From 82acaa07a8b86a20ef191091f50796a60bcc1971 Mon Sep 17 00:00:00 2001 From: 512song Date: Sun, 23 Feb 2025 18:18:10 +0800 Subject: [PATCH] 20250223 --- 体测单位/延庆.ipynb | 56 +++--- 体测单位/青海.ipynb | 442 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 468 insertions(+), 30 deletions(-) diff --git a/体测单位/延庆.ipynb b/体测单位/延庆.ipynb index 3139ec1..cdf16f4 100644 --- a/体测单位/延庆.ipynb +++ b/体测单位/延庆.ipynb @@ -10,15 +10,15 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 1, "id": "3d5ddc7a-a331-438d-aa8d-1ad74c7250d0", "metadata": { "execution": { - "iopub.execute_input": "2025-02-16T15:21:01.891534Z", - "iopub.status.busy": "2025-02-16T15:21:01.890870Z", - "iopub.status.idle": "2025-02-16T15:21:01.912369Z", - "shell.execute_reply": "2025-02-16T15:21:01.911830Z", - "shell.execute_reply.started": "2025-02-16T15:21:01.891472Z" + "iopub.execute_input": "2025-02-23T10:13:29.334391Z", + "iopub.status.busy": "2025-02-23T10:13:29.333636Z", + "iopub.status.idle": "2025-02-23T10:13:29.512654Z", + "shell.execute_reply": "2025-02-23T10:13:29.511636Z", + "shell.execute_reply.started": "2025-02-23T10:13:29.334322Z" } }, "outputs": [ @@ -65,15 +65,15 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 2, "id": "72ec680f-ec0d-44f9-919c-17c8e614b885", "metadata": { "execution": { - "iopub.execute_input": "2025-02-16T15:25:46.643327Z", - "iopub.status.busy": "2025-02-16T15:25:46.642655Z", - "iopub.status.idle": "2025-02-16T15:25:46.658469Z", - "shell.execute_reply": "2025-02-16T15:25:46.657469Z", - "shell.execute_reply.started": "2025-02-16T15:25:46.643266Z" + "iopub.execute_input": "2025-02-23T10:13:35.977412Z", + "iopub.status.busy": "2025-02-23T10:13:35.976513Z", + "iopub.status.idle": "2025-02-23T10:13:35.998305Z", + "shell.execute_reply": "2025-02-23T10:13:35.997869Z", + "shell.execute_reply.started": "2025-02-23T10:13:35.977335Z" } }, "outputs": [ @@ -81,7 +81,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "28\n" + "113\n" ] } ], @@ -98,7 +98,7 @@ "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "\n", - "filename = 'data/marks_20250216.csv'\n", + "filename = 'data/marks_20250223.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", @@ -149,15 +149,15 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 3, "id": "8f459ed3-fc14-404f-998b-5ed2a15958c3", "metadata": { "execution": { - "iopub.execute_input": "2025-02-16T15:26:06.721842Z", - "iopub.status.busy": "2025-02-16T15:26:06.721214Z", - "iopub.status.idle": "2025-02-16T15:26:06.738331Z", - "shell.execute_reply": "2025-02-16T15:26:06.737149Z", - "shell.execute_reply.started": "2025-02-16T15:26:06.721782Z" + "iopub.execute_input": "2025-02-23T10:13:40.888693Z", + "iopub.status.busy": "2025-02-23T10:13:40.887898Z", + "iopub.status.idle": "2025-02-23T10:13:40.910971Z", + "shell.execute_reply": "2025-02-23T10:13:40.910112Z", + "shell.execute_reply.started": "2025-02-23T10:13:40.888581Z" } }, "outputs": [ @@ -370,15 +370,15 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 5, "id": "f44c57ed-aac8-481a-9126-0dadcbe0190c", "metadata": { "execution": { - "iopub.execute_input": "2025-02-16T15:36:05.627841Z", - "iopub.status.busy": "2025-02-16T15:36:05.627122Z", - "iopub.status.idle": "2025-02-16T15:36:05.655606Z", - "shell.execute_reply": "2025-02-16T15:36:05.655044Z", - "shell.execute_reply.started": "2025-02-16T15:36:05.627774Z" + "iopub.execute_input": "2025-02-23T10:14:06.379557Z", + "iopub.status.busy": "2025-02-23T10:14:06.379298Z", + "iopub.status.idle": "2025-02-23T10:14:06.424726Z", + "shell.execute_reply": "2025-02-23T10:14:06.424184Z", + "shell.execute_reply.started": "2025-02-23T10:14:06.379536Z" } }, "outputs": [ @@ -396,7 +396,7 @@ "\n", "items = ['lung','grip','flexion','jump','pushup','situp','balance','reaction','step']\n", "bmi = ['height','weight']\n", - "title = ['编号','姓名','性别','身高','体重','bmi','肺活量','得分','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','身高','体重','bmi','肺活量','得分','握力','得分','坐位体前屈','得分','纵跳','得分','俯卧撑','得分','一分钟仰卧起坐','得分','单脚站立','得分','选择反应时','得分','台阶指数','得分']\n", "\n", "filename = 'data/result_延庆人员.json'\n", "with open(filename,'r') as fl:\n", @@ -432,7 +432,7 @@ " list2.append('') \n", " if i>2:\n", " list1.append(list2)\n", - "filename = 'data/延庆体测情况表250216.xlsx'\n", + "filename = 'data/延庆体测情况表250223.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "sheet.append(title)\n", diff --git a/体测单位/青海.ipynb b/体测单位/青海.ipynb index 723795b..3e20535 100644 --- a/体测单位/青海.ipynb +++ b/体测单位/青海.ipynb @@ -3,7 +3,9 @@ { "cell_type": "markdown", "id": "511a2aee-e09b-475a-a201-f6e1c72e053b", - "metadata": {}, + "metadata": { + "jp-MarkdownHeadingCollapsed": true + }, "source": [ "# 体测数据处理" ] @@ -1282,8 +1284,444 @@ }, { "cell_type": "markdown", - "id": "1208eb16-a220-48c4-8c9e-cc4dbf67306e", + "id": "8feaa7bb-92dd-44ab-9869-c601d468b4b8", "metadata": {}, + "source": [ + "# 体测数据处理（2025年）" + ] + }, + { + "cell_type": "markdown", + "id": "54ed5a3c-ba4d-463f-83f7-3c621142f7bb", + "metadata": {}, + "source": [ + "## 体测人员导入" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "80a24c3c-8f7d-4c02-a5ee-3daa438ca35b", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-20T01:27:26.442760Z", + "iopub.status.busy": "2025-01-20T01:27:26.442000Z", + "iopub.status.idle": "2025-01-20T01:27:26.468889Z", + "shell.execute_reply": "2025-01-20T01:27:26.468324Z", + "shell.execute_reply.started": "2025-01-20T01:27:26.442687Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "81 ok\n" + ] + } + ], + "source": [ + "import openpyxl\n", + "import json\n", + "\n", + "\n", + "wb = openpyxl.load_workbook('data/青海2025.xlsx')\n", + "sheet = wb.active\n", + "# sheets = wb.sheetnames\n", + "person = {}\n", + "\n", + "for n in range(2, sheet.max_row+1):\n", + " if sheet.cell(n, 1).value is not None:\n", + " #print(sheet.cell(n, 1).value)\n", + " code = int(sheet.cell(n, 1).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, 2).value\n", + " dict1['phone'] = int(sheet.cell(n, 6).value)\n", + " dict1['birth'] = str(sheet.cell(n, 5).value).replace('/','-').split(' ')[0]\n", + " person[code] = dict1\n", + "\n", + "filename = 'data/青海人员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": "90ce631b-0eeb-4d27-965a-7efa09332139", + "metadata": {}, + "source": [ + "## 获取人员测试成绩" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "905dbd60-ef28-4bf4-85a2-5b2e6543dcfe", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-20T01:12:15.444982Z", + "iopub.status.busy": "2025-01-20T01:12:15.444234Z", + "iopub.status.idle": "2025-01-20T01:12:15.461283Z", + "shell.execute_reply": "2025-01-20T01:12:15.460768Z", + "shell.execute_reply.started": "2025-01-20T01:12:15.444909Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "72\n" + ] + } + ], + "source": [ + "import json\n", + "import datetime\n", + "import csv\n", + "from datetime import date\n", + "\n", + "\n", + "re_ta = {}\n", + "list1 = []\n", + "filename = 'data/青海人员2025.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl) \n", + "\n", + "filename = 'data/marks_20250118.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", + "\n", + "for result in list1:\n", + " user = str(result[2])\n", + " rq = date.fromisoformat(result[5].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 'phone' in dict1[user].keys():\n", + " re_ta[user]['phone'] = dict1[user]['phone']\n", + " if dict1[user]['sex'] == '男':\n", + " l_xm = ['bmi','lung','grip','flexion','jump','pushup','balance','reaction','step']\n", + " else:\n", + " l_xm = ['bmi','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", + " item_name = result[3] \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[5]\n", + " re_ta[user].setdefault(item_name,{}) \n", + " score = result[4] \n", + " re_ta[user][item_name]['成绩'] = score\n", + "\n", + "filename = 'data/result_青海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": "c6ede59a-e5a0-489b-853f-f317e12b1fa3", + "metadata": {}, + "source": [ + "## 导出测试人员信息" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "f3d39079-fa3a-400c-990e-75a8a0a7b42d", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-20T01:12:49.821141Z", + "iopub.status.busy": "2025-01-20T01:12:49.820394Z", + "iopub.status.idle": "2025-01-20T01:12:49.854877Z", + "shell.execute_reply": "2025-01-20T01:12:49.854327Z", + "shell.execute_reply.started": "2025-01-20T01:12:49.821069Z" + } + }, + "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','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_青海2025.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl)\n", + "\n", + "filename = 'data/青海人员2025.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/青海体测情况表2025.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": "a19c9733-7af5-4dc6-a0ca-cc35069f532a", + "metadata": {}, + "source": [ + "## 统计参加问卷人员" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "f0ee678a-1dd1-4928-a198-df0ff5142f89", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-20T01:27:43.425720Z", + "iopub.status.busy": "2025-01-20T01:27:43.425142Z", + "iopub.status.idle": "2025-01-20T01:27:43.449977Z", + "shell.execute_reply": "2025-01-20T01:27:43.449445Z", + "shell.execute_reply.started": "2025-01-20T01:27:43.425664Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "80\n" + ] + } + ], + "source": [ + "import json\n", + "import csv\n", + "import openpyxl\n", + "import time\n", + "from datetime import date\n", + "\n", + "\n", + "filename = 'data/青海人员2025.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_20250118.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(len(phone1))\n", + "i =1\n", + "list2 = []\n", + "for item in list1:\n", + " code = int(item[2])\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/青海问卷情况表2025.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": "19aaf610-b15d-45c8-b22e-c56e9b8d8450", + "metadata": {}, + "source": [ + "## 统计问卷人员手机号码未登记" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "00eb991d-771f-4ff4-af9f-35a0d3b64581", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-20T01:27:34.074005Z", + "iopub.status.busy": "2025-01-20T01:27:34.073295Z", + "iopub.status.idle": "2025-01-20T01:27:34.085198Z", + "shell.execute_reply": "2025-01-20T01:27:34.084107Z", + "shell.execute_reply.started": "2025-01-20T01:27:34.073939Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "80\n" + ] + } + ], + "source": [ + "import json\n", + "import csv\n", + "import openpyxl\n", + "import time\n", + "from datetime import date\n", + "\n", + "\n", + "filename = 'data/青海人员2025.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_20250118.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(len(phone1))\n", + "i =1\n", + "list2 = []\n", + "for item in list1:\n", + " code = int(item[2])\n", + " if code not in phone1:\n", + " content = json.loads(item[5])\n", + " if 'name' in content.keys():\n", + " print(code,content['name'])" + ] + }, + { + "cell_type": "markdown", + "id": "9cabe52a-2862-4ba8-847f-d685df1060cd", + "metadata": {}, + "source": [ + "## 统计未参加问卷人员" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "d91e74d4-22f0-4db2-bad4-717f7537c043", + "metadata": { + "execution": { + "iopub.execute_input": "2025-01-22T05:32:09.347446Z", + "iopub.status.busy": "2025-01-22T05:32:09.346691Z", + "iopub.status.idle": "2025-01-22T05:32:09.373252Z", + "shell.execute_reply": "2025-01-22T05:32:09.372574Z", + "shell.execute_reply.started": "2025-01-22T05:32:09.347377Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "45\n" + ] + } + ], + "source": [ + "import json\n", + "import csv\n", + "import openpyxl\n", + "import time\n", + "from datetime import date\n", + "\n", + "\n", + "filename = 'data/青海人员2025.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_20250118.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", + " phone2.add(int(line[2]))\n", + "print(len(phone2))\n", + "i =1\n", + "\n", + "for k, v in dict1.items():\n", + " if v['phone'] not in phone2:\n", + " list2 = []\n", + " list2 = [k,v['name'],v['sex'],v['phone']]\n", + " list1.append(list2)\n", + "filename = 'data/青海未参加问卷人员2025.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": "1208eb16-a220-48c4-8c9e-cc4dbf67306e", + "metadata": { + "jp-MarkdownHeadingCollapsed": true + }, "source": [ "# 体测数据分析" ]