr>\n    <tr>\n      <th>2022-01-20</th>\n      <td>544.00</td>\n      <td>32416</td>\n      <td>3594</td>\n    </tr>\n    <tr>\n      <th>2022-01-21</th>\n      <td>561.29</td>\n      <td>34300</td>\n      <td>3891</td>\n    </tr>\n    <tr>\n      <th>2022-01-22</th>\n      <td>574.00</td>\n      <td>38342</td>\n      <td>4276</td>\n    </tr>\n    <tr>\n      <th>2022-01-23</th>\n      <td>534.94</td>\n      <td>37444</td>\n      <td>3767</td>\n    </tr>\n    <tr>\n      <th>2022-01-24</th>\n      <td>543.91</td>\n      <td>34539</td>\n      <td>3175</td>\n    </tr>\n    <tr>\n      <th>2022-01-25</th>\n      <td>538.31</td>\n      <td>36753</td>\n      <td>3860</td>\n    </tr>\n    <tr>\n      <th>2022-01-26</th>\n      <td>529.59</td>\n      <td>34148</td>\n      <td>3749</td>\n    </tr>\n    <tr>\n      <th>2022-01-27</th>\n      <td>525.88</td>\n      <td>33630</td>\n      <td>3725</td>\n    </tr>\n    <tr>\n      <th>2022-01-28</th>\n      <td>545.06</td>\n      <td>34181</td>\n      <td>3866</td>\n    </tr>\n    <tr>\n      <th>2022-01-29</th>\n      <td>522.68</td>\n      <td>30637</td>\n      <td>3395</td>\n    </tr>\n    <tr>\n      <th>2022-01-30</th>\n      <td>509.69</td>\n      <td>34254</td>\n      <td>3101</td>\n    </tr>\n    <tr>\n      <th>2022-01-31</th>\n      <td>516.51</td>\n      <td>32145</td>\n      <td>2985</td>\n    </tr>\n    <tr>\n      <th>2022-02-01</th>\n      <td>500.46</td>\n      <td>25687</td>\n      <td>2662</td>\n    </tr>\n    <tr>\n      <th>2022-02-02</th>\n      <td>477.03</td>\n      <td>29061</td>\n      <td>2821</td>\n    </tr>\n    <tr>\n      <th>2022-02-03</th>\n      <td>439.93</td>\n      <td>29598</td>\n      <td>2779</td>\n    </tr>\n    <tr>\n      <th>2022-02-04</th>\n      <td>452.76</td>\n      <td>28709</td>\n      <td>2523</td>\n    </tr>\n    <tr>\n      <th>2022-02-05</th>\n      <td>508.35</td>\n      <td>30133</td>\n      <td>2884</td>\n    </tr>\n    <tr>\n      <th>2022-02-06</th>\n      <td>485.41</td>\n      <td>27635</td>\n      <td>2902</td>\n    </tr>\n    <tr>\n      <th>2022-02-07</th>\n      <td>469.75</td>\n      <td>28259</td>\n      <td>2939</td>\n    </tr>\n    <tr>\n      <th>2022-02-08</th>\n      <td>452.87</td>\n      <td>26685</td>\n      <td>2556</td>\n    </tr>\n    <tr>\n      <th>2022-02-09</th>\n      <td>470.87</td>\n      <td>26037</td>\n      <td>2691</td>\n    </tr>\n    <tr>\n      <th>2022-02-10</th>\n      <td>490.75</td>\n      <td>25530</td>\n      <td>2901</td>\n    </tr>\n    <tr>\n      <th>2022-02-11</th>\n      <td>467.50</td>\n      <td>24359</td>\n      <td>2790</td>\n    </tr>\n    <tr>\n      <th>2022-02-12</th>\n      <td>446.31</td>\n      <td>24180</td>\n      <td>2766</td>\n    </tr>\n    <tr>\n      <th>2022-02-13</th>\n      <td>466.12</td>\n      <td>25274</td>\n      <td>3054</td>\n    </tr>\n    <tr>\n      <th>2022-02-14</th>\n      <td>464.96</td>\n      <td>29338</td>\n      <td>2533</td>\n    </tr>\n    <tr>\n      <th>2022-02-15</th>\n      <td>466.40</td>\n      <td>27394</td>\n      <td>2611</td>\n    </tr>\n    <tr>\n      <th>2022-02-16</th>\n      <td>493.26</td>\n      <td>27639</td>\n      <td>2905</td>\n    </tr>\n    <tr>\n      <th>2022-02-17</th>\n      <td>495.53</td>\n      <td>30228</td>\n      <td>2894</td>\n    </tr>\n    <tr>\n      <th>2022-02-18</th>\n      <td>524.59</td>\n      <td>28126</td>\n      <td>3030</td>\n    </tr>\n    <tr>\n      <th>2022-02-19</th>\n      <td>466.49</td>\n      <td>27575</td>\n      <td>2470</td>\n    </tr>\n    <tr>\n      <th>2022-02-20</th>\n      <td>503.46</td>\n      <td>27424</td>\n      <td>2799</td>\n    </tr>\n    <tr>\n      <th>2022-02-21</th>\n      <td>521.02</td>\n      <td>26965</td>\n      <td>3098</td>\n    </tr>\n    <tr>\n      <th>2022-02-22</th>\n      <td>528.08</td>\n      <td>26886</td>\n      <td>3317</td>\n    </tr>\n    <tr>\n      <th>2022-02-23</th>\n      <td>533.95</td>\n      <td>25022</td>\n      <td>3174</td>\n    </tr>\n    <tr>\n      <th>2022-02-24</th>\n      <td>505.76</td>\n      <td>26727</td>\n      <td>3079</td>\n    </tr>\n    <tr>\n      <th>2022-02-25</th>\n      <td>445.43</td>\n      <td>21930</td>\n      <td>2580</td>\n    </tr>\n    <tr>\n      <th>2022-02-26</th>\n      <td>491.01</td>\n      <td>16645</td>\n      <td>2733</td>\n    </tr>\n    <tr>\n      <th>2022-02-27</th>\n      <td>465.33</td>\n      <td>17884</td>\n      <td>2862</td>\n    </tr>\n    <tr>\n      <th>2022-02-28</th>\n      <td>487.21</td>\n      <td>15457</td>\n      <td>3029</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_daily_1"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "outputs": [],
   "source": [
    "hddj_daily_data = pd.concat([hddj_daily_1, hddj_daily_2], axis=1)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['时间', '企业名称', '监测点', '流量 （m3/h）', 'NOx浓度(mg/m3)', 'SO2浓度(mg/m3)',\n",
      "       '烟尘浓度(mg/m3)', '含氧量（%）', '温度（℃）', '烟气湿度（%）', '烟气压力（千帕）', '烟气流速（m/s）',\n",
      "       '状态', 'Unnamed: 13', '时间.1', '企业名称.1', '监测点.1', '流量 （m3/h）.1',\n",
      "       'NOx浓度(mg/m3).1', 'SO2浓度(mg/m3).1', '烟尘浓度(mg/m3).1', '含氧量（%）.1',\n",
      "       '温度（℃）.1', '烟气湿度（%）.1', '烟气压力（千帕）.1', '烟气流速（m/s）.1', '状态.1'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "hddj_emiss_data = pd.read_excel('data/机器学习样表_单位换算.xlsx', sheet_name=4)\n",
    "hddj_emiss_data.columns"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "outputs": [
    {
     "data": {
      "text/plain": "                   时间              企业名称               监测点  流量 （m3/h）  \\\n0 2022-01-01 00:00:00  国电电力邯郸东郊热电有限责任公司  1号机组排口DA002（DCS）   930582.0   \n1 2022-01-01 01:00:00  国电电力邯郸东郊热电有限责任公司  1号机组排口DA002（DCS）   891316.8   \n\n   NOx浓度(mg/m3)  SO2浓度(mg/m3)  烟尘浓度(mg/m3) 含氧量（%）   温度（℃）  烟气湿度（%）  ...  \\\n0        13.379        13.158        3.438  6.435  48.604   14.695  ...   \n1        19.312        17.951        2.798  7.164  47.819   14.156  ...   \n\n   流量 （m3/h）.1  NOx浓度(mg/m3).1 SO2浓度(mg/m3).1  烟尘浓度(mg/m3).1 含氧量（%）.1 温度（℃）.1  \\\n0    1111474.8          18.171         18.171          0.476    7.065  48.307   \n1    1103194.8          20.524         22.773          0.479    7.130  48.887   \n\n  烟气湿度（%）.1  烟气压力（千帕）.1  烟气流速（m/s）.1  状态.1  \n0    13.253      -0.012       13.693    停运  \n1    13.734      -0.021       13.691    停运  \n\n[2 rows x 27 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>时间</th>\n      <th>企业名称</th>\n      <th>监测点</th>\n      <th>流量 （m3/h）</th>\n      <th>NOx浓度(mg/m3)</th>\n      <th>SO2浓度(mg/m3)</th>\n      <th>烟尘浓度(mg/m3)</th>\n      <th>含氧量（%）</th>\n      <th>温度（℃）</th>\n      <th>烟气湿度（%）</th>\n      <th>...</th>\n      <th>流量 （m3/h）.1</th>\n      <th>NOx浓度(mg/m3).1</th>\n      <th>SO2浓度(mg/m3).1</th>\n      <th>烟尘浓度(mg/m3).1</th>\n      <th>含氧量（%）.1</th>\n      <th>温度（℃）.1</th>\n      <th>烟气湿度（%）.1</th>\n      <th>烟气压力（千帕）.1</th>\n      <th>烟气流速（m/s）.1</th>\n      <th>状态.1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2022-01-01 00:00:00</td>\n      <td>国电电力邯郸东郊热电有限责任公司</td>\n      <td>1号机组排口DA002（DCS）</td>\n      <td>930582.0</td>\n      <td>13.379</td>\n      <td>13.158</td>\n      <td>3.438</td>\n      <td>6.435</td>\n      <td>48.604</td>\n      <td>14.695</td>\n      <td>...</td>\n      <td>1111474.8</td>\n      <td>18.171</td>\n      <td>18.171</td>\n      <td>0.476</td>\n      <td>7.065</td>\n      <td>48.307</td>\n      <td>13.253</td>\n      <td>-0.012</td>\n      <td>13.693</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2022-01-01 01:00:00</td>\n      <td>国电电力邯郸东郊热电有限责任公司</td>\n      <td>1号机组排口DA002（DCS）</td>\n      <td>891316.8</td>\n      <td>19.312</td>\n      <td>17.951</td>\n      <td>2.798</td>\n      <td>7.164</td>\n      <td>47.819</td>\n      <td>14.156</td>\n      <td>...</td>\n      <td>1103194.8</td>\n      <td>20.524</td>\n      <td>22.773</td>\n      <td>0.479</td>\n      <td>7.130</td>\n      <td>48.887</td>\n      <td>13.734</td>\n      <td>-0.021</td>\n      <td>13.691</td>\n      <td>停运</td>\n    </tr>\n  </tbody>\n</table>\n<p>2 rows × 27 columns</p>\n</div>"
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_emiss_data.head(2)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "outputs": [],
   "source": [
    "hddj_emiss_data_1 = hddj_emiss_data[['时间', '流量 （m3/h）', 'NOx浓度(mg/m3)', 'SO2浓度(mg/m3)',\n",
    "                                     '烟尘浓度(mg/m3)', '含氧量（%）', '温度（℃）', '烟气湿度（%）', '烟气压力（千帕）', '烟气流速（m/s）',\n",
    "                                     '状态', ]].copy()\n",
    "hddj_emiss_data_2 = hddj_emiss_data[['时间.1', '流量 （m3/h）.1',\n",
    "                                     'NOx浓度(mg/m3).1', 'SO2浓度(mg/m3).1', '烟尘浓度(mg/m3).1', '含氧量（%）.1',\n",
    "                                     '温度（℃）.1', '烟气湿度（%）.1', '烟气压力（千帕）.1', '烟气流速（m/s）.1', '状态.1']].copy()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "outputs": [],
   "source": [
    "hddj_emiss_data_1.columns = ['date'] + hddj_emiss_data_1.columns[1:].tolist()\n",
    "hddj_emiss_data_2.columns = hddj_emiss_data_1.columns.tolist()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "outputs": [],
   "source": [
    "hddj_emiss_data_1.columns = [f'机组1_{x}' for x in hddj_emiss_data_1.columns]\n",
    "hddj_emiss_data_2.columns = [f'机组2_{x}' for x in hddj_emiss_data_2.columns]"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "outputs": [
    {
     "data": {
      "text/plain": "                机组2_date  机组2_流量 （m3/h）  机组2_NOx浓度(mg/m3)  机组2_SO2浓度(mg/m3)  \\\n0    2022-01-01 00:00:00      1111474.8            18.171            18.171   \n1    2022-01-01 01:00:00      1103194.8            20.524            22.773   \n2    2022-01-01 02:00:00      1086537.6            14.074            16.777   \n3    2022-01-01 03:00:00      1076364.0            18.024            17.549   \n4    2022-01-01 04:00:00      1066298.4            16.406            18.709   \n...                  ...            ...               ...               ...   \n1411 2022-02-28 19:00:00       960645.6            11.857            17.406   \n1412 2022-02-28 20:00:00      1014156.0            19.930            19.709   \n1413 2022-02-28 21:00:00       967834.8            19.400            19.780   \n1414 2022-02-28 22:00:00      1014112.8            16.875            20.308   \n1415 2022-02-28 23:00:00      1013400.0            16.565            16.111   \n\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（%）  机组2_烟气压力（千帕）  \\\n0               0.476       7.065     48.307       13.253        -0.012   \n1               0.479       7.130     48.887       13.734        -0.021   \n2               0.490       7.398     48.794       13.674        -0.026   \n3               0.481       7.694     48.866       13.691        -0.025   \n4               0.475       7.770     48.090       13.093        -0.022   \n...               ...         ...        ...          ...           ...   \n1411            0.415       7.353     48.755       14.155        -0.009   \n1412            0.420       7.532     48.974       13.962         0.007   \n1413            0.450       7.840     49.538       14.562         0.000   \n1414            0.432       7.822     48.593       13.728         0.013   \n1415            0.607       7.941     48.373       13.500         0.005   \n\n      机组2_烟气流速（m/s） 机组2_状态  \n0            13.693     停运  \n1            13.691     停运  \n2            13.470     停运  \n3            13.351     停运  \n4            13.103     停运  \n...             ...    ...  \n1411         11.975    NaN  \n1412         12.621    NaN  \n1413         12.148    NaN  \n1414         12.570    NaN  \n1415         12.515    NaN  \n\n[1416 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>机组2_date</th>\n      <th>机组2_流量 （m3/h）</th>\n      <th>机组2_NOx浓度(mg/m3)</th>\n      <th>机组2_SO2浓度(mg/m3)</th>\n      <th>机组2_烟尘浓度(mg/m3)</th>\n      <th>机组2_含氧量（%）</th>\n      <th>机组2_温度（℃）</th>\n      <th>机组2_烟气湿度（%）</th>\n      <th>机组2_烟气压力（千帕）</th>\n      <th>机组2_烟气流速（m/s）</th>\n      <th>机组2_状态</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2022-01-01 00:00:00</td>\n      <td>1111474.8</td>\n      <td>18.171</td>\n      <td>18.171</td>\n      <td>0.476</td>\n      <td>7.065</td>\n      <td>48.307</td>\n      <td>13.253</td>\n      <td>-0.012</td>\n      <td>13.693</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2022-01-01 01:00:00</td>\n      <td>1103194.8</td>\n      <td>20.524</td>\n      <td>22.773</td>\n      <td>0.479</td>\n      <td>7.130</td>\n      <td>48.887</td>\n      <td>13.734</td>\n      <td>-0.021</td>\n      <td>13.691</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2022-01-01 02:00:00</td>\n      <td>1086537.6</td>\n      <td>14.074</td>\n      <td>16.777</td>\n      <td>0.490</td>\n      <td>7.398</td>\n      <td>48.794</td>\n      <td>13.674</td>\n      <td>-0.026</td>\n      <td>13.470</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2022-01-01 03:00:00</td>\n      <td>1076364.0</td>\n      <td>18.024</td>\n      <td>17.549</td>\n      <td>0.481</td>\n      <td>7.694</td>\n      <td>48.866</td>\n      <td>13.691</td>\n      <td>-0.025</td>\n      <td>13.351</td>\n      <td>停运</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2022-01-01 04:00:00</td>\n      <td>1066298.4</td>\n      <td>16.406</td>\n      <td>18.709</td>\n      <td>0.475</td>\n      <td>7.770</td>\n      <td>48.090</td>\n      <td>13.093</td>\n      <td>-0.022</td>\n      <td>13.103</td>\n      <td>停运</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>1411</th>\n      <td>2022-02-28 19:00:00</td>\n      <td>960645.6</td>\n      <td>11.857</td>\n      <td>17.406</td>\n      <td>0.415</td>\n      <td>7.353</td>\n      <td>48.755</td>\n      <td>14.155</td>\n      <td>-0.009</td>\n      <td>11.975</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1412</th>\n      <td>2022-02-28 20:00:00</td>\n      <td>1014156.0</td>\n      <td>19.930</td>\n      <td>19.709</td>\n      <td>0.420</td>\n      <td>7.532</td>\n      <td>48.974</td>\n      <td>13.962</td>\n      <td>0.007</td>\n      <td>12.621</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1413</th>\n      <td>2022-02-28 21:00:00</td>\n      <td>967834.8</td>\n      <td>19.400</td>\n      <td>19.780</td>\n      <td>0.450</td>\n      <td>7.840</td>\n      <td>49.538</td>\n      <td>14.562</td>\n      <td>0.000</td>\n      <td>12.148</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1414</th>\n      <td>2022-02-28 22:00:00</td>\n      <td>1014112.8</td>\n      <td>16.875</td>\n      <td>20.308</td>\n      <td>0.432</td>\n      <td>7.822</td>\n      <td>48.593</td>\n      <td>13.728</td>\n      <td>0.013</td>\n      <td>12.570</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1415</th>\n      <td>2022-02-28 23:00:00</td>\n      <td>1013400.0</td>\n      <td>16.565</td>\n      <td>16.111</td>\n      <td>0.607</td>\n      <td>7.941</td>\n      <td>48.373</td>\n      <td>13.500</td>\n      <td>0.005</td>\n      <td>12.515</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>1416 rows × 11 columns</p>\n</div>"
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hddj_emiss_data_2"
   ],
   "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
}