From e9356da639f5f0d2449b58d2c6cce3a76f870af6 Mon Sep 17 00:00:00 2001 From: "512song@sina.com" Date: Sat, 14 Jan 2023 18:00:03 +0800 Subject: [PATCH] 20230114 --- 体测单位/天津石化.ipynb | 408 ++++++++++++++++++++++++++++++---------- 1 file changed, 305 insertions(+), 103 deletions(-) diff --git a/体测单位/天津石化.ipynb b/体测单位/天津石化.ipynb index b5ecdd9..4f38f71 100644 --- a/体测单位/天津石化.ipynb +++ b/体测单位/天津石化.ipynb @@ -830,27 +830,12 @@ }, { "cell_type": "code", - "execution_count": 151, + "execution_count": null, "id": "6e6f6a63-b297-42e8-a9ba-b2636fda5d09", "metadata": { - "execution": { - "iopub.execute_input": "2023-01-14T01:56:50.048701Z", - "iopub.status.busy": "2023-01-14T01:56:50.047669Z", - "iopub.status.idle": "2023-01-14T01:56:50.449993Z", - "shell.execute_reply": "2023-01-14T01:56:50.448696Z", - "shell.execute_reply.started": "2023-01-14T01:56:50.048628Z" - }, "tags": [] }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ok\n" - ] - } - ], + "outputs": [], "source": [ "import json\n", "import openpyxl\n", @@ -878,27 +863,12 @@ }, { "cell_type": "code", - "execution_count": 149, + "execution_count": null, "id": "4d77ec9b-c561-4355-98af-b18c42c1f3ca", "metadata": { - "execution": { - "iopub.execute_input": "2023-01-14T01:56:10.352541Z", - "iopub.status.busy": "2023-01-14T01:56:10.352010Z", - "iopub.status.idle": "2023-01-14T01:56:13.111656Z", - "shell.execute_reply": "2023-01-14T01:56:13.110214Z", - "shell.execute_reply.started": "2023-01-14T01:56:10.352494Z" - }, "tags": [] }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ok\n" - ] - } - ], + "outputs": [], "source": [ "import openpyxl\n", "import json\n", @@ -941,27 +911,12 @@ }, { "cell_type": "code", - "execution_count": 150, + "execution_count": null, "id": "db473c01-7e1a-48c4-a0d7-e44cdeb9e24b", "metadata": { - "execution": { - "iopub.execute_input": "2023-01-14T01:56:24.524792Z", - "iopub.status.busy": "2023-01-14T01:56:24.524267Z", - "iopub.status.idle": "2023-01-14T01:56:24.967568Z", - "shell.execute_reply": "2023-01-14T01:56:24.966212Z", - "shell.execute_reply.started": "2023-01-14T01:56:24.524745Z" - }, "tags": [] }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ok\n" - ] - } - ], + "outputs": [], "source": [ "import json\n", "import openpyxl\n", @@ -996,27 +951,12 @@ }, { "cell_type": "code", - "execution_count": 152, + "execution_count": null, "id": "224cdee4-153f-424a-aaaa-92ef58943edb", "metadata": { - "execution": { - "iopub.execute_input": "2023-01-14T01:56:53.363160Z", - "iopub.status.busy": "2023-01-14T01:56:53.362570Z", - "iopub.status.idle": "2023-01-14T01:56:53.912576Z", - "shell.execute_reply": "2023-01-14T01:56:53.911169Z", - "shell.execute_reply.started": "2023-01-14T01:56:53.363112Z" - }, "tags": [] }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ok\n" - ] - } - ], + "outputs": [], "source": [ "import json\n", "\n", @@ -1042,6 +982,14 @@ " 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", @@ -1066,15 +1014,264 @@ }, { "cell_type": "code", - "execution_count": 168, + "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": 183, + "id": "695b4933-b8c3-4be6-a024-742a982f0abb", "metadata": { "execution": { - "iopub.execute_input": "2023-01-14T03:54:06.706899Z", - "iopub.status.busy": "2023-01-14T03:54:06.706358Z", - "iopub.status.idle": "2023-01-14T03:54:06.815555Z", - "shell.execute_reply": "2023-01-14T03:54:06.814512Z", - "shell.execute_reply.started": "2023-01-14T03:54:06.706851Z" + "iopub.execute_input": "2023-01-14T08:57:36.572541Z", + "iopub.status.busy": "2023-01-14T08:57:36.571983Z", + "iopub.status.idle": "2023-01-14T08:57:36.671348Z", + "shell.execute_reply": "2023-01-14T08:57:36.670273Z", + "shell.execute_reply.started": "2023-01-14T08:57:36.572493Z" + }, + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{2: {'男': {'num': 700, 'score': 1913.639999999998, 'zhongyi': 91, 'pianpo': 73}, '女': {'num': 550, 'score': 1736.5499999999988, 'zhongyi': 47, 'pianpo': 43}}, 1: {'男': {'num': 465, 'score': 1291.3899999999994, 'zhongyi': 153, 'pianpo': 119}, '女': {'num': 265, 'score': 846.3700000000005, 'zhongyi': 47, 'pianpo': 45}}, 3: {'男': {'num': 1161, 'score': 3063.0399999999995, 'zhongyi': 144, 'pianpo': 109}, '女': {'num': 279, 'score': 865.81, 'zhongyi': 39, 'pianpo': 34}}, 4: {'男': {'num': 163, 'score': 406.15000000000003, 'zhongyi': 23, 'pianpo': 19}}, 0: {'女': {'num': 405, 'score': 1218.0100000000002, 'zhongyi': 40, 'pianpo': 27}, '男': {'num': 737, 'score': 1971.2600000000007, 'zhongyi': 87, 'pianpo': 44}}, 5: {'男': {'num': 1, 'score': 2.57, 'zhongyi': 0, 'pianpo': 0}}}\n" + ] + } + ], + "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": 188, + "id": "181ff60b-3372-441a-8cd7-29e8de66ceb8", + "metadata": { + "execution": { + "iopub.execute_input": "2023-01-14T09:14:36.031368Z", + "iopub.status.busy": "2023-01-14T09:14:36.030813Z", + "iopub.status.idle": "2023-01-14T09:14:36.136340Z", + "shell.execute_reply": "2023-01-14T09:14:36.135039Z", + "shell.execute_reply.started": "2023-01-14T09:14:36.031320Z" + }, + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{2: {'num': 1250, 'score': 3650.189999999998, 'zhongyi': 138, 'pianpo': 116}, 1: {'num': 730, 'score': 2137.7599999999993, 'zhongyi': 200, 'pianpo': 164}, 3: {'num': 1440, 'score': 3928.850000000005, 'zhongyi': 183, 'pianpo': 143}, 4: {'num': 163, 'score': 406.15000000000003, 'zhongyi': 23, 'pianpo': 19}, 0: {'num': 1142, 'score': 3189.270000000001, 'zhongyi': 127, 'pianpo': 71}, 5: {'num': 1, 'score': 2.57, 'zhongyi': 0, 'pianpo': 0}}\n", + "ok!\n" + ] + } + ], + "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": 192, + "id": "d5ab1a99-cb3e-4905-8c05-a6122ea09913", + "metadata": { + "execution": { + "iopub.execute_input": "2023-01-14T09:22:28.467869Z", + "iopub.status.busy": "2023-01-14T09:22:28.467341Z", + "iopub.status.idle": "2023-01-14T09:22:28.568909Z", + "shell.execute_reply": "2023-01-14T09:22:28.567550Z", + "shell.execute_reply.started": "2023-01-14T09:22:28.467822Z" }, "tags": [] }, @@ -1101,37 +1298,42 @@ "#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']][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", - "for k, v in dict2.items():\n", - " \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", + " 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 dict2.items():\n", + "for k, v in nl.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", - " list2 = [k,daoban,num,avg]\n", - " list1.append(list2)\n", + " gld = v\n", " \n", - "filename = 'data/天津倒班因素分析表.xlsx' \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", @@ -1145,7 +1347,7 @@ { "cell_type": "code", "execution_count": null, - "id": "4fdc1484-ea69-4779-9a75-c52784cc9c7c", + "id": "93ae7587-e49d-41c2-bd57-f89b9eed37e4", "metadata": {}, "outputs": [], "source": []