{ "cells": [ { "cell_type": "markdown", "id": "04524c85-988e-4dbf-86eb-939a9db7aa28", "metadata": {}, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": null, "id": "bbba6efc-73cd-4db6-bae7-014724fee731", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/南化人员信息表.xlsx',data_only=True)\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, 4).value)\n", " person.setdefault(code, {})\n", " dict1 = {}\n", " dict1['name'] = sheet.cell(n, 3).value\n", " dict1['sex'] = sheet.cell(n, 5).value\n", " dict1['unit'] = sheet.cell(n, 2).value \n", " dict1['birth'] = str(sheet.cell(n, 6).value).replace('/','-').split(' ')[0]\n", " dict1['phone'] = sheet.cell(n, 12).value \n", " person[code] = dict1\n", "filename = 'data/南京化工人员.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": "048a95aa-1691-45f6-b933-6eaf95ae1d30", "metadata": {}, "source": [ "## 生成读卡系统文件" ] }, { "cell_type": "code", "execution_count": null, "id": "ce406710-6b7d-4c51-98ec-78883bd3ce5f", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "\n", "filename = 'data/南京化工人员.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_南京化工人员.json\", \"w\",encoding = 'utf-8') as file:\n", " file.write(json_data) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "6bcd45c2-10af-4d5f-9e0b-5cd1df4f7a7f", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "970e171e-1360-448f-a28c-520ccb8f314a", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import datetime\n", "import csv\n", "from datetime import date\n", "import my_module as My\n", "\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "filename = 'data/marks_20250703.csv'\n", "re_ta = My.get_result(filename,dict1)\n", "\n", "\n", "filename = 'data/result_南京化工.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": "6d381859-6d21-45d2-8313-55ebbabf8bd4", "metadata": {}, "source": [ "## 生成测试得分" ] }, { "cell_type": "code", "execution_count": null, "id": "0905ad6a-f7e4-43ed-ae29-c4850deb946b", "metadata": {}, "outputs": [], "source": [ "import json\n", "import time\n", "import my_module as My\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_南京化工.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 'bmi' in v.keys():\n", " #bmi_data = v['height']['成绩'].split()[0]+','+ v['weight']['成绩'].split()[0]\n", " bmi_data = v['bmi']['成绩']\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'] = My.cal_bmi(data1)\n", " for item_en in list_item:\n", " if item_en in v.keys(): \n", " data1 = {'code':k,'sex':sex,'age':v['age'],'item':item_en,'result':float(v[item_en]['成绩'].split()[0])}\n", " #print(k,v['name'])\n", " dict2[k][item_en]['score'] = My.cal_score(data1)\n", " #print(k,v[item_en]['成绩'],cal_score(data1))\n", "\n", "filename = f'data/result_南京化工.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict2,fl , ensure_ascii=False) \n", "print('ok!') " ] }, { "cell_type": "markdown", "id": "d034a61d-1fbd-417b-99bd-277e43ebb678", "metadata": {}, "source": [ "## 导出测试人员信息" ] }, { "cell_type": "code", "execution_count": null, "id": "867ad6b0-9e9d-48bc-a10a-3b9cb6125890", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "items = ['lung','grip','flexion','jump','pushup','situp','balance','reaction','step']\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_南京化工.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/南京化工人员.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", " if 'bmi' in v.keys():\n", " height = v['bmi']['成绩'].split(',')[0]\n", " weight = v['bmi']['成绩'].split(',')[1]\n", " list2.append(height)\n", " list2.append(weight)\n", " else:\n", " list2.append('')\n", " list2.append('')\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", " \n", " list1.append(list2)\n", "filename = 'data/南京化工测试情况明细表（截至20250630）.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": "699c6a40-a6ae-4300-9646-708cb85aa5e8", "metadata": {}, "source": [ "## 统计问卷人员情况" ] }, { "cell_type": "code", "execution_count": null, "id": "def3f47a-24ef-4815-b63b-2a16b79b4c15", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "phone1 = set()\n", "phone2 = set()\n", "for k,v in dict1.items():\n", " phone1.add(v['phone'])\n", "list1 = []\n", "filename = 'data/survey_records_20250813.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " list1.append(line)\n", "\n", "i =1\n", "list2 = []\n", "for item in list1:\n", " content = json.loads(item[4])\n", " code = int(content['phone'])\n", " for k, v in dict1.items():\n", " list3 = []\n", " if v['phone'] == code: \n", " list3.append(k)\n", " list3.append(v['name'])\n", " list3.append(v['sex'])\n", " list3.append(v['unit'])\n", " list3.append(code)\n", " list2.append(list3)\n", "filename = 'data/南化问卷情况表（第二批）.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) " ] }, { "cell_type": "code", "execution_count": null, "id": "8b7c0528-17b6-4469-b15f-3c4b794e286e", "metadata": {}, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "\n", "\n", "filename = 'data/survey_records_20250813.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " list1.append(line)\n", "\n", "i =1\n", "list2 = []\n", "for item in list1:\n", " list3 = []\n", " content = json.loads(item[4])\n", " phone = int(content['phone'])\n", " name = content['name']\n", " sex = content['gender']\n", " list3.append(name)\n", " list3.append(sex)\n", " list3.append(phone)\n", " list2.append(list3)\n", "filename = 'data/南化问卷情况表（第二批）.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) " ] }, { "cell_type": "markdown", "id": "797717d5-47b9-4d47-be6c-8d54bede67d4", "metadata": {}, "source": [ "## 导入问卷信息" ] }, { "cell_type": "code", "execution_count": null, "id": "9d9dd574-9fbf-4d0a-96fd-9b55d98021d2", "metadata": {}, "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/result_南京化工.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict3 = json.load(fl)\n", "\n", "phone = {}\n", "for k,v in dict3.items():\n", " if 'phone' in v.keys():\n", " phone[v['phone']] = k\n", "\n", "list1 = []\n", "filename = 'data/survey_records_20250812.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " list1.append(line)\n", "\n", "\n", "\n", "nn = 0\n", "for item in list1:\n", " if int(item[3]) in phone.keys(): \n", " tcm = []\n", " code = phone[int(item[3])]\n", " \n", " for i in range(0,60):\n", " tcm.append(0)\n", " \n", " \n", " content = json.loads(item[4])\n", " if code not in dict1.keys():\n", " dict1[code] = dict3[code]\n", " rq = date.fromisoformat(item[5].replace('/','-').split(' ')[0])\n", " dict1[code]['rq'] = str(date.fromisoformat(item[5].replace('/','-').split(' ')[0]))\n", " #dict1[code]['rq'] = item[5].replace('/','-').split(' ')[0]\n", " else:\n", " rq=date.fromisoformat('2025-07-01')\n", " dict1[code]['rq'] = '2025-07-01'\n", " for k, v in content.items():\n", " \n", " if 'tcm' in k:\n", " i = int(k[3:])\n", " tcm[i-1] = int(v) \n", " \n", " if 'tcm' in item[4]: \n", " dict1[code]['tcm'] = tcm\n", " \n", " birth = date.fromisoformat(dict3[code]['birth'].replace('/','-'))\n", " \n", " days = (rq-birth).days \n", " dict1[code]['age'] = int(days/365)\n", " dict1[code]['month'] = int(days/365*12)\n", " #print(phone[item[2]])\n", " nn+=1\n", "filename = 'data/result_南京化工-2.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False)\n" ] }, { "cell_type": "markdown", "id": "4930b4cb-2114-4432-a8ae-e6d2cde69b5c", "metadata": {}, "source": [ "## 导入问卷信息(新)" ] }, { "cell_type": "code", "execution_count": null, "id": "9b801085-ca98-4958-8dcc-bcd9985fcd4b", "metadata": {}, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict3 = json.load(fl)\n", "\n", "\n", "list1 = []\n", "filename = 'data/survey_records_20250901.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " list1.append(line)\n", "\n", "\n", "dict1 = {}\n", "nn = 0\n", "for item in list1: \n", " tcm = [] \n", " for i in range(0,60):\n", " tcm.append(0)\n", " \n", " content = json.loads(item[4]) \n", " phone = content['phone']\n", " name = content['name']\n", " for k,v in dict3.items():\n", " if name == v['name']:\n", " code = k\n", " unit = v['unit']\n", " sex = v['sex']\n", " dict1.setdefault(code,{})\n", " \n", " #rq = date.fromisoformat(item[5].replace('/','-').split(' ')[0])\n", " #dict1[phone]['rq'] = str(date.fromisoformat(item[5].replace('/','-').split(' ')[0]))\n", " \n", " for k, v in content.items(): \n", " if 'tcm' in k:\n", " i = int(k[3:])\n", " tcm[i-1] = int(v) \n", " \n", " if 'tcm' in item[4]: \n", " dict1[code]['tcm'] = tcm\n", " \n", " dict1[code]['name'] = content['name']\n", " dict1[code]['unit'] = unit\n", " dict1[code]['sex'] = sex\n", " dict1[code]['weight'] = content['weight']\n", " dict1[code]['tun'] = content['hip']\n", " dict1[code]['yao'] = content['waist']\n", " #print(phone[item[2]])\n", " nn+=1\n", "filename = 'data/result_南京化工-2.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False)\n", "print(len(dict1))" ] }, { "cell_type": "markdown", "id": "acfc1736-9185-4217-bd05-a83b7e292725", "metadata": {}, "source": [ "## 导入问卷信息(20251027)" ] }, { "cell_type": "code", "execution_count": 23, "id": "4b6cf9bc-fe84-4cf6-b762-8c30f8dd7953", "metadata": { "execution": { "iopub.execute_input": "2025-10-28T02:58:31.746734Z", "iopub.status.busy": "2025-10-28T02:58:31.746060Z", "iopub.status.idle": "2025-10-28T02:58:31.786856Z", "shell.execute_reply": "2025-10-28T02:58:31.786112Z", "shell.execute_reply.started": "2025-10-28T02:58:31.746685Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "81\n" ] } ], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "\n", "dict1 = {}\n", "list1 = []\n", "filename = 'data/sql_20251028.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", "nn = 0\n", "for item in list1:\n", " dict2 = {}\n", " \n", " phone = str(item[0])[2:]\n", " content = json.loads(json.loads(item[1]))\n", " tcm = []\n", " for i in range(0,60):\n", " tcm.append(0)\n", " for k, v in content.items(): \n", " if 'tcm' not in k:\n", " dict2[k] = v\n", " else:\n", " i = int(k[3:])\n", " tcm[i-1] = int(v)\n", " \n", " code = dict2['code']\n", " dict1.setdefault(code,{})\n", " dict1[code]['name'] = dict2['name']\n", " if dict2['gender'] == 'male':\n", " dict1[code]['sex'] = '男'\n", " else:\n", " dict1[code]['sex'] = '女'\n", " dict1[code]['birth'] = str(dict2['birth'])+'-01'\n", " dict1[code]['unit'] = '南京化工'\n", " dict1[code]['phone'] = phone\n", " dict1[code]['weight'] = dict2['weight']\n", " dict1[code]['waist'] = dict2['waist']\n", " dict1[code]['hip'] = dict2['hip']\n", " dict1[code]['tcm'] = tcm\n", "filename = 'data/result_南京化工-3.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": "7392d5bf-c6a8-4cdf-8653-0fb4961f1405", "metadata": {}, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "import time\n", "from datetime import date\n", "\n", "\n", "dict1 = {}\n", "list1 = []\n", "filename = 'data/sql_20251027.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", "nn = 0\n", "for item in list1:\n", " dict2 = {}\n", " \n", " phone = str(item[0])[2:]\n", " content = json.loads(item[1])\n", " print(type(json.loads(content)))" ] }, { "cell_type": "markdown", "id": "89689b86-3fae-402e-a456-a646f0c7201f", "metadata": {}, "source": [ "## 导入腰臀数据" ] }, { "cell_type": "code", "execution_count": null, "id": "4a0678c6-0c64-4314-bb03-24b10a3d695a", "metadata": {}, "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/result_南京化工-1.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "wb = openpyxl.load_workbook('data/南化腰臀数据.xlsx',data_only=True)\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", " if code in dict1.keys():\n", " yao = str(sheet.cell(n, 2).value)\n", " tun = str(sheet.cell(n, 3).value)\n", " dict1[code]['腰臀比'] = yao+','+tun\n", "filename = 'data/result_南京化工-1.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False)\n" ] }, { "cell_type": "markdown", "id": "19c6e8b6-2663-447d-884b-a22af3944c71", "metadata": {}, "source": [ "## 计算中医体质并导出" ] }, { "cell_type": "code", "execution_count": 24, "id": "e233e6c3-9c3f-42c7-8057-012bbcfe8b26", "metadata": { "execution": { "iopub.execute_input": "2025-10-28T02:58:52.451889Z", "iopub.status.busy": "2025-10-28T02:58:52.451452Z", "iopub.status.idle": "2025-10-28T02:58:52.546239Z", "shell.execute_reply": "2025-10-28T02:58:52.545487Z", "shell.execute_reply.started": "2025-10-28T02:58:52.451850Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ok\n" ] } ], "source": [ "import openpyxl\n", "import json\n", "\n", "questions = [\n", " [1],\n", " [-1, 2],\n", " [-1, 2],\n", " [-1, 8],\n", " [-1, 3],\n", " [1],\n", " [-1],\n", " [-1, 7],\n", " [2],\n", " [2],\n", " [2],\n", " [2, 3],\n", " [2],\n", " [2],\n", " [3],\n", " [3],\n", " [3],\n", " [3],\n", " [3],\n", " [4],\n", " [4],\n", " [4],\n", " [4],\n", " [4],\n", " [4],\n", " [4],\n", " [4],\n", " [5],\n", " [5],\n", " [5],\n", " [5],\n", " [5],\n", " [5],\n", " [5],\n", " [5],\n", " [6],\n", " [6],\n", " [6],\n", " [6],\n", " [6],\n", " [6],\n", " [7],\n", " [7],\n", " [7],\n", " [7],\n", " [7],\n", " [7],\n", " [8],\n", " [8],\n", " [8],\n", " [8],\n", " [8],\n", " [8],\n", " [9],\n", " [9],\n", " [9],\n", " [9],\n", " [9],\n", " [9],\n", " [9]\n", "]\n", "\n", "kinds = [\n", " '平和',\n", " '气虚',\n", " '阳虚',\n", " '阴虚',\n", " '痰湿',\n", " '湿热',\n", " '血瘀',\n", " '气郁',\n", " '特禀'\n", "]\n", "\n", "def tcm_calc(arr):\n", " qa = [8, 8, 7, 8, 8, 6, 7, 7, 7]\n", " # 成绩数组\n", " s = [0] * 9\n", " # 遍历五进制\n", " for i in range(len(questions)):\n", " m = arr[i] - 1\n", " for v in questions[i]:\n", " if v < 0:\n", " s[-v - 1] += 4 - m\n", " else:\n", " s[v - 1] += m\n", " return [int((v / qa[i]) * 25) for i, v in enumerate(s)]\n", "\n", "def tcm_kind(score):\n", " kind = 0\n", " near = False\n", " max_kind = 0\n", " max_score = 0\n", " for i in range(1, 9):\n", " if score[i] > max_score:\n", " max_kind = i\n", " max_score = score[i]\n", " if score[0] >= 60 and max_score < 40:\n", " if max_score >= 30:\n", " near = True\n", " kind = max_kind\n", " else:\n", " kind = max_kind\n", " return {\n", " \"kind\": kind,\n", " \"near\": near\n", " }\n", "\n", "\n", "filename = 'data/result_南京化工-3.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "i = 1\n", "list2 = []\n", "for k, v in dict1.items():\n", " if 'tcm' in v.keys():\n", " list1 = []\n", " tcm =v['tcm']\n", " for item in tcm:\n", " list1.append(item)\n", " score = tcm_calc(list1)\n", "\n", " result = tcm_kind(score)\n", " kind = result['kind']\n", " near = result['near']\n", " #print(i,k,kinds[kind], near, score)\n", " #i+=1\n", " list3 = []\n", " list3.append(k)\n", " list3.append(v['name'])\n", " list3.append(v['sex'])\n", " list3.append(v['phone'])\n", " list3.append(v['weight'])\n", " list3.append(v['waist'])\n", " list3.append(v['hip'])\n", " list3.append(kinds[kind])\n", " list3.append(near)\n", " for item in score:\n", " list3.append(item)\n", " list2.append(list3)\n", "\n", "filename = 'data/南化第三次问卷明细表（截至20251028）.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list2:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok') " ] }, { "cell_type": "markdown", "id": "caf77c95-3090-4fa1-bcec-c9e8a38d4ca9", "metadata": {}, "source": [ "## 体检报告汇总" ] }, { "cell_type": "code", "execution_count": null, "id": "b815a478-d178-4b87-9080-a779d397d945", "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "import json\n", "import shutil\n", "\n", "\n", "target_directory = Path('./file/南化体重')\n", "new_path = './file/南化体重/new'\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "# 遍历目标目录及其子目录获取所有文件\n", "\n", "for fl in target_directory.rglob('*.pdf'):\n", " if fl.is_file():\n", " fl_name = fl.stem\n", " name = fl_name[12:] \n", " for k, v in dict1.items(): \n", " if name == v['name']:\n", " n_name = Path(new_path,str(k)+'-'+name+'.pdf')\n", " shutil.copyfile(fl,n_name)\n", " print(n_name)\n", " \n", " " ] }, { "cell_type": "code", "execution_count": null, "id": "4f192b79-5dc7-4517-b7f3-409e30d60dad", "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "import json\n", "import shutil\n", "import pymupdf4llm\n", "#md_text = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\")\n", "llama_reader = pymupdf4llm.LlamaMarkdownReader()\n", "#llama_docs = llama_reader.load_data(\"data/1782596-唐荣.pdf\")\n", "\n", "\n", "target_directory = Path('./file/北海体检报告')\n", "new_path = './file/北海体检报告/md'\n", "\n", "\n", "for fl in target_directory.rglob('*.pdf'):\n", " if fl.is_file():\n", " fl_name = fl.stem\n", " llama_lists = pymupdf4llm.to_markdown(fl,page_chunks=True)\n", " list1 = []\n", " for item in llama_lists:\n", " list1.append(item['text'])\n", " llama_docs = '\\n'.join(list1)\n", " Path(new_path,fl_name+'.md').write_bytes(llama_docs.encode())\n", " " ] }, { "cell_type": "code", "execution_count": null, "id": "e5863760-0d11-45b0-acb3-1a38c78d4fc7", "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "import json\n", "import shutil\n", "import pymupdf4llm\n", "#md_text = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\")\n", "llama_reader = pymupdf4llm.LlamaMarkdownReader()\n", "llama_docs = llama_reader.load_data(\"data/1782596-唐荣.pdf\",page_chunks=True)\n", "print(llama_docs)\n", "\n" ] }, { "cell_type": "markdown", "id": "8d5f4103-0d1e-4711-b324-ece360f8dcd3", "metadata": {}, "source": [ "## 生成报告" ] }, { "cell_type": "code", "execution_count": 18, "id": "23ffd115-72a3-4f90-9e64-ffa6420df8a4", "metadata": { "execution": { "iopub.execute_input": "2025-10-27T06:11:24.661422Z", "iopub.status.busy": "2025-10-27T06:11:24.660908Z", "iopub.status.idle": "2025-10-27T06:11:24.977141Z", "shell.execute_reply": "2025-10-27T06:11:24.975637Z", "shell.execute_reply.started": "2025-10-27T06:11:24.661386Z" } }, "outputs": [ { "ename": "KeyError", "evalue": "'month'", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[18], line 32\u001b[0m\n\u001b[1;32m 29\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 30\u001b[0m mydata[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgender\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfemale\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m---> 32\u001b[0m mydata[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmonth\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[43mv\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mmonth\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m 33\u001b[0m mydata[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfits\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m {}\n\u001b[1;32m 34\u001b[0m survey_list \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtcm\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpsy57\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mspine\u001b[39m\u001b[38;5;124m'\u001b[39m]\n", "\u001b[0;31mKeyError\u001b[0m: 'month'" ] } ], "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_南京化工-3.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "file_path ='./南京化工第三批问卷（251021）/'\n", "list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi']\n", "i=0\n", "list2 = []\n", "for k, v in dict1.items():\n", " list1 = []\n", " mydata = {}\n", " \n", " id = str(k).rjust(4,\"0\")\n", " mydata['path'] = file_path+id+'-'+ v['name']+'.pdf'\n", " mydata['title'] = '南化公司'\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", " survey_list = ['tcm','psy57','spine']\n", " for item in survey_list:\n", " if item in v.keys():\n", " mydata.setdefault('surveys',{})\n", " mydata['surveys'][item] = v[item]\n", " \n", " \n", " #mydata['fits'] = {}\n", " for item in list_item:\n", " if item in v.keys():\n", " mydata.setdefault('fits',{})\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 or len(mydata['surveys']) >0:\n", " #if len(mydata['fits']) >2 : \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", " #print(mydata)\n", " #x.close()\n", "print(i)" ] }, { "cell_type": "markdown", "id": "007a67c3-3590-47d9-a6d3-9080574a7940", "metadata": {}, "source": [ "### 生成报告(单问卷)" ] }, { "cell_type": "code", "execution_count": 19, "id": "fc2bfab2-7f56-4abf-b2c4-0fb49a0da563", "metadata": { "execution": { "iopub.execute_input": "2025-10-27T06:12:04.742517Z", "iopub.status.busy": "2025-10-27T06:12:04.738837Z", "iopub.status.idle": "2025-10-27T06:12:30.134155Z", "shell.execute_reply": "2025-10-27T06:12:30.133408Z", "shell.execute_reply.started": "2025-10-27T06:12:04.742463Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "72\n" ] } ], "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_南京化工-3.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "file_path ='./南京化工第三批问卷/'\n", "list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi']\n", "i=0\n", "list2 = []\n", "for k, v in dict1.items():\n", " list1 = []\n", " mydata = {}\n", " \n", " id = str(k)\n", " mydata['path'] = file_path+id+'-'+ v['name']+'.pdf'\n", " mydata['title'] = '南化公司'\n", " mydata['subtitle'] = v['unit']\n", " mydata['id'] = id\n", " mydata['name'] = v['name']\n", " if v['sex'] == 'm':\n", " mydata['gender'] = 'male'\n", " else:\n", " mydata['gender'] = 'female'\n", " \n", " #mydata['month'] = v['month']\n", " #mydata['fits'] = {}\n", " survey_list = ['tcm','psy57','spine']\n", " for item in survey_list:\n", " if item in v.keys():\n", " mydata.setdefault('surveys',{})\n", " mydata['surveys'][item] = v[item]\n", " \n", " \n", " #mydata['fits'] = {}\n", " \n", " if len(mydata['surveys']) >0:\n", " #if len(mydata['fits']) >2 : \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", " #print(mydata)\n", " #x.close()\n", "print(i)" ] }, { "cell_type": "markdown", "id": "42f1a67c-756a-4cf0-bd53-d71fb9c95aa6", "metadata": {}, "source": [ "## 导入体检报告数据" ] }, { "cell_type": "code", "execution_count": null, "id": "c2fb2c7c-6541-4c41-ba38-0e1fee29aa97", "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "import json\n", "import shutil\n", "\n", "\n", "target_directory = Path('./data/json')\n", "filename = 'data/南京化工人员.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "# 遍历目标目录及其子目录获取所有文件\n", "dict2 = {}\n", "list2 = ['总胆固醇','甘油三酯','尿微量白蛋白']\n", "for fl in target_directory.glob('*.json'):\n", " if fl.is_file():\n", " code = fl.stem\n", " dict2.setdefault(code,{})\n", " dict2[code] = dict1[code]\n", " with open(fl,'r') as fl1:\n", " dict3 = json.load(fl1)\n", " for k, v in dict3.items():\n", " if k =='血压情况' and len(v)>0:\n", " dict2[code].setdefault('血压',{})\n", " list1 = [] \n", " for item in v:\n", " \n", " dict2[code]['血压'][item['项目']] = item['结果']\n", " if '状态' in item.keys():\n", " list1.append(item['项目']+item['状态'])\n", " if len(list1)>0:\n", " dict2[code]['血压']['状态'] = ','.join(list1)\n", " \n", " if k in list2:\n", " dict2[code].setdefault(k,{})\n", " dict2[code][k]['结果'] = v['结果']\n", " dict2[code][k]['参考值'] = v['参考值']\n", " if '状态' in v.keys():\n", " dict2[code][k]['状态'] = v['状态']\n", " if k in ['空腹血糖','糖化血红蛋白']:\n", " dict2[code].setdefault(k,{})\n", " if '结果' in v.keys():\n", " dict2[code][k]['结果'] = v['结果']\n", " dict2[code][k]['参考值'] = v['参考值']\n", " if '状态' in v.keys():\n", " dict2[code][k]['状态'] = v['状态']\n", " if k in ['ALT、AST、GGT','TSH、FT3、FT4']:\n", " for item in v:\n", " xm = item['项目']\n", " dict2[code].setdefault(xm,{})\n", " if '结果' in item.keys():\n", " dict2[code][xm]['结果'] = item['结果']\n", " if '参考值' in item.keys():\n", " dict2[code][xm]['参考值'] = item['参考值']\n", " if '状态' in item.keys():\n", " dict2[code][xm]['状态'] = item['状态']\n", " if k =='肾功能与尿微量白蛋白':\n", " for item in v['肾功能']:\n", " xm = item['项目']\n", " dict2[code].setdefault(xm,{})\n", " if '结果' in item.keys():\n", " dict2[code][xm]['结果'] = item['结果']\n", " if '参考值' in item.keys():\n", " dict2[code][xm]['参考值'] = item['参考值']\n", " if '状态' in item.keys():\n", " dict2[code][xm]['状态'] = item['状态'] \n", " dict2[code].setdefault('尿微量白蛋白',{})\n", " xm = v['尿微量白蛋白']\n", " if '结果' in xm.keys() and len(xm['结果'])>0:\n", " dict2[code]['尿微量白蛋白']['结果'] = xm['结果']\n", " if '参考值' in xm.keys() and len(xm['参考值'])>0:\n", " dict2[code]['尿微量白蛋白']['参考值'] = xm['参考值']\n", " if '状态' in xm.keys():\n", " dict2[code]['尿微量白蛋白']['状态'] = xm['状态'] \n", " \n", " \n", "\n", "filename = 'data/南京化工体检情况.json'\n", "\n", "with open(filename,'w') as fl:\n", " json.dump(dict2, fl, ensure_ascii=False) " ] }, { "cell_type": "markdown", "id": "da43ceef-4215-4187-a76d-4e1434e50043", "metadata": {}, "source": [ "## 导出体检报告数据" ] }, { "cell_type": "code", "execution_count": null, "id": "daa1b36e-1b62-49ee-9539-84c2d286fefe", "metadata": {}, "outputs": [], "source": [ "import json\n", "import csv\n", "import openpyxl\n", "\n", "filename = 'data/南京化工体检情况.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "list1 = [\"总胆固醇\",\"甘油三酯\",\"空腹血糖\",\"糖化血红蛋白\",\"谷丙转氨酶 (ALT)\",\"谷草转氨酶 (AST)\",\"γ- 谷氨酰转肽酶 (GGT)\",\"促甲状腺激素 (TSH)\",\"游离三碘甲状腺原氨酸 (FT3)\",\"游离甲状腺素 (FT4)\",\"肌酐\",\"尿素氮\",\"尿酸\",\"尿微量白蛋白\"]\n", "title = ['编号','姓名','性别','血压','状态']\n", "for item in list1:\n", " title.append(item)\n", " title.append('状态')\n", "list3 = []\n", "for k, v in dict1.items():\n", " list2 = []\n", " list2.append(k)\n", " list2.append(v['name'])\n", " list2.append(v['sex'])\n", " if '血压' in v.keys():\n", " xueya = v['血压']['舒张压']+'/'+v['血压']['收缩压']\n", " if '状态' in v['血压'].keys():\n", " zt = v['血压']['状态']\n", " else:\n", " zt = ''\n", " else:\n", " xueya = ''\n", " zt = ''\n", " \n", " list2.append(xueya)\n", " list2.append(zt)\n", " for item in list1:\n", " if item in v.keys() and '结果' in v[item]:\n", " list2.append(v[item]['结果'])\n", " if '状态' in v[item]:\n", " list2.append(v[item]['状态'])\n", " else:\n", " list2.append('')\n", " else:\n", " list2.append('')\n", " list2.append('') \n", " list3.append(list2)\n", "\n", "filename = 'data/南京化工体检相关数据明细.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)" ] }, { "cell_type": "code", "execution_count": null, "id": "221b35dc-3a17-4950-993c-b634ee9a53cf", "metadata": {}, "outputs": [], "source": [ "from spire.pdf.common import *\n", "from spire.pdf import *\n", "\n", "# 创建PdfDocument类的实例\n", "pdf = PdfDocument()\n", "\n", "# 加载PDF文档\n", "pdf.LoadFromFile(\"file/北海体检报告/2405280074.pdf\")\n", "\n", "# 将PDF转换为Markdown文件\n", "pdf.SaveToFile(\"PDF转Markdown.md\", FileFormat.Markdown)\n", "pdf.Close()\n" ] }, { "cell_type": "code", "execution_count": null, "id": "1b9d4042-5e73-44e3-8079-eee2c5be1858", "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 }