panda/saas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ngv添加保存数据

Browse Source
This commit is contained in:
z66
2025-10-15 15:19:36 +08:00
parent d6c6ead9f3
commit b799d383df
5 changed files with 400 additions and 521 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/logs/task.log
+7
View File
@@ -1048,3 +1048,10 @@
2025-09-26 17:54:18,517 - api.py - task_logger - INFO - 获取了145条数据
2025-09-26 17:54:18,517 - ngv更新.py - task_logger - INFO - 已获取数据
2025-09-26 17:54:45,037 - common_module.py - task_logger - INFO - 任务错误发生成功: {'data': {'creator': {'name': 'F6汽车科技', 'username': '#admin', 'status': 1, 'type': 0}, 'updater': {'name': 'F6汽车科技', 'username': '#admin', 'status': 1, 'type': 0}, 'deleter': None, 'createTime': '2025-09-26T09:54:42.260Z', 'updateTime': '2025-09-26T09:54:42.260Z', 'deleteTime': None, '_widget_1744873387500': '2025-09-26T00:00:00.000Z', '_widget_1743644977694': 'NGV更新数据', '_widget_1744873387501': '2025-09-26T09:50:53.000Z', '_widget_1744873387502': '2025-09-26T09:54:44.000Z', '_widget_1744873387504': '231', '_widget_1754981992215': "'org_code'", '_id': '68d662e29d29ff42168403fc', 'appId': '6694d3c4fcb69ca9a111a6c4', 'entryId': '689ae65da00c17578e27cd74'}}
2025-10-15 15:02:50,242 - api.py - task_logger - INFO - 获取了145条数据
2025-10-15 15:08:43,148 - api.py - task_logger - INFO - 获取了145条数据
2025-10-15 15:08:43,149 - 4214907192.py - task_logger - INFO - 数据加载完成
2025-10-15 15:09:13,069 - api.py - task_logger - INFO - 获取了145条数据
2025-10-15 15:09:13,069 - 477214183.py - task_logger - INFO - 数据加载完成
2025-10-15 15:09:39,129 - 477214183.py - task_logger - INFO - 时间转换完成
2025-10-15 15:09:39,140 - 477214183.py - task_logger - INFO - 人员转换完成
test/ngv更新.ipynb
+383 -512
View File
@@ -425,575 +425,446 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-08-04T08:30:00.126830Z",
"start_time": "2025-08-04T08:27:19.632414Z"
"end_time": "2025-10-15T07:03:16.566548Z",
"start_time": "2025-10-15T07:02:49.835394Z"
}
},
"cell_type": "code",
"source": [
"# -*- coding: utf-8 -*-\n",
"import os\n",
"import datetime\n",
"import concurrent.futures\n",
"import pandas as pd\n",
"import datetime\n",
"from config import Config\n",
"from api import API\n",
"from back_ground_module import CommonModule\n",
"from log_config import configure_task_logger, configure_error_task_logger\n",
"import concurrent.futures\n",
"\n",
"# 获取已经配置好的常规日志记录器\n",
"logger = configure_task_logger()\n",
"\n",
"# 获取已经配置好的错误任务日志记录器\n",
"error_task_logger = configure_error_task_logger()\n",
"\n",
"start_time = datetime.datetime.now()\n",
"api_instance = API()\n",
"common_module = CommonModule()\n",
"\n",
"\n",
"class UpdateAllNGVDataDaily:\n",
" \"\"\"NGV数据每日更新\"\"\"\n",
"\n",
" def __init__(self):\n",
" self.field_mapping = {}\n",
" # self.fields()\n",
"\n",
" def main(self):\n",
" # 保存为CSV文件\n",
" output_dir = \"output\" # 设置输出目录\n",
"\n",
" # 创建输出目录（如果不存在）\n",
" import os\n",
" os.makedirs(output_dir, exist_ok=True)\n",
"\n",
" task_start_time = datetime.datetime.now().strftime(\"%Y-%m-%d %H:%M:%S\")\n",
" # 获取NGV数据\n",
" payload = {\"api_key\": \"675b900991ad2491c69389ca\", \"entry_id\": \"675bb02bd2d53c2034c665e4\"}\n",
" # NGV_data_list = api_instance.entry_data_list(payload).get(\"data\", [])\n",
" # jdy_NGV_data = pd.DataFrame(NGV_data_list)\n",
"\n",
" payload = {\"api_key\": \"6694d3c4fcb69ca9a111a6c4\",\n",
" \"entry_id\": \"6769204a1902c9341340a1bc\",\n",
" }\n",
" staff_id = api_instance.entry_data_list(payload)\n",
" staff_id_list = staff_id.get(\"data\") # api请求格式，将数据封装在data字典里\n",
"\n",
" # for i in range(1,2):\n",
" data_NGV_j = common_module.get_ngv_details(days_back=1)\n",
" data_NGV_j.to_csv(os.path.join(output_dir, f\"data_NGV_j.csv\"), index=False)\n",
" data_NGV_j1 = common_module.get_ngv_details(days_back=2)\n",
"\n",
" # 对 data_NGV 进行进一步的过滤，只保留 org_type 为 \"一般\" 的记录\n",
" data_NGV_j = data_NGV_j[data_NGV_j['org_type'] == '一般']\n",
" data_NGV_j1 = data_NGV_j1[data_NGV_j1['org_type'] == '一般']\n",
"\n",
" # 去除不需要的列\n",
" columns_to_remove = {'date_id', 'date_fmt', 'pt', 'etl_time'}\n",
"\n",
" # 获取所有列名并计算要保留的列\n",
" columns_to_keep_df1 = list(set(data_NGV_j.columns) - columns_to_remove)\n",
" columns_to_keep_df2 = list(set(data_NGV_j1.columns) - columns_to_remove)\n",
"\n",
" # 过滤DataFrame以去除指定列\n",
" df1_filtered = data_NGV_j[columns_to_keep_df1]\n",
" df2_filtered = data_NGV_j1[columns_to_keep_df2]\n",
"\n",
"\n",
"if __name__ == '__main__':\n",
" start = UpdateAllNGVDataDaily()\n",
" start.main()\n"
],
"id": "82d58cced4a6e02",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"已获取 100 条数据\n",
"已获取 145 条数据\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001B[92m2025-10-15 15:02:50,242 - api.py - task_logger - INFO - 获取了145条数据\u001B[0m\n"
]
}
],
"execution_count": 4
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-10-15T07:14:36.277142Z",
"start_time": "2025-10-15T07:14:11.975620Z"
}
},
"cell_type": "code",
"source": [
"# -*- coding: utf-8 -*-\n",
"import pandas as pd\n",
"import datetime\n",
"from config import Config\n",
"from api import API\n",
"from back_ground_module import CommonModule\n",
"from log_config import configure_task_logger, configure_error_task_logger\n",
"\n",
"# 获取日志记录器\n",
"logger = configure_task_logger()\n",
"error_logger = configure_error_task_logger()\n",
"\n",
"class NGVDataUpdater:\n",
" \"\"\"NGV数据每日更新处理器\"\"\"\n",
"# 获取已经配置好的错误任务日志记录器\n",
"error_task_logger = configure_error_task_logger()\n",
"start_time = datetime.datetime.now()\n",
"api_instance = API()\n",
"common_module = CommonModule()\n",
" # 保存为CSV文件\n",
"output_dir = \"output\" # 设置输出目录\n",
"\n",
"# 创建输出目录（如果不存在）\n",
"import os\n",
"os.makedirs(output_dir, exist_ok=True)\n",
"\n",
"class UpdateNGVData:\n",
" \"\"\"NGV数据每日新增\"\"\"\n",
"\n",
" def __init__(self):\n",
" self.api = API()\n",
" self.common = CommonModule()\n",
" self.output_dir = \"output\"\n",
" self.start_time = datetime.datetime.now()\n",
" self.field_mapping = self._initialize_field_mapping()\n",
" self.staff_id_list = None\n",
" self.field_mapping = {}\n",
" self.fields()\n",
"\n",
" # 创建输出目录\n",
" os.makedirs(self.output_dir, exist_ok=True)\n",
" def load_all_data(self):\n",
" # 获取简道云员工id\n",
" payload = {\"api_key\": \"6694d3c4fcb69ca9a111a6c4\",\n",
" \"entry_id\": \"6769204a1902c9341340a1bc\",\n",
" }\n",
" staff_id = api_instance.entry_data_list(payload)\n",
" self.staff_id_list = staff_id.get(\"data\") # api请求格式，将数据封装在data字典里\n",
"\n",
" def _initialize_field_mapping(self):\n",
" \"\"\"初始化字段映射关系\"\"\"\n",
" return dict(date_id='_widget_1734062123065', date_fmt='_widget_1734062123066',\n",
" id_own_group='_widget_1734062123067', group_name='_widget_1734062123068',\n",
" id_own_org='_widget_1734062123069', org_name='_widget_1734062123070',\n",
" org_code='_widget_1734062123071', group_grade='_widget_1734062123072',\n",
" org_type='_widget_1734062123073', org_status='_widget_1734062123074',\n",
" saas_version='_widget_1734062123075', is_wechat='_widget_1734062123076',\n",
" is_mini_app='_widget_1734062123077', is_wx_shop='_widget_1734062123078',\n",
" is_camera_service='_widget_1734062123079',\n",
" is_maintenance_service='_widget_1734062123080',\n",
" saas_create_time='_widget_1734062123081', expiry_time='_widget_1734062123082',\n",
" saas_use_days='_widget_1734062123083', saas_use_year='_widget_1734062123084',\n",
" is_main_org='_widget_1734062123085', license_code='_widget_1734062123086',\n",
" license_name='_widget_1734062123087', org_crm_id='_widget_1734062123088',\n",
" province_id='_widget_1734062123089', province_name='_widget_1734062123090',\n",
" city_id='_widget_1734062123091', city_name='_widget_1734062123092',\n",
" area_id='_widget_1734062123093', area_name='_widget_1734062123094',\n",
" region_name='_widget_1734062123095', region_short_name='_widget_1734062123096',\n",
" branch_name='_widget_1734062123097', carzone_store_id='_widget_1734062123098',\n",
" carzone_store_name='_widget_1734062123099',\n",
" customer_carzone_id='_widget_1734062123100', salesmen='_widget_1734062123101',\n",
" area_manager='_widget_1734062123102', service_salesmen='_widget_1734062123103',\n",
" impl_principal='_widget_1734062123104',\n",
" service_impl_principal='_widget_1734062123105',\n",
" active_user_count='_widget_1734062123106', active_user_type='_widget_1734062123107',\n",
" limit_user_count='_widget_1734062123108', limit_user_type='_widget_1734062123109',\n",
" is_n='_widget_1734062123110', is_g='_widget_1734062123111',\n",
" is_v='_widget_1734062123112', is_visited='_widget_1734062123113',\n",
" is_active='_widget_1734062123114', active_status_fmt='_widget_1734062123115',\n",
" bill_count_last_30_day='_widget_1734062123116',\n",
" bill_day_count_last_30_day='_widget_1734062123117',\n",
" bill_day_count_this_month='_widget_1734062123118',\n",
" bill_count_last_7_day='_widget_1734062123119',\n",
" bill_day_count_last_7_day='_widget_1734062123120', pv_count='_widget_1734062123121',\n",
" uv_count='_widget_1734062123122', bill_count_1d='_widget_1734062123123',\n",
" bill_count_2d='_widget_1734062123124', bill_count_3d='_widget_1734062123125',\n",
" bill_count_4d='_widget_1734062123126', bill_count_5d='_widget_1734062123127',\n",
" bill_count_6d='_widget_1734062123128', bill_count_7d='_widget_1734062123129',\n",
" bill_count_8d='_widget_1734062123130', bill_count_9d='_widget_1734062123131',\n",
" bill_count_10d='_widget_1734062123132', bill_count_11d='_widget_1734062123133',\n",
" bill_count_12d='_widget_1734062123134', bill_count_13d='_widget_1734062123135',\n",
" bill_count_14d='_widget_1734062123136', bill_count_15d='_widget_1734062123137',\n",
" bill_count_16d='_widget_1734062123138', bill_count_17d='_widget_1734062123139',\n",
" bill_count_18d='_widget_1734062123140', bill_count_19d='_widget_1734062123141',\n",
" bill_count_20d='_widget_1734062123142', bill_count_21d='_widget_1734062123143',\n",
" bill_count_22d='_widget_1734062123144', bill_count_23d='_widget_1734062123145',\n",
" bill_count_24d='_widget_1734062123146', bill_count_25d='_widget_1734062123147',\n",
" bill_count_26d='_widget_1734062123148', bill_count_27d='_widget_1734062123149',\n",
" bill_count_28d='_widget_1734062123150', bill_count_29d='_widget_1734062123151',\n",
" bill_count_30d='_widget_1734062123152', bill_count_31d='_widget_1734062123153',\n",
" etl_time='_widget_1734062123154',\n",
" maintain_bill_count_last_30_day='_widget_1734062123155',\n",
" washing_bill_count_last_30_day='_widget_1734062123156',\n",
" maintain_bill_day_count_last_30_day='_widget_1734062123157',\n",
" washing_bill_day_count_last_30_day='_widget_1734062123158',\n",
" retail_bill_count_last_30_day='_widget_1734062123159',\n",
" retail_bill_day_count_last_30_day='_widget_1734062123160',\n",
" purchase_bill_count_last_30_day='_widget_1734062123161',\n",
" purchase_bill_day_count_last_30_day='_widget_1734062123162',\n",
" card_bill_count_last_30_day='_widget_1734062123163',\n",
" card_bill_day_count_last_30_day='_widget_1734062123164',\n",
" gd_sales_bill_count_last_30_day='_widget_1734062123165',\n",
" gd_sales_bill_day_count_last_30_day='_widget_1734062123166',\n",
" g_change_flag='_widget_1734062123167', saas_package='_widget_1734062123168',\n",
" manage_model='_widget_1734062123169', contacts='_widget_1734062123170',\n",
" contact_number='_widget_1734062123171', contact_mobile='_widget_1734062123172',\n",
" g_month_count='_widget_1734062123173', g_month_percentage='_widget_1734062123174',\n",
" is_install_service='_widget_1734062123175',\n",
" install_create_time='_widget_1734062123176', last_end_date='_widget_1734062123177',\n",
" renew_date='_widget_1734062123178', is_chain_owner='_widget_1734062123179',\n",
" group_org_count='_widget_1734062123180',\n",
" recent_bill_warning_days='_widget_1734062123181',\n",
" g_change_flag_d='_widget_1734062123182', g_lost_warning_days='_widget_1734062123183',\n",
" saas_edition_fmt='_widget_1734062123184', g_flag_1m='_widget_1734062123185',\n",
" g_flag_2m='_widget_1734062123186', g_flag_3m='_widget_1734062123187',\n",
" g_flag_4m='_widget_1734062123188', g_flag_5m='_widget_1734062123189',\n",
" g_flag_6m='_widget_1734062123190', g_flag_day_count='_widget_1734062123191',\n",
" add_org_flag='_widget_1734062123192', pt='_widget_1734062123193',\n",
" org_size='_widget_1734062123194', qualification_type_fmt='_widget_1734062123195',\n",
" business_scope_fmt='_widget_1734062123196', store_type_fmt='_widget_1734062123197',\n",
" area='_widget_1734062123198', station_number='_widget_1734062123199',\n",
" header_type_fmt='_widget_1734062123200', org_stage='_widget_1734062123201',\n",
" g_count_this_month='_widget_1734062123202',\n",
" saas_customer_type='_widget_1734062123203', technician='_widget_1734062123204',\n",
" tmall_maintain_service_status_desc='_widget_1734062123205',\n",
" date_fmt_date='_widget_1749000071375',\n",
" area_manager_staff_id='_widget_1748496855779',\n",
" service_impl_principal_staff_id=\"_widget_1748496855780\",\n",
" service_salesmen_staff_id=\"_widget_1748496855778\",\n",
" technician_staff_id=\"_widget_1751877712235\",\n",
" saas_create_time_date=\"_widget_1749000071377\",\n",
" expiry_time_date=\"_widget_1749000071382\",\n",
" install_create_time_date=\"_widget_1749000071384\",\n",
" last_end_date_date=\"_widget_1749000071389\", renew_date_date=\"_widget_1749000071391\")\n",
"\n",
" def _get_ngv_data(self, days_back):\n",
" \"\"\"获取NGV数据\"\"\"\n",
" try:\n",
" data = self.common.get_ngv_details(days_back=days_back)\n",
" return data[data['org_type'] == '一般']\n",
" except Exception as e:\n",
" error_logger.error(f\"获取NGV数据失败: {str(e)}\")\n",
" raise\n",
"\n",
" def _get_jdy_data(self):\n",
" \"\"\"获取简道云数据\"\"\"\n",
" try:\n",
" payload = {\n",
" \"api_key\": \"675b900991ad2491c69389ca\",\n",
" \"entry_id\": \"675bb02bd2d53c2034c665e4\"\n",
" }\n",
" response = self.api.entry_data_list(payload)\n",
" return pd.DataFrame(response.get(\"data\", []))\n",
" except Exception as e:\n",
" error_logger.error(f\"获取简道云数据失败: {str(e)}\")\n",
" raise\n",
"\n",
" def _get_staff_data(self):\n",
" \"\"\"获取员工数据\"\"\"\n",
" try:\n",
" payload = {\n",
" \"api_key\": \"6694d3c4fcb69ca9a111a6c4\",\n",
" \"entry_id\": \"6769204a1902c9341340a1bc\",\n",
" }\n",
" response = self.api.entry_data_list(payload)\n",
" return response.get(\"data\", [])\n",
" except Exception as e:\n",
" error_logger.error(f\"获取员工数据失败: {str(e)}\")\n",
" raise\n",
"\n",
" def _prepare_dataframes(self, df1, df2):\n",
" \"\"\"准备数据框进行比较\"\"\"\n",
" # 去除不需要的列\n",
" columns_to_remove = {'date_id', 'date_fmt', 'pt', 'etl_time'}\n",
" df1 = df1.drop(columns=columns_to_remove.intersection(df1.columns))\n",
" df2 = df2.drop(columns=columns_to_remove.intersection(df2.columns))\n",
"\n",
" # 设置索引并处理空值\n",
" df1 = df1.set_index('id_own_org').astype(str).replace(['nan', 'None'], '').fillna(\"\")\n",
" df2 = df2.set_index('id_own_org').astype(str).replace(['nan', 'None'], '').fillna(\"\")\n",
"\n",
" return df1, df2\n",
"\n",
" def _compare_dataframes(self, df1, df2):\n",
" \"\"\"比较两个数据框\"\"\"\n",
" # 找到共有的索引\n",
" common_index = df1.index.intersection(df2.index)\n",
"\n",
" # 重新索引并确保列顺序一致\n",
" common_columns = df1.columns.intersection(df2.columns)\n",
" df1_common = df1.loc[common_index, common_columns]\n",
" df2_common = df2.loc[common_index, common_columns]\n",
"\n",
" # 比较内容\n",
" matches = (df1_common == df2_common).all(axis=1)\n",
" df1_common['match_status'] = matches.map({True: '一致', False: '不一致'})\n",
"\n",
" # 获取仅在某一数据框中的行\n",
" df1_only = df1.loc[df1.index.difference(df2.index)]\n",
" df2_only = df2.loc[df2.index.difference(df1.index)]\n",
"\n",
" return df1_common, df1_only, df2_only\n",
"\n",
" def _process_jdy_data(self, jdy_data):\n",
" \"\"\"处理简道云数据\"\"\"\n",
" jdy_data = jdy_data.copy()\n",
" if '_widget_1734062123069' not in jdy_data.columns:\n",
" logger.warning(\"列 '门店id' 不存在\")\n",
" jdy_data = jdy_data.rename(columns={'_widget_1734062123069': 'id_own_org'})\n",
" return jdy_data.set_index('id_own_org')\n",
"\n",
" def _mark_deleted_stores(self, jdy_data, ngv_data):\n",
" \"\"\"标记已删除的门店\"\"\"\n",
" ids_in_jdy_not_in_ngv = jdy_data.index[~jdy_data.index.isin(ngv_data.index)]\n",
" only_in_jdy = jdy_data.loc[ids_in_jdy_not_in_ngv]\n",
"\n",
" for _, row in only_in_jdy.iterrows():\n",
" if '_id' in row and not pd.isna(row['_id']):\n",
" data = {\n",
" 'api_key': Config.SaaS_Tasks_APP_ID,\n",
" 'entry_id': Config.NGV_TASKS_ENTRY_ID,\n",
" \"data_id\": str(row['_id']),\n",
" \"data\": {\"_widget_1754285499851\": {\"value\": \"已删除\"}}\n",
" }\n",
" self.api.entry_data_update(data=data, max_retries=20)\n",
"\n",
" def _process_datetime_fields(self, df):\n",
" \"\"\"处理日期时间字段\"\"\"\n",
" time_columns = ['saas_create_time', 'expiry_time', 'install_create_time', \"last_end_date\", \"renew_date\"]\n",
" df = df.copy()\n",
"\n",
" for col in time_columns:\n",
" if col in df.columns:\n",
" # 转换为datetime类型\n",
" df[col] = pd.to_datetime(df[col], errors='coerce', utc=False)\n",
" # 本地化为北京时间并转换为UTC\n",
" df[col + '_date'] = (\n",
" df[col]\n",
" .dt.tz_localize('Asia/Shanghai', ambiguous='infer', nonexistent='NaT')\n",
" .dt.tz_convert('UTC')\n",
" .dt.strftime('%Y-%m-%dT%H:%M:%SZ')\n",
" )\n",
" return df\n",
"\n",
" def _process_staff_fields(self, df, staff_data):\n",
" \"\"\"处理员工字段\"\"\"\n",
" staff_columns = ['area_manager', 'service_impl_principal', \"service_salesmen\", \"technician\"]\n",
"\n",
" for col in staff_columns:\n",
" if col in df.columns:\n",
" # 创建员工ID映射\n",
" staff_map = {\n",
" str(staff['_widget_1734942794144']): staff['_widget_1734942794145']\n",
" for staff in staff_data\n",
" }\n",
" # 映射员工ID\n",
" df[col + \"_staff_id\"] = df[col].map(staff_map)\n",
"\n",
" return df\n",
"\n",
" def _update_ngv_data(self, df):\n",
" \"\"\"更新NGV数据\"\"\"\n",
" futures = []\n",
"\n",
" for _, row in df.iterrows():\n",
" data_dict = {}\n",
"\n",
" # 构建数据字典\n",
" for col_name, widget_id in self.field_mapping.items():\n",
" if col_name in df.columns:\n",
" value = row[col_name]\n",
" clean_value = None if pd.isna(value) else value\n",
" data_dict[widget_id] = {\"value\": clean_value}\n",
"\n",
" # 根据是否有_id决定是更新还是创建\n",
" if '_id' in row and not pd.isna(row['_id']):\n",
" data = {\n",
" 'api_key': Config.SaaS_Tasks_APP_ID,\n",
" 'entry_id': Config.NGV_TASKS_ENTRY_ID,\n",
" \"data_id\": str(row['_id']),\n",
" \"data\": data_dict\n",
" }\n",
" futures.append(self.api.entry_data_update(data=data, max_retries=20))\n",
" else:\n",
" data = {\n",
" 'api_key': Config.SaaS_Tasks_APP_ID,\n",
" 'entry_id': Config.NGV_TASKS_ENTRY_ID,\n",
" \"data\": data_dict\n",
" }\n",
" futures.append(self.api.data_batch_create(data=data, max_retries=20))\n",
"\n",
" # 等待所有请求完成\n",
" for future in concurrent.futures.as_completed(futures):\n",
" try:\n",
" future.result()\n",
" except Exception as exc:\n",
" error_logger.error(f\"请求发生异常: {exc}\")\n",
" @staticmethod\n",
" def get_staff_id(row_item, name):\n",
" \"\"\"辅助函数，用于获取员工ID\"\"\"\n",
" if str(row_item[\"_widget_1734942794144\"]) == str(name): # 检查姓名是否匹配\n",
" return row_item[\"_widget_1734942794145\"] # 返回员工ID\n",
" return None\n",
"\n",
" def main(self):\n",
" \"\"\"执行数据更新流程\"\"\"\n",
" task_start_time = datetime.datetime.now().strftime(\"%Y-%m-%d %H:%M:%S\")\n",
"\n",
" try:\n",
" logger.info(\"开始NGV数据更新流程\")\n",
" self.load_all_data()\n",
" logger.info(f\"数据加载完成\")\n",
"\n",
" # 获取数据\n",
" data_ngv_today = self._get_ngv_data(days_back=1)\n",
" data_ngv_yesterday = self._get_ngv_data(days_back=2)\n",
" jdy_data = self._get_jdy_data()\n",
" staff_data = self._get_staff_data()\n",
" data_NGV_j = common_module.get_ngv_details(days_back=2)\n",
" data_NGV_j1 = common_module.get_ngv_details(days_back=3)\n",
"\n",
" # 准备和比较数据\n",
" df1, df2 = self._prepare_dataframes(data_ngv_today, data_ngv_yesterday)\n",
" df_common, _, _ = self._compare_dataframes(df1, df2)\n",
" # 找出在 data_NGV_j 中存在但在 data_NGV_j1 中不存在的 data_id\n",
" unique_data_ids = data_NGV_j[~data_NGV_j['org_code'].isin(data_NGV_j1['org_code'])]\n",
"\n",
" # 处理简道云数据\n",
" jdy_data_processed = self._process_jdy_data(jdy_data)\n",
" # 创建一个新的 DataFrame 保存这些唯一的 data_id 及其对应的数据\n",
" new_df = data_NGV_j[data_NGV_j['org_code'].isin(unique_data_ids['org_code'])]\n",
"\n",
" # 标记已删除的门店\n",
" self._mark_deleted_stores(jdy_data_processed, df_common)\n",
" # 对 new_df 进行进一步的过滤，只保留 org_type 为 \"一般\" 的记录\n",
" data_NGV_j = data_NGV_j[data_NGV_j['org_type'] == '一般']\n",
" data_NGV_j1 = data_NGV_j1[data_NGV_j1['org_type'] == '一般']\n",
" filtered_df = new_df[new_df['org_type'] == '一般']\n",
"\n",
" # 合并简道云ID\n",
" df_common = df_common.join(jdy_data_processed[\"_id\"], how='left')\n",
" df_common = df_common[df_common['match_status'] == '不一致']\n",
" # 日期字段转换为日期格式\n",
" time_columns = ['date_fmt', 'saas_create_time', 'expiry_time', 'install_create_time', \"last_end_date\",\n",
" \"renew_date\"]\n",
" new_filtered_df = filtered_df.copy() # 复制df，以调整时间\n",
" for col in time_columns:\n",
" # 1. 转换为datetime类型（带错误处理）\n",
" # 使用.loc安全赋值\n",
" new_filtered_df[col] = pd.to_datetime(filtered_df[col], errors='coerce', utc=False)\n",
"\n",
" # 处理特殊字段\n",
" df_common = self._process_datetime_fields(df_common)\n",
" df_common = self._process_staff_fields(df_common, staff_data)\n",
" # 2. 优化后的时区转换（高效向量化操作）\n",
" filtered_df[col + '_date'] = (\n",
" new_filtered_df[col]\n",
" # 本地化为北京时间（东八区）\n",
" .dt.tz_localize('Asia/Shanghai', ambiguous='infer', nonexistent='NaT')\n",
" # 转换为UTC时区\n",
" .dt.tz_convert('UTC')\n",
" # 格式化为ISO8601字符串\n",
" .dt.strftime('%Y-%m-%dT%H:%M:%SZ')\n",
" )\n",
" logger.info(f\"时间转换完成\")\n",
"\n",
" # 更新数据\n",
" self._update_ngv_data(df_common)\n",
" # 人员字段转换为人员字段\n",
" staff_columns = ['area_manager', 'service_impl_principal', \"service_salesmen\", \"technician\"]\n",
" # 将员工列表转为DataFrame\n",
" # 三重循环临时方案（确保可写入）\n",
" for col in staff_columns:\n",
" staff_ids = []\n",
" for _, row in filtered_df.iterrows():\n",
" matched = False\n",
" for staff in self.staff_id_list:\n",
" if str(staff['_widget_1734942794144']) == str(row[col]):\n",
" staff_ids.append(staff['_widget_1734942794145'])\n",
" matched = True\n",
" break\n",
" if not matched:\n",
" staff_ids.append(None)\n",
" filtered_df[col + \"_staff_id\"] = staff_ids\n",
" logger.info(f\"人员转换完成\")\n",
"\n",
" # 记录执行时间\n",
" end_time = datetime.datetime.now()\n",
" time_diff = end_time - self.start_time\n",
" logger.info(f\"执行时间: {time_diff.days} 天, {time_diff.seconds} 秒, {time_diff.microseconds} 微秒\")\n",
" # filtered_df.to_csv(r\"D:\\Idea Project\\SaaS_V1.3\\back_ground_module\\output\\NGV.csv\")\n",
"\n",
" # 发送任务状态\n",
" self.common.send_task_status(task_start_time, \"NGV更新数据\")\n",
" # 生成包含所有行转换后的字典列表\n",
" # all_data = [self.row_to_dict(row, self.field_mapping) for index, row in data_NGV_j1.iterrows()] # 前两天的全部数据\n",
" # all_data = [self.row_to_dict(row, self.field_mapping) for index, row in data_NGV_j.iterrows()] # 前一天的全部数据\n",
" all_data = [self.row_to_dict(row, self.field_mapping) for index, row in filtered_df.iterrows()] # 增量数据\n",
" filtered_df.to_csv(output_dir + \"\\\\filtered_df.csv\", index=False)\n",
"\n",
"\n",
" #\n",
" # data = {'api_key': Config.SaaS_Tasks_APP_ID, 'entry_id': Config.NGV_TASKS_ENTRY_ID, \"data_list\": all_data}\n",
" #\n",
" # result = api_instance.entry_data_batch_create(data)\n",
" # logger.info(f\"数据已推送:{result}\")\n",
" # result_str = str(result)\n",
" # print(result_str[:500])\n",
"\n",
" # 保存到Excel文件\n",
" # output_path = r'D:\\Idea Project\\F6+宜搭+其它(1)\\new\\文件输出\\ngv明细1.xlsx'\n",
" # filtered_df.to_excel(output_path, index=False)\n",
" # data_NGV_j1.to_excel( r'D:\\Idea Project\\F6+宜搭+其它(1)\\new\\文件输出\\ngv明细j1.xlsx', index=False)\n",
" # data_NGV_j.to_excel( r'D:\\Idea Project\\F6+宜搭+其它(1)\\new\\文件输出\\ngv明细j.xlsx', index=False)\n",
" # new_df.to_excel(r'D:\\Idea Project\\F6+宜搭+其它(1)\\new\\文件输出\\ngv明细ndf.xlsx', index=False)\n",
"\n",
" # common_module.send_task_status(task_start_time, \"NGV新增数据\")\n",
" # logger.info(f\"任务完成。\")\n",
" except Exception as e:\n",
" error_logger.error(f\"NGV数据更新流程失败: {str(e)}\")\n",
" raise\n",
" error_task_logger.error(f\"任务执行时发生异常: {e}\")\n",
" common_module.send_task_error(task_start_time, \"NGV新增数据\", str(e))\n",
"\n",
" @staticmethod\n",
" def row_to_dict(row, field_mapping):\n",
" \"\"\"将一行数据转换为指定格式的字典\"\"\"\n",
" result = {}\n",
" for col_name, widget_id in field_mapping.items():\n",
" if col_name in row:\n",
" value = row[col_name]\n",
" clean_value = None if pd.isna(value) else value\n",
" result[widget_id] = {\"value\": clean_value}\n",
" return result\n",
"\n",
" def fields(self):\n",
" self.field_mapping = dict(date_id='_widget_1734062123065', date_fmt='_widget_1734062123066',\n",
" id_own_group='_widget_1734062123067', group_name='_widget_1734062123068',\n",
" id_own_org='_widget_1734062123069', org_name='_widget_1734062123070',\n",
" org_code='_widget_1734062123071', group_grade='_widget_1734062123072',\n",
" org_type='_widget_1734062123073', org_status='_widget_1734062123074',\n",
" saas_version='_widget_1734062123075', is_wechat='_widget_1734062123076',\n",
" is_mini_app='_widget_1734062123077', is_wx_shop='_widget_1734062123078',\n",
" is_camera_service='_widget_1734062123079',\n",
" is_maintenance_service='_widget_1734062123080',\n",
" saas_create_time='_widget_1734062123081', expiry_time='_widget_1734062123082',\n",
" saas_use_days='_widget_1734062123083', saas_use_year='_widget_1734062123084',\n",
" is_main_org='_widget_1734062123085', license_code='_widget_1734062123086',\n",
" license_name='_widget_1734062123087', org_crm_id='_widget_1734062123088',\n",
" province_id='_widget_1734062123089', province_name='_widget_1734062123090',\n",
" city_id='_widget_1734062123091', city_name='_widget_1734062123092',\n",
" area_id='_widget_1734062123093', area_name='_widget_1734062123094',\n",
" region_name='_widget_1734062123095', region_short_name='_widget_1734062123096',\n",
" branch_name='_widget_1734062123097', carzone_store_id='_widget_1734062123098',\n",
" carzone_store_name='_widget_1734062123099',\n",
" customer_carzone_id='_widget_1734062123100', salesmen='_widget_1734062123101',\n",
" area_manager='_widget_1734062123102', service_salesmen='_widget_1734062123103',\n",
" impl_principal='_widget_1734062123104',\n",
" service_impl_principal='_widget_1734062123105',\n",
" active_user_count='_widget_1734062123106', active_user_type='_widget_1734062123107',\n",
" limit_user_count='_widget_1734062123108', limit_user_type='_widget_1734062123109',\n",
" is_n='_widget_1734062123110', is_g='_widget_1734062123111',\n",
" is_v='_widget_1734062123112', is_visited='_widget_1734062123113',\n",
" is_active='_widget_1734062123114', active_status_fmt='_widget_1734062123115',\n",
" bill_count_last_30_day='_widget_1734062123116',\n",
" bill_day_count_last_30_day='_widget_1734062123117',\n",
" bill_day_count_this_month='_widget_1734062123118',\n",
" bill_count_last_7_day='_widget_1734062123119',\n",
" bill_day_count_last_7_day='_widget_1734062123120', pv_count='_widget_1734062123121',\n",
" uv_count='_widget_1734062123122', bill_count_1d='_widget_1734062123123',\n",
" bill_count_2d='_widget_1734062123124', bill_count_3d='_widget_1734062123125',\n",
" bill_count_4d='_widget_1734062123126', bill_count_5d='_widget_1734062123127',\n",
" bill_count_6d='_widget_1734062123128', bill_count_7d='_widget_1734062123129',\n",
" bill_count_8d='_widget_1734062123130', bill_count_9d='_widget_1734062123131',\n",
" bill_count_10d='_widget_1734062123132', bill_count_11d='_widget_1734062123133',\n",
" bill_count_12d='_widget_1734062123134', bill_count_13d='_widget_1734062123135',\n",
" bill_count_14d='_widget_1734062123136', bill_count_15d='_widget_1734062123137',\n",
" bill_count_16d='_widget_1734062123138', bill_count_17d='_widget_1734062123139',\n",
" bill_count_18d='_widget_1734062123140', bill_count_19d='_widget_1734062123141',\n",
" bill_count_20d='_widget_1734062123142', bill_count_21d='_widget_1734062123143',\n",
" bill_count_22d='_widget_1734062123144', bill_count_23d='_widget_1734062123145',\n",
" bill_count_24d='_widget_1734062123146', bill_count_25d='_widget_1734062123147',\n",
" bill_count_26d='_widget_1734062123148', bill_count_27d='_widget_1734062123149',\n",
" bill_count_28d='_widget_1734062123150', bill_count_29d='_widget_1734062123151',\n",
" bill_count_30d='_widget_1734062123152', bill_count_31d='_widget_1734062123153',\n",
" etl_time='_widget_1734062123154',\n",
" maintain_bill_count_last_30_day='_widget_1734062123155',\n",
" washing_bill_count_last_30_day='_widget_1734062123156',\n",
" maintain_bill_day_count_last_30_day='_widget_1734062123157',\n",
" washing_bill_day_count_last_30_day='_widget_1734062123158',\n",
" retail_bill_count_last_30_day='_widget_1734062123159',\n",
" retail_bill_day_count_last_30_day='_widget_1734062123160',\n",
" purchase_bill_count_last_30_day='_widget_1734062123161',\n",
" purchase_bill_day_count_last_30_day='_widget_1734062123162',\n",
" card_bill_count_last_30_day='_widget_1734062123163',\n",
" card_bill_day_count_last_30_day='_widget_1734062123164',\n",
" gd_sales_bill_count_last_30_day='_widget_1734062123165',\n",
" gd_sales_bill_day_count_last_30_day='_widget_1734062123166',\n",
" g_change_flag='_widget_1734062123167', saas_package='_widget_1734062123168',\n",
" manage_model='_widget_1734062123169', contacts='_widget_1734062123170',\n",
" contact_number='_widget_1734062123171', contact_mobile='_widget_1734062123172',\n",
" g_month_count='_widget_1734062123173', g_month_percentage='_widget_1734062123174',\n",
" is_install_service='_widget_1734062123175',\n",
" install_create_time='_widget_1734062123176', last_end_date='_widget_1734062123177',\n",
" renew_date='_widget_1734062123178', is_chain_owner='_widget_1734062123179',\n",
" group_org_count='_widget_1734062123180',\n",
" recent_bill_warning_days='_widget_1734062123181',\n",
" g_change_flag_d='_widget_1734062123182', g_lost_warning_days='_widget_1734062123183',\n",
" saas_edition_fmt='_widget_1734062123184', g_flag_1m='_widget_1734062123185',\n",
" g_flag_2m='_widget_1734062123186', g_flag_3m='_widget_1734062123187',\n",
" g_flag_4m='_widget_1734062123188', g_flag_5m='_widget_1734062123189',\n",
" g_flag_6m='_widget_1734062123190', g_flag_day_count='_widget_1734062123191',\n",
" add_org_flag='_widget_1734062123192', pt='_widget_1734062123193',\n",
" org_size='_widget_1734062123194', qualification_type_fmt='_widget_1734062123195',\n",
" business_scope_fmt='_widget_1734062123196', store_type_fmt='_widget_1734062123197',\n",
" area='_widget_1734062123198', station_number='_widget_1734062123199',\n",
" header_type_fmt='_widget_1734062123200', org_stage='_widget_1734062123201',\n",
" g_count_this_month='_widget_1734062123202',\n",
" saas_customer_type='_widget_1734062123203', technician='_widget_1734062123204',\n",
" tmall_maintain_service_status_desc='_widget_1734062123205',\n",
" date_fmt_date='_widget_1749000071375',\n",
" area_manager_staff_id='_widget_1748496855779',\n",
" service_impl_principal_staff_id=\"_widget_1748496855780\",\n",
" service_salesmen_staff_id=\"_widget_1748496855778\",\n",
" technician_staff_id=\"_widget_1751877712235\",\n",
" saas_create_time_date=\"_widget_1749000071377\",\n",
" expiry_time_date=\"_widget_1749000071382\",\n",
" install_create_time_date=\"_widget_1749000071384\",\n",
" last_end_date_date=\"_widget_1749000071389\", renew_date_date=\"_widget_1749000071391\")\n",
"\n",
"\n",
"if __name__ == '__main__':\n",
" updater = NGVDataUpdater()\n",
" updater.main()"
" start = UpdateNGVData()\n",
" start.main()\n"
],
"id": "82d58cced4a6e02",
"id": "6ce49b7686e91712",
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2025-08-04 16:27:26,074 - task_logger - INFO - 开始NGV数据更新流程\n"
"\u001B[92m2025-10-15 15:14:12,293 - api.py - task_logger - INFO - 获取了145条数据\u001B[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1de1bc8bae6d3111bb0f6332472b8cd4\n",
"1de1bc8bae6d3111bb0f6332472b8cd4\n",
"已获取 100 条数据\n",
"已获取 200 条数据\n",
"已获取 300 条数据\n",
"已获取 400 条数据\n",
"已获取 500 条数据\n",
"已获取 600 条数据\n",
"已获取 700 条数据\n",
"已获取 800 条数据\n",
"已获取 900 条数据\n",
"已获取 1000 条数据\n",
"已获取 1100 条数据\n",
"已获取 1200 条数据\n",
"已获取 1300 条数据\n",
"已获取 1400 条数据\n",
"已获取 1500 条数据\n",
"已获取 1600 条数据\n",
"已获取 1700 条数据\n",
"已获取 1800 条数据\n",
"已获取 1900 条数据\n",
"已获取 2000 条数据\n",
"已获取 2100 条数据\n",
"已获取 2200 条数据\n",
"已获取 2300 条数据\n",
"已获取 2400 条数据\n",
"已获取 2500 条数据\n",
"已获取 2600 条数据\n",
"已获取 2700 条数据\n",
"已获取 2800 条数据\n",
"已获取 2900 条数据\n",
"已获取 3000 条数据\n",
"已获取 3100 条数据\n",
"已获取 3200 条数据\n",
"已获取 3300 条数据\n",
"已获取 3400 条数据\n",
"已获取 3500 条数据\n",
"已获取 3600 条数据\n",
"已获取 3700 条数据\n",
"已获取 3800 条数据\n",
"已获取 3900 条数据\n",
"已获取 4000 条数据\n",
"已获取 4100 条数据\n",
"已获取 4200 条数据\n",
"已获取 4300 条数据\n",
"已获取 4400 条数据\n",
"已获取 4500 条数据\n",
"已获取 4600 条数据\n",
"已获取 4700 条数据\n",
"已获取 4800 条数据\n",
"已获取 4900 条数据\n",
"已获取 5000 条数据\n",
"已获取 5100 条数据\n",
"已获取 5200 条数据\n",
"已获取 5300 条数据\n",
"已获取 5400 条数据\n",
"已获取 5500 条数据\n",
"已获取 5600 条数据\n",
"已获取 5700 条数据\n",
"已获取 5800 条数据\n",
"已获取 5900 条数据\n",
"已获取 6000 条数据\n",
"已获取 6100 条数据\n",
"已获取 6200 条数据\n",
"已获取 6300 条数据\n",
"已获取 6400 条数据\n",
"已获取 6500 条数据\n",
"已获取 6600 条数据\n",
"已获取 6700 条数据\n",
"已获取 6800 条数据\n",
"已获取 6900 条数据\n",
"已获取 7000 条数据\n",
"已获取 7100 条数据\n",
"已获取 7200 条数据\n",
"已获取 7300 条数据\n",
"已获取 7400 条数据\n",
"已获取 7500 条数据\n",
"已获取 7600 条数据\n",
"已获取 7700 条数据\n",
"已获取 7800 条数据\n",
"已获取 7900 条数据\n",
"已获取 8000 条数据\n",
"已获取 8100 条数据\n",
"已获取 8200 条数据\n",
"已获取 8300 条数据\n",
"已获取 8400 条数据\n",
"已获取 8500 条数据\n",
"已获取 8600 条数据\n",
"已获取 8700 条数据\n",
"已获取 8800 条数据\n",
"已获取 8900 条数据\n",
"已获取 9000 条数据\n",
"已获取 9100 条数据\n",
"已获取 9200 条数据\n",
"已获取 9300 条数据\n",
"已获取 9400 条数据\n",
"已获取 9500 条数据\n",
"已获取 9600 条数据\n",
"已获取 9700 条数据\n",
"已获取 9800 条数据\n",
"已获取 9900 条数据\n",
"已获取 10000 条数据\n",
"已获取 10100 条数据\n",
"已获取 10200 条数据\n",
"已获取 10300 条数据\n",
"已获取 10400 条数据\n",
"已获取 10500 条数据\n",
"已获取 10600 条数据\n",
"已获取 10700 条数据\n",
"已获取 10800 条数据\n",
"已获取 10900 条数据\n",
"已获取 11000 条数据\n",
"已获取 11100 条数据\n",
"已获取 11200 条数据\n",
"已获取 11300 条数据\n",
"已获取 11400 条数据\n",
"已获取 11500 条数据\n",
"已获取 11600 条数据\n",
"已获取 11700 条数据\n",
"已获取 11800 条数据\n",
"已获取 11900 条数据\n",
"已获取 12000 条数据\n",
"已获取 12100 条数据\n",
"已获取 12200 条数据\n",
"已获取 12300 条数据\n",
"已获取 12400 条数据\n",
"已获取 12500 条数据\n",
"已获取 12600 条数据\n",
"已获取 12700 条数据\n",
"已获取 12800 条数据\n",
"已获取 12900 条数据\n",
"已获取 13000 条数据\n",
"已获取 13100 条数据\n",
"已获取 13200 条数据\n",
"已获取 13300 条数据\n",
"已获取 13400 条数据\n",
"已获取 13500 条数据\n",
"已获取 13600 条数据\n",
"已获取 13700 条数据\n",
"已获取 13800 条数据\n",
"已获取 13900 条数据\n",
"已获取 14000 条数据\n",
"已获取 14100 条数据\n",
"已获取 14200 条数据\n",
"已获取 14300 条数据\n",
"已获取 14400 条数据\n",
"已获取 14500 条数据\n",
"已获取 14600 条数据\n",
"已获取 14700 条数据\n",
"已获取 14800 条数据\n",
"已获取 14900 条数据\n",
"已获取 15000 条数据\n",
"已获取 15100 条数据\n",
"已获取 15200 条数据\n",
"已获取 15300 条数据\n",
"已获取 15400 条数据\n",
"已获取 15500 条数据\n",
"已获取 15600 条数据\n",
"已获取 15700 条数据\n",
"已获取 15800 条数据\n",
"已获取 15900 条数据\n",
"已获取 16000 条数据\n",
"已获取 16100 条数据\n",
"已获取 16200 条数据\n",
"已获取 16300 条数据\n",
"已获取 16400 条数据\n",
"已获取 16500 条数据\n",
"已获取 16600 条数据\n",
"已获取 16700 条数据\n",
"已获取 16800 条数据\n",
"已获取 16900 条数据\n",
"已获取 17000 条数据\n",
"已获取 17100 条数据\n",
"已获取 17200 条数据\n",
"已获取 17300 条数据\n",
"已获取 17400 条数据\n",
"已获取 17500 条数据\n",
"已获取 17600 条数据\n",
"已获取 17700 条数据\n",
"已获取 17800 条数据\n",
"已获取 17900 条数据\n",
"已获取 18000 条数据\n",
"已获取 18100 条数据\n",
"已获取 18200 条数据\n",
"已获取 18300 条数据\n",
"已获取 18400 条数据\n",
"已获取 18500 条数据\n",
"已获取 18600 条数据\n",
"已获取 18700 条数据\n",
"已获取 18800 条数据\n",
"已获取 18900 条数据\n",
"已获取 19000 条数据\n",
"已获取 19100 条数据\n",
"已获取 19200 条数据\n",
"已获取 19300 条数据\n",
"已获取 19400 条数据\n",
"已获取 19500 条数据\n",
"已获取 19600 条数据\n",
"已获取 19700 条数据\n",
"已获取 19800 条数据\n",
"已获取 19900 条数据\n"
"已获取 145 条数据\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001B[92m2025-10-15 15:14:12,294 - 4281365028.py - task_logger - INFO - 数据加载完成\u001B[0m\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"KeyboardInterrupt\n",
"\n"
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:76: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + '_date'] = (\n",
"\u001B[92m2025-10-15 15:14:36,032 - 4281365028.py - task_logger - INFO - 时间转换完成\u001B[0m\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:102: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + \"_staff_id\"] = staff_ids\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:102: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + \"_staff_id\"] = staff_ids\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:102: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + \"_staff_id\"] = staff_ids\n",
"C:\\Users\\zy187\\AppData\\Local\\Temp\\ipykernel_5028\\4281365028.py:102: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered_df[col + \"_staff_id\"] = staff_ids\n",
"\u001B[92m2025-10-15 15:14:36,045 - 4281365028.py - task_logger - INFO - 人员转换完成\u001B[0m\n"
]
}
],
"execution_count": 1
"execution_count": 2
}
],
"metadata": {