2229 lines
66 KiB
Plaintext
2229 lines
66 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1c72f0cf-165b-4025-af9d-6771e4a0a5d1",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"# 2022年体质检测"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "61f4a6eb-797e-4fe2-95df-e27b316c95f1",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"### 人员基本信息导入"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f6bc68b5-9ed8-4b28-ab1a-452107b6429a",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/北海石化监测花名册2022 .xlsx')\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"person = {}\n",
|
||
"for n in range(2, sheet.max_row+1):\n",
|
||
" if sheet.cell(n,2).value is None:\n",
|
||
" break\n",
|
||
" else: \n",
|
||
" code = int(sheet.cell(n, 4).value)\n",
|
||
" person.setdefault(code, {})\n",
|
||
" dict1 = {}\n",
|
||
" dict1['name'] = sheet.cell(n, 6).value \n",
|
||
" xb = str(sheet.cell(n, 7).value)\n",
|
||
" if xb == '1':\n",
|
||
" sex = '男'\n",
|
||
" elif xb =='2':\n",
|
||
" sex = '女'\n",
|
||
" dict1['sex'] = sex\n",
|
||
" dict1['unit'] = sheet.cell(n, 3).value\n",
|
||
" dict1['birth'] = str(sheet.cell(n,8).value).split(' ')[0]\n",
|
||
" person[code] = dict1\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(person, fl, ensure_ascii=False)\n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fe54b0b2-0abd-4ee9-827d-0e3a4c9bd1f2",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 获取人员测试成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "97031317-76ed-4404-b922-6ca749e4fd2a",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import time\n",
|
||
"import csv\n",
|
||
"\n",
|
||
"filename = '../item.json'\n",
|
||
"item = {}\n",
|
||
"unit = {}\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"for k,v in dict1.items():\n",
|
||
" item[k] = v\n",
|
||
"#SQL语句为：\n",
|
||
"# SELECT a.item_id,a.performance,a.score,a.date AS DATE1,a.avatar_id,b.unit,b.name FROM places_result AS a,_zgshhgxs AS b WHERE a.place_id=135 AND a.avatar_id=b.id AND a.avatar_id < 4999\n",
|
||
"\n",
|
||
"re_ta = {}\n",
|
||
"dict1 = {}\n",
|
||
"list1 = []\n",
|
||
"#print(\"\\n运动项目信息：\")\n",
|
||
"filename = 'data/138_2210.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n",
|
||
" list1.append(line)\n",
|
||
"#print(list1)\n",
|
||
"for result in list1:\n",
|
||
" user = str(result[4])\n",
|
||
" m_item = str(result[0]) \n",
|
||
" re_ta.setdefault(user,{}) \n",
|
||
" re_ta[user]['name'] = str(result[6])\n",
|
||
" re_ta[user]['unit'] = str(result[5]) \n",
|
||
" item_name = item[m_item]['name']\n",
|
||
" re_ta[user].setdefault(item_name,{}) \n",
|
||
" score = int(result[1])/item[m_item]['divisor'] \n",
|
||
" re_ta[user][item_name]['成绩'] = f'{score} {item[m_item][\"unit\"]}'\n",
|
||
" re_ta[user][item_name]['得分'] =result[2]\n",
|
||
"filename = 'data/result_北海炼化2022.json'\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(re_ta, fl) \n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "be6b6709-a2b0-4c34-aca1-000e1fb45953",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 导出测试成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f70a02f2-934e-43ed-93ff-b34cb732dfc6",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"items = ['身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']\n",
|
||
"title = ['编号','姓名','性别','单位/部门','身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']\n",
|
||
"filename = 'data/result_北海炼化2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
" \n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items():\n",
|
||
" list2 = []\n",
|
||
" list2.append(str(k).rjust(8,'0'))\n",
|
||
" list2.append(v['name']) \n",
|
||
" list2.append(dict2[k]['sex'])\n",
|
||
" list2.append(dict2[k]['unit']) \n",
|
||
" \n",
|
||
" for item in items:\n",
|
||
" if item in v.keys():\n",
|
||
" list2.append(v[item]['成绩']) \n",
|
||
" elif item =='name':\n",
|
||
" list2.append(v[item])\n",
|
||
" else:\n",
|
||
" list2.append('') \n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/北海炼化体测情况表（截至20221101）.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9443f552-16a9-4c0d-82f8-279c42fa5e47",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 统计报告人员信息表"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7a0a9111-2f2c-4c5d-bb5e-3e4fbd7ab1aa",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"import os\n",
|
||
"import glob\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"m_path = '../file/221103'\n",
|
||
"fls = glob.glob(f'../file/221103/*.pdf')\n",
|
||
"list1 = []\n",
|
||
"for fn in fls:\n",
|
||
" list2 = []\n",
|
||
" code = os.path.basename(fn).split('.')[0]\n",
|
||
" list2 = [code.rjust(5,\"0\"),dict1[code]['name'],dict1[code]['unit']]\n",
|
||
" list1.append(list2)\n",
|
||
"title = ['编号','姓名','部门'] \n",
|
||
"filename = 'data/北海体测报告情况表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "84325f89-1408-4d0a-b877-f4b54bcb22ce",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 统计部门测试人员情况"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c42c5c04-49f3-4b4c-8f77-e37cfa9748f2",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"title = ['部门','部门人数','已测人数','未测人数']\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"filename = 'data/result_北海炼化2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"\n",
|
||
"dict3 = {}\n",
|
||
"for k, v in dict1.items():\n",
|
||
" dict3.setdefault(v['unit'],{})\n",
|
||
" dict3[v['unit']].setdefault('人数',0)\n",
|
||
" dict3[v['unit']].setdefault('已测人数',0)\n",
|
||
" dict3[v['unit']]['人数'] = dict3[v['unit']]['人数']+1\n",
|
||
"for k, v in dict2.items():\n",
|
||
" if len(v.keys())>5: \n",
|
||
" dict3[v['unit']]['已测人数'] = dict3[v['unit']]['已测人数'] + 1\n",
|
||
"list1 = []\n",
|
||
"\n",
|
||
"for k, v in dict3.items():\n",
|
||
" list2 = []\n",
|
||
" list2 = [k,v['人数'],v['已测人数'],v['人数']-v['已测人数']]\n",
|
||
" \n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/北海炼化体测人数统计表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)\n",
|
||
"print('ok!')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5ec595eb-f979-425e-b7eb-9af094ffb43d",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 导入2021年人员信息"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a9460ee7-1f60-4a3b-a45d-8a1dba04b920",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"filename = 'data/all_result.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"dict3 = {}\n",
|
||
"dict3 = dict2['北海炼化']\n",
|
||
"\n",
|
||
"for k, v in dict1.items():\n",
|
||
" name = v['name']\n",
|
||
" birth = v['birth']\n",
|
||
" for k1, v1 in dict3.items():\n",
|
||
" if v1['name'] == name and v1['birth'] == birth:\n",
|
||
" dict1[k]['old_code'] = int(k1)\n",
|
||
" dict1[k]['record'] = v1['record']\n",
|
||
" \n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(dict1, fl, ensure_ascii=False) \n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0a221ef2-0d86-45a7-916e-bce634a57bfe",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 核对2021体测人员"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "61fbd157-f4f0-4c85-98dc-0e79ee99280b",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"list1 = []\n",
|
||
"for k,v in dict1.items():\n",
|
||
" if 'old_code' in v.keys():\n",
|
||
" list1.append(v['old_code'])\n",
|
||
"filename = 'data/all_result.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"dict3 = {}\n",
|
||
"dict3 = dict2['北海炼化']\n",
|
||
"for k, v in dict3.items():\n",
|
||
" if int(k) not in list1:\n",
|
||
" print(k,v['name'],v['birth'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e6698931-04fb-4dd8-a844-55790cbe3eb9",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 比照人员两年成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "727be8d7-8a4c-4cf4-8139-476f407a31b0",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### 比照两年单项成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d3ca4d45-6a83-4d50-8419-cf8aa9b3aa4c",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化人员_2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"list1 = dict1.keys()\n",
|
||
"items = ['台阶指数']\n",
|
||
"title = ['编号','姓名','部门','22年台阶指数','21年台阶指数']\n",
|
||
"filename = 'data/result_北海炼化2022.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"list4 = []\n",
|
||
"for k, v in dict2.items():\n",
|
||
" if k in list1:\n",
|
||
" list2 = [k,v['name'],v['unit']]\n",
|
||
" list3 = []\n",
|
||
" for item in items:\n",
|
||
" # 获取2022年成绩\n",
|
||
" if item in v.keys(): \n",
|
||
" list2.append(v[item]['成绩'].split()[0]) \n",
|
||
" else:\n",
|
||
" list2.append('')\n",
|
||
" # 获取2021年成绩\n",
|
||
" if 'record' in dict1[k].keys() and item in dict1[k]['record'].keys():\n",
|
||
" list3.append(dict1[k]['record'][item]['成绩']) \n",
|
||
" else:\n",
|
||
" list3.append('')\n",
|
||
" for cj in list3:\n",
|
||
" if cj != '':\n",
|
||
" list2.append(cj.split()[0]) \n",
|
||
" \n",
|
||
" list4.append(list2)\n",
|
||
"filename = 'data/b北海炼化成绩对照221026.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list4:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e17b1435-2b31-421f-8755-c11f0a4ac5c9",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 北海体检情况汇总"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "26343c71-535f-445b-9274-6492febfd435",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/中国石化北海炼化有限责任公司2022年健康体检团体报告统计表.xlsx')\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"dict1 = {}\n",
|
||
"for n in range(2, sheet.max_row+1):\n",
|
||
" if sheet.cell(n,2).value is None:\n",
|
||
" break\n",
|
||
" else: \n",
|
||
" code = sheet.cell(n, 2).value\n",
|
||
" dict1.setdefault(code, {}) \n",
|
||
" dict1[code]['name'] = sheet.cell(n, 3).value \n",
|
||
" \n",
|
||
" dict1[code]['sex'] = sheet.cell(n, 4).value \n",
|
||
" dict1[code]['age'] = sheet.cell(n, 5).value \n",
|
||
" dict1[code].setdefault('bz',[]) \n",
|
||
" dict1[code]['bz'].append(sheet.cell(n, 6).value) \n",
|
||
" \n",
|
||
"filename = 'data/北海炼化2022年健康体检团体报告.json'\n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(dict1, fl, ensure_ascii=False)\n",
|
||
"print('ok')\n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items():\n",
|
||
" list2 = []\n",
|
||
" mbz = set(v['bz'])\n",
|
||
" list2.append(k)\n",
|
||
" list2.append(v['name'])\n",
|
||
" list2.append(v['sex'])\n",
|
||
" list2.append(v['age'])\n",
|
||
" list2.append(','.join(mbz))\n",
|
||
" list1.append(list2)\n",
|
||
"title = ['体检编号','姓名','性别','年龄','体检症状']\n",
|
||
"filename = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告汇总统计表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a14e0cfc-e2ac-41ff-acd9-69d669ad1fc2",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 北海体检情况汇总(文本文件)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6f7b0837-a623-47fb-8451-3860df6ec133",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"list2 = []\n",
|
||
"file_name = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告.txt'\n",
|
||
"with open(file_name,'r',encoding='utf-8') as fl:\n",
|
||
" for l in fl:\n",
|
||
" list1 = []\n",
|
||
" list1 = l.strip('\\n').split()\n",
|
||
" del list1[0]\n",
|
||
" list2.append(list1)\n",
|
||
" \n",
|
||
"print(list2) \n",
|
||
"title = ['体检编号','姓名','性别','年龄','体检症状']\n",
|
||
"filename = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告统计表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list2:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) \n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1a05cd85-32a0-4c91-a281-9e7253562ba3",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 北海体检情况统计"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "81fefc86-cd07-446c-ad08-bdb36b9e1722",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"import itertools\n",
|
||
"import operator\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2022年健康体检团体报告.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"bz = set()\n",
|
||
"for k, v in dict1.items():\n",
|
||
" for i in v['bz']:\n",
|
||
" bz.add(i)\n",
|
||
"print(len(bz))\n",
|
||
"dict2 = {}\n",
|
||
"dict3 = {}\n",
|
||
"i = 1\n",
|
||
"for n in [2,3,4]:\n",
|
||
" iter1 = itertools.combinations(bz, n)\n",
|
||
" list1 = list(iter1)\n",
|
||
" print(len(list1)) \n",
|
||
" \n",
|
||
" list2 = []\n",
|
||
" for item in list1:\n",
|
||
" \n",
|
||
" for k, v in dict1.items(): \n",
|
||
" list3 = []\n",
|
||
" if set(item).issubset(v['bz']):\n",
|
||
" dict3[i] =item \n",
|
||
" list3 = [k,i]\n",
|
||
" list2.append(list3)\n",
|
||
" i = i+1\n",
|
||
" dict2[n] = list2\n",
|
||
"dict2['bingzheng'] = dict3\n",
|
||
"filename = 'data/北海炼化2022年健康体检病症组合.json'\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(dict2, fl, ensure_ascii=False) \n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "149104bd-76d8-4c42-b325-b0290439c3b2",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 北海体检情况分析"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "e1b2e465-3ebb-448f-a3df-e2aaab70e688",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"import itertools\n",
|
||
"import operator\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2022年健康体检病症组合.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"bz = dict1['bingzheng']\n",
|
||
"bz1 = dict1['2']\n",
|
||
"list1 = []\n",
|
||
"for k, v in bz.items():\n",
|
||
" list2 = []\n",
|
||
" i = 1\n",
|
||
" bzs = len(v)\n",
|
||
" for v1 in dict1[str(bzs)]:\n",
|
||
" if v1[1] == int(k):\n",
|
||
" \n",
|
||
" i+=1\n",
|
||
" list2 =[bzs,','.join(v),i]\n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/中国石化北海炼化有限责任公司2022年病症统计表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"#sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c103301b-d540-4bf5-861a-0eb2e313e26e",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"# 2023年体质检测"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1ab2aa22-5cc2-4f53-a28d-b30b1ecab15f",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"## 人员信息处理"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1e3f67e9-e332-41c5-89f8-b64ec0bace4c",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"### 人员信息汇总（批量人员）"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "648d597d-2ac4-470c-9562-271e3e2863d6",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os,sys,shutil\n",
|
||
"import json\n",
|
||
"import glob\n",
|
||
"from pathlib import Path\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"fi_path = 'data/北海炼化/'\n",
|
||
"\n",
|
||
"fls = glob.glob(f'{fi_path}/*.xlsx')\n",
|
||
"i = 1\n",
|
||
"person = {}\n",
|
||
"for fl in fls:\n",
|
||
" wb = openpyxl.load_workbook(fl)\n",
|
||
" sheet = wb.active\n",
|
||
" # sheets = wb.sheetnames\n",
|
||
" \n",
|
||
"\n",
|
||
" for n in range(3,sheet.max_row+1):\n",
|
||
" if sheet.cell(n,1).value is not None:\n",
|
||
" code = str(i)\n",
|
||
" person.setdefault(code, {})\n",
|
||
" dict1 = {}\n",
|
||
" dict1['name'] = sheet.cell(n, 2).value\n",
|
||
" dict1['sex'] = sheet.cell(n,3 ).value\n",
|
||
" dict1['婚姻'] = sheet.cell(n, 5).value\n",
|
||
" dict1['phone'] = str(sheet.cell(n,6).value)\n",
|
||
" dict1['id'] = sheet.cell(n,7 ).value\n",
|
||
" dict1['总工龄'] = sheet.cell(n, 8).value\n",
|
||
" dict1['损害工龄'] = sheet.cell(n, 9).value\n",
|
||
" dict1['既往病史'] = sheet.cell(n,10 ).value\n",
|
||
" dict1['有毒因素'] = sheet.cell(n, 11).value\n",
|
||
" dict1['unit'] = sheet.cell(n, 12).value\n",
|
||
" dict1['工种'] = sheet.cell(n, 13).value\n",
|
||
" dict1['防护措施'] = sheet.cell(n,15 ).value \n",
|
||
" person[code] = dict1\n",
|
||
" i+=1\n",
|
||
" \n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(person, fl, ensure_ascii=False)\n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b1f47560-4183-4699-8d63-3d81a3ec002b",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 检查身份证及手机号码唯一性"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a2c1c315-c522-433a-9611-e08dca2445a9",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"id= []\n",
|
||
"phone = [] \n",
|
||
"\n",
|
||
"for k, v in dict1.items():\n",
|
||
" if v['phone'] not in phone:\n",
|
||
" phone.append(v['phone'] )\n",
|
||
" else:\n",
|
||
" print(v['name'] ,v['phone'])\n",
|
||
" if v['id'] not in id:\n",
|
||
" id.append(v['id'] )\n",
|
||
" else:\n",
|
||
" print(v['id'] ,v['id'] )\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c1842f66-c81f-423d-bcda-0d49be82b32a",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 查找身份证号码"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7ba235d2-4638-4479-babb-2f9867c177c2",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"id= '440906199104060046'\n",
|
||
"for k, v in dict1.items():\n",
|
||
" if v['id'] == id:\n",
|
||
" print(id,v['name'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f9d8aafa-9a00-484a-a3c2-b3e9252b505d",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"phone= ['13807799565','18877976757','13927509537']\n",
|
||
"for k, v in dict1.items():\n",
|
||
" if v['phone'] in phone:\n",
|
||
" print(v['phone'],v['name'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1ea37f21-f03a-4450-8867-71fb8c3eeee7",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 生成出生日期"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "dff13fe9-d5cd-45e3-a3e7-f47d12560699",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"for k, v in dict1.items():\n",
|
||
" id = str(v['id']) \n",
|
||
" #print(id)\n",
|
||
" birth = id[6:10] + '-' +id[10:12] + '-' +id[12:14]\n",
|
||
" dict1[k]['birth'] = birth\n",
|
||
" \n",
|
||
" \n",
|
||
"filename = 'data/北海炼化2023.json' \n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(dict1, fl, ensure_ascii=False)\n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "de060103-776c-40d8-9704-ece6cc574308",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-10-25T06:22:41.417620Z",
|
||
"iopub.status.busy": "2023-10-25T06:22:41.417111Z",
|
||
"iopub.status.idle": "2023-10-25T06:22:41.439732Z",
|
||
"shell.execute_reply": "2023-10-25T06:22:41.437319Z",
|
||
"shell.execute_reply.started": "2023-10-25T06:22:41.417575Z"
|
||
},
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"### 人员信息汇总（单个文件）"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "61f8d7c3-b7f2-44b7-86f1-5b29d22193cb",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" person = json.load(fl)\n",
|
||
"i = len(person)+1\n",
|
||
"fl = 'data/北海炼化机关名单表(2023年汇总156人).xlsx'\n",
|
||
"wb = openpyxl.load_workbook(fl)\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"\n",
|
||
"\n",
|
||
"for n in range(3,sheet.max_row+1):\n",
|
||
" if sheet.cell(n,1).value is not None:\n",
|
||
" code = str(i)\n",
|
||
" person.setdefault(code, {})\n",
|
||
" dict1 = {}\n",
|
||
" dict1['name'] = sheet.cell(n, 2).value\n",
|
||
" dict1['sex'] = sheet.cell(n,3 ).value \n",
|
||
" dict1['phone'] = sheet.cell(n,6).value\n",
|
||
" dict1['id'] = sheet.cell(n,5 ).value \n",
|
||
" dict1['婚姻'] = sheet.cell(n, 11).value\n",
|
||
" dict1['unit'] = sheet.cell(n, 8).value \n",
|
||
" person[code] = dict1\n",
|
||
" i+=1\n",
|
||
"filename = 'data/北海炼化2023.json' \n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(person, fl, ensure_ascii=False)\n",
|
||
"print('ok')\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "8da8e47d-b62b-4719-82d5-fcfc61473e08",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" person = json.load(fl)\n",
|
||
"i = len(person)+1\n",
|
||
"fl = 'data/北海炼化上岗体检人员名单 （2023年）.xlsx'\n",
|
||
"wb = openpyxl.load_workbook(fl)\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"\n",
|
||
"\n",
|
||
"for n in range(5,sheet.max_row+1):\n",
|
||
" if sheet.cell(n,1).value is not None:\n",
|
||
" code = str(i)\n",
|
||
" person.setdefault(code, {})\n",
|
||
" dict1 = {}\n",
|
||
" dict1['name'] = sheet.cell(n, 2).value\n",
|
||
" dict1['sex'] = sheet.cell(n,3 ).value \n",
|
||
" dict1['phone'] = str(sheet.cell(n,7).value)\n",
|
||
" dict1['id'] = sheet.cell(n,6 ).value\n",
|
||
" \n",
|
||
" dict1['有毒因素'] = sheet.cell(n, 11).value\n",
|
||
" dict1['unit'] = '新上岗'\n",
|
||
" dict1['工种'] = sheet.cell(n, 8).value\n",
|
||
" dict1['防护措施'] = sheet.cell(n,13 ).value \n",
|
||
" person[code] = dict1\n",
|
||
" i+=1\n",
|
||
"filename = 'data/北海炼化2023.json' \n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(person, fl, ensure_ascii=False)\n",
|
||
"print('ok')\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3e890abb-5e49-4a80-b401-602cd2e83533",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 人员信息汇总导出"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "474786b8-e172-4335-aa4d-bb5bde17ceb7",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items():\n",
|
||
" list2 = []\n",
|
||
" list2 = [str(k).rjust(4,'0'),v['name'],v['sex'],v['unit'],v['birth'],v['phone']]\n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/北海炼化人员信息（2023年）.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e613feb8-b03d-4afc-aa56-c91d80903a22",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 生成人员信息"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "0bafbf66-c909-413e-a9c1-c1a5f9c22953",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/北海炼化人员信息（2023年） (更新).xlsx')\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"person = {}\n",
|
||
"\n",
|
||
"for n in range(2, sheet.max_row+1):\n",
|
||
" code = int(sheet.cell(n, 1).value)\n",
|
||
" person.setdefault(code, {})\n",
|
||
" dict1 = {}\n",
|
||
" dict1['name'] = sheet.cell(n, 2).value\n",
|
||
" dict1['sex'] = sheet.cell(n, 3).value\n",
|
||
" dict1['unit'] = sheet.cell(n, 4).value\n",
|
||
" dict1['birth'] = sheet.cell(n,5).value\n",
|
||
" if sheet.cell(n,6).value is not None:\n",
|
||
" dict1['phone'] = str(sheet.cell(n,6).value) \n",
|
||
" person[code] = dict1\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(person, fl, ensure_ascii=False)\n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b373563f-0b78-4d37-9428-89d3f4e04883",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 生成读卡系统文件"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ff1e0a37-6119-4f64-8e05-4d25cb144817",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items():\n",
|
||
" dict2 = {}\n",
|
||
" #if dict1['sex'] =='男':\n",
|
||
" # sex = 1\n",
|
||
" \n",
|
||
" dict2 = {'id':k,'name':v['name'],'gender':v['sex'],'birth':v['birth'],'unit':v['unit']}\n",
|
||
" list1.append(dict2)\n",
|
||
"json_data = json.dumps(list1,ensure_ascii=False, indent=4) \n",
|
||
"\n",
|
||
"# 将 json 数据写入文件\n",
|
||
"with open(\"data/data_北海炼化.json\", \"w\",encoding = 'utf-8') as file:\n",
|
||
" file.write(json_data) \n",
|
||
"print('ok')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "405f3461-fcef-47d4-a88b-a2975f8d522f",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 获取人员测试成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1aa45b35-7376-4c50-8275-79b090a6c758",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import time\n",
|
||
"import csv\n",
|
||
"\n",
|
||
"filename = '../item.json'\n",
|
||
"item = {}\n",
|
||
"unit = {}\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"for k,v in dict1.items():\n",
|
||
" item[k] = v\n",
|
||
"re_ta = {}\n",
|
||
"dict1 = {}\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/places_result_20231122.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n",
|
||
" list1.append(line)\n",
|
||
"#print(list1)\n",
|
||
"for result in list1:\n",
|
||
" user = str(result[2])\n",
|
||
" \n",
|
||
" if user in dict1.keys(): \n",
|
||
" m_item = str(result[3]) \n",
|
||
" re_ta.setdefault(user,{}) \n",
|
||
" re_ta[user]['name'] = dict1[user]['name']\n",
|
||
" re_ta[user]['sex'] = dict1[user]['sex'] \n",
|
||
" re_ta[user]['unit'] = dict1[user]['unit']\n",
|
||
" re_ta[user]['phone'] = dict1[user]['phone']\n",
|
||
" item_name = item[m_item]['name']\n",
|
||
" re_ta[user].setdefault(item_name,{}) \n",
|
||
" score = int(result[4])/item[m_item]['divisor'] \n",
|
||
" re_ta[user][item_name]['成绩'] = f'{score} {item[m_item][\"unit\"]}'\n",
|
||
" re_ta[user]['rq'] = str(result[6]) \n",
|
||
" rq = date.fromisoformat(str(result[6]))\n",
|
||
" birth = date.fromisoformat(dict1[user]['birth'])\n",
|
||
" days = (rq-birth).days \n",
|
||
" re_ta[user]['age'] = int(days/365)\n",
|
||
" re_ta[user]['month'] = int(days/365*12)\n",
|
||
" \n",
|
||
" \n",
|
||
"print(len(re_ta))\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(re_ta, fl, ensure_ascii=False) \n",
|
||
"print(len(re_ta))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "429ed5f7-57cb-4fcd-a267-2d222e08d81c",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 统计所有部门未体测人员明细表"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1172a79c-ec8f-4274-8c43-6ec11d95f8ca",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"\n",
|
||
"list1 = []\n",
|
||
"\n",
|
||
"i = 1\n",
|
||
"for k, v in dict2.items():\n",
|
||
" \n",
|
||
" if k not in dict1.keys():\n",
|
||
" list2 = [i,k,v['name'],v['unit']]\n",
|
||
" i+=1\n",
|
||
" list1.append(list2)\n",
|
||
"filename = f'data/北海炼化未测试人员名单（截至20231111）.xlsx'\n",
|
||
"title = ['序号','员工编号','姓名','部门']\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row) \n",
|
||
"wb.save(filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c410f403-5c93-4a03-a06b-900ecd08a1b4",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 导入问卷信息"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c0128f52-8697-4258-aba0-89a522fb9cc0",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"import time\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict3 = json.load(fl)\n",
|
||
"\n",
|
||
"phone = {}\n",
|
||
"for k,v in dict3.items():\n",
|
||
" if 'phone' in v.keys():\n",
|
||
" phone[v['phone']] = k\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/Survey_20231127.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" list1.append(line)\n",
|
||
"#print(list1)\n",
|
||
"dict2 = {}\n",
|
||
"psy =[]\n",
|
||
"tcm = []\n",
|
||
"spine = []\n",
|
||
"for i in range(0,45):\n",
|
||
" psy.append(0)\n",
|
||
"psy[44] = []\n",
|
||
"for i in range(0,60):\n",
|
||
" tcm.append(0)\n",
|
||
"for i in range(0,26):\n",
|
||
" spine.append(0)\n",
|
||
"\n",
|
||
"for item in list1:\n",
|
||
" if item[2] in phone.keys():\n",
|
||
" psy =[]\n",
|
||
" tcm = []\n",
|
||
" spine = []\n",
|
||
" for i in range(0,45):\n",
|
||
" psy.append(0)\n",
|
||
" psy[44] = []\n",
|
||
" for i in range(0,60):\n",
|
||
" tcm.append(0)\n",
|
||
" for i in range(0,26):\n",
|
||
" spine.append(0)\n",
|
||
" \n",
|
||
" content = json.loads(item[5])\n",
|
||
" if phone[item[2]] not in dict1.keys():\n",
|
||
" dict1[phone[item[2]]] = dict3[phone[item[2]]]\n",
|
||
" rq = date.fromisoformat(item[6].replace('/','-').split(' ')[0])\n",
|
||
" #dict1[phone[item[2]]]['rq'] = date.fromisoformat(item[6].replace('/','-').split(' ')[0])\n",
|
||
" for k, v in content.items():\n",
|
||
" if 'psy' in k:\n",
|
||
" i = int(k[3:])\n",
|
||
" psy[i-1] = int(v)\n",
|
||
" if 'tcm' in k:\n",
|
||
" i = int(k[3:])\n",
|
||
" tcm[i-1] = int(v)\n",
|
||
" if 'spine' in k:\n",
|
||
" i = int(k[5:])\n",
|
||
" spine[i-1] = int(v)\n",
|
||
" if 'psy' in item[5]:\n",
|
||
" #for i in range(5,26):\n",
|
||
" # new_valve = 5-psy[i]\n",
|
||
" # psy[i] = new_valve\n",
|
||
" for i in range(26,40):\n",
|
||
" new_valve = 1+psy[i]\n",
|
||
" psy[i] = new_valve\n",
|
||
" \n",
|
||
" dict1[phone[item[2]]]['psy'] = psy\n",
|
||
" if 'tcm' in item[5]:\n",
|
||
" dict1[phone[item[2]]]['tcm'] = tcm\n",
|
||
" if 'spine' in item[5]:\n",
|
||
" dict1[phone[item[2]]]['spine'] = spine\n",
|
||
" birth = date.fromisoformat(dict3[phone[item[2]]]['birth'].replace('/','-'))\n",
|
||
" \n",
|
||
" days = (rq-birth).days \n",
|
||
" dict1[phone[item[2]]]['age'] = int(days/365)\n",
|
||
" dict1[phone[item[2]]]['month'] = int(days/365*12)\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(dict1, fl, ensure_ascii=False) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "5f222727-d5b4-481f-8f1c-bea74b35936b",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"import time\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict3 = json.load(fl)\n",
|
||
"\n",
|
||
"phone = {}\n",
|
||
"for k,v in dict3.items():\n",
|
||
" if 'phone' in v.keys():\n",
|
||
" phone[v['phone']] = k\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/Survey_20231114.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" list1.append(line)\n",
|
||
"#print(list1)\n",
|
||
"dict2 = {}\n",
|
||
"psy = []\n",
|
||
"tcm = []\n",
|
||
"spine = []\n",
|
||
"for i in range(0,44):\n",
|
||
" psy.append(0)\n",
|
||
"for i in range(0,60):\n",
|
||
" tcm.append(0)\n",
|
||
"for i in range(0,26):\n",
|
||
" spine.append(0)\n",
|
||
"print(len(spine))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0690df67-fc6b-4386-a18f-a99bd065c894",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 统计项目数"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "87e0c0f1-5f07-424d-98b2-aa301fd77c82",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"items = ['身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"list1 = []\n",
|
||
"for k,v in dict1.items():\n",
|
||
" i = 0\n",
|
||
" list2 = []\n",
|
||
" for item in items:\n",
|
||
" if item in v.keys():\n",
|
||
" i+=1\n",
|
||
" print(k)\n",
|
||
" list2 = [k,v['name'],v['sex'],v['age'],v['unit'],v['phone'],i]\n",
|
||
" if 'psy' in v.keys():\n",
|
||
" list2.append(1)\n",
|
||
" else:\n",
|
||
" list2.append(0)\n",
|
||
" if 'tcm' in v.keys():\n",
|
||
" list2.append(1)\n",
|
||
" else:\n",
|
||
" list2.append(0)\n",
|
||
" if 'spine' in v.keys():\n",
|
||
" list2.append(1)\n",
|
||
" else:\n",
|
||
" list2.append(0)\n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/北海炼化员工测试项目情况表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "cd06cd33-668f-4b5a-8c98-587d503a39eb",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 统计手机号码不明确人员"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6faef501-54eb-436b-8c51-093a05c38686",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"import time\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict3 = json.load(fl)\n",
|
||
"\n",
|
||
"phone = {}\n",
|
||
"for k,v in dict3.items():\n",
|
||
" if 'phone' in v.keys():\n",
|
||
" phone[v['phone']] = k\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/Survey_20231119.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" list1.append(line)\n",
|
||
"\n",
|
||
"for item in list1:\n",
|
||
" if item[2] not in phone.keys():\n",
|
||
" print(item[2])\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "95e2d0f2-c0c7-4647-a34d-1b998ca89293",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 统计各部门测试情况"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d554c400-8f2f-4f60-97ba-ab5ace254d6f",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl)\n",
|
||
"\n",
|
||
"dict3 = {}\n",
|
||
"for k, v in dict2.items():\n",
|
||
" unit = v['unit']\n",
|
||
" #sub_unit = v['sub_unit']\n",
|
||
" dict3.setdefault(unit,{})\n",
|
||
" dict3[unit].setdefault('人数',0)\n",
|
||
" #dict3[unit].setdefault(sub_unit,0)\n",
|
||
" #dict3[unit][sub_unit] = dict3[unit][sub_unit] + 1\n",
|
||
" dict3[unit]['人数'] = dict3[unit]['人数'] + 1\n",
|
||
"\n",
|
||
"title =['单位','体测人数']\n",
|
||
"list1 = []\n",
|
||
"for k,v in dict1.items(): \n",
|
||
" unit = v['unit']\n",
|
||
" #sub_unit = v['sub_unit']\n",
|
||
" #dict3[unit][sub_unit] = dict3[unit][sub_unit] - 1\n",
|
||
" dict3[unit].setdefault('体测人数',0)\n",
|
||
" dict3[unit]['体测人数'] = dict3[unit]['体测人数'] + 1\n",
|
||
"for k, v in dict3.items():\n",
|
||
" list2 = [k,v['人数'],v['体测人数']]\n",
|
||
" list1.append(list2)\n",
|
||
"\n",
|
||
"filename = 'data/北海炼化部门测试情况.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "14101d8f-4e74-4982-a984-c0ebe4099107",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 生成新格式测试成绩"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f21b1c8d-1b2d-45f6-8f35-4a62d5b944f7",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import datetime\n",
|
||
"import csv\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = '../item.json'\n",
|
||
"item = {}\n",
|
||
"unit = {}\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"for k,v in dict1.items():\n",
|
||
" item[k] = v\n",
|
||
"item['1']['en'] = 'lung'\n",
|
||
"item['2']['en'] = 'grip'\n",
|
||
"item['3']['en'] = 'flexion'\n",
|
||
"item['4']['en'] = 'jump'\n",
|
||
"item['5']['en'] = 'pushup'\n",
|
||
"item['6']['en'] = 'balance'\n",
|
||
"item['7']['en'] = 'reaction'\n",
|
||
"item['8']['en'] = 'step'\n",
|
||
"item['9']['en'] = 'situp'\n",
|
||
"item['10']['en'] = 'height'\n",
|
||
"item['11']['en'] = 'weight'\n",
|
||
"\n",
|
||
"\n",
|
||
"re_ta = {}\n",
|
||
"dict1 = {}\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/places_result_20231122.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n",
|
||
" list1.append(line)\n",
|
||
"#f_item = ['lung','grip','flexion','jump','balance','reaction','step','situp']\n",
|
||
"#m_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step']\n",
|
||
"for result in list1:\n",
|
||
" user = str(result[2])\n",
|
||
" rq = date.fromisoformat(result[6].replace('/','-'))\n",
|
||
" if user in dict1.keys():\n",
|
||
" l_xm = []\n",
|
||
" m_item = str(result[3]) \n",
|
||
" re_ta.setdefault(user,{}) \n",
|
||
" re_ta[user]['name'] = dict1[user]['name']\n",
|
||
" re_ta[user]['sex'] = dict1[user]['sex']\n",
|
||
" re_ta[user]['phone'] = dict1[user]['phone']\n",
|
||
" if dict1[user]['sex'] == '男':\n",
|
||
" l_xm = ['weight','height','lung','grip','flexion','jump','pushup','balance','reaction','step']\n",
|
||
" else:\n",
|
||
" l_xm = ['weight','height','lung','grip','flexion','jump','balance','reaction','step','situp']\n",
|
||
" re_ta[user]['unit'] = dict1[user]['unit']\n",
|
||
" birth = date.fromisoformat(dict1[user]['birth'].replace('/','-'))\n",
|
||
" #nian = int(birth[0].strip())\n",
|
||
" #yue = int(birth[1].strip())\n",
|
||
" #ri = int(birth[2].strip())\n",
|
||
" #print(k,nian,yue,ri)\n",
|
||
" item_name = item[m_item]['en'] \n",
|
||
" if item_name in l_xm: \n",
|
||
" days = (rq-birth).days \n",
|
||
" re_ta[user]['age'] = int(days/365)\n",
|
||
" re_ta[user]['month'] = int(days/365*12)\n",
|
||
" re_ta[user]['rq'] = result[6]\n",
|
||
"\n",
|
||
"\n",
|
||
" re_ta[user].setdefault(item_name,{}) \n",
|
||
" score = int(result[4])/item[m_item]['divisor'] \n",
|
||
" re_ta[user][item_name]['成绩'] = f'{score} {item[m_item][\"unit\"]}'\n",
|
||
"print(len(re_ta))\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(re_ta, fl, ensure_ascii=False) \n",
|
||
"print(len(re_ta))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "89a02e6b-0418-4516-a9e0-12364aa38783",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 生成测试得分"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9ca97d8f-6320-48f1-9a16-2d34167dac19",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import time\n",
|
||
"\n",
|
||
"filename = '../item.json'\n",
|
||
"item = {}\n",
|
||
"unit = {}\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict3 = json.load(fl) \n",
|
||
"for k,v in dict3.items():\n",
|
||
" item[k] = v\n",
|
||
"item['1']['en'] = 'lung'\n",
|
||
"item['2']['en'] = 'grip'\n",
|
||
"item['3']['en'] = 'flexion'\n",
|
||
"item['4']['en'] = 'jump'\n",
|
||
"item['5']['en'] = 'pushup'\n",
|
||
"item['6']['en'] = 'balance'\n",
|
||
"item['7']['en'] = 'reaction'\n",
|
||
"item['8']['en'] = 'step'\n",
|
||
"item['9']['en'] = 'situp'\n",
|
||
"item['10']['en'] = 'height'\n",
|
||
"item['11']['en'] = 'weight'\n",
|
||
"\n",
|
||
"filename = 'data/体质检测标准 (1).json' \n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"def cal_score(data1):\n",
|
||
" #data = {'name':'张三','sex':'M','age':37,'item':'StepExperiment','result':46} \n",
|
||
" person = dict1['person']\n",
|
||
" criteria = dict1['criteria']\n",
|
||
" if data1['age'] >59:\n",
|
||
" data1['age'] = 59\n",
|
||
" if data1['age'] <20:\n",
|
||
" data1['age'] = 20\n",
|
||
" info = data1['sex']+str(data1['age'])\n",
|
||
" bz = person[info]\n",
|
||
" mx = criteria[bz][data1['item']]\n",
|
||
" result = data1['result'] \n",
|
||
" if data1['item'] == 'reaction':\n",
|
||
" for bz1 in mx:\n",
|
||
" if result > bz1:\n",
|
||
" #print(bz1)\n",
|
||
" score = mx.index(bz1,0)\n",
|
||
" break\n",
|
||
" else:\n",
|
||
" score = 5\n",
|
||
" else:\n",
|
||
" for bz1 in mx:\n",
|
||
" if result < bz1:\n",
|
||
" #print(bz1)\n",
|
||
" score = mx.index(bz1,0)\n",
|
||
" break\n",
|
||
" else:\n",
|
||
" score = 5\n",
|
||
" return(score)\n",
|
||
"filename = 'data/体质检测标准_BMI.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict4 = json.load(fl) \n",
|
||
" \n",
|
||
"def cal_bmi(data1):\n",
|
||
" # data = {'name':'张三','sex':'M','age':37,'item':'HeightWeight','result':'177.7,97.0'}\n",
|
||
" person = dict4['person']\n",
|
||
" criteria = dict4['criteria']\n",
|
||
" if data1['age'] > 59:\n",
|
||
" data1['age'] = 59\n",
|
||
" if data1['age'] <20:\n",
|
||
" data1['age'] = 20\n",
|
||
" info = data1['sex']+str(data1['age'])\n",
|
||
" bz = person[info]\n",
|
||
" #print(bz)\n",
|
||
" result = data1['result']\n",
|
||
" #print(data1['code'],result)\n",
|
||
" height = int(float(result.split(',')[0]))\n",
|
||
" weight = float(result.split(',')[1])\n",
|
||
" if str(height) not in criteria[bz]:\n",
|
||
" score = 1\n",
|
||
" else: \n",
|
||
" mx = criteria[bz][str(height)]\n",
|
||
" if weight < mx[0]:\n",
|
||
" score = 1\n",
|
||
" elif weight < mx[1]:\n",
|
||
" score = 3\n",
|
||
" elif weight < mx[2]:\n",
|
||
" score = 5 \n",
|
||
" elif weight <= mx[3]:\n",
|
||
" score = 3 \n",
|
||
" elif weight > mx[3]:\n",
|
||
" score = 1\n",
|
||
" return score\n",
|
||
" \n",
|
||
" \n",
|
||
"\n",
|
||
"#list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','height','weight']\n",
|
||
"list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp']\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict2 = json.load(fl) \n",
|
||
"for k, v in dict2.items():\n",
|
||
" #print(k)\n",
|
||
" if v['sex'] == '男':\n",
|
||
" sex = 'M'\n",
|
||
" else:\n",
|
||
" sex = 'F' \n",
|
||
" if 'height' in v.keys() and 'weight' in v.keys():\n",
|
||
" bmi_data = v['height']['成绩'].split()[0]+','+ v['weight']['成绩'].split()[0]\n",
|
||
" data1 = {'code':k,'sex':sex,'age':v['age'],'item':'HeightWeight','result':bmi_data}\n",
|
||
" dict2[k]['bmi'] = {}\n",
|
||
" dict2[k]['bmi']['成绩'] = bmi_data\n",
|
||
" dict2[k]['bmi']['score'] = cal_bmi(data1)\n",
|
||
" for item_en in list_item:\n",
|
||
" if item_en in v.keys(): \n",
|
||
" data1 = {'code':k,'sex':sex,'age':v['age'],'item':item_en,'result':float(v[item_en]['成绩'].split()[0])}\n",
|
||
" #print(k,v['name'])\n",
|
||
" dict2[k][item_en]['score'] = cal_score(data1)\n",
|
||
" #print(k,v[item_en]['成绩'],cal_score(data1))\n",
|
||
"\n",
|
||
"filename = f'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'w') as fl:\n",
|
||
" json.dump(dict2,fl , ensure_ascii=False) \n",
|
||
"print('ok!') "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "abace6bc-9c99-497d-a1c1-9ff045ccfc03",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 生成体测成绩明细表"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f0608de5-07ae-458c-999e-60968314f058",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import openpyxl\n",
|
||
"\n",
|
||
"items = ['lung','grip','flexion','jump','pushup','situp','balance','reaction','step']\n",
|
||
"bmi = ['height','weight']\n",
|
||
"title = ['编号','姓名','性别','单位/部门','身高','体重','bmi','肺活量','','握力','','坐位体前屈','','纵跳','','俯卧撑','','一分钟仰卧起坐','','单脚站立','','选择反应时','','台阶指数']\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items(): #print(k,dict2[str(k)]['name'])\n",
|
||
" list2 = []\n",
|
||
" list2.append(str(k).rjust(5,'0'))\n",
|
||
" list2.append(dict1[k]['name']) \n",
|
||
" list2.append(dict1[k]['sex'])\n",
|
||
" list2.append(dict1[k]['unit'])\n",
|
||
" list2.append(dict1[k]['phone'])\n",
|
||
" i = 0\n",
|
||
" if 'bmi' in dict1[k].keys():\n",
|
||
" list2.append(dict1[k]['height']['成绩'])\n",
|
||
" list2.append(dict1[k]['weight']['成绩'])\n",
|
||
" list2.append(dict1[k]['bmi']['score'])\n",
|
||
" i+=1\n",
|
||
" else:\n",
|
||
" list2.append('') \n",
|
||
" list2.append('') \n",
|
||
" list2.append('') \n",
|
||
" \n",
|
||
" \n",
|
||
" for item in items:\n",
|
||
" if item in dict1[k].keys():\n",
|
||
" list2.append(dict1[k][item]['成绩'])\n",
|
||
" list2.append(dict1[k][item]['score']) \n",
|
||
" i+=1\n",
|
||
" elif item =='name':\n",
|
||
" list2.append(dict1[k][item])\n",
|
||
" else:\n",
|
||
" list2.append('') \n",
|
||
" list2.append('') \n",
|
||
" if i>2:\n",
|
||
" list1.append(list2)\n",
|
||
"filename = 'data/北海炼化体测情况表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename)\n",
|
||
"print('ok') "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5f46d541-c7db-4adf-b452-d901c757e9c5",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 查询参加问卷未参加体测人员"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "2c867c7f-00b4-4a41-a6eb-18d6c39fa4cc",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"import time\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"filename = 'data/北海炼化2023年.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict3 = json.load(fl)\n",
|
||
"\n",
|
||
"phone = set()\n",
|
||
"phone1 = set()\n",
|
||
"for k,v in dict3.items():\n",
|
||
" phone.add(v['phone'])\n",
|
||
"for k,v in dict1.items():\n",
|
||
" phone1.add(v['phone'])\n",
|
||
"list1 = []\n",
|
||
"filename = 'data/Survey_20231122.csv'\n",
|
||
"with open(filename,'r',newline='') as csv_file:\n",
|
||
" fl = csv.reader(csv_file,delimiter=',')\n",
|
||
" header = next(fl) \n",
|
||
" for line in fl:\n",
|
||
" list1.append(line)\n",
|
||
"\n",
|
||
"for item in list1:\n",
|
||
" if item[2] in phone and item[2] not in phone1:\n",
|
||
" print(item[2])\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "33b0075e-5b48-44ed-9cc7-f316ad9a0237",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 核对报告缺失情况"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "2e5ae18e-c153-4cdf-825e-f969080eea16",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import glob\n",
|
||
"from pathlib import Path\n",
|
||
"\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"\n",
|
||
"fi_path = '/home/songyi/pdf-typescript/北海炼化2023_1'\n",
|
||
"fls = glob.glob(f'{fi_path}/*.pdf')\n",
|
||
"list1 = []\n",
|
||
"for fl in fls:\n",
|
||
" fn = Path(fl).stem.split('-')[0]\n",
|
||
" list1.append(int(fn))\n",
|
||
"print(len(dict1))\n",
|
||
"for k ,v in dict1.items():\n",
|
||
" if int(k) not in list1:\n",
|
||
" print(k,v['name'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e7e0e29c-0f12-4478-b687-a03486adc85e",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 报告按部门分类"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "3ff8ad3c-7868-4eb2-b879-4e8da19407ff",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os,sys,shutil\n",
|
||
"import json\n",
|
||
"import glob\n",
|
||
"from pathlib import Path\n",
|
||
"\n",
|
||
"fi_path = '/home/songyi/pdf-typescript/134'\n",
|
||
"new_path = 'file/134'\n",
|
||
"old = []\n",
|
||
"dict2 = {}\n",
|
||
"\n",
|
||
"filename = 'data/天津石化人员名单2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl)\n",
|
||
"fls = glob.glob(f'{fi_path}/*.pdf')\n",
|
||
"for fn in fls:\n",
|
||
" fi_name =Path(fn).stem.split('-')[0]\n",
|
||
" code = int(fi_name)\n",
|
||
" unit_path = Path(new_path,dict1[str(code)]['unit'])\n",
|
||
" unit_path.mkdir(parents = True, exist_ok = True)\n",
|
||
" n_name = Path(unit_path,Path(fn).stem+'.pdf')\n",
|
||
" if not os.path.exists(n_name):\n",
|
||
" shutil.copyfile(fn,n_name)\n",
|
||
" #print(n_name)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "abe43620-c456-43a0-905a-b29aad8b2e3c",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 核对新部门分类人员"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a3f1476d-5f70-45c4-aa04-ebc6558033b8",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import json\n",
|
||
"import csv\n",
|
||
"import openpyxl\n",
|
||
"import time\n",
|
||
"from datetime import date\n",
|
||
"\n",
|
||
"filename = 'data/result_北海炼化2023.json'\n",
|
||
"with open(filename,'r') as fl:\n",
|
||
" dict1 = json.load(fl) \n",
|
||
"\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/北海炼化新名单.xlsx')\n",
|
||
"sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"list1 = []\n",
|
||
"\n",
|
||
"for n in range(5, sheet.max_row+1):\n",
|
||
" if sheet.cell(n,2).value is not None:\n",
|
||
" list1.append(sheet.cell(n,2).value)\n",
|
||
"print(len(list1)) \n",
|
||
"i = 1\n",
|
||
"for k, v in dict1.items():\n",
|
||
" name = v['name']\n",
|
||
" if name not in list1:\n",
|
||
" print(i,name)\n",
|
||
" i+=1"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "76c5c17a-462d-4a7b-95a5-6b895f5a25dc",
|
||
"metadata": {},
|
||
"source": [
|
||
"# 2024年体质检测"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a51dadfb-30e7-40f3-a437-321aa986a10f",
|
||
"metadata": {},
|
||
"source": [
|
||
"### 北海体检情况汇总"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 149,
|
||
"id": "7410324c-92c2-4a20-9715-f003d4915c8a",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2024-04-10T11:51:24.039781Z",
|
||
"iopub.status.busy": "2024-04-10T11:51:24.039544Z",
|
||
"iopub.status.idle": "2024-04-10T11:51:24.665413Z",
|
||
"shell.execute_reply": "2024-04-10T11:51:24.664830Z",
|
||
"shell.execute_reply.started": "2024-04-10T11:51:24.039764Z"
|
||
},
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"ok\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/北海体检报告数据整理2024.xlsx')\n",
|
||
"#sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"sheet = wb['Sheet3']\n",
|
||
"dict1 = {}\n",
|
||
"for n in range(2, sheet.max_row+1):\n",
|
||
" if sheet.cell(n,2).value is None:\n",
|
||
" break\n",
|
||
" else: \n",
|
||
" code = sheet.cell(n, 2).value\n",
|
||
" dict1.setdefault(code, {}) \n",
|
||
" dict1[code]['name'] = sheet.cell(n, 3).value \n",
|
||
" \n",
|
||
" dict1[code]['sex'] = sheet.cell(n, 4).value \n",
|
||
" dict1[code]['age'] = sheet.cell(n, 5).value \n",
|
||
" dict1[code].setdefault('bz',[]) \n",
|
||
" dict1[code]['bz'].append(sheet.cell(n, 7).value) \n",
|
||
" \n",
|
||
"filename = 'data/北海炼化2023年健康体检团体报告.json'\n",
|
||
"with open(filename, 'w') as fl:\n",
|
||
" json.dump(dict1, fl, ensure_ascii=False)\n",
|
||
"print('ok')\n",
|
||
"list1 = []\n",
|
||
"for k, v in dict1.items():\n",
|
||
" list2 = []\n",
|
||
" mbz = set(v['bz'])\n",
|
||
" list2.append(k)\n",
|
||
" list2.append(v['name'])\n",
|
||
" list2.append(v['sex'])\n",
|
||
" list2.append(v['age'])\n",
|
||
" list2.append(','.join(mbz))\n",
|
||
" list1.append(list2)\n",
|
||
"title = ['体检编号','姓名','性别','年龄','体检症状']\n",
|
||
"filename = 'data/中国石化北海炼化有限责任公司2023年职业体检团体报告汇总统计表.xlsx'\n",
|
||
"wb = openpyxl.Workbook()\n",
|
||
"sheet = wb.active\n",
|
||
"sheet.append(title)\n",
|
||
"for row in list1:\n",
|
||
" sheet.append(row)\n",
|
||
" \n",
|
||
"wb.save(filename) "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3cb5a5c9-e3d5-4959-a085-b3a34d778334",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 统计体检项目"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 148,
|
||
"id": "28825d80-9123-4ec5-b107-9ad133f11a82",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2024-04-10T11:47:45.024742Z",
|
||
"iopub.status.busy": "2024-04-10T11:47:45.024528Z",
|
||
"iopub.status.idle": "2024-04-10T11:47:45.386052Z",
|
||
"shell.execute_reply": "2024-04-10T11:47:45.385453Z",
|
||
"shell.execute_reply.started": "2024-04-10T11:47:45.024726Z"
|
||
},
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"畸胎瘤\n",
|
||
"细胞角蛋白19片段增高\n",
|
||
"癌胚抗原(定量)(CEA)增高\n",
|
||
"尿糖阳性\n",
|
||
"脊柱侧弯\n",
|
||
"甲状腺结节\n",
|
||
"游离三碘甲状腺原氨酸（FT3）增高\n",
|
||
"2级高血压(中度)\n",
|
||
"肾错构瘤\n",
|
||
"胆囊结石\n",
|
||
"天门冬氨酸氨基转移酶（AST）增高\n",
|
||
"颈椎退行性变\n",
|
||
"血脂异常\n",
|
||
"听力下降\n",
|
||
"肺少许慢性炎症\n",
|
||
"卵巢囊肿\n",
|
||
"色弱\n",
|
||
"肥胖\n",
|
||
"窦性心动过缓\n",
|
||
"预激综合征\n",
|
||
"甲胎蛋白(AFP)增高\n",
|
||
"体重偏低\n",
|
||
"糖链抗原(CA-125)偏高\n",
|
||
"前列腺特异抗原（PSA）增高\n",
|
||
"肾钙乳症\n",
|
||
"血压高\n",
|
||
"轻度ST段改变\n",
|
||
"肺大疱\n",
|
||
"心影增大\n",
|
||
"肝囊肿\n",
|
||
"乳腺囊肿\n",
|
||
"胆管扩张\n",
|
||
"C-14呼气试验阳性\n",
|
||
"肾结石\n",
|
||
"胆囊壁稍毛糙\n",
|
||
"尿蛋白阳性\n",
|
||
"血清γ-谷氨酰基转移酶(GGT)增高\n",
|
||
"咽部充血\n",
|
||
"糖链抗原(CA-242)偏高\n",
|
||
"脂肪肝\n",
|
||
"前列腺囊肿\n",
|
||
"动脉血管弹性下降\n",
|
||
"肝脂肪度为中度\n",
|
||
"胆囊息肉\n",
|
||
"白内障\n",
|
||
"前列腺稍大并钙化灶\n",
|
||
"肝纤维化为轻度\n",
|
||
"肝血管瘤\n",
|
||
"血压低\n",
|
||
"空腹血糖增高\n",
|
||
"肝脂肪度为轻度\n",
|
||
"前列腺增大\n",
|
||
"肝纤维化为中度\n",
|
||
"人乳头瘤病毒基因分型(HPV)高危型阳\n",
|
||
"前列腺钙化灶\n",
|
||
"EB病毒抗体(EB-Ab)阳性\n",
|
||
"颈椎骨质增生\n",
|
||
"肝脂肪度为重度\n",
|
||
"胆囊息肉样病变\n",
|
||
"轻度ST-T改变\n",
|
||
"胆囊泥沙样结石\n",
|
||
"肝实质光点密集\n",
|
||
"肾囊肿\n",
|
||
"血尿酸增高\n",
|
||
"尿潜血阳性\n",
|
||
"心电图提示：V1呈QS型\n",
|
||
"血肌酐增高\n",
|
||
"室性早搏\n",
|
||
"宫颈息肉\n",
|
||
"肺结节\n",
|
||
"胆固醇结晶\n",
|
||
"神经元特异性烯醇化酶(NSE）偏高\n",
|
||
"心房纤颤\n",
|
||
"肝纤维化为重度\n",
|
||
"糖化血红蛋白（HbA1c）增高\n",
|
||
"甲状腺囊肿\n",
|
||
"肺少许炎症\n",
|
||
"脾囊肿\n",
|
||
"肝低回声区\n",
|
||
"屈光不正\n",
|
||
"血清丙氨酸氨基转移酶(ALT)增高\n",
|
||
"肝实质光点稍密集\n",
|
||
"动脉血管弹性稍下降\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import openpyxl\n",
|
||
"import json\n",
|
||
"\n",
|
||
"wb = openpyxl.load_workbook('data/北海体检报告数据整理2024.xlsx')\n",
|
||
"#sheet = wb.active\n",
|
||
"# sheets = wb.sheetnames\n",
|
||
"sheet = wb['Sheet3']\n",
|
||
"xm = set()\n",
|
||
"for n in range(2, sheet.max_row+1):\n",
|
||
" if sheet.cell(n,2).value is None:\n",
|
||
" break\n",
|
||
" else: \n",
|
||
" xm.add(sheet.cell(n, 7).value) \n",
|
||
"for item in xm:\n",
|
||
" print(item)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d3e0075b-7a93-4454-860b-ba523e63ea08",
|
||
"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": "3.10.12"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|