update

ad_user_video_predict.py

@@ -66,8 +66,8 @@ def predict_ad_group_video():
     video_df = predict_video_share_rate(dt=dt, app_type=app_type)
     print(f"user_group_df count = {len(user_group_df)}, \nvideo_df count = {len(video_df)}")
     predict_df = video_df
-    for item in user_group_df:
-        predict_df[item['group']] = predict_df['videoid'] * item['group_ad_share_rate']
+    for index, item in user_group_df.iterrows():
+        predict_df[item['group']] = predict_df['video_ad_share_rate'] * item['group_ad_share_rate']
     predict_df.to_csv('./data/ad_user_video_predict.csv')
     return predict_df
 

ad_users_data_update.py

@@ -33,7 +33,7 @@ def predict_user_group_share_rate(project, table, dt, app_type):
     # 结果写入redis
     key_name = f"{config_.KEY_NAME_PREFIX_AD_GROUP}{dt}"
     redis_data = {}
-    for item in user_group_df:
+    for index, item in user_group_df.iterrows():
         redis_data[item['group']] = item['group_ad_share_rate']
     group_ad_share_rate_mean = user_group_df['group_ad_share_rate'].mean()
     redis_data['mean_group'] = group_ad_share_rate_mean

ad_video_data_upate.py

@@ -34,7 +34,7 @@ def predict_video_share_rate(project, table, dt, app_type):
     # 结果写入redis
     key_name = f"{config_.KEY_NAME_PREFIX_AD_VIDEO}{dt}"
     redis_data = {}
-    for item in video_df:
+    for index, item in video_df.iterrows():
         redis_data[int(item['videoid'])] = item['video_ad_share_rate']
     group_ad_share_rate_mean = video_df['video_ad_share_rate'].mean()
     redis_data[-1] = group_ad_share_rate_mean