update

config.py

@@ -312,9 +312,9 @@ class BaseConfig(object):
                        'region_24h_rule_key': 'rule7', '24h_rule_key': 'rule6', 'back_score_rate': 0.7},
             'rule14': {'view_type': 'video-show-region', 'platform_return_rate': 0.001,
                        'region_24h_rule_key': 'rule9', '24h_rule_key': 'rule8', 'back_score_rate': 0.8},
-            # 19点地域小时级列表中增加7点-18点地域小时级的优质视频
+            # 20点地域小时级列表中增加7点-19点地域小时级的优质视频
             'rule12': {'view_type': 'video-show-region', 'platform_return_rate': 0.001,
-                       'region_24h_rule_key': 'rule2', '24h_rule_key': 'rule3', 'add_videos_in_19h': True},
+                       'region_24h_rule_key': 'rule2', '24h_rule_key': 'rule3', 'add_videos_in_20h': True},
         },
         'data_params': DATA_PARAMS,
         'params_list': [

region_rule_rank_h.py

@@ -168,8 +168,8 @@ def cal_score(df, param):
 
 def add_videos(initial_df, now_date, rule_key, region, data_key):
     """
-    19点地域小时级数据列表中增加7点-18点优质视频
-    :param initial_df: 19点地域小时级筛选结果
+    20点地域小时级数据列表中增加7点-19点优质视频
+    :param initial_df: 20点地域小时级筛选结果
     :param now_date:
     :param data_key:
     :param region:
@@ -178,7 +178,7 @@ def add_videos(initial_df, now_date, rule_key, region, data_key):
     """
     redis_helper = RedisHelper()
     pre_h_data = []
-    for pre_h in range(7, 19):
+    for pre_h in range(7, 20):
         pre_h_recall_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_REGION_BY_H}{region}:{data_key}:{rule_key}:" \
                                 f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{pre_h}"
         initial_data = redis_helper.get_all_data_from_zset(key_name=pre_h_recall_key_name, with_scores=True)
@@ -200,7 +200,7 @@ def add_videos(initial_df, now_date, rule_key, region, data_key):
     return df
 
 
-def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank_h_flag, add_videos_in_19h=False):
+def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank_h_flag, add_videos_in_20h=False):
     """
     获取符合进入召回源条件的视频，与每日更新的rov模型结果视频列表进行合并
     :param df:
@@ -225,8 +225,8 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
     h_recall_df = h_recall_df.drop_duplicates(subset=['videoid'], keep='first')
     h_recall_df['videoid'] = h_recall_df['videoid'].astype(int)
 
-    # 19点增加打捞的优质视频
-    if now_h == 19 and add_videos_in_19h is True:
+    # 20点增加打捞的优质视频
+    if now_h == 20 and add_videos_in_20h is True:
         # print(len(h_recall_df))
         h_recall_df = add_videos(initial_df=h_recall_df, now_date=now_date, rule_key=rule_key,
                                  region=region, data_key=data_key)
@@ -405,7 +405,7 @@ def merge_df_with_score(df_left, df_right):
 
 
 def process_with_region(region, df_merged, data_key, rule_key, rule_param, now_date, now_h,
-                        rule_rank_h_flag, add_videos_in_19h):
+                        rule_rank_h_flag, add_videos_in_20h):
     log_.info(f"region = {region} start...")
     # 计算score
     region_df = df_merged[df_merged['code'] == region]
@@ -413,18 +413,18 @@ def process_with_region(region, df_merged, data_key, rule_key, rule_param, now_d
     score_df = cal_score(df=region_df, param=rule_param)
     video_rank(df=score_df, now_date=now_date, now_h=now_h, rule_key=rule_key, param=rule_param,
                region=region, data_key=data_key, rule_rank_h_flag=rule_rank_h_flag,
-               add_videos_in_19h=add_videos_in_19h)
+               add_videos_in_20h=add_videos_in_20h)
     log_.info(f"region = {region} end!")
 
 
 def process_with_region2(region, df_merged, data_key, rule_key, rule_param, now_date, now_h,
-                         rule_rank_h_flag, add_videos_in_19h):
+                         rule_rank_h_flag, add_videos_in_20h):
     log_.info(f"region = {region} start...")
     region_score_df = df_merged[df_merged['code'] == region]
     log_.info(f'region = {region}, region_score_df count = {len(region_score_df)}')
     video_rank(df=region_score_df, now_date=now_date, now_h=now_h, region=region,
                rule_key=rule_key, param=rule_param, data_key=data_key, rule_rank_h_flag=rule_rank_h_flag,
-               add_videos_in_19h=add_videos_in_19h)
+               add_videos_in_20h=add_videos_in_20h)
     log_.info(f"region = {region} end!")
 
 
@@ -520,8 +520,8 @@ def process_with_param(param, data_params_item, rule_params_item, region_code_li
     rule_param = rule_params_item.get(rule_key)
     log_.info(f"rule_key = {rule_key}, rule_param = {rule_param}")
     merge_func = rule_param.get('merge_func', None)
-    # 是否在19点的数据中增加打捞的优质视频
-    add_videos_in_19h = rule_param.get('add_videos_in_19h', False)
+    # 是否在20点的数据中增加打捞的优质视频
+    add_videos_in_20h = rule_param.get('add_videos_in_20h', False)
 
     if merge_func == 2:
         score_df_list = []
@@ -538,7 +538,7 @@ def process_with_param(param, data_params_item, rule_params_item, region_code_li
         task_list = [
             gevent.spawn(process_with_region2,
                          region, df_merged, data_key, rule_key, rule_param, now_date, now_h, rule_rank_h_flag,
-                         add_videos_in_19h)
+                         add_videos_in_20h)
             for region in region_code_list
         ]
     else:
@@ -547,7 +547,7 @@ def process_with_param(param, data_params_item, rule_params_item, region_code_li
         task_list = [
             gevent.spawn(process_with_region,
                          region, df_merged, data_key, rule_key, rule_param, now_date, now_h, rule_rank_h_flag,
-                         add_videos_in_19h)
+                         add_videos_in_20h)
             for region in region_code_list
         ]