0-4点改为新公式

region_rule_rank_h_v2.py

@@ -176,7 +176,7 @@ def cal_score_initial_20240223(df, param):
     df = df.sort_values(by=['score'], ascending=False)
     return df
 
-def cal_score_initial(df, param):
+def cal_score_initial(df, param, now_h):
     """
     计算score
     :param df: 特征数据
@@ -190,13 +190,23 @@ def cal_score_initial(df, param):
     # score = sharerate * backrate * LOG(lastonehour_return+1) * K2
 
     df = df.fillna(0)
-    df['share_rate'] = df['lastonehour_share'] / (df['lastonehour_play'] + 1000)
-    df['back_rate'] = df['lastonehour_return'] / (df['lastonehour_share'] + 10)
-    df['log_back'] = (df['lastonehour_return'] + 1).apply(math.log)
+    # zhangbo
+    if now_h in [1,2,3,4]:
+        df['log_back'] = (df['lastonehour_allreturn'] + 1).apply(math.log)
+        df['share_rate'] = (df['lastonehour_share'] + 1) / (df['lastonehour_play'] + 1000)
+        df['back_rate'] = (df['lastonehour_return'] + 1) / (df['lastonehour_share'] + 10)
+    else:
+        df['log_back'] = (df['lastonehour_return'] + 1).apply(math.log)
+        df['share_rate'] = df['lastonehour_share'] / (df['lastonehour_play'] + 1000)
+        df['back_rate'] = df['lastonehour_return'] / (df['lastonehour_share'] + 10)
+
     if param.get('view_type', None) == 'video-show':
         df['ctr'] = df['lastonehour_play'] / (df['lastonehour_show'] + 1000)
     elif param.get('view_type', None) == 'video-show-region':
-        df['ctr'] = df['lastonehour_play'] / (df['lastonehour_show_region'] + 1000)
+        if now_h in [1, 2, 3, 4]:
+            df['ctr'] = (df['lastonehour_play'] + 1) / (df['lastonehour_show_region'] + 1000)
+        else:
+            df['ctr'] = df['lastonehour_play'] / (df['lastonehour_show_region'] + 1000)
     else:
         df['ctr'] = df['lastonehour_play'] / (df['lastonehour_preview'] + 1000)
     df['K2'] = df['ctr'].apply(lambda x: 0.6 if x > 0.6 else x)
@@ -524,7 +534,7 @@ def cal_score_with_back_rate_by_rank_weighting(df, param):
 
 
 
-def cal_score(df, param):
+def cal_score(df, param, now_h):
     if param.get('return_data', None) == 'share_region_return':
         if param.get('score_func', None) == 'multiply_return_retention':
             df = cal_score_multiply_return_retention_with_new_return(df=df, param=param)
@@ -550,7 +560,7 @@ def cal_score(df, param):
         elif param.get('score_func', None) == '20240223':
             df = cal_score_initial_20240223(df=df, param=param)
         else:
-            df = cal_score_initial(df=df, param=param)
+            df = cal_score_initial(df=df, param=param, now_h=now_h)
     return df
 
 
@@ -642,10 +652,17 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
     platform_return_rate = param.get('platform_return_rate', 0)
     # h_recall_df = df[(df['lastonehour_return'] >= return_count) & (df['score'] >= score_value)
     #                  & (df['platform_return_rate'] >= platform_return_rate)]
-    h_recall_df = df[
-        (df['lastonehour_return'] >= return_count) &
-        (df['score'] >= score_value) &
-        (df['platform_return_rate'] >= platform_return_rate)
+    # zhangbo
+    if now_h in [1, 2, 3, 4]:
+        h_recall_df = df[
+            (df['lastonehour_return'] > 0) |
+            (df['lastonehour_allreturn'] > 1)
+        ]
+    else:
+        h_recall_df = df[
+            (df['lastonehour_return'] >= return_count) &
+            (df['score'] >= score_value) &
+            (df['platform_return_rate'] >= platform_return_rate)
         ]
     if "lastonehour_allreturn" in param.keys():
         log_.info("采用 lastonehour_allreturn 过滤")
@@ -763,7 +780,7 @@ def process_with_region(region, df_merged, data_key, rule_key, rule_param, now_d
     log_.info(f"多协程的region = {region} 开始执行")
     region_df = df_merged[df_merged['code'] == region]
     log_.info(f'该区域region = {region}, 下有多少数据量 = {len(region_df)}')
-    score_df = cal_score(df=region_df, param=rule_param)
+    score_df = cal_score(df=region_df, param=rule_param, now_h=now_h)
     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_with_pre_h=add_videos_with_pre_h, hour_count=hour_count)
@@ -861,7 +878,7 @@ def process_with_param(param, data_params_item, rule_params_item, region_code_li
         for apptype, weight in data_param.items():
             df = feature_df[feature_df['apptype'] == apptype]
             # 计算score
-            score_df = cal_score(df=df, param=rule_param)
+            score_df = cal_score(df=df, param=rule_param, now_h=now_h)
             score_df['score'] = score_df['score'] * weight
             score_df_list.append(score_df)
         # 分数合并