20230522

体测单位/体检报告分析.ipynb

@@ -0,0 +1,232 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4b3853d4-d30f-4b1d-99de-fa52777ce65c",
+   "metadata": {},
+   "source": [
+    "## 体质指标问卷导入"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "202a0266-f578-4d75-b04c-5ae9957391bf",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-22T08:51:23.135343Z",
+     "iopub.status.busy": "2023-05-22T08:51:23.134459Z",
+     "iopub.status.idle": "2023-05-22T08:51:23.150352Z",
+     "shell.execute_reply": "2023-05-22T08:51:23.149334Z",
+     "shell.execute_reply.started": "2023-05-22T08:51:23.135304Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import time\n",
+    "import csv\n",
+    "\n",
+    "filename = 'data/淄博交警体质指标问卷.json'\n",
+    "item = {}\n",
+    "unit = {}\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict1 = json.load(fl) \n",
+    "dict2 = {}\n",
+    "for items in dict1['pages']:\n",
+    "    for item in items['elements']:\n",
+    "        #print(item)\n",
+    "        dict2.setdefault(item['name'],{})\n",
+    "        name = item['name']\n",
+    "        dict2[name]['type'] = item['type']\n",
+    "        dict2[name]['title'] = item['title']['zh-cn']\n",
+    "        if 'isRequired' in item.keys():\n",
+    "            dict2[name]['isRequired'] = item['isRequired']\n",
+    "        else:\n",
+    "            dict2[name]['isRequired'] = False\n",
+    "        if item['type'] == 'text':\n",
+    "            dict2[name]['inputType'] = item['inputType']\n",
+    "        else:\n",
+    "            dict2[name]['choices'] = item['choices']\n",
+    "filename = 'data/淄博交警体质问卷参数.json'\n",
+    "with open(filename, 'w') as fl:\n",
+    "    json.dump(dict2, fl, ensure_ascii=False)\n",
+    "print('ok')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d7ab7cfd-3448-45a6-abb4-04e7f317b843",
+   "metadata": {},
+   "source": [
+    "## 问卷数据分析"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "e05bb84b-e649-4201-95d7-f9fee7b1a254",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-22T09:31:19.028959Z",
+     "iopub.status.busy": "2023-05-22T09:31:19.028116Z",
+     "iopub.status.idle": "2023-05-22T09:31:19.043637Z",
+     "shell.execute_reply": "2023-05-22T09:31:19.042568Z",
+     "shell.execute_reply.started": "2023-05-22T09:31:19.028917Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "13718887655\n",
+      "您的性别 女性\n",
+      "您的年龄 39\n",
+      "您的身高（cm） 160\n",
+      "您的体重（kg） 52\n",
+      "您的血压（BP） 临界偏低（收缩压90-94mmHg和/或舒张压60-65mmHg）\n",
+      "您的空腹血糖（FPG） 正常（3.89-6.1mmol/L）\n",
+      "您的白细胞计数（WBC） 临界偏高（9.6-10×10^9/L）\n",
+      "您的血红蛋白（HGB） 临界偏低（110-114g/L）\n",
+      "您的血小板（PLT） 正常（125-350×10^9/L）\n",
+      "您的低密度脂蛋白（LDL-C） 临界偏高（5.18-6.19mmol/L）\n",
+      "您的甘油三酯（TG） 正常（0.45-1.69mmol/L）\n",
+      "您的尿酸（UA） 正常（155.00- 350.00 μmol/L）\n",
+      "您的肌酐（Cr） 正常（44.00- 73.00μmol/L）\n",
+      "您的谷丙转氨酶（ALT） 正常（7.00- 19.00U/L）\n",
+      "您的谷草转氨酶（AST） 正常（13.00- 35.00U/L）\n",
+      "您的甲状腺功能 正常\n",
+      "您的尿蛋白 阴性\n",
+      "您的便潜血 阴性\n",
+      "您的幽门螺旋杆菌 阴性\n",
+      "囊肿（选做题，没有囊肿问题的请跳过） ['卵巢囊肿']\n",
+      "结节（选做题，没有结节问题的请跳过） ['肺结节']\n",
+      "息肉（选做题，没有息肉问题的请跳过） ['其他息肉']\n",
+      "您的其他问题（选做题，没有这些问题的请跳过） ['过敏性鼻炎']\n",
+      "您的饮食口味 ['清淡']\n",
+      "您吸烟吗 不吸烟\n",
+      "您喝酒吗 不喝\n",
+      "您参加规律的体育锻炼吗 不参加\n",
+      "您的睡眠状况如何 非常好\n",
+      "您的排便频率如何 2天一次\n",
+      "您的职业 管理人员\n",
+      "您的父母或兄弟姐妹是否患有明确诊断的疾病？（选做题，没有遗传病史的请跳过） ['高血压', '冠心病', '脑卒中']\n",
+      "15210715398\n",
+      "您的性别 女性\n",
+      "您的年龄 36\n",
+      "您的身高（cm） 162\n",
+      "您的体重（kg） 56\n",
+      "您的血压（BP） 正常（收缩压95-130mmHg和舒张压65-85mmHg）\n",
+      "您的空腹血糖（FPG） 正常（3.89-6.1mmol/L）\n",
+      "您的白细胞计数（WBC） 正常（4-9.5×10^9/L）\n",
+      "您的血红蛋白（HGB） 正常（115-145g/L）\n",
+      "您的血小板（PLT） 正常（125-350×10^9/L）\n",
+      "您的低密度脂蛋白（LDL-C） 正常（3.1-5.18mmol/L）\n",
+      "您的甘油三酯（TG） 正常（0.45-1.69mmol/L）\n",
+      "您的尿酸（UA） 正常（155.00- 350.00 μmol/L）\n",
+      "您的肌酐（Cr） 正常（44.00- 73.00μmol/L）\n",
+      "您的谷丙转氨酶（ALT） 正常（7.00- 19.00U/L）\n",
+      "您的谷草转氨酶（AST） 正常（13.00- 35.00U/L）\n",
+      "您的甲状腺功能 正常\n",
+      "您的尿蛋白 阴性\n",
+      "您的便潜血 阴性\n",
+      "您的幽门螺旋杆菌 阴性\n",
+      "您的心脏（选做题，没有心脏问题的请跳过） ['窦性心律不齐']\n",
+      "您的饮食口味 ['辛辣']\n",
+      "您吸烟吗 不吸烟\n",
+      "您喝酒吗 不喝\n",
+      "您参加规律的体育锻炼吗 经常参加（平均每周锻炼3次及以上，每次锻炼＞30分钟）\n",
+      "您的睡眠状况如何 非常好\n",
+      "您的排便频率如何 2天一次\n",
+      "您的职业 行政工作\n",
+      "您的父母或兄弟姐妹是否患有明确诊断的疾病？（选做题，没有遗传病史的请跳过） ['高血压']\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import time\n",
+    "import csv\n",
+    "\n",
+    "filename = 'data/淄博交警体质问卷参数.json'\n",
+    "item = {}\n",
+    "unit = {}\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict1 = json.load(fl) \n",
+    "\n",
+    "filename = 'data/Survey_20230522.json'\n",
+    "item = {}\n",
+    "unit = {}\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict2 = json.load(fl) \n",
+    "for items in dict2['Survey']:\n",
+    "    #print(items)\n",
+    "    phone = items['phone']\n",
+    "    print(phone)\n",
+    "    data = json.loads(items['data'])\n",
+    "    for k, v in data.items():\n",
+    "        if dict1[k]['type'] == 'radiogroup':\n",
+    "            title = dict1[k]['title']\n",
+    "            for item in dict1[k]['choices']:\n",
+    "                if item['value'] == v:\n",
+    "                    value = item['text']\n",
+    "            \n",
+    "        if dict1[k]['type'] == 'text':\n",
+    "            title = dict1[k]['title']\n",
+    "            value = v\n",
+    "        if dict1[k]['type'] == 'checkbox':\n",
+    "            title = dict1[k]['title']\n",
+    "            value = []\n",
+    "            for choice in v:\n",
+    "                for item in dict1[k]['choices']:\n",
+    "                    if item['value'] == choice:\n",
+    "                        value.append(item['text'])\n",
+    "\n",
+    "        print(title,value)  \n",
+    "                                \n",
+    "        \n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f5c6a39a-3e3e-4844-8ff8-b9ebb7e8f8af",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

体测单位/体质检测数据处理.ipynb

@@ -350,9 +350,9 @@
     "    data_list.append((int(k),v['name'])) \n",
     "conn = psycopg2.connect(database=\"mycrm\", user=\"postgres\", password=\"songyi\", host=\"localhost\", port=\"5432\")\n",
     "cursor = conn.cursor()\n",
-    "sql = 'insert into tianjin_item (id,name) values %s'\n",
+    "sql = 'insert into shijiazhuang_item (id,name) values %s'\n",
     "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "conn.commit()\n",
+    "#conn.commit()\n",
     "cursor.close()\n",
     "conn.close()\n",
     "print('ok!')"
@@ -381,7 +381,7 @@
     "\n",
     "conn = psycopg2.connect(database=\"mycrm\", user=\"postgres\", password=\"songyi\", host=\"localhost\", port=\"5432\")\n",
     "cursor = conn.cursor()\n",
-    "filename = 'data/天津石化人员名单.json'\n",
+    "filename = 'data/result_石家庄.json'\n",
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl)\n",
     "unit = set()\n",
@@ -399,9 +399,9 @@
     "for k,  v in dict2.items():\n",
     "    data_list.append((v,k)) \n",
     "    \n",
-    "sql = 'insert into tianjin_unit (id,name) values %s'\n",
+    "sql = 'insert into shijiazhuang_unit (id,name) values %s'\n",
     "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "conn.commit()\n",
+    "#conn.commit()\n",
     "cursor.close()\n",
     "conn.close()\n",
     "print('ok!')"
@@ -457,7 +457,7 @@
     "        i+=1\n",
     "sql = 'insert into tianjin_sub_unit (id,name,unit_id) values %s'\n",
     "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "conn.commit()\n",
+    "#conn.commit()\n",
     "cursor.close()\n",
     "conn.close()\n",
     "print('ok!')"
@@ -484,7 +484,7 @@
     "import csv\n",
     "\n",
     "dict1 = {}\n",
-    "filename = 'data/unit_134.csv'\n",
+    "filename = 'data/shijiazhuang_unit_20230517.csv'\n",
     "with open(filename,'r',newline='') as csv_file:\n",
     "    fl = csv.reader(csv_file,delimiter=',')\n",
     "    header = next(fl)\n",
@@ -511,6 +511,36 @@
     "print(len(dict1))    "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5e57329d-a0ef-47b2-9866-fe2a911ff01d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import csv\n",
+    "\n",
+    "dict1 = {}\n",
+    "filename = 'data/shijiazhuang_unit_20230517.csv'\n",
+    "with open(filename,'r',newline='') as csv_file:\n",
+    "    fl = csv.reader(csv_file,delimiter=',')\n",
+    "    header = next(fl)\n",
+    "    list1 = []\n",
+    "    for line in fl:\n",
+    "        #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n",
+    "        list1.append({'id':int(line[0]),'name':line[1]})\n",
+    "        dict1[int(line[0])] = line[1]\n",
+    "\n",
+    "\n",
+    "filename = 'data/石家庄石化部门.json'\n",
+    "with open(filename,'w') as fl:\n",
+    "    json.dump(dict1, fl, ensure_ascii=False) \n",
+    "print(len(dict1))    "
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "53bf98fe-0ae9-402f-b8d8-495e8f31df3d",
@@ -538,15 +568,10 @@
     "with open(filename,'r') as fl:\n",
     "    person = json.load(fl)\n",
     "    \n",
-    "filename = 'data/天津石化人员名单.json'\n",
+    "filename = 'data/石家庄石化部门.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",
-    "    #if 'sub_unit' not in v.keys():\n",
-    "    #    print(k,v['name'])\n",
-    "    unit.add(v['unit'])\n",
-    "print(unit)    \n",
     "i = 1\n",
     "dict2 = {}\n",
     "for item in unit:\n",
@@ -591,13 +616,54 @@
     "    data_list.append((id,name,sex,birth,unit))\n",
     "sql = 'insert into tianjin_person (id,name,sex,birth,unit_id) values %s'\n",
     "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "conn.commit()\n",
+    "#conn.commit()\n",
     "cursor.close()\n",
     "conn.close()\n",
     "print('ok!')   \n",
     "    "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c2007c46-38c8-4a20-9917-b0b8743fe2a9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import psycopg2\n",
+    "from psycopg2 import extras as ex\n",
+    "\n",
+    "conn = psycopg2.connect(database=\"mycrm\", user=\"postgres\", password=\"songyi\", host=\"localhost\", port=\"5432\")\n",
+    "cursor = conn.cursor()\n",
+    "    \n",
+    "filename = 'data/石家庄石化部门.json'\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict1 = json.load(fl)\n",
+    "dict3 = {}\n",
+    "for k,v in dict1.items():\n",
+    "    dict3[v] = int(k)\n",
+    "filename = 'data/result_石家庄.json'\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict2 = json.load(fl)\n",
+    "data_list = []\n",
+    "for k, v in dict2.items():\n",
+    "    id = int(k)\n",
+    "    name = dict2[k]['name']\n",
+    "    sex = dict2[k]['sex']\n",
+    "    birth = dict2[k]['birth']    \n",
+    "    unit = dict3[dict2[k]['unit']]\n",
+    "    data_list.append((id,name,sex,birth,unit))\n",
+    "sql = 'insert into shijiazhuang_person (id,name,sex,birth,unit_id) values %s'\n",
+    "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
+    "#conn.commit()\n",
+    "cursor.close()\n",
+    "conn.close()\n",
+    "print('ok!')   "
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "fd95a45a-c6df-47c3-9941-2d0579b2c5d9",
@@ -607,28 +673,23 @@
    ]
   },
   {
-   "cell_type": "code",
+   "cell_type": "markdown",
-   "execution_count": 84,
+   "id": "c989de3f-a8ab-47dc-9662-544e4b6a0e2f",
-   "id": "360e61e9-7895-484b-a9d6-333bdefa1a86",
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-05-01T04:48:05.728955Z",
-     "iopub.status.busy": "2023-05-01T04:48:05.728103Z",
-     "iopub.status.idle": "2023-05-01T04:48:08.066386Z",
-     "shell.execute_reply": "2023-05-01T04:48:08.065262Z",
-     "shell.execute_reply.started": "2023-05-01T04:48:05.728912Z"
-    },
     "tags": []
    },
-   "outputs": [
+   "source": [
-    {
+    "#### 二级部门导入"
-     "name": "stdout",
+   ]
-     "output_type": "stream",
+  },
-     "text": [
+  {
-      "ok!\n"
+   "cell_type": "code",
-     ]
+   "execution_count": null,
-    }
+   "id": "360e61e9-7895-484b-a9d6-333bdefa1a86",
-   ],
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
    "source": [
     "import json\n",
     "import psycopg2\n",
@@ -685,13 +746,21 @@
     "         \n",
     "sql = 'insert into tianjin_records (performance,score,avatar_id_id,item_id_id,unit_id_id,sub_unit_id_id) values %s'\n",
     "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "conn.commit()\n",
+    "#conn.commit()\n",
     "cursor.close()\n",
     "conn.close()\n",
     "print('ok!')           \n",
     "    "
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "4aeabbbc-5b51-4dd0-b428-83e2012e63c4",
+   "metadata": {},
+   "source": [
+    "#### 一级部门导入"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -712,47 +781,37 @@
     "for k, v in dict1.items():\n",
     "    dict2[v['name']] = int(k)\n",
     "\n",
-    "filename = 'data/天津石化部门.json'\n",
+    "filename = 'data/石家庄石化部门.json'\n",
-    "with open(filename,'r') as fl:\n",
-    "    dict1 = json.load(fl) \n",
-    "unit = {}\n",
-    "for item in dict1['unit']:\n",
-    "    unit[item['name']] = item['id']\n",
-    "\n",
-    "sub_unit = {}\n",
-    "for item in dict1['sub_unit']:\n",
-    "    sub_unit.setdefault(item['unit_id'],[])\n",
-    "    sub_unit[item['unit_id']].append({'id':item['id'],'name':item['name']})\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",
-    "person = {}\n",
+    "dict3 = {}\n",
-    "for k, v in dict1.items():\n",
+    "for k,v in dict1.items():\n",
-    "    person[k] = {'unit':v['unit'],'sub_unit':v['sub_unit']}\n",
+    "    dict3[v] = int(k)\n",
-    "\n",
     "    \n",
+    "\n",
     "conn = psycopg2.connect(database=\"mycrm\", user=\"postgres\", password=\"songyi\", host=\"localhost\", port=\"5432\")\n",
     "cursor = conn.cursor()\n",
     "data_list = []\n",
-    "filename = 'data/result_天津.json'\n",
+    "filename = 'data/result_石家庄.json'\n",
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl) \n",
     "for k, v in dict1.items():\n",
     "    for item in v.keys():\n",
     "        if item in dict2.keys():\n",
-    "            item_id = dict2[item]\n",
+    "            item_id = dict2[item]            \n",
-    "            if v[item]['得分'] == '\\\\N':\n",
+    "            if v[item]['得分'] == '':\n",
     "                score = None\n",
     "            else:\n",
     "                score = int(v[item]['得分'])\n",
-    "            unit_name = person[k]['unit']  \n",
+    "            unit_name = v['unit']\n",
-    "            sub_unit_name = person[k]['sub_unit']\n",
+    "            unit_id = dict3[unit_name]\n",
-    "            unit_id = unit[unit_name]\n",
+    "            data_list.append((v[item]['成绩'],score,int(k),item_id,unit_id))\n",
-    "            for items in sub_unit[unit_id]:\n",
+    "sql = 'insert into shijiazhuang_records (performance,score,avatar_id_id,item_id_id,unit_id_id) values %s'\n",
-    "                if items['name'] ==sub_unit_name:\n",
+    "ex.execute_values(cursor, sql, data_list, page_size=10000)\n",
-    "                    sub_id = items['id'] \n",
+    "#conn.commit()\n",
-    "            print(unit_id,sub_id)"
+    "cursor.close()\n",
+    "conn.close()\n",
+    "print('ok!')"
    ]
   },
   {
@@ -781,6 +840,130 @@
     "    unit[item['name']] = item['id']\n",
     "print(unit)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bdb81e20-32ec-4e0e-b2ac-13dac2060068",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 体质报告在线管理"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1485fc89-4fc2-437d-a29e-b4a0aab12aa0",
+   "metadata": {},
+   "source": [
+    "## 新增体测单位"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "cf345bf0-f11b-459e-9b69-b2843836f6f3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-19T08:30:41.861658Z",
+     "iopub.status.busy": "2023-05-19T08:30:41.860765Z",
+     "iopub.status.idle": "2023-05-19T08:30:42.006745Z",
+     "shell.execute_reply": "2023-05-19T08:30:42.006220Z",
+     "shell.execute_reply.started": "2023-05-19T08:30:41.861616Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
+    "mydb = myclient[\"baogao\"]\n",
+    "mycol = mydb[\"place\"]\n",
+    "\n",
+    "mydict = { \"id\": \"714309\",\"name\": \"中国石化石家庄炼化公司\",  }\n",
+    " \n",
+    "x = mycol.insert_one(mydict) "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df2d18e2-d2e4-499e-876a-59d8550a8201",
+   "metadata": {},
+   "source": [
+    "## 新增报告信息"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1acaf159-637e-4101-9881-f6bb79400136",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-19T09:08:35.287714Z",
+     "iopub.status.busy": "2023-05-19T09:08:35.286693Z",
+     "iopub.status.idle": "2023-05-19T09:08:35.304177Z",
+     "shell.execute_reply": "2023-05-19T09:08:35.303461Z",
+     "shell.execute_reply.started": "2023-05-19T09:08:35.287667Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
+    "mydb = myclient[\"baogao\"]\n",
+    "mycol = mydb[\"pdf\"]\n",
+    "\n",
+    "mydict = { \"place\": \"714309\",\"code\":\"4\",\"name\": \"朱维\",  }\n",
+    " \n",
+    "x = mycol.insert_one(mydict) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ad3078ac-ae53-4bb4-95bd-387631092bf1",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-20T04:06:02.667541Z",
+     "iopub.status.busy": "2023-05-20T04:06:02.667013Z",
+     "iopub.status.idle": "2023-05-20T04:06:02.681377Z",
+     "shell.execute_reply": "2023-05-20T04:06:02.680428Z",
+     "shell.execute_reply.started": "2023-05-20T04:06:02.667502Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'_id': ObjectId('64673c9319e8481e9c0ad1a3'), 'place': '714309', 'code': '4', 'name': '朱维'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
+    "mydb = myclient[\"baogao\"]\n",
+    "mycol = mydb[\"pdf\"]\n",
+    "\n",
+    "mydict = { \"place\": \"714309\",\"code\":\"4\",\"name\": \"朱维\",  }\n",
+    " \n",
+    "x = mycol.find_one(mydict) \n",
+    "print(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc0571b6-1da5-4bcc-96ad-5613cd1198e3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

体测单位/燕山石化.ipynb

@@ -10,15 +10,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 10,
    "id": "1b92b7c5-cb77-49da-95b7-34827ecf1d16",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-16T06:27:55.181932Z",
+     "iopub.execute_input": "2023-05-18T12:36:59.824733Z",
-     "iopub.status.busy": "2023-05-16T06:27:55.181018Z",
+     "iopub.status.busy": "2023-05-18T12:36:59.824148Z",
-     "iopub.status.idle": "2023-05-16T06:27:57.546786Z",
+     "iopub.status.idle": "2023-05-18T12:37:02.051168Z",
-     "shell.execute_reply": "2023-05-16T06:27:57.545822Z",
+     "shell.execute_reply": "2023-05-18T12:37:02.050045Z",
-     "shell.execute_reply.started": "2023-05-16T06:27:55.181895Z"
+     "shell.execute_reply.started": "2023-05-18T12:36:59.824691Z"
     },
     "tags": []
    },
@@ -27,9 +27,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "8206\n",
+      "8208\n",
-      "8171\n",
+      "8208\n",
-      "8109\n",
+      "8208\n",
       "ok\n"
      ]
     }
@@ -76,19 +76,19 @@
     "        if sheet.cell(n,12).value is not None:\n",
     "            dict1['工作性质'] = sheet.cell(n, 11).value\n",
     "        person[code] = dict1\n",
-    "jianyuan = [6484,7110,6441,6541,6543,6549,6555,6600,2958,2981,3033,3231,3249,3287,3228,7741,7749,7794,7799,7806,7837,7863,7870,7880,7894,7895,7904,7936,7947,7953,7958,7968,7969,7974,8086,8114]\n",
+    "#jianyuan = [6484,7110,6441,6541,6543,6549,6555,6600,2958,2981,3033,3231,3249,3287,3228,7741,7749,7794,7799,7806,7837,7863,7870,7880,7894,7895,7904,7936,7947,7953,7958,7968,7969,7974,8086,8114]\n",
     "\n",
     "print(len(person))\n",
-    "for k in jianyuan:\n",
+    "#for k in jianyuan:\n",
-    "    if k in person.keys():\n",
+    "#    if k in person.keys():\n",
-    "        del person[k]\n",
+    "#        del person[k]\n",
     "print(len(person))\n",
-    "bianwai =[449,6839]\n",
+    "#bianwai =[449,6839]\n",
-    "for i in range(7139,7200):\n",
+    "#for i in range(7139,7200):\n",
-    "    bianwai.append(i)\n",
+    "#    bianwai.append(i)\n",
-    "for k in bianwai:\n",
+    "#for k in bianwai:\n",
-    "    if k in person.keys():\n",
+    "#    if k in person.keys():\n",
-    "        del person[k]\n",
+    "#        del person[k]\n",
     "print(len(person))\n",
     "filename = 'data/燕山石化人员名单.json'\n",
     "with open(filename, 'w') as fl:\n",
@@ -106,15 +106,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 4,
    "id": "71e1ec6a-6797-4496-969a-1d1461b9ea58",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-16T08:36:31.303752Z",
+     "iopub.execute_input": "2023-05-17T08:58:25.400000Z",
-     "iopub.status.busy": "2023-05-16T08:36:31.302937Z",
+     "iopub.status.busy": "2023-05-17T08:58:25.399131Z",
-     "iopub.status.idle": "2023-05-16T08:36:31.711617Z",
+     "iopub.status.idle": "2023-05-17T08:58:25.810982Z",
-     "shell.execute_reply": "2023-05-16T08:36:31.710715Z",
+     "shell.execute_reply": "2023-05-17T08:58:25.810241Z",
-     "shell.execute_reply.started": "2023-05-16T08:36:31.303711Z"
+     "shell.execute_reply.started": "2023-05-17T08:58:25.399960Z"
     },
     "tags": []
    },
@@ -123,12 +123,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "214\n",
+      "133\n",
-      "8151 赵春先 已测试！\n",
+      "2004 刘鹏 已测试！\n",
-      "999 张术申 已测试！\n",
+      "133\n",
-      "2709 刘巍 已测试！\n",
+      "7730\n"
-      "214\n",
-      "7598\n"
      ]
     }
    ],
@@ -151,7 +149,7 @@
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl) \n",
     "\n",
-    "filename = 'data/places_result_20230516.csv'\n",
+    "filename = 'data/places_result_20230517.csv'\n",
     "with open(filename,'r',newline='') as csv_file:\n",
     "    fl = csv.reader(csv_file,delimiter=',')\n",
     "    header = next(fl)    \n",
@@ -184,7 +182,7 @@
     "    else:\n",
     "        for k1,v1 in v.items():\n",
     "            dict2[k][k1] = v1\n",
-    "filename = 'data/result_燕山石化（20230516）.json'\n",
+    "filename = 'data/result_燕山石化（20230517）.json'\n",
     "with open(filename,'w') as fl:\n",
     "    json.dump(re_ta, fl, ensure_ascii=False) \n",
     "print(len(re_ta))\n",
@@ -204,15 +202,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 5,
    "id": "c24880ad-bbbd-4ad8-a894-cbcea389e822",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-16T08:37:27.708591Z",
+     "iopub.execute_input": "2023-05-17T09:00:37.129834Z",
-     "iopub.status.busy": "2023-05-16T08:37:27.707778Z",
+     "iopub.status.busy": "2023-05-17T09:00:37.129418Z",
-     "iopub.status.idle": "2023-05-16T08:37:27.839300Z",
+     "iopub.status.idle": "2023-05-17T09:00:37.212119Z",
-     "shell.execute_reply": "2023-05-16T08:37:27.838623Z",
+     "shell.execute_reply": "2023-05-17T09:00:37.211419Z",
-     "shell.execute_reply.started": "2023-05-16T08:37:27.708561Z"
+     "shell.execute_reply.started": "2023-05-17T09:00:37.129806Z"
     },
     "tags": []
    },
@@ -224,7 +222,7 @@
     "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','车间','班组','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_燕山石化（20230516）.json'\n",
+    "filename = 'data/result_燕山石化（20230517）.json'\n",
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl)\n",
     "\n",
@@ -249,7 +247,7 @@
     "        else:\n",
     "            list2.append('') \n",
     "    list1.append(list2)\n",
-    "filename = 'data/燕山石化体测情况表(20230516).xlsx'\n",
+    "filename = 'data/燕山石化体测情况表(20230517).xlsx'\n",
     "wb = openpyxl.Workbook()\n",
     "sheet = wb.active\n",
     "sheet.append(title)\n",
@@ -269,15 +267,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 198,
+   "execution_count": 12,
    "id": "79c9c728-12e9-4107-bc5a-8c3e3d8b64a6",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-08T00:52:23.460649Z",
+     "iopub.execute_input": "2023-05-18T12:37:39.026994Z",
-     "iopub.status.busy": "2023-05-08T00:52:23.459824Z",
+     "iopub.status.busy": "2023-05-18T12:37:39.026072Z",
-     "iopub.status.idle": "2023-05-08T00:52:25.090804Z",
+     "iopub.status.idle": "2023-05-18T12:37:41.214470Z",
-     "shell.execute_reply": "2023-05-08T00:52:25.090044Z",
+     "shell.execute_reply": "2023-05-18T12:37:41.213773Z",
-     "shell.execute_reply.started": "2023-05-08T00:52:23.460608Z"
+     "shell.execute_reply.started": "2023-05-18T12:37:39.026953Z"
     },
     "tags": []
    },
@@ -289,7 +287,7 @@
     "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','车间','班组','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_燕山石化.json'\n",
+    "filename = 'data/result_燕山石化-all.json'\n",
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl)\n",
     "\n",
@@ -314,7 +312,7 @@
     "        else:\n",
     "            list2.append('') \n",
     "    list1.append(list2)\n",
-    "filename = 'data/燕山石化体测情况表(截至20230506).xlsx'\n",
+    "filename = 'data/燕山石化体测情况表.xlsx'\n",
     "wb = openpyxl.Workbook()\n",
     "sheet = wb.active\n",
     "sheet.append(title)\n",
@@ -523,15 +521,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "id": "641863ef-324f-4c33-a0a9-699031afb6f1",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-11T04:50:37.384699Z",
+     "iopub.execute_input": "2023-05-17T01:34:11.475000Z",
-     "iopub.status.busy": "2023-05-11T04:50:37.383858Z",
+     "iopub.status.busy": "2023-05-17T01:34:11.474266Z",
-     "iopub.status.idle": "2023-05-11T04:50:37.543557Z",
+     "iopub.status.idle": "2023-05-17T01:34:11.673023Z",
-     "shell.execute_reply": "2023-05-11T04:50:37.542638Z",
+     "shell.execute_reply": "2023-05-17T01:34:11.672256Z",
-     "shell.execute_reply.started": "2023-05-11T04:50:37.384657Z"
+     "shell.execute_reply.started": "2023-05-17T01:34:11.474959Z"
     },
     "tags": []
    },
@@ -540,7 +538,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[['4025', '马珺', '教育培训中心工会', '身高,体重,选择反应时'], ['7790', '吴志鹏', '生产运行保障中心', '身高,体重,握力'], ['8151', '赵春先', '合成树脂厂', '身高,体重,握力'], ['7682', '孙宏林', '有机化工厂工会', '肺活量,身高,体重'], ['2004', '刘鹏', '合成树脂厂', '身高,体重,握力'], ['3125', '李志斌', '化学品厂工会', '身高,体重,握力']]\n"
+      "[['4025', '马珺', '教育培训中心工会', '身高,体重,选择反应时'], ['7790', '吴志鹏', '生产运行保障中心', '身高,体重,握力'], ['3377', '安明海', '检验计量中心工会', '俯卧撑,纵跳'], ['3520', '于海军', '检验计量中心工会', '握力'], ['3125', '李志斌', '化学品厂工会', '身高,体重,握力'], ['5690', '胡勇', '热电厂工会', '身高,体重'], ['4551', '韩立江', '炼油厂工会', '身高,体重'], ['8150', '王重荃', '高科公司工会', '台阶指数']]\n"
      ]
     }
    ],
@@ -566,7 +564,7 @@
     "    dict3[k] = list1\n",
     "list1 = []\n",
     "for k, v in dict3.items():\n",
-    "    if len(v)<4 and '身高' in v and '体重' in v:\n",
+    "    if len(v)<4 and '身高' in v and '体重' in v or ((len(v)<3 and '身高' not in v and '体重' not in v)):\n",
     "        list2 = []\n",
     "        xm = ','.join(v)\n",
     "        list2.append(k)\n",
@@ -575,7 +573,7 @@
     "        list2.append(xm)\n",
     "        list1.append(list2)\n",
     "print(list1)\n",
-    "filename = 'data/燕山石化测试项目不足人员（截止5月11日）.xlsx'\n",
+    "filename = 'data/燕山石化测试项目不足人员（截止5月16日）.xlsx'\n",
     "wb = openpyxl.Workbook()\n",
     "sheet = wb.active\n",
     "#sheet.append(title)\n",
@@ -595,15 +593,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 11,
    "id": "b735248a-c1b0-4e90-8df4-37cd7625cb1a",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-05-14T14:16:50.290820Z",
+     "iopub.execute_input": "2023-05-18T12:37:18.648377Z",
-     "iopub.status.busy": "2023-05-14T14:16:50.290016Z",
+     "iopub.status.busy": "2023-05-18T12:37:18.647570Z",
-     "iopub.status.idle": "2023-05-14T14:16:51.077768Z",
+     "iopub.status.idle": "2023-05-18T12:37:19.435077Z",
-     "shell.execute_reply": "2023-05-14T14:16:51.076992Z",
+     "shell.execute_reply": "2023-05-18T12:37:19.434303Z",
-     "shell.execute_reply.started": "2023-05-14T14:16:50.290789Z"
+     "shell.execute_reply.started": "2023-05-18T12:37:18.648344Z"
     },
     "tags": []
    },
@@ -612,8 +610,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "7117\n",
+      "7734\n",
-      "7117\n"
+      "7734\n"
      ]
     }
    ],
@@ -636,7 +634,7 @@
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl) \n",
     "\n",
-    "filename = 'data/places_result_20230514.csv'\n",
+    "filename = 'data/places_result_20230518.csv'\n",
     "with open(filename,'r',newline='') as csv_file:\n",
     "    fl = csv.reader(csv_file,delimiter=',')\n",
     "    header = next(fl)    \n",
@@ -664,6 +662,63 @@
     "print(len(re_ta))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "fbdf2c54-7303-43ad-bbec-0fbcd033603a",
+   "metadata": {},
+   "source": [
+    "## 统计测试人数"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "6d10738f-8da8-4f18-970b-e67433a06661",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-05-18T12:55:07.441554Z",
+     "iopub.status.busy": "2023-05-18T12:55:07.440708Z",
+     "iopub.status.idle": "2023-05-18T12:55:07.819534Z",
+     "shell.execute_reply": "2023-05-18T12:55:07.818801Z",
+     "shell.execute_reply.started": "2023-05-18T12:55:07.441512Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "7734\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import time\n",
+    "import csv\n",
+    "\n",
+    "person = set()\n",
+    "filename = 'data/places_result_20230518.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",
+    "filename = 'data/燕山石化人员名单.json'\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict1 = json.load(fl) \n",
+    "\n",
+    "for result in list1:\n",
+    "    user = str(result[2])\n",
+    "    if user in dict1.keys():\n",
+    "        person.add(user)\n",
+    "\n",
+    "print(len(person))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5bdcad97-309f-4d29-82c4-b53c68b9ee22",