diff --git a/dags/jh/dag_samples_notice.py b/dags/jh/dag_samples_notice.py index 0f2a546..d2668d5 100644 --- a/dags/jh/dag_samples_notice.py +++ b/dags/jh/dag_samples_notice.py @@ -6,7 +6,7 @@ with DAG( dag_id="samples_notice_dag", # 每月10日1点运行 schedule_interval="0 0 10 * *", - start_date=pendulum.datetime(2023, 8, 1, tz="Asia/Shanghai"), + start_date=pendulum.datetime(2025, 6, 9, tz="Asia/Shanghai"), catchup=True, description="样本数量监控提醒" ) as dag: diff --git a/dags/jh/sample/samples_notice.py b/dags/jh/sample/samples_notice.py index ceeb28f..0e0e98c 100644 --- a/dags/jh/sample/samples_notice.py +++ b/dags/jh/sample/samples_notice.py @@ -22,7 +22,8 @@ def proc(): log.info(f"城市区域维度 sql : {sql}") df = es206_client.scan_by_sql_to_data_frame(sql) - + if 'city' not in df.columns or 'region' not in df.columns : + return False df_region = pd.DataFrame(df.groupby(by=['city', 'region'])['_id'].count()).reset_index() df_region = df_region.rename(columns={'_id': 'count'}) df_region_res = df_region[df_region['count'] < 20] @@ -83,7 +84,8 @@ def proc(): topCities = cities.head(70) city_list = list(topCities['cityname']) log.info(f"房源网站维度-数量 city_list : {city_list}") - + if 'city' not in df_root1.columns or 'root' not in df.columns: + return False df_root_city_group1 = pd.DataFrame(df_root1.groupby(by=['root', 'city'])['_id'].count()).reset_index() df_root_city_group1 = df_root_city_group1.rename(columns={'_id': 'count'}) df_root_city_res = df_root_city_group1[