diff --git a/体测单位/体质检测数据处理.ipynb b/体测单位/体质检测数据处理.ipynb index 7612f3a..e0186e8 100644 --- a/体测单位/体质检测数据处理.ipynb +++ b/体测单位/体质检测数据处理.ipynb @@ -215,29 +215,12 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": null, "id": "b32fbbdd-eb0a-4f0d-8901-e39a727c3ff8", "metadata": { - "execution": { - "iopub.execute_input": "2023-04-30T01:48:23.869481Z", - "iopub.status.busy": "2023-04-30T01:48:23.868619Z", - "iopub.status.idle": "2023-04-30T01:48:23.882339Z", - "shell.execute_reply": "2023-04-30T01:48:23.881272Z", - "shell.execute_reply.started": "2023-04-30T01:48:23.869438Z" - }, "tags": [] }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "M50~59\n", - "177.0,81.1\n", - "5\n" - ] - } - ], + "outputs": [], "source": [ "import json\n", "import time\n", @@ -480,6 +463,54 @@ "print('ok!')" ] }, + { + "cell_type": "markdown", + "id": "12917000-59e0-4f8a-beee-929c6d7b60a0", + "metadata": {}, + "source": [ + "### 生成部门JSON文件" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5446269c-d324-4a16-b10e-f24d87178d77", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "import csv\n", + "\n", + "dict1 = {}\n", + "filename = 'data/unit_134.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['unit'] = list1\n", + "\n", + "filename = 'data/sub_unit_134.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],'unit_id':int(line[2])})\n", + "dict1['sub_unit'] = list1\n", + "print(dict1)\n", + "\n", + "filename = 'data/天津石化部门.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", @@ -577,15 +608,15 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 84, "id": "360e61e9-7895-484b-a9d6-333bdefa1a86", "metadata": { "execution": { - "iopub.execute_input": "2023-04-29T14:29:07.198753Z", - "iopub.status.busy": "2023-04-29T14:29:07.197888Z", - "iopub.status.idle": "2023-04-29T14:29:08.464741Z", - "shell.execute_reply": "2023-04-29T14:29:08.463607Z", - "shell.execute_reply.started": "2023-04-29T14:29:07.198711Z" + "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": [] }, @@ -609,6 +640,27 @@ "dict2 = {}\n", "for k, v in dict1.items():\n", " dict2[v['name']] = int(k)\n", + "\n", + "filename = 'data/天津石化部门.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", + "for k, v in dict1.items():\n", + " person[k] = {'unit':v['unit'],'sub_unit':v['sub_unit']}\n", + "\n", + " \n", "conn = psycopg2.connect(database=\"mycrm\", user=\"postgres\", password=\"songyi\", host=\"localhost\", port=\"5432\")\n", "cursor = conn.cursor()\n", "data_list = []\n", @@ -623,10 +675,15 @@ " score = None\n", " else:\n", " score = int(v[item]['得分'])\n", - " \n", - " data_list.append((v[item]['成绩'],score,int(k),item_id))\n", + " unit_name = person[k]['unit'] \n", + " sub_unit_name = person[k]['sub_unit']\n", + " unit_id = unit[unit_name]\n", + " for items in sub_unit[unit_id]:\n", + " if items['name'] ==sub_unit_name:\n", + " sub_id = items['id'] \n", + " data_list.append((v[item]['成绩'],score,int(k),item_id,unit_id,sub_id))\n", " \n", - "sql = 'insert into tianjin_records (performance,score,avatar_id_id,item_id_id) values %s'\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", "cursor.close()\n", @@ -645,13 +702,57 @@ "outputs": [], "source": [ "import json\n", + "import psycopg2\n", + "from psycopg2 import extras as ex\n", "\n", + "filename = '../item.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl) \n", + "dict2 = {}\n", + "for k, v in dict1.items():\n", + " dict2[v['name']] = int(k)\n", + "\n", + "filename = 'data/天津石化部门.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", "for k, v in dict1.items():\n", - " if 'num_id' not in v.keys():\n", - " print(k,v['name'])" + " person[k] = {'unit':v['unit'],'sub_unit':v['sub_unit']}\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", + "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", + " if v[item]['得分'] == '\\\\N':\n", + " score = None\n", + " else:\n", + " score = int(v[item]['得分'])\n", + " unit_name = person[k]['unit'] \n", + " sub_unit_name = person[k]['sub_unit']\n", + " unit_id = unit[unit_name]\n", + " for items in sub_unit[unit_id]:\n", + " if items['name'] ==sub_unit_name:\n", + " sub_id = items['id'] \n", + " print(unit_id,sub_id)" ] }, { @@ -660,7 +761,26 @@ "id": "51dc35a5-dc07-40a4-9ea7-375ca7f983c3", "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import json\n", + "import psycopg2\n", + "from psycopg2 import extras as ex\n", + "\n", + "filename = '../item.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl) \n", + "dict2 = {}\n", + "for k, v in dict1.items():\n", + " dict2[v['name']] = int(k)\n", + "\n", + "filename = 'data/天津石化部门.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", + "print(unit)" + ] } ], "metadata": { diff --git a/体测单位/燕山石化.ipynb b/体测单位/燕山石化.ipynb index 31fa0a1..da67544 100644 --- a/体测单位/燕山石化.ipynb +++ b/体测单位/燕山石化.ipynb @@ -10,15 +10,15 @@ }, { "cell_type": "code", - "execution_count": 149, + "execution_count": 153, "id": "1b92b7c5-cb77-49da-95b7-34827ecf1d16", "metadata": { "execution": { - "iopub.execute_input": "2023-04-28T23:44:56.066757Z", - "iopub.status.busy": "2023-04-28T23:44:56.065886Z", - "iopub.status.idle": "2023-04-28T23:44:58.568470Z", - "shell.execute_reply": "2023-04-28T23:44:58.567666Z", - "shell.execute_reply.started": "2023-04-28T23:44:56.066716Z" + "iopub.execute_input": "2023-05-04T11:27:38.797630Z", + "iopub.status.busy": "2023-05-04T11:27:38.796775Z", + "iopub.status.idle": "2023-05-04T11:27:41.228231Z", + "shell.execute_reply": "2023-05-04T11:27:41.227480Z", + "shell.execute_reply.started": "2023-05-04T11:27:38.797589Z" }, "tags": [] }, @@ -89,15 +89,15 @@ }, { "cell_type": "code", - "execution_count": 150, + "execution_count": 154, "id": "71e1ec6a-6797-4496-969a-1d1461b9ea58", "metadata": { "execution": { - "iopub.execute_input": "2023-04-28T23:45:21.332726Z", - "iopub.status.busy": "2023-04-28T23:45:21.331812Z", - "iopub.status.idle": "2023-04-28T23:45:21.591418Z", - "shell.execute_reply": "2023-04-28T23:45:21.590691Z", - "shell.execute_reply.started": "2023-04-28T23:45:21.332693Z" + "iopub.execute_input": "2023-05-04T11:27:59.843239Z", + "iopub.status.busy": "2023-05-04T11:27:59.842790Z", + "iopub.status.idle": "2023-05-04T11:28:00.142474Z", + "shell.execute_reply": "2023-05-04T11:28:00.141539Z", + "shell.execute_reply.started": "2023-05-04T11:27:59.843195Z" }, "tags": [] }, @@ -106,10 +106,9 @@ "name": "stdout", "output_type": "stream", "text": [ - "335\n", - "123 孙剑 已测试！\n", - "335\n", - "4136\n" + "466\n", + "466\n", + "4602\n" ] } ], @@ -132,7 +131,7 @@ "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "\n", - "filename = 'data/places_result_20230428.csv'\n", + "filename = 'data/places_result_20230504.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", @@ -165,7 +164,7 @@ " else:\n", " for k1,v1 in v.items():\n", " dict2[k][k1] = v1\n", - "filename = 'data/result_燕山石化（20230428）.json'\n", + "filename = 'data/result_燕山石化（20230504）.json'\n", "with open(filename,'w') as fl:\n", " json.dump(re_ta, fl, ensure_ascii=False) \n", "print(len(re_ta))\n", @@ -185,15 +184,15 @@ }, { "cell_type": "code", - "execution_count": 151, + "execution_count": 156, "id": "c24880ad-bbbd-4ad8-a894-cbcea389e822", "metadata": { "execution": { - "iopub.execute_input": "2023-04-28T23:46:14.648250Z", - "iopub.status.busy": "2023-04-28T23:46:14.647361Z", - "iopub.status.idle": "2023-04-28T23:46:14.803308Z", - "shell.execute_reply": "2023-04-28T23:46:14.802604Z", - "shell.execute_reply.started": "2023-04-28T23:46:14.648208Z" + "iopub.execute_input": "2023-05-04T11:28:48.304876Z", + "iopub.status.busy": "2023-05-04T11:28:48.304030Z", + "iopub.status.idle": "2023-05-04T11:28:48.493153Z", + "shell.execute_reply": "2023-05-04T11:28:48.492438Z", + "shell.execute_reply.started": "2023-05-04T11:28:48.304834Z" }, "tags": [] }, @@ -205,7 +204,7 @@ "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（20230428）.json'\n", + "filename = 'data/result_燕山石化（20230504）.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", @@ -230,7 +229,7 @@ " else:\n", " list2.append('') \n", " list1.append(list2)\n", - "filename = 'data/燕山石化体测情况表(20230428).xlsx'\n", + "filename = 'data/燕山石化体测情况表(20230504).xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "sheet.append(title)\n", @@ -250,15 +249,15 @@ }, { "cell_type": "code", - "execution_count": 152, + "execution_count": 157, "id": "68454877-f1fe-4eed-8a48-265e428f892e", "metadata": { "execution": { - "iopub.execute_input": "2023-04-28T23:46:28.786698Z", - "iopub.status.busy": "2023-04-28T23:46:28.786246Z", - "iopub.status.idle": "2023-04-28T23:46:28.816358Z", - "shell.execute_reply": "2023-04-28T23:46:28.815328Z", - "shell.execute_reply.started": "2023-04-28T23:46:28.786667Z" + "iopub.execute_input": "2023-05-04T11:29:06.618769Z", + "iopub.status.busy": "2023-05-04T11:29:06.617928Z", + "iopub.status.idle": "2023-05-04T11:29:06.651954Z", + "shell.execute_reply": "2023-05-04T11:29:06.651052Z", + "shell.execute_reply.started": "2023-05-04T11:29:06.618729Z" }, "tags": [] }, @@ -267,7 +266,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "{'储运厂工会': 37, '炼油厂工会': 42, '化学品厂工会': 29, '高科公司工会': 69, '有机化工厂工会': 91, '物装中心工会': 3, '合成树脂厂': 10, '热电厂工会': 2, '合成橡胶厂工会': 27, '教育培训中心工会': 2, '烯烃厂工会': 11, '检验计量中心工会': 8, '机关工会': 2, '生产运行保障中心': 2}\n" + "{'储运厂工会': 254, '合成树脂厂': 114, '检验计量中心工会': 13, '合成橡胶厂工会': 19, '炼油厂工会': 26, '化学品厂工会': 17, '烯烃厂工会': 12, '热电厂工会': 11}\n" ] } ], @@ -275,7 +274,7 @@ "import json\n", "import openpyxl\n", "\n", - "filename = 'data/result_燕山石化（20230428）.json'\n", + "filename = 'data/result_燕山石化（20230504）.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "dict2 = {}\n", @@ -290,7 +289,7 @@ " list2 = []\n", " list2 = [k,v]\n", " list1.append(list2)\n", - "filename = 'data/燕山石化部门测试人数情况表(20230428).xlsx'\n", + "filename = 'data/燕山石化部门测试人数情况表(20230504).xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "sheet.append(title)\n",