diff --git a/dags/office/rent/base_price.py b/dags/office/rent/base_price.py index ee93aae..525e60a 100644 --- a/dags/office/rent/base_price.py +++ b/dags/office/rent/base_price.py @@ -272,8 +272,16 @@ def calc(city, year_month): keep='first') # 计算价格的写字楼 db_df = db_df.rename(columns={'district': 'region'}) - combined = pd.concat([office_info, db_df[['city', 'region', 'name']]]) - diff_df = combined.drop_duplicates(subset=['city', 'region', 'name'], keep=False) + # 使用 merge 操作并结合 indicator 参数 + merged = office_info.merge(db_df[['city', 'region', 'name']], on=['city', 'region', 'name'], how='left', + indicator=True) + + # 过滤出仅在 office_info 中存在的记录 + diff_df = merged[merged['_merge'] == 'left_only'].drop(columns=['_merge']) + + # 如果需要保持原始列顺序,可以重新排列列 + diff_df = diff_df[office_info.columns] + actions.clear() for index, item in diff_df.iterrows(): try: