update

config.py

@@ -370,6 +370,7 @@ class BaseConfig(object):
             {'data': 'data1', 'rule': 'rule15'},  # 200 vlog
             {'data': 'data1', 'rule': 'rule16'},  # 214 vlog
             {'data': 'data1', 'rule': 'rule17'},  # 215 vlog
+            {'data': 'data1', 'rule': 'rule18'},  # 224 vlog
         ],
     }
 

region_rule_rank_h.py

@@ -183,7 +183,7 @@ def add_func1(initial_df, pre_h_df):
 
 
 def add_func2(initial_df, pre_h_df):
-    """当前小时级数据与前几个小时数据合并"""
+    """当前小时级数据与前几个小时数据合并: 当前小时存在的视频以当前小时为准，否则以高分为主"""
     score_list = initial_df['score'].to_list()
     if len(score_list) > 0:
         min_score = min(score_list)
@@ -191,12 +191,16 @@ def add_func2(initial_df, pre_h_df):
         min_score = 0
     initial_video_id_list = initial_df['videoid'].to_list()
     pre_h_df = pre_h_df[pre_h_df['score'] > min_score]
+    print(f"pre1: {len(pre_h_df)}\n{pre_h_df}")
     pre_h_df = pre_h_df[~pre_h_df['videoid'].isin(initial_video_id_list)]
+    print(f"pre2: {len(pre_h_df)}\n{pre_h_df}")
+
     df = pd.concat([initial_df, pre_h_df], ignore_index=True)
     # videoid去重，保留分值高
     df['videoid'] = df['videoid'].astype(int)
     df = df.sort_values(by=['score'], ascending=False)
     df = df.drop_duplicates(subset=['videoid'], keep="first")
+    print(f"initial = {len(initial_df)}, df = {len(df)}")
     return df
 
 
@@ -766,6 +770,7 @@ def h_rank_bottom(now_date, now_h, rule_params, region_code_list, rule_rank_h_fl
 def h_timer_check():
     try:
         rule_rank_h_flag = sys.argv[1]
+        # rule_rank_h_flag = '24h'
         if rule_rank_h_flag == '48h':
             rule_params = config_.RULE_PARAMS_REGION_APP_TYPE_48H
         else: