{ "cells": [ { "cell_type": "markdown", "id": "e764be85-0ddf-4055-abd6-de2990e75db8", "metadata": { "jp-MarkdownHeadingCollapsed": true, "tags": [], "toc-hr-collapsed": true }, "source": [ "# 第一次体测" ] }, { "cell_type": "markdown", "id": "ae533fe9-e20e-4e44-b9bb-030c4fa4e714", "metadata": { "tags": [] }, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": null, "id": "1144aaac-92a0-4bcf-aba7-096f7dd3ad3b", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/天津石化员工检测花名册 （20221014）.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, 6).value)\n", " person.setdefault(code, {})\n", " dict1 = {}\n", " dict1['name'] = sheet.cell(n, 3).value\n", " dict1['sex'] = sheet.cell(n, 4).value\n", " dict1['unit'] = sheet.cell(n, 1).value\n", " dict1['sub_unit'] = sheet.cell(n, 2).value\n", " if sheet.cell(n,5).value is not None:\n", " dict1['id_num'] = sheet.cell(n,5).value\n", " person[code] = dict1\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "93b9bfba-5404-4c9b-ac8f-48a3bf296669", "metadata": {}, "source": [ "## 合并人员信息" ] }, { "cell_type": "code", "execution_count": null, "id": "d5171966-95ae-47ae-a75e-db08de772348", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "\n", "for k, v in dict2.items():\n", " if k not in dict1.keys():\n", " dict1.setdefault(k,{})\n", " dict1[k]['name'] = dict2[k]['name']\n", " dict1[k]['sex'] = dict2[k]['sex']\n", " dict1[k]['unit'] = dict2[k]['name']\n", " dict1[k]['sub_unit'] = dict2[k]['sub_unit']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "5e648b69-40bf-4494-9079-e4e2b6ab8866", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "a57ebb22-543c-4804-8d44-89984058ec1d", "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,a.date_joined FROM places_result AS a,_tianjin AS b WHERE a.place_id=134 AND a.avatar_id=b.id\n", "\n", "re_ta = {}\n", "dict1 = {}\n", "list1 = []\n", "#print(\"\\n运动项目信息：\")\n", "filename = '体测单位/data/20230428_134.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_天津.json'\n", "with open(filename,'w') as fl:\n", " json.dump(re_ta, fl) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "55d961e5-a512-44b2-808e-7c55d7000d52", "metadata": {}, "source": [ "## 导出测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "38397ad4-2bb3-4b5e-8ece-9ea11e801890", "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','车间/科室','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_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单.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", " list2.append(dict2[k]['sub_unit'])\n", " \n", " for item in items:\n", " if item in v.keys():\n", " list2.append(v[item]['成绩'])\n", " \n", " elif item =='name':\n", " list2.append(v[item])\n", " else:\n", " list2.append('') \n", " \n", " list1.append(list2)\n", "filename = 'data/天津石化体测情况表（截至20221122）.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": "239ceb76-f690-4dae-991c-62c38d617c85", "metadata": {}, "source": [ "## 导出测试成绩(带得分)" ] }, { "cell_type": "code", "execution_count": null, "id": "27529013-f3de-4e23-980d-f62203e4df88", "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','车间/科室','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_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "del dict1['1730253']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict2 = 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(dict2[k]['name']) \n", " list2.append(dict2[k]['sex'])\n", " list2.append(dict2[k]['unit']) \n", " list2.append(dict2[k]['sub_unit']) \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]['得分']) \n", " elif item =='name':\n", " list2.append(dict1[k][item])\n", " else:\n", " list2.append('') \n", " list2.append('') \n", " list1.append(list2)\n", "filename = 'data/天津石化体测情况表.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": "1c7b219f-43cd-4bf0-971f-2c398f8db8ed", "metadata": {}, "source": [ "## 按照日期进行报告分类" ] }, { "cell_type": "markdown", "id": "3d57ff66-69c3-4c13-811b-f1e13b404077", "metadata": {}, "source": [ "### 按照体测明细分类" ] }, { "cell_type": "code", "execution_count": null, "id": "29c0f15b-1345-4b46-ac1d-b45ddede9641", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import time\n", "import csv\n", "import os,sys,shutil\n", "import glob\n", "\n", "dict1 = {}\n", "list1 = []\n", "filename = 'data/134_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", "for result in list1:\n", " user = str(result[4])\n", " dict1.setdefault(user,'2022-10-01')\n", " m_date = result[7]\n", " if m_date> dict1[user]:\n", " dict1[user] = m_date\n", "\n", "m_path = 'file/134'\n", "\n", "fls = glob.glob(f'file/new/*.pdf')\n", "for fn in fls:\n", " #old = os.path.basename(fn).split('.')[0].rjust(8,'0') \n", " old = os.path.basename(fn).split('.')[0]\n", " mrq = str(dict1[old]).split(' ')[0].replace('-', '', 2)\n", " if not os.path.exists(m_path + '/new/' + mrq):\n", " os.mkdir(m_path + '/new/' + mrq)\n", " n_name = f'{m_path}/new/{mrq}/{str(old).rjust(8,\"0\")}_{mrq}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "ae2b17bd-38b9-4809-affb-01441a5581eb", "metadata": {}, "source": [ "### 按照报告生成日期分类" ] }, { "cell_type": "code", "execution_count": null, "id": "eb24c1be-b5d3-4e61-a432-854a887746d4", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import time\n", "import csv\n", "import os,sys,shutil\n", "import glob\n", "\n", "dict1 = {}\n", "list1 = []\n", "\n", "m_path = 'file/134'\n", "mrq = '20221028'\n", "if not os.path.exists(m_path + '/' + mrq):\n", " os.mkdir(m_path + '/' + mrq)\n", "fls = glob.glob(f'file/new/*.pdf')\n", "for fn in fls:\n", " #old = os.path.basename(fn).split('.')[0].rjust(8,'0') \n", " old = os.path.basename(fn).split('.')[0] \n", " n_name = f'{m_path}/{mrq}/{str(old).rjust(8,\"0\")}_{mrq}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "d9061d26-b09b-4bff-af24-a14adda3d83f", "metadata": {}, "source": [ "## 按照部门报告分组" ] }, { "cell_type": "code", "execution_count": null, "id": "7ea2541f-461f-4eb5-860d-4b56d6be74ab", "metadata": {}, "outputs": [], "source": [ "import os,sys,shutil\n", "import json\n", "import math\n", "import glob\n", "from pathlib import Path\n", "\n", "fi_path = './file'\n", "old = []\n", "dict2 = {}\n", "\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k, v in dict1.items():\n", " m_name = v['name']\n", " m_depart = v['unit'] \n", " dict2[int(k)] = [m_name,m_depart]\n", "\n", "\n", "\n", "fls = glob.glob(f'./file/*.pdf')\n", "\n", "for fn in fls:\n", " old.append(os.path.basename(fn).split('.')[0])\n", " #print(fn)\n", "\n", "\n", "for n in old: \n", " o_name = f'{fi_path}/{n}.pdf'\n", " if not os.path.exists(f'{fi_path}/new/{dict2[int(n)][1]}'):\n", " os.mkdir(f'{fi_path}/new/{dict2[int(n)][1]}') \n", " n_name = f'{fi_path}/new/{dict2[int(n)][1]}/{str(n).rjust(5,\"0\")}-{dict2[int(n)][0]}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(o_name,n_name)\n", " print(n_name)" ] }, { "cell_type": "code", "execution_count": null, "id": "63eb8a23-4876-4be6-8800-1a67df8773ff", "metadata": { "tags": [] }, "outputs": [], "source": [ "import os,sys,shutil\n", "import json\n", "import math\n", "import glob\n", "from pathlib import Path\n", "\n", "fi_path = './file'\n", "old = []\n", "dict2 = {}\n", "\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k, v in dict1.items():\n", " m_name = v['name']\n", " m_depart = v['unit'] \n", " dict2[int(k)] = [m_name,m_depart]\n", "\n", "\n", "\n", "fls = glob.glob(f'./file/*.pdf')\n", "\n", "for fn in fls:\n", " old.append(os.path.basename(fn).split('.')[0])\n", "\n", "for n in old: \n", " o_name = f'{fi_path}/{n}.pdf'\n", " new_path = Path('file/new',dict1[n]['unit'],dict1[n]['sub_unit'])\n", " new_path.mkdir(parents = True, exist_ok = True)\n", " n_name = Path(new_path,f'{str(n).rjust(7,\"0\")}-{dict2[int(n)][0]}.pdf')\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(o_name,n_name)\n", " print(n_name)\n", " \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "e4590323-6645-450a-8055-756a5bf35b34", "metadata": {}, "source": [ "## 统计报告人员信息表" ] }, { "cell_type": "code", "execution_count": null, "id": "ed681a0d-4ee8-48ec-ab05-23da7156a44e", "metadata": {}, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "import os\n", "import glob\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "m_path ='./file'\n", "fls = glob.glob(f'file/*.pdf')\n", "list1 = []\n", "for fn in fls:\n", " list2 = []\n", " code = os.path.basename(fn).split('.')[0]\n", " list2 = [code.rjust(7,\"0\"),dict1[code]['name'],dict1[code]['unit'],dict1[code]['sub_unit']]\n", " list1.append(list2)\n", "title = ['编号','姓名','单位/部门','车间/科室',] \n", "filename = 'data/天津石化体测情况表.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)" ] }, { "cell_type": "markdown", "id": "838ec7d3-137c-4ccd-9f16-7b6312d1ffa6", "metadata": {}, "source": [ "## PDF文件压缩" ] }, { "cell_type": "code", "execution_count": null, "id": "a6ab0943-b018-4dd6-9176-85a762f9f60c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import fitz\n", "from pdf2image import convert_from_path, convert_from_bytes\n", "import os,sys\n", "import tempfile\n", "from pdf2image.exceptions import (\n", " PDFInfoNotInstalledError,\n", " PDFPageCountError,\n", " PDFSyntaxError\n", ")\n", "import img2pdf \n", "import glob\n", "import shutil\n", "\n", "def covert2pic(old_fn):\n", " if os.path.exists('.pdf'): # 临时文件，需为空\n", " shutil.rmtree('.pdf')\n", " os.mkdir('.pdf')\n", " with tempfile.TemporaryDirectory() as path:\n", " images_from_path = convert_from_path(old_fn, dpi=100,fmt='jpg', output_folder='.pdf')\n", "\n", "def pic2pdf(new_fn):\n", " fl1=glob.glob('.pdf/*.jpg')\n", " fl1.sort()\n", " a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", " layout_fun = img2pdf.get_layout_fun(a4inpt)\n", " with open(new_fn,\"wb\") as f:\n", " f.write(img2pdf.convert(fl1,layout_fun=layout_fun))\n", " print(f'{new_fn}转换成功！')\n", " \n", "\n", "\n", "def pdfz(sor, obj, zoom): \n", " covert2pic(zoom)\n", " pic2pdf(obj)\n", " \n", "fi_path = 'file/134/20221122/'\n", "fl = glob.glob(f'{fi_path}*.pdf')\n", "\n", "for fn in fl:\n", " new_fn = fi_path+'new/'+os.path.basename(fn)\n", " covert2pic(fn)\n", " pic2pdf(new_fn)\n", " shutil.rmtree('.pdf')\n", "print('ok!')\n", "\n" ] }, { "cell_type": "markdown", "id": "a0cc9662-4171-4c2a-828d-f58c327ec8c1", "metadata": {}, "source": [ "## 统计未测试人员名单" ] }, { "cell_type": "code", "execution_count": null, "id": "daef91be-1b58-4fb1-b182-64f43c07c90f", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/result_天津.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", " if k not in dict2.keys(): \n", " list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] \n", " list1.append(list2)\n", "filename = 'data/天津石化未参加体测人数统计表.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": "72c693e1-dd7c-40fa-8948-4fd6fbea8ddc", "metadata": {}, "source": [ "## 区分新文件" ] }, { "cell_type": "code", "execution_count": null, "id": "9d06d4f0-364b-438c-844b-7d5badaf3496", "metadata": { "tags": [] }, "outputs": [], "source": [ "import os,sys,shutil\n", "import glob\n", "import time\n", "\n", "fi_path = 'file/'\n", "fls = glob.glob(f'{fi_path}*.pdf')\n", "m_date = time.strptime('2022-10-28','%Y-%m-%d')\n", "for fn in fls:\n", " c_time = time.gmtime(os.path.getctime(fn))\n", " if c_time > m_date:\n", " n_name = f'{fi_path}new/{os.path.basename(fn)}'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", " print(n_name)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "32b61559-4495-4fbe-8eb6-2614e6225b5c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/result_天津.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "print(len(dict2),len(dict1),)" ] }, { "cell_type": "markdown", "id": "47015abe-4cb8-436b-afa5-9ffd78d4a628", "metadata": {}, "source": [ "## 心理测试情况统计" ] }, { "cell_type": "code", "execution_count": null, "id": "c21efc40-2639-4b22-851f-925cd3f12d3a", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/134_xinli.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[4])\n", "list3 = []\n", "for k, v in dict1.items():\n", " list2 = []\n", " if k not in list1: \n", " list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] \n", " list3.append(list2)\n", "filename = 'data/天津石化未参加心理测试人数统计表.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "sheet.append(title)\n", "for row in list3:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "code", "execution_count": null, "id": "6b8ae75d-71a3-4cbe-a216-03c28d78156c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "filename = 'data/134_xinli.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", " print(line[4])" ] }, { "cell_type": "markdown", "id": "20e98f0d-61ea-43a5-8993-9656fed23099", "metadata": {}, "source": [ "## 体检报告统计分析" ] }, { "cell_type": "markdown", "id": "0436a3a2-6230-43b3-beae-bc89e789b285", "metadata": {}, "source": [ "### excel数据导入" ] }, { "cell_type": "code", "execution_count": null, "id": "7bb2e3aa-591d-4fce-983a-cde5d4c30e56", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "import re\n", "\n", "wb = openpyxl.load_workbook('data/体检结果(模板)化工.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "dict1 = {}\n", "\n", "for n in range(11, sheet.max_row+1):\n", " code = sheet.cell(n, 1).value\n", " name = sheet.cell(n, 8).value\n", " txt = sheet[f'DT{str(n)}'].value \n", " txt = re.sub(r'\\n', \"\", txt)\n", " txt = re.sub(r'\\t', \"\", txt)\n", " txt = re.sub(r'二、尊敬的顾客您好,您本次体检的建议信息如下：', \"\", txt)\n", " ss = r'三、温馨提示： 鉴于医学技术发展的局限性，个体间可能存在的生物差异性以及您选择的检查项目的局限性，任何一次医学检查的手段和方法都不具备绝对的特异性和灵敏度，对于疾病筛检仍有其盲点，因此，我们建议您对本次检查的异常结果进行随诊复查和其他相关检查，以获得更可靠的医学证据建立准确地医学判断。'\n", " txt1 = re.sub(r'三、温馨提示.*', \"\", txt,re.S)\n", " dict1.setdefault(code, {})\n", " dict1[code]['name'] = name\n", " dict1[code]['xb'] = sheet.cell(n, 9).value\n", " #dict1[code]['birth'] = sheet.cell(n, 10).value\n", " dict1[code]['report'] = txt1\n", "filename = 'data/体检结果.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "227a1c0b-fc78-4951-97ab-5664b59edd1d", "metadata": {}, "source": [ "### 体检结果分解" ] }, { "cell_type": "code", "execution_count": null, "id": "b38aef28-5d1b-4762-9c7e-70a531594fa4", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "import re\n", "\n", "mo1 = r'[0-9]、'\n", "mo2 = '【.*】'\n", "filename = 'data/体检结果.json'\n", "list3 = []\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "for k, v in dict1.items():\n", " \n", " ss = v['report']\n", " list1 = re.split(mo1,ss)\n", " if len(list1) ==1:\n", " continue\n", " else:\n", " list1.remove('')\n", " #print(list1)\n", " for item in list1:\n", " list2 = re.search( mo2, item)\n", " xm =list2.group()\n", " \n", " txt = item.replace(xm,'').strip()\n", " list3.append([k,v['name'],v['xb'],xm,txt])\n", "filename = 'data/症状表.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list3:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "964526bc-9c9c-4b63-9300-67b02d2608f5", "metadata": {}, "source": [ "## 天津人员制卡" ] }, { "cell_type": "code", "execution_count": null, "id": "83f02525-fd26-41ba-8b6a-c3cd584825e6", "metadata": { "tags": [] }, "outputs": [], "source": [ "import binascii\n", "import openpyxl\n", "gbs = 'C2EDC1A2D1C7'\n", "bs = binascii.a2b_hex(gbs)\n", "#print('bs', bs)\n", "#print('decode-bs:', bs.decode('gb2312'))\n", "\n", "s = '马立亚'\n", "gbcode = s.encode('gb2312') # 先转成 bytes格式\n", "#print('gbcode:', gbcode)\n", "gbs = \"\".join([hex(ch)[2:] for ch in gbcode]) #\n", "#print('gbs:', gbs)\n", "\n", "wb = openpyxl.load_workbook('data/联合六车间体质测定人员名单.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "person = {}\n", "list1 = []\n", "for n in range(3, sheet.max_row+1):\n", " name = sheet.cell(n, 3).value\n", " code = sheet.cell(n, 2).value\n", " gbcode = code.encode('gbk')\n", " code = \"\".join([hex(ch)[2:] for ch in gbcode])\n", " gbcode = name.encode('gbk')\n", " name = \"\".join([hex(ch)[2:] for ch in gbcode])\n", " #for s in code:\n", " # print(ord(s))\n", " \n", " list1.append([sheet.cell(n, 1).value,sheet.cell(n, 2).value,sheet.cell(n, 3).value,code.ljust(32,'0'),name.ljust(32,'0')])\n", " print(code.ljust(32,'0'),name.ljust(32,'0'))\n", "\n", "filename = 'data/联合六车间体质测定人员制卡名单.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list1:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')\n" ] }, { "cell_type": "markdown", "id": "638bbe8e-3770-40e1-b884-ceeeec5a053c", "metadata": {}, "source": [ "## 因素分析" ] }, { "cell_type": "markdown", "id": "9e25a7f2-0571-438b-9aa4-e3337d9fd840", "metadata": {}, "source": [ "### 清除修改测试项目" ] }, { "cell_type": "code", "execution_count": null, "id": "6e6f6a63-b297-42e8-a9ba-b2636fda5d09", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "\n", "filename = 'data/天津石化人员231113.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "code = '1734094'\n", "items = ['身高','体重']\n", "for item in items:\n", " del dict1[code][item]\n", "with open(filename, 'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "f96b3aeb-bf37-4a8b-bf18-d0ae8f7df653", "metadata": {}, "source": [ "### 人员情况导入" ] }, { "cell_type": "code", "execution_count": null, "id": "4d77ec9b-c561-4355-98af-b18c42c1f3ca", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/员工个人基础信息20230113.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "person = {}\n", "\n", "for n in range(4, 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, 6).value\n", " dict1['sub_unit'] = sheet.cell(n, 7).value\n", " if sheet.cell(n,10).value is not None:\n", " dict1['daoban'] = '是'\n", " else:\n", " dict1['daoban'] = '否'\n", " dict1['age'] = sheet.cell(n, 13).value\n", " dict1['gl'] = sheet.cell(n, 14).value\n", " dict1['jhgl'] = sheet.cell(n, 15).value \n", " person[code] = dict1\n", "filename = 'data/天津石化人员231113.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "a5c58b77-69b6-4d76-8927-6e734556e848", "metadata": {}, "source": [ "### 人员体测得分导入合并" ] }, { "cell_type": "code", "execution_count": null, "id": "db473c01-7e1a-48c4-a0d7-e44cdeb9e24b", "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", "\n", "filename = 'data/result_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员231113.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "for k, v in dict2.items():\n", " if k in dict1.keys():\n", " for item in dict1[k].keys():\n", " dict2[k][item] = dict1[k][item]\n", "filename = 'data/天津石化人员231113.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(dict2, fl, ensure_ascii=False)\n", "print('ok')\n", " " ] }, { "cell_type": "markdown", "id": "cc53ec68-cfc4-449a-9905-095a079dc8ab", "metadata": {}, "source": [ "### 筛选体测人员，计算得分" ] }, { "cell_type": "code", "execution_count": null, "id": "224cdee4-153f-424a-aaaa-92ef58943edb", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员231113.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "dict3 = {}\n", "for k, v in dict2.items():\n", " if k in dict1.keys():\n", " dict3[k] = dict2[k]\n", " i = 0\n", " score =0\n", " for item in dict2[k].keys(): \n", " if item in items:\n", " score = score + int(dict2[k][item]['得分'])\n", " i+=1\n", " dict3[k]['score'] = score\n", " dict3[k]['item_num'] = i\n", " dict3[k]['avg'] = round(score/i,2)\n", "filename = 'data/天津石化线上测试结果.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "for k, v in dict2.items():\n", " if k in dict1.keys():\n", " dict3[k] = dict2[k]\n", " dict3[k]['zhongyi'] = dict1[k]['中医体质']\n", " \n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(dict3, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "dd014e41-18f2-44e7-9f20-1190df4e7b45", "metadata": {}, "source": [ "### 因素分析" ] }, { "cell_type": "markdown", "id": "c63bca31-f003-49e9-a20d-1931c050c740", "metadata": {}, "source": [ "#### 倒班因素分析" ] }, { "cell_type": "code", "execution_count": null, "id": "2a964412-8408-4039-a788-8cc1fc7cd518", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "\n", "for k, v in dict1.items():\n", " unit.add(dict1[k]['unit'])\n", "#print(unit)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " dict2.setdefault(v['unit'],{})\n", " dict2[v['unit']].setdefault('是',{})\n", " dict2[v['unit']].setdefault('否',{})\n", " dict2[v['unit']]['是'].setdefault('num',0)\n", " dict2[v['unit']]['否'].setdefault('num',0)\n", " dict2[v['unit']]['是'].setdefault('score',0)\n", " dict2[v['unit']]['否'].setdefault('score',0)\n", " dict2[v['unit']]['是'].setdefault('zhongyi',0)\n", " dict2[v['unit']]['否'].setdefault('zhongyi',0) \n", " dict2[v['unit']]['是'].setdefault('pianpo',0)\n", " dict2[v['unit']]['否'].setdefault('pianpo',0) \n", " if 'avg' in v.keys():\n", " dict2[v['unit']][v['daoban']]['num'] = dict2[v['unit']][v['daoban']]['num'] + 1\n", " dict2[v['unit']][v['daoban']]['score'] = dict2[v['unit']][v['daoban']]['score'] + v['avg']\n", " if 'zhongyi' in v.keys() :\n", " dict2[v['unit']][v['daoban']]['zhongyi'] = dict2[v['unit']][v['daoban']]['zhongyi'] + 1\n", " if 'zhongyi' in v.keys() and v['zhongyi']!='平和':\n", " dict2[v['unit']][v['daoban']]['pianpo'] = dict2[v['unit']][v['daoban']]['pianpo'] + 1\n", " \n", " \n", "for k, v in dict2.items(): \n", " if v['是']['num'] > 0:\n", " dict2[k]['是']['avg'] = round(v['是']['score']/v['是']['num'],2)\n", " else:\n", " dict2[k]['是']['avg'] = 0\n", " if v['否']['num'] > 0:\n", " dict2[k]['否']['avg'] = round(v['否']['score']/v['否']['num'],2)\n", " else:\n", " dict2[k]['否']['avg'] = 0\n", "list1 = [] \n", "for k, v in dict2.items():\n", " list2 = []\n", " unit = k\n", " for k1, v1 in v.items():\n", " daoban = k1\n", " num = v1['num']\n", " avg = v1['avg']\n", " zhongyi = v1['zhongyi']\n", " pianpo = v1['pianpo']\n", " list2 = [k,daoban,num,avg,zhongyi,pianpo]\n", " list1.append(list2)\n", " \n", "filename = 'data/天津倒班因素分析表.xlsx' \n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list1:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "2ccc4f6c-9cde-42d5-b41d-5b35ad86f042", "metadata": { "tags": [] }, "source": [ "#### 工龄因素分析" ] }, { "cell_type": "code", "execution_count": null, "id": "695b4933-b8c3-4be6-a024-742a982f0abb", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "\n", "for k, v in dict1.items():\n", " unit.add(dict1[k]['unit'])\n", "#print(unit)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " gld = int(int(v['gl'])/10)\n", " dict2.setdefault(gld,{})\n", " dict2[gld].setdefault(v['sex'],{})\n", " dict2[gld][v['sex']].setdefault('num',0)\n", " dict2[gld][v['sex']].setdefault('score',0)\n", " dict2[gld][v['sex']].setdefault('zhongyi',0)\n", " dict2[gld][v['sex']].setdefault('pianpo',0) \n", " if 'avg' in v.keys():\n", " dict2[gld][v['sex']]['num'] = dict2[gld][v['sex']]['num'] + 1\n", " dict2[gld][v['sex']]['score'] = dict2[gld][v['sex']]['score'] + v['avg']\n", " if 'zhongyi' in v.keys() :\n", " dict2[gld][v['sex']]['zhongyi'] = dict2[gld][v['sex']]['zhongyi'] + 1\n", " if 'zhongyi' in v.keys() and v['zhongyi']!='平和':\n", " dict2[gld][v['sex']]['pianpo'] = dict2[gld][v['sex']]['pianpo'] + 1\n", "nl = {}\n", "nl[0] = '工龄0-9年'\n", "nl[1] = '工龄10-19年'\n", "nl[2] = '工龄20-29年'\n", "nl[3] = '工龄30-39年'\n", "nl[4] = '工龄40-49年'\n", "nl[5] = '工龄50年以上'\n", "list1 = [] \n", "for k, v in nl.items():\n", " list2 = []\n", " gld = v\n", " for k1, v1 in dict2[k].items():\n", " num = v1['num']\n", " score = v1['score']\n", " zhongyi = v1['zhongyi']\n", " pianpo = v1['pianpo']\n", " list2 = [k,daoban,num,avg,zhongyi,pianpo]\n", " list1.append(list2)" ] }, { "cell_type": "code", "execution_count": null, "id": "181ff60b-3372-441a-8cd7-29e8de66ceb8", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "\n", "for k, v in dict1.items():\n", " unit.add(dict1[k]['unit'])\n", "#print(unit)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " gld = int(int(v['gl'])/10)\n", " dict2.setdefault(gld,{}) \n", " dict2[gld].setdefault('num',0)\n", " dict2[gld].setdefault('score',0)\n", " dict2[gld].setdefault('zhongyi',0)\n", " dict2[gld].setdefault('pianpo',0) \n", " if 'avg' in v.keys():\n", " dict2[gld]['num'] = dict2[gld]['num'] + 1\n", " dict2[gld]['score'] = dict2[gld]['score'] + v['avg']\n", " if 'zhongyi' in v.keys() :\n", " dict2[gld]['zhongyi'] = dict2[gld]['zhongyi'] + 1\n", " if 'zhongyi' in v.keys() and v['zhongyi']!='平和':\n", " dict2[gld]['pianpo'] = dict2[gld]['pianpo'] + 1\n", "print(dict2)\n", "nl = {}\n", "nl[0] = '工龄0-9年'\n", "nl[1] = '工龄10-19年'\n", "nl[2] = '工龄20-29年'\n", "nl[3] = '工龄30-39年'\n", "nl[4] = '工龄40-49年'\n", "nl[5] = '工龄50年以上'\n", "list1 = [] \n", "for k, v in nl.items():\n", " list2 = []\n", " gld = v\n", " \n", " num = dict2[k]['num']\n", " score = dict2[k]['score']\n", " if num > 0:\n", " avg = round(score/num,2)\n", " else:\n", " avg = 0\n", " zhongyi = dict2[k]['zhongyi']\n", " pianpo = dict2[k]['pianpo']\n", " list2 = [gld,num,avg,zhongyi,pianpo]\n", " list1.append(list2)\n", "filename = 'data/天津倒班因素分析表（工龄）.xlsx' \n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list1:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "f8fa3027-c88a-43a1-88c8-c6e9b7e94f91", "metadata": {}, "source": [ "#### 年龄因素分析" ] }, { "cell_type": "code", "execution_count": null, "id": "d5ab1a99-cb3e-4905-8c05-a6122ea09913", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "\n", "for k, v in dict1.items():\n", " unit.add(dict1[k]['unit'])\n", "#print(unit)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " gld = int(int(v['age'])/10)\n", " dict2.setdefault(gld,{}) \n", " dict2[gld].setdefault('num',0)\n", " dict2[gld].setdefault('score',0)\n", " dict2[gld].setdefault('zhongyi',0)\n", " dict2[gld].setdefault('pianpo',0) \n", " if 'avg' in v.keys():\n", " dict2[gld]['num'] = dict2[gld]['num'] + 1\n", " dict2[gld]['score'] = dict2[gld]['score'] + v['avg']\n", " if 'zhongyi' in v.keys() :\n", " dict2[gld]['zhongyi'] = dict2[gld]['zhongyi'] + 1\n", " if 'zhongyi' in v.keys() and v['zhongyi']!='平和':\n", " dict2[gld]['pianpo'] = dict2[gld]['pianpo'] + 1\n", "nl = {}\n", "\n", "nl[2] = '20-29岁'\n", "nl[3] = '30-39岁'\n", "nl[4] = '40-49岁'\n", "nl[5] = '50-59岁'\n", "nl[6] = '60岁及以上'\n", "list1 = [] \n", "for k, v in nl.items():\n", " list2 = []\n", " gld = v\n", " \n", " num = dict2[k]['num']\n", " score = dict2[k]['score']\n", " if num > 0:\n", " avg = round(score/num,2)\n", " else:\n", " avg = 0\n", " zhongyi = dict2[k]['zhongyi']\n", " pianpo = dict2[k]['pianpo']\n", " list2 = [gld,num,avg,zhongyi,pianpo]\n", " list1.append(list2)\n", "filename = 'data/天津倒班因素分析表（年龄）.xlsx' \n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list1:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "42e4ef5b-9aa8-4098-8f33-df9787dd34ab", "metadata": {}, "source": [ "#### 倒班时间因素分析" ] }, { "cell_type": "code", "execution_count": null, "id": "255b5649-fb85-424d-9fad-0f3e1dff2be3", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/天津石化人员231113_1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "\n", "for k, v in dict1.items():\n", " unit.add(dict1[k]['unit'])\n", "#print(unit)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " if v['daoban'] == '是':\n", " \n", " gld = int(int(v['gl'])/10)\n", " dict2.setdefault(gld,{}) \n", " dict2[gld].setdefault('num',0)\n", " dict2[gld].setdefault('score',0)\n", " dict2[gld].setdefault('zhongyi',0)\n", " dict2[gld].setdefault('pianpo',0) \n", " if 'avg' in v.keys():\n", " dict2[gld]['num'] = dict2[gld]['num'] + 1\n", " dict2[gld]['score'] = dict2[gld]['score'] + v['avg']\n", " if 'zhongyi' in v.keys() :\n", " dict2[gld]['zhongyi'] = dict2[gld]['zhongyi'] + 1\n", " if 'zhongyi' in v.keys() and v['zhongyi']!='平和':\n", " dict2[gld]['pianpo'] = dict2[gld]['pianpo'] + 1\n", "print(dict2)\n", "nl = {}\n", "nl[0] = '倒班工龄0-9年'\n", "nl[1] = '倒班工龄10-19年'\n", "nl[2] = '倒班工龄20-29年'\n", "nl[3] = '倒班工龄30-39年'\n", "nl[4] = '倒班工龄40-49年'\n", "list1 = [] \n", "for k, v in nl.items():\n", " list2 = []\n", " gld = v\n", " \n", " num = dict2[k]['num']\n", " score = dict2[k]['score']\n", " if num > 0:\n", " avg = round(score/num,2)\n", " else:\n", " avg = 0\n", " zhongyi = dict2[k]['zhongyi']\n", " pianpo = dict2[k]['pianpo']\n", " list2 = [gld,num,avg,zhongyi,pianpo]\n", " list1.append(list2)\n", "filename = 'data/天津倒班因素分析表（倒班工龄）.xlsx' \n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list1:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "73524e7f-4262-46d3-a733-74ac18e43855", "metadata": { "jp-MarkdownHeadingCollapsed": true, "tags": [] }, "source": [ "# 第二次体测" ] }, { "cell_type": "markdown", "id": "1be2bf2c-b1c8-494b-bc6b-681b9e75d18d", "metadata": {}, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": null, "id": "25283932-c03a-4a34-a59d-314fc64d8fbd", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/天津石化员工检测花名册（20230915）.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, 5).value\n", " dict1['sub_unit'] = sheet.cell(n, 6).value\n", " dict1['birth'] = sheet.cell(n,4).value\n", " person[code] = dict1\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "b758be8c-c9e2-46d4-b646-88403bb41e29", "metadata": {}, "source": [ "## 生产读卡系统文件" ] }, { "cell_type": "code", "execution_count": null, "id": "c908e5e7-c014-4b8d-a583-a8c2f7115a96", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\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", "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/data1.json\", \"w\",encoding = 'utf-8') as file:\n", " file.write(json_data) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "60f4831c-b44e-40d2-ad8a-d79079c071f9", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "e26b88fc-c75b-4c1e-82ea-5017370afa9b", "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/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "\n", "filename = 'data/places_result_20231017.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", " 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]['sub_unit'] = dict1[user]['sub_unit']\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", "print(len(re_ta))\n", "filename = 'data/result_天津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": "43bd1127-fa76-4c1e-8890-4bb47b28ecdf", "metadata": {}, "source": [ "## 导出测试人员信息" ] }, { "cell_type": "code", "execution_count": null, "id": "0a6ea33d-c112-4ed8-9366-3376e55a5731", "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", "\n", "filename = 'data/result_天津2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.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(5,'0'))\n", " list2.append(v['name']) \n", " list2.append(dict2[k]['sex'])\n", " list2.append(dict2[k]['unit'])\n", " list2.append(dict2[k]['sub_unit'])\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/天津石化体测情况（截至20231017）.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": "4a53db48-365e-4056-8468-bbc829e83682", "metadata": {}, "source": [ "## 统计各部门测试情况" ] }, { "cell_type": "code", "execution_count": null, "id": "589a5d44-605d-41a1-a981-7ec7258305ed", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/result_天津2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.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]['人数'] = dict3[unit]['人数'] - 1\n", "for k, v in dict3.items():\n", " list2 = [k,v['人数']]\n", " list1.append(list2)\n", "\n", "filename = 'data/天津部门未测试情况（截至20231013）.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": "d8e4038d-8ba0-48e7-b101-d30539cc2c2a", "metadata": {}, "source": [ "## 统计单一部门未体测人员明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "2f7c9847-f283-4a09-b385-2c7559be7c7e", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/result_天津2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "unit_name = '炼油部'\n", "rq = '20231008'\n", "list1 = []\n", "\n", "i = 1\n", "for k, v in dict2.items():\n", " unit = v['unit']\n", " if unit == unit_name and k not in dict1.keys():\n", " list2 = [i,k,v['name'],unit,v['sub_unit']]\n", " i+=1\n", " list1.append(list2)\n", "filename = f'data/天津石化{unit_name}未测试人员名单（截至{rq}）.xlsx'\n", "title = ['序号','员工编号','姓名','部门','车间（科室）']\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": "a0754a83-0b8e-4bd8-9deb-b7d70a850f43", "metadata": {}, "source": [ "## 统计所有部门未体测人员明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "e47c361d-a047-4932-b24e-fdcf65cb8a73", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/result_天津2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "unit = set()\n", "for k, v in dict1.items():\n", " unit.add(v['unit'])\n", "rq = '20231013'\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "for unit_name in unit:\n", " list1 = []\n", "\n", " i = 1\n", " for k, v in dict2.items():\n", " unit = v['unit']\n", " if unit == unit_name and k not in dict1.keys():\n", " list2 = [i,k,v['name'],unit,v['sub_unit']]\n", " i+=1\n", " list1.append(list2)\n", " filename = f'data/天津石化{unit_name}未测试人员名单（截至{rq}）.xlsx'\n", " title = ['序号','员工编号','姓名','部门','车间（科室）']\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)\n", " wb.close\n", " print(f'{unit_name}未测试人员名单（截至{rq}）生产成功！')\n", "\n", " " ] }, { "cell_type": "markdown", "id": "6246f8b0-d9fc-4c9a-8ffa-07bd8dcdc3ed", "metadata": {}, "source": [ "## 统计未体测人员明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "b7f62515-c45d-4d10-8e94-b5f9a9a98e3f", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/result_天津2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.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'],unit,v['sub_unit']]\n", " i+=1\n", " list1.append(list2)\n", "filename = f'data/天津石化未测试人员名单.xlsx'\n", "title = ['序号','员工编号','姓名','部门','车间（科室）']\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": "ed2a999f-47b9-4f36-88e2-354a0e37243b", "metadata": {}, "source": [ "## 转换报告格式" ] }, { "cell_type": "code", "execution_count": null, "id": "678ce52b-5368-4ec8-8b9e-0567895d856a", "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/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "\n", "filename = 'data/places_result_20231017.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", " 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_天津231017.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": "code", "execution_count": null, "id": "17a9248a-18b3-4696-a895-dde38f7f88a5", "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_天津231017.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", " 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_天津231017.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict2,fl , ensure_ascii=False) \n", "print('ok!') " ] }, { "cell_type": "markdown", "id": "c1c98895-27e7-41c8-a43b-a63ebfa1c5e2", "metadata": {}, "source": [ "## 生成报告" ] }, { "cell_type": "code", "execution_count": null, "id": "f6171872-6b48-480a-b2c7-cf368d6cc6d8", "metadata": { "tags": [] }, "outputs": [], "source": [ "import requests\n", "import json\n", "import openpyxl\n", "\n", "\n", "headers = {\n", " \"Content-Type\": \"application/json; charset=UTF-8\"\n", " }\n", "filename = 'data/result_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "fiie_path ='./134/'\n", "list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi']\n", "i=1\n", "list2 = []\n", "for k, v in dict1.items():\n", " list1 = []\n", " mydata = {}\n", " \n", " id = str(k).rjust(8,\"0\")\n", " mydata['path'] = fiie_path+id+'-'+ v['name']+'.pdf'\n", " mydata['title'] = '中石化(天津)石油化工\\n有限公司'\n", " mydata['subtitle'] = v['unit']\n", " mydata['id'] = id\n", " mydata['name'] = v['name']\n", " if v['sex'] == '男':\n", " mydata['gender'] = 'male'\n", " else:\n", " mydata['gender'] = 'female'\n", " \n", " mydata['month'] = v['month']\n", " mydata['fits'] = {}\n", " for item in list_item:\n", " if item in v.keys():\n", " if item in ['lung','pushup','step','situp']:\n", " mark = v[item]['成绩'].split()[0].split('.')[0]\n", " else:\n", " mark = v[item]['成绩'].split()[0]\n", " mydata['fits'][item] = {'mark':mark,'score':v[item]['score']}\n", " if len(mydata['fits']) >2:\n", " \n", " list1.append(mydata)\n", " list2.append([k,v['name']])\n", " i+=1\n", " x = requests.post('http://localhost:3003', data = json.dumps(list1), headers=headers)\n", " print(id,v['name'],x.text)\n", " #x.close()\n", "print(i)" ] }, { "cell_type": "markdown", "id": "489fdbe1-30ed-4630-b2fa-d926e41bdcc9", "metadata": {}, "source": [ "## 核对报告人数" ] }, { "cell_type": "code", "execution_count": null, "id": "906fa6c6-3446-4176-a443-fe16e52a8a3a", "metadata": { "tags": [] }, "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-old2/134'\n", "\n", "fls = glob.glob(f'{fi_path}/*.pdf')\n", "\n", "filename = 'data/result_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "for fn in fls:\n", " fi_name =Path(fn).stem.split('-')[0]\n", " code = int(fi_name)\n", " list1.append(str(code))\n", "for k, v in dict1.items():\n", " if k not in list1:\n", " print(k,v['name'])" ] }, { "cell_type": "markdown", "id": "cb587095-1a0c-4ab1-b9e5-e9e5b0d52cee", "metadata": {}, "source": [ "## 报告按部门分类" ] }, { "cell_type": "code", "execution_count": null, "id": "3fa6a1a9-63af-4f4e-9d30-b94f4357f7dc", "metadata": { "tags": [] }, "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/天津石化问卷'\n", "new_path = 'file/天津石化问卷1'\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'],dict1[str(code)]['sub_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": "code", "execution_count": null, "id": "3f75763f-79bd-4a8c-9612-2eba89ce32f1", "metadata": { "tags": [] }, "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_2'\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", " if dict1[str(code)]['sex'] =='男': \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": "fdcd8ea1-21ab-48ab-b7cc-0dad65b06bf2", "metadata": {}, "source": [ "## 生成体测报告打印明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "623671be-cef0-4a2c-bf1a-889ab159760f", "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 = '/home/songyi/pdf-typescript/134'\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", "list1 = []\n", "for fn in fls:\n", " list2 = []\n", " fi_name =Path(fn).stem.split('-')[0] \n", " code = int(fi_name)\n", " unit = dict1[str(code)]['unit']\n", " list2 = [fi_name,Path(fn).stem.split('-')[1],unit]\n", " \n", " list1.append(list2)\n", "print(list1)\n", "filename = 'data/天津石化体测报告打印明细表.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": "code", "execution_count": null, "id": "91fbc553-da7c-4c1e-bcf3-944dc59204b6", "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 = '/home/songyi/pdf-typescript/134'\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", "list1 = []\n", "for fn in fls:\n", " list2 = []\n", " fi_name =Path(fn).stem.split('-')[0] \n", " code = int(fi_name)\n", " if dict1[str(code)]['sex'] =='男':\n", " unit = dict1[str(code)]['unit']\n", " list2 = [fi_name,Path(fn).stem.split('-')[1],unit]\n", " \n", " list1.append(list2)\n", "print(list1)\n", "filename = 'data/天津石化体测报告打印明细表(第一批).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": "4a075c1b-41d9-4ff5-8f0a-115127e5e155", "metadata": {}, "source": [ "## 生成体测成绩明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "b363792b-cbc6-46a7-b87f-1e122bcb116e", "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_天津231017.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", " 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/天津石化体测情况表.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": "5608369a-f33f-4c02-a68f-f4f7bb410069", "metadata": {}, "source": [ "## 生成新格式文件" ] }, { "cell_type": "code", "execution_count": null, "id": "8397633f-fddb-4cfa-b9bd-e38f3fe6772c", "metadata": { "tags": [] }, "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/天津石化问卷'\n", "new_path = 'file/134_2'\n", "old = []\n", "filename = 'data/result_天津问卷2.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "fls = glob.glob(f'{fi_path}/*.pdf')\n", "i =0\n", "for fn in fls:\n", " code =str(int(Path(fn).stem.split('-')[0]))\n", " if code in dict1.keys():\n", " i+=1\n", " #print(i,code,dict1[code]['rq'].replace('-',''))\n", " \n", " n_name = Path(new_path,code.rjust(8,'0')+'_'+dict1[code]['rq'].replace('-','')+'.pdf')\n", " #print(i,n_name)\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "5facc164-841c-4866-8a2c-2d54f72d6a0b", "metadata": {}, "source": [ "## 导入网上问卷内容" ] }, { "cell_type": "code", "execution_count": null, "id": "35d1738a-1ec1-4764-bcbd-c1333fac6bfd", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "dict1 = {}\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict3 = json.load(fl)\n", "\n", "\n", "list1 = []\n", "filename = 'data/Survey_20231218.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", "\n", "\n", "\n", "\n", "for item in list1:\n", " psy = []\n", " tcm = []\n", " spine = []\n", " for i in range(0,45):\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(item)\n", " content = json.loads(item[5])\n", " if str(item[4]) not in dict1.keys():\n", " dict1[str(item[4])] = dict3[str(item[4])]\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", " psy[44] = []\n", " dict1[str(item[4])]['psy'] = psy\n", " if 'tcm' in item[5]:\n", " dict1[str(item[4])]['tcm'] = tcm\n", " if 'spine' in item[5]:\n", " dict1[str(item[4])]['spine'] = spine\n", " birth = date.fromisoformat(dict3[str(item[4])]['birth'].replace('/','-'))\n", "\n", " days = (rq-birth).days \n", " dict1[str(item[4])]['age'] = int(days/365)\n", " dict1[str(item[4])]['month'] = int(days/365*12)\n", " dict1[str(item[4])]['rq'] = item[6].replace('/','-').split(' ')[0]\n", "#print(dict1)\n", "filename = 'data/result_天津问卷2.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False) " ] }, { "cell_type": "code", "execution_count": null, "id": "d842c189-dcc2-4e31-9bc2-e272c929e6af", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "cc9e1717-f445-49a9-a770-c103da603434", "metadata": { "tags": [] }, "outputs": [], "source": [ "import requests\n", "import json\n", "\n", "\n", "\n", "headers = {\n", " \"Content-Type\": \"application/json; charset=UTF-8\"\n", " }\n", "filename = 'data/result_天津问卷1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "fiie_path ='./天津石化问卷/'\n", "list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi']\n", "i = 27\n", "list2 = []\n", "#list1 = []\n", "for k,v in dict1.items(): \n", " list1 = []\n", " mydata = {} \n", " id = k.rjust(8,\"0\")\n", " mydata['path'] = fiie_path+id+'-'+ v['name']+'.pdf'\n", " mydata['title'] = '中石化(天津)石油化工\\n有限公司'\n", " mydata['subtitle'] = v['unit']\n", " mydata['id'] = id\n", " mydata['name'] = v['name']\n", " if v['sex'] == '男':\n", " mydata['gender'] = 'male'\n", " else:\n", " mydata['gender'] = 'female' \n", " mydata['month'] = v['month']\n", " \n", " if 'tcm' in v.keys():\n", " mydata.setdefault('surveys',{})\n", " mydata['surveys']['tcm'] = v['tcm']\n", " if 'psy' in v.keys():\n", " mydata.setdefault('surveys',{})\n", " mydata['surveys']['psy'] = v['psy']\n", " if 'tcm' in v.keys():\n", " mydata.setdefault('surveys',{})\n", " mydata['surveys']['spine'] = v['spine']\n", " \n", " \n", " \n", " list1.append(mydata)\n", " #list2.append([k,dict1[k]['name']])\n", "\n", " x = requests.post('http://localhost:3003', data = json.dumps(list1), headers=headers)\n", " print(id,dict1[k]['name'],x.text)\n", " x.close()\n", " #print(mydata)\n", "#filename = 'data/data_天津问卷.json'\n", "\n", "#with open(filename,'w') as fl:\n", "# json.dump(list1, fl, ensure_ascii=False) " ] }, { "cell_type": "markdown", "id": "72a5c88e-d8b0-473c-b9d1-37c7acbdcf0f", "metadata": {}, "source": [ "## 核对网上问卷人员信息" ] }, { "cell_type": "code", "execution_count": null, "id": "ca0780fe-5d74-4d4e-ad1d-38813040c778", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "\n", "dict1 = {}\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict3 = json.load(fl)\n", "\n", "\n", "list1 = []\n", "filename = 'data/Survey_20231218.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", "list2 = []\n", "for item in list1:\n", " list3 = []\n", " name = item[3]\n", " code = item[4]\n", " if str(code) in dict3.keys() and name ==dict3[str(code)]['name']:\n", " list3 = [code,name,dict3[str(code)]['sex'],dict3[str(code)]['unit']] \n", " list2.append(list3)\n", "\n", "filename = 'data/天津石化问卷情况表（20231218）.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", "print('ok') " ] }, { "cell_type": "code", "execution_count": null, "id": "9b469138-1da9-43ca-98e8-8dc6cb3916ce", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "\n", "dict1 = {}\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict3 = json.load(fl)\n", "\n", "\n", "list1 = []\n", "filename = 'data/Survey_20231218.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", "list2 = []\n", "\n", "for item in list1:\n", " list3 = []\n", " name = item[3]\n", " code = item[4]\n", " if code in list2:\n", " print(code)\n", " else:\n", " list2.append(code)\n", " " ] }, { "cell_type": "markdown", "id": "08bcbf58-4356-4f30-850f-0d0ff0e2528b", "metadata": { "jp-MarkdownHeadingCollapsed": true }, "source": [ "# 第三次体测（2024年10月）" ] }, { "cell_type": "markdown", "id": "e439892b-fd46-4264-8f3c-202bc6388384", "metadata": {}, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": null, "id": "2fdbadd7-e9b1-45bf-ae95-52b4d65e03e8", "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/天津石化名单（2024年）.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, 4).value\n", " dict1['sex'] = sheet.cell(n, 6).value\n", " dict1['unit'] = sheet.cell(n, 2).value\n", " dict1['sub_unit'] = sheet.cell(n, 3).value\n", " dict1['birth'] = str(sheet.cell(n, 7).value).replace('/','-').split(' ')[0] \n", " dict1['id'] = sheet.cell(n,5).value\n", " person[code] = dict1\n", "filename = 'data/天津石化人员2024.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "df164df9-66b9-44bf-871b-d137f2322648", "metadata": {}, "source": [ "## 生成读卡系统文件" ] }, { "cell_type": "code", "execution_count": null, "id": "ddb84188-aafb-49b3-836d-79d9b13dfe35", "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/天津石化人员2024.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_天津石化人员2024.json\", \"w\",encoding = 'utf-8') as file:\n", " file.write(json_data) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "8222893c-b6e6-47bf-9daa-81b8b7a1952c", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "f922ad6a-e7ff-4ff9-923f-3e7aa8ea112b", "metadata": {}, "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/天津石化人员2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "\n", "filename = 'data/places_result_20241104.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", " 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]['sub_unit'] = dict1[user]['sub_unit']\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", "print(len(re_ta))\n", "filename = 'data/result_天津2024.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": "618e765d-c75d-4a46-9097-557e3c568123", "metadata": {}, "source": [ "## 导出测试人员信息" ] }, { "cell_type": "code", "execution_count": null, "id": "f59cf12c-d409-4de8-80f9-8264e4a2d221", "metadata": {}, "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", "\n", "filename = 'data/result_天津2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2024.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(5,'0'))\n", " list2.append(v['name']) \n", " list2.append(dict2[k]['sex'])\n", " list2.append(dict2[k]['unit'])\n", " list2.append(dict2[k]['sub_unit'])\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/天津石化体测情况（2024年）.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": "12837ccf-90a5-43cd-8201-2777aa6d3dd4", "metadata": {}, "source": [ "## 统计各部门测试情况" ] }, { "cell_type": "code", "execution_count": null, "id": "8301201e-43fc-4d24-94a0-9c554ca39dfb", "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/result_天津2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2024.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]['人数'] = dict3[unit]['人数'] - 1\n", "for k, v in dict3.items():\n", " list2 = [k,v['人数']]\n", " list1.append(list2)\n", "\n", "filename = 'data/天津部门未测试情况（截至20241031）.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": "code", "execution_count": null, "id": "efff43f0-a5f8-4de8-9f79-9564bf4fbb63", "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/result_天津2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2024.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", "\n", "for k, v in dict3.items():\n", " list2 = [k,v['人数']]\n", " list1.append(list2)\n", "\n", "filename = 'data/天津部门人员情况.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": "0e3c4368-a2d7-43c7-805a-7262cf43060c", "metadata": {}, "source": [ "## 部门、车间合并" ] }, { "cell_type": "code", "execution_count": null, "id": "e3eeb600-81a7-4220-bbfd-b0325f2ca06d", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/result_天津石化2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2024.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "\n", "dict3 = {}\n", "for k, v in dict1.items():\n", " unit = v['unit'].replace(' ','').replace('（','(').replace('）',')')\n", " sub_unit = dict2[k]['sub_unit'].replace(' ','').replace('（','(').replace('）',')')\n", " v['unit'] = unit\n", " v['sub_unit'] = sub_unit\n", "filename = 'data/result_天津2024（部门）.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False) \n", "print(len(dict1))" ] }, { "cell_type": "code", "execution_count": null, "id": "9554ebdf-6a19-4301-8c14-465d6ae4d870", "metadata": { "tags": [] }, "outputs": [], "source": [ "filename = 'data/result_天津2024（部门）.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "set1 = set()\n", "for k,v in dict1.items():\n", " unit = v['unit']+' '+v['sub_unit']\n", " set1.add(unit)\n", "for item in set1:\n", " print(item,len(item))" ] }, { "cell_type": "markdown", "id": "6d673f9e-e91b-40f6-bee6-c4bf59308302", "metadata": {}, "source": [ "## 体测报告按部门、车间分类" ] }, { "cell_type": "code", "execution_count": null, "id": "0f945c49-ac5e-4587-8d8c-96667c327248", "metadata": { "tags": [] }, "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/天津石化2024'\n", "new_path = 'file/天津石化2024'\n", "old = []\n", "dict2 = {}\n", "\n", "filename = 'data/天津石化人员2024.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'],dict1[str(code)]['sub_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)" ] }, { "cell_type": "code", "execution_count": null, "id": "5eaa34bb-c5a4-4bb4-8d7b-5116fb6bacc6", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 2, "id": "98d2da23-cfd4-461a-890a-4533f0409712", "metadata": { "execution": { "iopub.execute_input": "2024-11-12T03:00:45.476616Z", "iopub.status.busy": "2024-11-12T03:00:45.475867Z", "iopub.status.idle": "2024-11-12T03:00:48.668118Z", "shell.execute_reply": "2024-11-12T03:00:48.667607Z", "shell.execute_reply.started": "2024-11-12T03:00:45.476543Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ok\n" ] } ], "source": [ "import os,sys,shutil\n", "import json\n", "import glob\n", "from pathlib import Path\n", "\n", "fi_path = '/home/songyi/pdf-typescript/天津石化2024'\n", "new_path = 'file/天津石化2024_1'\n", "old = []\n", "filename = 'data/result_天津石化2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2024.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "\n", "fls = glob.glob(f'{fi_path}/*.pdf')\n", "\n", "for fn in fls:\n", " code =str(int(Path(fn).stem.split('-')[0]))\n", " if code in dict1.keys():\n", " \n", " n_name = Path(new_path,dict2[code]['id']+'_'+dict1[code]['rq'].replace('/','')+'.pdf')\n", " #print(i,n_name)\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "5cab4519-5ffa-4ac0-8db7-5674e181fc14", "metadata": {}, "source": [ "## 生成体测报告打印明细表" ] }, { "cell_type": "code", "execution_count": null, "id": "9dcbc866-2481-4cf6-a563-df4bb6596dfd", "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 = '/home/songyi/pdf-typescript/天津石化2024'\n", "\n", "filename = 'data/天津石化人员2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "fls = glob.glob(f'{fi_path}/*.pdf')\n", "list1 = []\n", "title = ['测试编号','姓名','性别','部门','车间']\n", "for fn in fls:\n", " list2 = []\n", " fi_name =Path(fn).stem.split('-')[0] \n", " code = int(fi_name)\n", " sex = dict1[str(code)]['sex']\n", " unit = dict1[str(code)]['unit']\n", " sub_unit = dict1[str(code)]['sub_unit']\n", " list2 = [fi_name,Path(fn).stem.split('-')[1],sex,unit,sub_unit]\n", " \n", " list1.append(list2)\n", "\n", "filename = 'data/天津石化体测报告明细表（2024年）.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": "0651c618-6504-44b2-83f6-40b2f2fe5cfc", "metadata": {}, "source": [ "## 生成体测成绩明细表" ] }, { "cell_type": "code", "execution_count": 1, "id": "e92d76a8-6841-4a1b-8529-caa5e37d624a", "metadata": { "execution": { "iopub.execute_input": "2024-11-22T02:08:10.643448Z", "iopub.status.busy": "2024-11-22T02:08:10.642748Z", "iopub.status.idle": "2024-11-22T02:08:12.178978Z", "shell.execute_reply": "2024-11-22T02:08:12.178427Z", "shell.execute_reply.started": "2024-11-22T02:08:10.643386Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ok\n" ] } ], "source": [ "import json\n", "import openpyxl\n", "\n", "items = ['lung','grip','flexion','jump','pushup','situp','balance','reaction','step']\n", "bmi = ['height','weight']\n", "title = ['测试编号','员工编号','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_天津石化2024.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/天津石化人员2024.json'\n", "with open(filename,'r') as fl:\n", " dict2 = 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(dict2[k]['id'])\n", " list2.append(dict1[k]['name']) \n", " list2.append(dict1[k]['sex'])\n", " list2.append(dict1[k]['unit'])\n", " list2.append(dict2[k]['sub_unit'])\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/天津石化体测情况表（2024年）.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": "dd32c384-262d-4137-bb44-2d3a590438f4", "metadata": {}, "source": [ "# 2025年体测" ] }, { "cell_type": "markdown", "id": "cd516502-5515-47f5-85a0-2312d78cdca7", "metadata": {}, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": 6, "id": "c101eccb-a2f3-4404-9583-682cec049160", "metadata": { "execution": { "iopub.execute_input": "2025-11-10T10:34:09.617871Z", "iopub.status.busy": "2025-11-10T10:34:09.617343Z", "iopub.status.idle": "2025-11-10T10:34:10.297071Z", "shell.execute_reply": "2025-11-10T10:34:10.296491Z", "shell.execute_reply.started": "2025-11-10T10:34:09.617822Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "5053 ok\n" ] } ], "source": [ "import openpyxl\n", "import json\n", "from datetime import date\n", "\n", "wb = openpyxl.load_workbook('data/天津石化人员2025.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "person = {}\n", "\n", "for n in range(2, sheet.max_row+1):\n", " code = str(sheet.cell(n, 1).value)\n", " person.setdefault(code, {})\n", " dict1 = {}\n", " dict1['name'] = sheet.cell(n, 4).value\n", " dict1['sex'] = sheet.cell(n, 5).value\n", " dict1['birth'] = str(sheet.cell(n, 6).value).replace('/','-').split(' ')[0] \n", " dict1['unit'] = sheet.cell(n, 2).value\n", " dict1['sub_unit'] = sheet.cell(n, 3).value\n", " person[code] = dict1\n", "filename = 'data/天津石化人员2025.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print(len(person),'ok')" ] }, { "cell_type": "markdown", "id": "3319058d-0a39-46f7-b493-260e1b529786", "metadata": {}, "source": [ "## 生成读卡系统文件" ] }, { "cell_type": "code", "execution_count": 7, "id": "85bae94e-f480-4c0b-a120-e516e6a5c14d", "metadata": { "execution": { "iopub.execute_input": "2025-11-10T10:34:12.756830Z", "iopub.status.busy": "2025-11-10T10:34:12.756579Z", "iopub.status.idle": "2025-11-10T10:34:12.798482Z", "shell.execute_reply": "2025-11-10T10:34:12.797837Z", "shell.execute_reply.started": "2025-11-10T10:34:12.756807Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "5053 ok\n" ] } ], "source": [ "import json\n", "\n", "filename = 'data/天津石化人员2025.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']+'-'+v['sub_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/card_天津石化2025.json\", \"w\",encoding = 'utf-8') as file:\n", " file.write(json_data) \n", "print(len(list1),'ok')" ] }, { "cell_type": "markdown", "id": "fd5cb794-6197-4204-a421-fd7a14aeab20", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": 2, "id": "52de3ba0-f430-444b-87e9-1f13c3e2dcc2", "metadata": { "execution": { "iopub.execute_input": "2025-11-17T13:15:52.024202Z", "iopub.status.busy": "2025-11-17T13:15:52.023733Z", "iopub.status.idle": "2025-11-17T13:15:52.062303Z", "shell.execute_reply": "2025-11-17T13:15:52.061818Z", "shell.execute_reply.started": "2025-11-17T13:15:52.024158Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "253\n" ] } ], "source": [ "import json\n", "import datetime\n", "import csv\n", "from datetime import date\n", "import my_module1 as My\n", "\n", "filename = 'data/天津石化人员2025.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "filename = 'data/marks_20251117-2.csv'\n", "re_ta = My.get_result(filename,dict1)\n", "\n", "\n", "filename = 'data/result_天津石化2025.json'\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": "f58f041b-a3cb-475c-8ac2-a8a747c96386", "metadata": {}, "source": [ "## 统计未体测人员明细表" ] }, { "cell_type": "code", "execution_count": 4, "id": "04990b9f-a8f9-4442-935e-d223fde24e72", "metadata": { "execution": { "iopub.execute_input": "2025-11-17T13:21:58.571623Z", "iopub.status.busy": "2025-11-17T13:21:58.570712Z", "iopub.status.idle": "2025-11-17T13:21:58.620055Z", "shell.execute_reply": "2025-11-17T13:21:58.619536Z", "shell.execute_reply.started": "2025-11-17T13:21:58.571556Z" } }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "filename = 'data/result_天津石化2025.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员2025.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 dict1.items(): \n", " list2 = [i,k,v['name'],v['unit']]\n", " i+=1\n", " list1.append(list2)\n", "#print(list1)\n", "filename = f'data/天津石化体测人员名单（截至20251117）.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": "85a03b00-9624-4ae9-aa6d-386798d457df", "metadata": { "execution": { "iopub.execute_input": "2023-10-25T02:50:56.997544Z", "iopub.status.busy": "2023-10-25T02:50:56.995911Z", "iopub.status.idle": "2023-10-25T02:50:57.006678Z", "shell.execute_reply": "2023-10-25T02:50:57.004773Z", "shell.execute_reply.started": "2023-10-25T02:50:56.997463Z" }, "jp-MarkdownHeadingCollapsed": true, "tags": [] }, "source": [ "# 体测数据分析" ] }, { "cell_type": "markdown", "id": "dca06570-73e6-4f60-8cf9-b3f9da64f1c4", "metadata": {}, "source": [ "## 清理报告数据" ] }, { "cell_type": "code", "execution_count": null, "id": "f9fee64f-41ff-4453-8a32-a33df086022e", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "\n", "filename = 'data/result_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\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", "items = {}\n", "items['lung'] = '肺活量'\n", "items['grip'] ='握力'\n", "items['flexion'] ='坐位体前屈'\n", "items['jump'] ='纵跳'\n", "items['pushup'] ='俯卧撑'\n", "items['balance'] ='单脚站立'\n", "items['reaction'] ='选择反应时'\n", "items['step'] ='台阶指数'\n", "items['situp'] ='一分钟仰卧起坐'\n", "items['bmi'] ='BMI'\n", "\n", "\n", "list1 = []\n", "fiie_path ='./134/'\n", "list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi']\n", "i=1\n", "list2 = []\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " list1 = []\n", " mydata = {}\n", " \n", " id = str(k).rjust(8,\"0\")\n", " mydata['unit'] = v['unit']\n", " mydata['name'] = v['name']\n", " mydata['sex'] = v['sex']\n", " mydata['month'] = v['month']\n", " age = int(v['month']/12)\n", " if age <20:\n", " mydata['age'] = 20\n", " else:\n", " mydata['age'] = int(v['month']/12)\n", " \n", " mydata['fits'] = {}\n", " score = 0\n", " for item in list_item:\n", " if item in v.keys():\n", " if item in ['lung','pushup','step','situp']:\n", " mark = v[item]['成绩'].split()[0].split('.')[0]\n", " else:\n", " mark = v[item]['成绩'].split()[0]\n", " mydata['fits'][items[item]] = {'mark':mark,'score':v[item]['score']}\n", " score = score + v[item]['score']\n", " mydata['score'] = round(score/len(mydata['fits']),2)\n", " if len(mydata['fits']) >2:\n", " dict2[str(k)] = mydata\n", "filename = f'data/data_天津231017.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict2,fl , ensure_ascii=False) \n", "print('ok!') " ] }, { "cell_type": "markdown", "id": "bd1f8f42-c14a-4bb7-8656-14a0f7968cfc", "metadata": {}, "source": [ "## 计算测试等级" ] }, { "cell_type": "code", "execution_count": null, "id": "006afc6c-2b1f-4edf-be1b-5f60e2029ee8", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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/data_天津231017_非倒班.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "dict2 = {}\n", "dict2['不合格'] = [0,255]\n", "dict2['合格'] = [256,332]\n", "dict2['良好'] = [333,367]\n", "dict2['优秀'] = [368,500]\n", "\n", "for k1, v1 in dict2.items():\n", " di = v1[0]\n", " gao = v1[1]\n", " i = 0 \n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if int(v['score']*100) in range(di,gao+1):\n", " dict1[k]['level'] = k1\n", " i+=1\n", " if v['sex'] == '男':\n", " m = m +1\n", " else:\n", " f = f+1\n", " print(f'{di}~{gao}分人数：{i}人,男性：{m}人,女性:{f}人')\n", "print(len(dict1))" ] }, { "cell_type": "markdown", "id": "ed3c0653-087a-4a9d-ba21-8cf5f48515d9", "metadata": {}, "source": [ "## 根据年龄汇总人员信息及成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "949e4c3c-023d-44a4-b99e-c5460da61161", "metadata": { "tags": [] }, "outputs": [], "source": [ "nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,69]]\n", "\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "for item in nld:\n", " di = item[0]\n", " gao = item[1]\n", " i = 1\n", " score = 0\n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if v['age'] in range(di,gao+1):\n", " score = score+v['score']\n", " i+=1\n", " if v['sex'] == '男':\n", " m = m +1\n", " \n", " print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人,男性：{m}人')" ] }, { "cell_type": "markdown", "id": "6a967a44-7c12-4e82-827b-d75926c09e77", "metadata": {}, "source": [ "### 根据年龄汇总人员信息及成绩（男）" ] }, { "cell_type": "code", "execution_count": null, "id": "721977d3-5816-4bf6-82fc-26fd170e5454", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]\n", "\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "for item in nld:\n", " di = item[0]\n", " gao = item[1]\n", " i = 1\n", " score = 0\n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if v['age'] in range(di,gao+1) and v['sex'] == '男':\n", " score = score+v['score']\n", " i+=1\n", " \n", " \n", " print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人')" ] }, { "cell_type": "markdown", "id": "3a8f747e-aacd-45bf-b94a-b505cfd31922", "metadata": {}, "source": [ "### 根据年龄汇总人员信息及成绩（女）" ] }, { "cell_type": "code", "execution_count": null, "id": "f493dc0a-d3cd-4dbd-ad35-e06eb96afbc5", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]\n", "\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "for item in nld:\n", " di = item[0]\n", " gao = item[1]\n", " i = 1\n", " score = 0\n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if v['age'] in range(di,gao+1) and v['sex'] == '女':\n", " score = score+v['score']\n", " i+=1\n", " \n", " \n", " print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人')" ] }, { "cell_type": "markdown", "id": "e9c6bd2e-b6ac-4a6f-ba28-aafcabb40c0d", "metadata": {}, "source": [ "## 计算平均成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "7155f2c2-0719-4558-aa3b-629fb70194d6", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]\n", "#filename = 'data/result_石家庄.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "i = 1\n", "m = 0\n", "f = 0\n", "score = 0\n", "t_score = 0\n", "for k,v in dict1.items():\n", " if v['sex'] == '男':\n", " m = m +1\n", " score = score+v['score']\n", "print(f'平均成绩：{round(score/m,4)}分，男性：{m}人')\n", "t_score = t_score + score\n", "score = 0\n", "for k,v in dict1.items():\n", " if v['sex'] == '女':\n", " f = f +1\n", " score = score+v['score']\n", "print(f'平均成绩：{round(score/f,4)}分，女性：{f}人')\n", "t_score = t_score + score\n", "print(f'平均成绩：{round(t_score/3657,4)}分，总体：3657人')" ] }, { "cell_type": "markdown", "id": "9a544eec-ec58-47dc-aa36-d890b0b309c2", "metadata": {}, "source": [ "## 计算测试等级" ] }, { "cell_type": "code", "execution_count": null, "id": "a0bbb339-ee4e-4dc1-83ec-b2055e3c670e", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "dict2 = {}\n", "dict2['不合格'] = [0,255]\n", "dict2['合格'] = [256,332]\n", "dict2['良好'] = [333,367]\n", "dict2['优秀'] = [368,500]\n", "\n", "for k1, v1 in dict2.items():\n", " di = v1[0]\n", " gao = v1[1]\n", " i = 0 \n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if int(v['score']*100) in range(di,gao+1):\n", " dict1[k]['level'] = k1\n", " i+=1\n", " if v['sex'] == '男':\n", " m = m +1\n", " else:\n", " f = f+1\n", " print(f'{di}~{gao}分人数：{i}人,男性：{m}人,女性:{f}人')\n", "#filename = 'data/result_石家庄.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "92103efb-a3e4-43ec-acfb-e4cb0b07c2fb", "metadata": {}, "source": [ "### 计算各年龄段测试等级(女）" ] }, { "cell_type": "code", "execution_count": null, "id": "f8949993-7501-4359-aa7c-2cd5de348056", "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "dict2 = {}\n", "dict2['不合格'] = [0,255]\n", "dict2['合格'] = [256,332]\n", "dict2['良好'] = [333,367]\n", "dict2['优秀'] = [368,500]\n", "\n", "for k1, v1 in dict2.items():\n", " di = v1[0]\n", " gao = v1[1]\n", " i = 0 \n", " m = 0\n", " f = 0\n", " for k,v in dict1.items():\n", " if int(v['score']*100) in range(di,gao+1):\n", " dict1[k]['level'] = k1\n", " i+=1\n", " if v['sex'] == '女':\n", " m = m +1\n", " else:\n", " f = f+1\n", " print(f'{di}~{gao}分人数：{i}人,男性：{m}人,女性:{f}人')\n", "#filename = 'data/result_石家庄.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "194217e0-f1cf-4945-ad5a-52304ed2f943", "metadata": {}, "source": [ "## 计算各项目成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "5ed284c6-1a1c-43ab-92a8-b3c411cd77a1", "metadata": { "tags": [] }, "outputs": [], "source": [ "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "items = ['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", "for item in items:\n", " score = 0\n", " n = 0\n", " for k, v in dict1.items(): \n", " if item in v['fits'].keys():\n", " n = n + 1\n", " score =score + int(v['fits'][item]['score'])\n", " print(item,round(score/n,2),n)" ] }, { "cell_type": "markdown", "id": "5a130857-4dd1-4b5e-b21b-42fe32b367cf", "metadata": {}, "source": [ "## 按部门统计" ] }, { "cell_type": "markdown", "id": "cb1e13ae-3eba-4f6e-b70a-2bf87168ef1a", "metadata": {}, "source": [ "### 计算部门完成情况" ] }, { "cell_type": "code", "execution_count": null, "id": "5e7c1c49-75bf-4238-9bd7-b8511687f639", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "\n", "filename = 'data/data_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "dict3 = {}\n", "\n", "for k, v in dict2.items():\n", " unit = v['unit']\n", " dict3.setdefault(unit,{})\n", " dict3[unit].setdefault('应测',0)\n", " dict3[unit].setdefault('已测',0)\n", " dict3[unit]['应测']+=1\n", "for k, v in dict1.items():\n", " unit = v['unit']\n", " \n", " dict3[unit]['已测']+=1\n", " \n", "print(dict3)\n", "for k ,v in dict3.items():\n", " print(k,v['应测'],v['已测'])\n", " " ] }, { "cell_type": "markdown", "id": "e83941b9-b2b5-41db-b08a-a619f07c2487", "metadata": { "execution": { "iopub.execute_input": "2023-11-08T13:52:50.838712Z", "iopub.status.busy": "2023-11-08T13:52:50.838249Z", "iopub.status.idle": "2023-11-08T13:52:50.844168Z", "shell.execute_reply": "2023-11-08T13:52:50.843014Z", "shell.execute_reply.started": "2023-11-08T13:52:50.838676Z" }, "tags": [] }, "source": [ "### 计算部门合格率" ] }, { "cell_type": "code", "execution_count": null, "id": "d023724c-46b7-4b4e-bbcc-8b4f171590c5", "metadata": { "tags": [] }, "outputs": [], "source": [ "for k, v in dict1.items():\n", " unit = v['unit']\n", " dict3[unit].setdefault(v['level'],0)\n", " dict3[unit][v['level']]+=1\n", "print(dict3)\n", "for k ,v in dict3.items():\n", " print(k,v['已测'],v['不合格'])" ] }, { "cell_type": "markdown", "id": "4b996a8a-70e7-4c95-8b14-0f8fa89df7a4", "metadata": {}, "source": [ "### 计算部门成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "1d93d58e-115a-44a4-988f-fa5353c5fd0e", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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", "filename = 'data/data_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单2023.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "dict3 = {}\n", "\n", "for k, v in dict1.items():\n", " unit = v['unit']\n", " dict3.setdefault(unit,{})\n", " for item in items:\n", " dict3[unit].setdefault(item,{})\n", " dict3[unit][item].setdefault('score',0)\n", " dict3[unit][item].setdefault('count',0)\n", " for k1,v1 in v['fits'].items():\n", " if k1 in items:\n", " dict3[unit][k1]['score']+=v1['score']\n", " dict3[unit][k1]['count']+=1\n", "print(dict3)" ] }, { "cell_type": "markdown", "id": "23a654a2-69f1-41cb-b3dc-23bc7dc7e294", "metadata": {}, "source": [ "### 显示部门成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "0cb7ff83-69a9-4c03-a539-bde7ffd4a8a8", "metadata": { "tags": [] }, "outputs": [], "source": [ "\n", "for k ,v in dict3.items():\n", " print(k)\n", " for k1,v1 in v.items():\n", " if v1['count']>0:\n", " print(k1,round(v1['score']/v1['count'],4))\n", " print()" ] }, { "cell_type": "markdown", "id": "d3d9d517-61e5-4c4c-bddb-1f386a518d99", "metadata": {}, "source": [ "## 倒班人员数据分析" ] }, { "cell_type": "markdown", "id": "6b0b8d09-ce15-4a36-9421-251ab50ae706", "metadata": {}, "source": [ "### 倒班员工数据导入" ] }, { "cell_type": "code", "execution_count": null, "id": "518a1e40-d383-4d78-a4ea-224ddab49b79", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "\n", "filename = 'data/data_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", " \n", "wb = openpyxl.load_workbook('data/员工个人基础信息-倒班.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "dict2 = {}\n", "i = 1\n", "for n in range(4, sheet.max_row+1):\n", " if sheet.cell(n, 1).value is not None:\n", " code = int(sheet.cell(n, 1).value)\n", " daoban = sheet.cell(n, 6).value\n", " if str(code) in dict1.keys() and daoban == '倒班':\n", " dict2[str(code)] = dict1[str(code)]\n", "print(len(dict2))\n", "filename = 'data/data_天津231017_倒班.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict2, fl) \n", "dict3 = {}\n", "for k, v in dict1.items():\n", " if k not in dict2.keys():\n", " dict3[k] = dict1[k]\n", "print(len(dict3))\n", " \n", "filename = 'data/data_天津231017_非倒班.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict3, fl) \n" ] }, { "cell_type": "markdown", "id": "cf45ba36-896d-4d28-ae4a-08c512ff1ddb", "metadata": {}, "source": [ "### 核对倒班员工信息" ] }, { "cell_type": "code", "execution_count": null, "id": "08167b05-8719-41c9-a71d-57906a55eb63", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/data_天津231017_非倒班.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", " \n", "wb = openpyxl.load_workbook('data/员工个人基础信息-倒班.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "dict2 = {}\n", "i = 0\n", "for n in range(4, sheet.max_row+1):\n", " if sheet.cell(n, 1).value is not None:\n", " code = int(sheet.cell(n, 1).value)\n", " daoban = sheet.cell(n, 6).value\n", " if str(code) in dict1.keys():# and daoban != '倒班':\n", " dict2[str(code)] = dict1[str(code)]\n", "for k,v in dict1.items():\n", " if str(k) not in dict2.keys():\n", " i+=1\n", " print(i,k,v['name'])" ] }, { "cell_type": "markdown", "id": "dc51915d-7593-411c-8730-4ee9445ebd51", "metadata": {}, "source": [ "### 对比倒班及非倒班人员得分" ] }, { "cell_type": "code", "execution_count": null, "id": "096bb641-c000-490b-bd77-296fb0395dc8", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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/data_天津231017_非倒班.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "dict3 = {}\n", "for k, v in dict1.items():\n", " unit = v['unit']\n", " dict3.setdefault(unit,{})\n", " dict3[unit].setdefault('非倒班',[0,0,0])\n", " dict3[unit].setdefault('倒班',[0,0,0])\n", " for k1,v1 in v['fits'].items():\n", " if k1 in items:\n", " dict3[unit]['非倒班'][0] = dict3[unit]['非倒班'][0]+ v1['score']\n", " dict3[unit]['非倒班'][2]+=1\n", " dict3[unit]['非倒班'][1] +=1\n", "filename = 'data/data_天津231017_倒班.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k, v in dict1.items():\n", " unit = v['unit']\n", " dict3.setdefault(unit,{})\n", " dict3[unit].setdefault('非倒班',[0,0])\n", " dict3[unit].setdefault('倒班',[0,0])\n", " for k1,v1 in v['fits'].items():\n", " if k1 in items:\n", " dict3[unit]['倒班'][0] = dict3[unit]['倒班'][0]+ v1['score']\n", " dict3[unit]['倒班'][2] +=1\n", " dict3[unit]['倒班'][1] +=1\n", "\n", "for k ,v in dict3.items():\n", " print(k,v)" ] }, { "cell_type": "markdown", "id": "ce2c7879-308c-45aa-aaeb-2323b3a060be", "metadata": {}, "source": [ "### 划分年龄段" ] }, { "cell_type": "code", "execution_count": null, "id": "c1b68d99-e8c1-455a-973f-20f4c1fd58a2", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "\n", "filename = 'data/data_天津231017.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "nld ={'20':[20,29],'30':[30,39],'40':[40,49],'50':[50,69]}\n", "for k,v in nld.items():\n", " age_min = v[0]\n", " age_max = v[1]\n", " for k1,v1 in dict1.items():\n", " if v1['age'] >=v[0] and v1['age']<=v[1]:\n", " dict1[k1]['nld'] = k\n", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl) \n", " " ] }, { "cell_type": "markdown", "id": "eb35716c-cd5a-476b-95d0-b326bfa04963", "metadata": {}, "source": [ "### 上肢、下肢力量分析（男）" ] }, { "cell_type": "code", "execution_count": null, "id": "6a8cfab1-c99b-4376-9ad2-4ae096dd4866", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "list1 = ['20','30','40','50']\n", "shangzhi = ['握力','俯卧撑']\n", "xiazhi = ['纵跳','闭眼单脚站立']\n", "zongrenshu = 0\n", "ruo = 0\n", "for item in list1:\n", " print(item)\n", " renshu = 0\n", " ruo = 0\n", " \n", " for k, v in dict1.items():\n", " if v['nld'] == item and v['sex']=='男':\n", " renshu+=1\n", " n =0\n", " defen = 0\n", " for k1, v1 in v['fits'].items():\n", " if k1 in xiazhi:\n", " n+=1\n", " defen =defen+v1['score']\n", " if n>0 and (defen/n)<3:\n", " ruo+=1\n", " print(renshu,ruo)\n", " \n", " \n", " \n", " \n", " \n", " " ] }, { "cell_type": "markdown", "id": "6f83db87-9844-41dc-bf43-789c3367f411", "metadata": {}, "source": [ "### 上肢、下肢力量分析（女）" ] }, { "cell_type": "code", "execution_count": null, "id": "2cb586f9-cdf1-4b51-8900-50416b5f0ae5", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "list1 = ['20','30','40','50']\n", "shangzhi = ['握力']\n", "xiazhi = ['纵跳','闭眼单脚站立']\n", "zongrenshu = 0\n", "ruo = 0\n", "for item in list1:\n", " print(item)\n", " renshu = 0\n", " ruo = 0\n", " \n", " for k, v in dict1.items():\n", " if v['nld'] == item and v['sex']=='女':\n", " renshu+=1\n", " n =0\n", " defen = 0\n", " for k1, v1 in v['fits'].items():\n", " if k1 in xiazhi:\n", " n+=1\n", " defen =defen+v1['score']\n", " if n>0 and (defen/n)<3:\n", " ruo+=1\n", " print(renshu,ruo)\n", " " ] }, { "cell_type": "code", "execution_count": null, "id": "dd822864-0226-40c1-b385-cd146f6972c9", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k ,v in dict1.items():\n", " if v['sex'] == '男' and '握力' in v['fits'].keys():\n", " print(v['name'],v['nld'],v['fits']['握力']['mark'],v['fits']['握力']['score'])\n", " " ] }, { "cell_type": "markdown", "id": "1015b957-448a-4029-827f-3abc3c0e9173", "metadata": {}, "source": [ "### 弱项分析（男）" ] }, { "cell_type": "code", "execution_count": null, "id": "d3ea1ddb-db7a-4b4f-a23c-6951e88df2ff", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "list1 = ['20','30','40','50']\n", "\n", "for nld in list1:\n", " \n", " print(nld)\n", " for item in items:\n", " n =0\n", " defen = 0\n", " for k, v in dict1.items():\n", " \n", " if v['nld'] == nld and v['sex']=='男' and item in v['fits'].keys():\n", " n+=1\n", " defen =defen+ v['fits'][item]['score']\n", " if n>0:\n", " print(item,round(defen/n,2)) " ] }, { "cell_type": "markdown", "id": "727fda65-7268-44f5-b953-285c86602254", "metadata": {}, "source": [ "### 弱项分析（女）" ] }, { "cell_type": "code", "execution_count": null, "id": "723b50a1-60f1-4001-8b30-6f77c6a4b460", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "items = ['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", "\n", "filename = 'data/data_天津_nld.json' \n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "list1 = ['20','30','40','50']\n", "\n", "for nld in list1:\n", " \n", " print(nld)\n", " for item in items:\n", " n =0\n", " defen = 0\n", " for k, v in dict1.items():\n", " \n", " if v['nld'] == nld and v['sex']=='女' and item in v['fits'].keys():\n", " n+=1\n", " defen =defen+ v['fits'][item]['score']\n", " if n>0:\n", " print(item,round(defen/n,2))" ] }, { "cell_type": "code", "execution_count": null, "id": "62278ae0-be57-4f7c-85d6-cfb9cf61e341", "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": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 5 }