add region-h-rule preview -> videoshow

config.py

@@ -120,8 +120,8 @@ class BaseConfig(object):
 
     # 地域分组小时级规则参数
     RULE_PARAMS_REGION = {
-        'rule1': {'view_type': 'pre-view', 'platform_return_rate': 0.001},
-        'rule2': {'view_type': 'video-show', 'platform_return_rate': 0.001},
+        'rule1': {'view_type': 'pre-view', 'platform_return_rate': 0.001, 'region_24h_rule_key': 'rule1'},
+        'rule2': {'view_type': 'video-show', 'platform_return_rate': 0.001, 'region_24h_rule_key': 'rule2'},
     }
 
     # 地域分组天级规则更新使用数据
@@ -140,6 +140,7 @@ class BaseConfig(object):
     # 地域分组小时级更新24h规则参数
     RULE_PARAMS_REGION_24H = {
         'rule1': {'view_type': 'pre-view', 'return_count': 21, 'score_rule': 0, 'platform_return_rate': 0.001},
+        'rule2': {'view_type': 'video-show', 'return_count': 21, 'score_rule': 0, 'platform_return_rate': 0.001},
     }
 
     # 老视频更新使用数据

region_rule_rank_h.py

@@ -216,11 +216,13 @@ def video_rank(df, now_date, now_h, rule_key, param, region):
     # if len(initial_data_dup) > 0:
     #     redis_helper.add_data_with_zset(key_name=initial_key_name, data=initial_data_dup, expire_time=23 * 3600)
 
+    region_24h_rule_key = param.get('region_24h_rule_key', 'rule1')
     # 与其他召回视频池去重，存入对应的redis
-    dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h, rule_key=rule_key, region=region)
+    dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h, rule_key=rule_key,
+                 region_24h_rule_key=region_24h_rule_key, region=region)
 
 
-def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region):
+def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, region):
     """将地域分组小时级数据与其他召回视频池去重，存入对应的redis"""
     redis_helper = RedisHelper()
     # # ##### 去重更新地域分组天级列表，并另存为redis中
@@ -245,7 +247,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region):
 
     # ##### 去重更新地域分组小时级24h列表，并另存为redis中
     region_24h_key_name = \
-        f"{config_.RECALL_KEY_NAME_PREFIX_REGION_BY_24H}{region}.rule1." \
+        f"{config_.RECALL_KEY_NAME_PREFIX_REGION_BY_24H}{region}.{region_24h_rule_key}." \
         f"{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}"
     if redis_helper.key_exists(key_name=region_24h_key_name):
         region_24h_data = redis_helper.get_data_zset_with_index(
@@ -324,9 +326,10 @@ def rank_by_h(project, table, now_date, now_h, rule_params, region_code_list):
                        "score_df": score_df[['videoid', 'score']]})
 
 
-def h_rank_bottom(now_date, now_h, rule_key, region_code_list):
+def h_rank_bottom(now_date, now_h, rule_key, region_code_list, param):
     """未按时更新数据，用上一小时结果作为当前小时的数据"""
     log_.info(f"rule_key = {rule_key}")
+    region_24h_rule_key = param.get('region_24h_rule_key', 'rule1')
     # 获取rov模型结果
     redis_helper = RedisHelper()
     if now_h == 0:
@@ -364,7 +367,8 @@ def h_rank_bottom(now_date, now_h, rule_key, region_code_list):
         # 清空线上过滤应用列表
         redis_helper.del_keys(key_name=f"{config_.REGION_H_VIDEO_FILER}{region}.{rule_key}")
         # 与其他召回视频池去重，存入对应的redis
-        dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h, rule_key=rule_key, region=region)
+        dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h,
+                     rule_key=rule_key, region_24h_rule_key=region_24h_rule_key, region=region)
 
 
 def h_timer_check():
@@ -377,8 +381,8 @@ def h_timer_check():
     now_h = datetime.datetime.now().hour
     now_min = datetime.datetime.now().minute
     if now_h == 0:
-        for key, _ in rule_params.items():
-            h_rank_bottom(now_date=now_date, now_h=now_h, rule_key=key, region_code_list=region_code_list)
+        for key, value in rule_params.items():
+            h_rank_bottom(now_date=now_date, now_h=now_h, rule_key=key, region_code_list=region_code_list, param=value)
         return
     # 查看当前小时更新的数据是否已准备好
     h_data_count = h_data_check(project=project, table=table, now_date=now_date)
@@ -389,8 +393,8 @@ def h_timer_check():
                   project=project, table=table, region_code_list=region_code_list)
     elif now_min > 50:
         log_.info('h_recall data is None, use bottom data!')
-        for key, _ in rule_params.items():
-            h_rank_bottom(now_date=now_date, now_h=now_h, rule_key=key, region_code_list=region_code_list)
+        for key, value in rule_params.items():
+            h_rank_bottom(now_date=now_date, now_h=now_h, rule_key=key, region_code_list=region_code_list, param=value)
     else:
         # 数据没准备好，1分钟后重新检查
         Timer(60, h_timer_check).start()

region_rule_rank_h_by24h.py

@@ -125,10 +125,11 @@ def get_feature_data(project, table, now_date):
     return feature_df
 
 
-def cal_score(df):
+def cal_score(df, param):
     """
     计算score
     :param df: 特征数据
+    :param param:
     :return:
     """
     # score计算公式: sharerate*backrate*logback*ctr
@@ -141,7 +142,10 @@ def cal_score(df):
     df['share_rate'] = df['lastday_share'] / (df['lastday_play'] + 1000)
     df['back_rate'] = df['lastday_return'] / (df['lastday_share'] + 10)
     df['log_back'] = (df['lastday_return'] + 1).apply(math.log)
-    df['ctr'] = df['lastday_play'] / (df['lastday_preview'] + 1000)
+    if param.get('view_type', None) == 'video-show':
+        df['ctr'] = df['lastday_play'] / (df['platform_show'] + 1000)
+    else:
+        df['ctr'] = df['lastday_play'] / (df['lastday_preview'] + 1000)
     df['K2'] = df['ctr'].apply(lambda x: 0.6 if x > 0.6 else x)
     df['score'] = df['share_rate'] * df['back_rate'] * df['log_back'] * df['K2']
     df['platform_return_rate'] = df['platform_return'] / df['lastday_return']
@@ -209,7 +213,7 @@ def rank_by_24h(project, table, now_date, now_h, rule_params, region_code_list):
             # 计算score
             region_df = feature_df[feature_df['code'] == region]
             log_.info(f'region_df count = {len(region_df)}')
-            score_df = cal_score(df=region_df)
+            score_df = cal_score(df=region_df, param=value)
             video_rank(df=score_df, now_date=now_date, now_h=now_h, rule_key=key, param=value, region=region)
             # to-csv
             score_filename = f"score_24h_{region}_{key}_{datetime.datetime.strftime(now_date, '%Y%m%d%H')}.csv"