T85_code/.ipynb_checkpoints/data_extract-checkpoint.ipynb

683 lines
24 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
},
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
},
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"data": {
"text/plain": [
"635"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file_path = [x for x in os.listdir('./new_data/') if x.endswith('xls') and '经济性' in x]\n",
"len(file_path)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"data = pd.read_excel(f'./new_data/{file_path[0]}', header=[3,4,5])"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['序号',\n",
" '机组编号',\n",
" '时间',\n",
" '发电量(万kWh)',\n",
" '供电量(万kWh)',\n",
" '标煤量t',\n",
" '发电用标煤量t',\n",
" '供热用标煤量t',\n",
" '利用小时(h)',\n",
" '平均负荷(MW)',\n",
" '出力系数(%)',\n",
" '出力系数(%)',\n",
" '出力系数(%)',\n",
" '工业供热量',\n",
" '工业热电比(%)',\n",
" '采暖供热量',\n",
" '采暖热电比(%)',\n",
" '总热电比(%)',\n",
" '总供热量',\n",
" '供热煤耗',\n",
" '给水泵汽轮机总耗热量',\n",
" '供电煤耗gce/(kWh)',\n",
" '综合厂用电率(%)',\n",
" '发电厂用电率(%)',\n",
" '供热厂用电率(%)',\n",
" '非生产厂用电率(%)',\n",
" '最新THA工况二类修正后汽机热耗率kJ/KWh',\n",
" '点火用油(kg/万kWh)',\n",
" '助燃用油(kg/万kWh)',\n",
" '主蒸汽压力(MPa)',\n",
" '主蒸汽温度(℃)',\n",
" '再热蒸汽温度(℃)',\n",
" '高加投入率(%)',\n",
" '给水温度(℃)',\n",
" '真空严密性V(Pa/min)',\n",
" '真空度(%)',\n",
" '凝汽器端差(℃)',\n",
" '凝结水过冷度(℃)',\n",
" '发电补给水率(%)',\n",
" '发电综合耗水率',\n",
" '排烟温度(℃)',\n",
" '飞灰含碳量(%)',\n",
" '空预器漏风率(%)',\n",
" '过热器减温水量(t/h)',\n",
" '再热器减温水量(t/h)',\n",
" '入厂煤低位热值(kJ/kg)',\n",
" '入炉煤低位热值(kJ/kg)',\n",
" '燃煤挥发份Var(%)',\n",
" '燃煤灰份Aar(%)',\n",
" '燃煤低位热值Qar,net(kJ/kg)',\n",
" '燃煤硫份Sar(%)',\n",
" '锅炉专业主要辅机耗电率 送风机耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 引风机耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 一次风机耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 炉水泵耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 给煤机耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 磨煤机耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 电除尘器耗电率(%)',\n",
" '锅炉专业主要辅机耗电率 除灰系统耗电率(%)',\n",
" '汽机专业主要辅机耗电率 凝结水泵耗电率(%)',\n",
" '汽机专业主要辅机耗电率 前置泵耗电率(%)',\n",
" '汽机专业主要辅机耗电率 电动给水泵耗电率(%)',\n",
" '汽机专业主要辅机耗电率 循环水泵耗电率(%)',\n",
" '汽机专业主要辅机耗电率 空冷风机耗电率(%)',\n",
" '汽机专业主要辅机耗电率 热网循环水泵耗电率(%)',\n",
" '环保专业耗电率 脱硫系统耗电率(%)',\n",
" '环保专业耗电率 脱销系统耗电率(%)',\n",
" '输煤专业耗电率输煤系统耗电率(%)',\n",
" '化学系统耗电率 (%)',\n",
" '化学系统耗电率 (%)']"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cols = [''.join([x for x in y if 'Unnamed' not in x]) for y in data.columns]\n",
"cols"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
},
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"data_list = list()\n",
"for file in file_path:\n",
" data = pd.read_excel(f'./new_data/{file}', header=[3,4,5])\n",
" data.columns = cols\n",
" plant = file.split('-')[0]\n",
" data['时间'] = data['时间'].astype(str)\n",
" use_data = data[~data['时间'].str.contains('半年')].copy()\n",
" use_data['电厂名称'] = plant\n",
" data_list.append(use_data)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"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>序号</th>\n",
" <th>机组编号</th>\n",
" <th>时间</th>\n",
" <th>发电量(万kWh)</th>\n",
" <th>供电量(万kWh)</th>\n",
" <th>标煤量t</th>\n",
" <th>发电用标煤量t</th>\n",
" <th>供热用标煤量t</th>\n",
" <th>利用小时(h)</th>\n",
" <th>平均负荷(MW)</th>\n",
" <th>...</th>\n",
" <th>汽机专业主要辅机耗电率 电动给水泵耗电率(%)</th>\n",
" <th>汽机专业主要辅机耗电率 循环水泵耗电率(%)</th>\n",
" <th>汽机专业主要辅机耗电率 空冷风机耗电率(%)</th>\n",
" <th>汽机专业主要辅机耗电率 热网循环水泵耗电率(%)</th>\n",
" <th>环保专业耗电率 脱硫系统耗电率(%)</th>\n",
" <th>环保专业耗电率 脱销系统耗电率(%)</th>\n",
" <th>输煤专业耗电率输煤系统耗电率(%)</th>\n",
" <th>化学系统耗电率 (%)</th>\n",
" <th>化学系统耗电率 (%)</th>\n",
" <th>电厂名称</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2008</td>\n",
" <td>90133.898438</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7210.709961</td>\n",
" <td>113.171409</td>\n",
" <td>...</td>\n",
" <td>2.22</td>\n",
" <td>0.220</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.100</td>\n",
" <td>0.0</td>\n",
" <td>0.02</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>万方发电厂(焦作爱依斯万方电力有限公司)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2008</td>\n",
" <td>91543.898438</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7323.509766</td>\n",
" <td>112.801718</td>\n",
" <td>...</td>\n",
" <td>2.28</td>\n",
" <td>0.220</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.000</td>\n",
" <td>0.0</td>\n",
" <td>0.02</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>万方发电厂(焦作爱依斯万方电力有限公司)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2007</td>\n",
" <td>88968.703125</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3550.750000</td>\n",
" <td>109.667990</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>万方发电厂(焦作爱依斯万方电力有限公司)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2007</td>\n",
" <td>92342.750000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3693.709961</td>\n",
" <td>112.702716</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>万方发电厂(焦作爱依斯万方电力有限公司)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2021</td>\n",
" <td>154638.030000</td>\n",
" <td>146317.63</td>\n",
" <td>597224.38</td>\n",
" <td>398069.77</td>\n",
" <td>199154.61</td>\n",
" <td>4418.229429</td>\n",
" <td>204.300000</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.936</td>\n",
" <td>0.0</td>\n",
" <td>0.31</td>\n",
" <td>1.018</td>\n",
" <td>0.0</td>\n",
" <td>0.05</td>\n",
" <td>0.02</td>\n",
" <td>NaN</td>\n",
" <td>三河发电有限责任公司</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>10</th>\n",
" <td>11</td>\n",
" <td>1</td>\n",
" <td>2005</td>\n",
" <td>131498.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6574.899902</td>\n",
" <td>171.999827</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>黔桂发电有限责任公司</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>12</td>\n",
" <td>2</td>\n",
" <td>2005</td>\n",
" <td>143572.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7178.589844</td>\n",
" <td>171.555440</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>黔桂发电有限责任公司</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>13</td>\n",
" <td>3</td>\n",
" <td>2005</td>\n",
" <td>137886.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6894.310059</td>\n",
" <td>174.126182</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>黔桂发电有限责任公司</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>14</td>\n",
" <td>4</td>\n",
" <td>2005</td>\n",
" <td>154531.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7726.549805</td>\n",
" <td>184.107277</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>黔桂发电有限责任公司</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>15</td>\n",
" <td>5</td>\n",
" <td>2005</td>\n",
" <td>155969.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7798.459961</td>\n",
" <td>184.192211</td>\n",
" <td>...</td>\n",
" <td>0.00</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.000</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>黔桂发电有限责任公司</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>15758 rows × 71 columns</p>\n",
"</div>"
],
"text/plain": [
" 序号 机组编号 时间 发电量(万kWh) 供电量(万kWh) 标煤量t 发电用标煤量t 供热用标煤量t \\\n",
"0 1 1 2008 90133.898438 NaN NaN NaN NaN \n",
"1 2 2 2008 91543.898438 NaN NaN NaN NaN \n",
"2 3 1 2007 88968.703125 NaN NaN NaN NaN \n",
"3 4 2 2007 92342.750000 NaN NaN NaN NaN \n",
"0 1 1 2021 154638.030000 146317.63 597224.38 398069.77 199154.61 \n",
".. .. ... ... ... ... ... ... ... \n",
"10 11 1 2005 131498.000000 NaN NaN NaN NaN \n",
"11 12 2 2005 143572.000000 NaN NaN NaN NaN \n",
"12 13 3 2005 137886.000000 NaN NaN NaN NaN \n",
"13 14 4 2005 154531.000000 NaN NaN NaN NaN \n",
"14 15 5 2005 155969.000000 NaN NaN NaN NaN \n",
"\n",
" 利用小时(h) 平均负荷(MW) ... 汽机专业主要辅机耗电率 电动给水泵耗电率(%) \\\n",
"0 7210.709961 113.171409 ... 2.22 \n",
"1 7323.509766 112.801718 ... 2.28 \n",
"2 3550.750000 109.667990 ... 0.00 \n",
"3 3693.709961 112.702716 ... 0.00 \n",
"0 4418.229429 204.300000 ... 0.00 \n",
".. ... ... ... ... \n",
"10 6574.899902 171.999827 ... 0.00 \n",
"11 7178.589844 171.555440 ... 0.00 \n",
"12 6894.310059 174.126182 ... 0.00 \n",
"13 7726.549805 184.107277 ... 0.00 \n",
"14 7798.459961 184.192211 ... 0.00 \n",
"\n",
" 汽机专业主要辅机耗电率 循环水泵耗电率(%) 汽机专业主要辅机耗电率 空冷风机耗电率(%) 汽机专业主要辅机耗电率 热网循环水泵耗电率(%) \\\n",
"0 0.220 NaN NaN \n",
"1 0.220 NaN NaN \n",
"2 0.000 NaN NaN \n",
"3 0.000 NaN NaN \n",
"0 0.936 0.0 0.31 \n",
".. ... ... ... \n",
"10 0.000 NaN NaN \n",
"11 0.000 NaN NaN \n",
"12 0.000 NaN NaN \n",
"13 0.000 NaN NaN \n",
"14 0.000 NaN NaN \n",
"\n",
" 环保专业耗电率 脱硫系统耗电率(%) 环保专业耗电率 脱销系统耗电率(%) 输煤专业耗电率输煤系统耗电率(%) 化学系统耗电率 (%) \\\n",
"0 1.100 0.0 0.02 NaN \n",
"1 1.000 0.0 0.02 NaN \n",
"2 0.000 0.0 0.00 NaN \n",
"3 0.000 0.0 0.00 NaN \n",
"0 1.018 0.0 0.05 0.02 \n",
".. ... ... ... ... \n",
"10 0.000 0.0 0.00 NaN \n",
"11 0.000 0.0 0.00 NaN \n",
"12 0.000 0.0 0.00 NaN \n",
"13 0.000 0.0 0.00 NaN \n",
"14 0.000 0.0 0.00 NaN \n",
"\n",
" 化学系统耗电率 (%) 电厂名称 \n",
"0 NaN 万方发电厂(焦作爱依斯万方电力有限公司) \n",
"1 NaN 万方发电厂(焦作爱依斯万方电力有限公司) \n",
"2 NaN 万方发电厂(焦作爱依斯万方电力有限公司) \n",
"3 NaN 万方发电厂(焦作爱依斯万方电力有限公司) \n",
"0 NaN 三河发电有限责任公司 \n",
".. ... ... \n",
"10 NaN 黔桂发电有限责任公司 \n",
"11 NaN 黔桂发电有限责任公司 \n",
"12 NaN 黔桂发电有限责任公司 \n",
"13 NaN 黔桂发电有限责任公司 \n",
"14 NaN 黔桂发电有限责任公司 \n",
"\n",
"[15758 rows x 71 columns]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.concat(data_list, axis=0)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 机组信息"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['中国中信集团公司-32020-电厂机组数据查询-20220707.xls',\n",
" '中国中煤能源集团有限公司-34027-电厂机组数据查询-20220707.xls',\n",
" '中国华电集团有限公司-21060-电厂机组数据查询-20220707.xls',\n",
" '中国华能集团有限公司-17021-电厂机组数据查询-20220707.xls',\n",
" '中国大唐集团有限公司-61005-电厂机组数据查询-20220707.xls']"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"unit_data_files = [x for x in os.listdir('./new_data/') if '电厂机组' in x]\n",
"unit_data_files[:5]"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['序号',\n",
" '企业编码',\n",
" '电厂名称',\n",
" '简称',\n",
" '机组编号',\n",
" '铭牌容量 (MW)',\n",
" '投产时间',\n",
" '机组类型',\n",
" '参数分类',\n",
" '所处地区',\n",
" '机组产地',\n",
" '锅炉制造厂家',\n",
" '汽轮机制造厂家',\n",
" '发电机制造厂家',\n",
" '主变压器制造厂家',\n",
" '二级公司',\n",
" '所属集团',\n",
" '所属电网',\n",
" '所属电网']"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"unit_samples = pd.read_excel(f'./new_data/{unit_data_files[0]}', header=[3,4])\n",
"unit_cols = [''.join([x for x in y if 'Unnamed' not in x]) for y in unit_samples.columns]\n",
"unit_cols"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"unit_list = list()\n",
"for file in unit_data_files:\n",
" data = pd.read_excel(f'./new_data/{file}', header=[3,4])\n",
" data.columns = cols\n",
" plant = file.split('-')[0]\n",
" data['时间'] = data['时间'].astype(str)\n",
" use_data = data[~data['时间'].str.contains('半年')].copy()\n",
" use_data['电厂名称'] = plant\n",
" unit_list.append(use_data)"
]
}
],
"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
}