data66 rule68 新实验

config.py

@@ -427,8 +427,8 @@ class BaseConfig(object):
                 'region_24h_rule_key': 'rule66', '24h_rule_key': 'rule66'
             },
             'rule68': {
-                'view_type': 'video-show-region', "return_countv2": 2, 'platform_return_ratev2': 0.001,
-                'region_24h_rule_key': 'rule66', '24h_rule_key': 'rule66'
+                 'view_type': 'video-show-region','region_24h_rule_key': 'rule68', '24h_rule_key': 'rule68',
+                 'score_func': '20240322', '20240322':''
             },
         },
         'data_params': DATA_PARAMS,

region_rule_rank_h_v2.py

@@ -145,34 +145,30 @@ def get_feature_data(project, table, now_date):
     return feature_df
 
 
-def cal_score_initial_20240223(df, param):
+def cal_score_initial_20240322(df, param):
     """
     计算score
     :param df: 特征数据
     :param param: 规则参数
     :return:
     """
-    log_.info("进入了cal_score_initial_20240223")
+    log_.info("进入了cal_score_initial_20240322")
     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['back_rate_new'] = (df['lastonehour_return'] + 1) / (df['lastonehour_share'] + 10)
-    df['back_rate_all'] = df['lastonehour_allreturn'] / (df['lastonehour_allreturn_sharecnt'] + 10)
-    df['log_back'] = (df['lastonehour_return'] + 1).apply(math.log)
-    df['log_back_all'] = (df['lastonehour_allreturn'] + 1).apply(math.log)
-    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)
-    else:
-        df['ctr'] = df['lastonehour_play'] / (df['lastonehour_preview'] + 1000)
+    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)
+    df['ctr'] = (df['lastonehour_play'] + 1) / (df['lastonehour_show_region'] + 1000)
     df['K2'] = df['ctr'].apply(lambda x: 0.6 if x > 0.6 else x)
     df['platform_return_rate'] = df['platform_return'] / df['lastonehour_return']
-    df['score'] = df['share_rate'] * (
-        df['back_rate_new'] + 0.01 * df['back_rate_all']
-    ) * (
-            df['log_back'] + 0.01 * df['log_back_all']
-    ) * df['K2']
+    df['score1'] = df['share_rate'] * df['back_rate'] * df['log_back'] * df['K2']
+    click_score_rate = param.get('click_score_rate', None)
+    back_score_rate = param.get('click_score_rate', None)
+    if click_score_rate is not None:
+        df['score'] = (1 - click_score_rate) * df['score1'] + click_score_rate * df['K2']
+    elif back_score_rate is not None:
+        df['score'] = (1 - back_score_rate) * df['score1'] + back_score_rate * df['back_rate']
+    else:
+        df['score'] = df['score1']
     df = df.sort_values(by=['score'], ascending=False)
     return df
 
@@ -557,8 +553,8 @@ def cal_score(df, param, now_h):
             df = cal_score_with_back_rate_exponential_weighting2(df=df, param=param)
         elif param.get('score_func', None) == 'back_rate_rank_weighting':
             df = cal_score_with_back_rate_by_rank_weighting(df=df, param=param)
-        elif param.get('score_func', None) == '20240223':
-            df = cal_score_initial_20240223(df=df, param=param)
+        elif param.get('score_func', None) == '20240322':
+            df = cal_score_initial_20240322(df=df, param=param)
         else:
             df = cal_score_initial(df=df, param=param, now_h=now_h)
     return df
@@ -650,8 +646,6 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
     return_count = param.get('return_count', 1)
     score_value = param.get('score_rule', 0)
     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)]
     # zhangbo
     if now_h in [1, 2, 3, 4]:
         h_recall_df = df[
@@ -664,22 +658,12 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
             (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")
+    if "20240322" in param.keys():
+        log_.info("采用20240322新加的过滤")
         h_recall_df = df[
-            (df['lastonehour_allreturn'] > 0)
-            ]
-        
-    # try:
-    #     if "return_countv2" in param.keys() and "platform_return_ratev2" in param.keys():
-    #         return_countv2 = param["return_countv2"]
-    #         platform_return_ratev2 = param["platform_return_ratev2"]
-    #         h_recall_df = h_recall_df[
-    #             df['platform_return_rate'] >= platform_return_ratev2 |
-    #             (df['platform_return_rate'] < platform_return_ratev2 & df['lastonehour_return'] > return_countv2)
-    #             ]
-    # except Exception as e:
-    #     log_.error("return_countv2 is wrong with{}".format(e))
+            (df['lastonehour_return'] > 0) |
+            (df['lastonehour_allreturn'] > 1)
+        ]
 
     # videoid重复时，保留分值高
     h_recall_df = h_recall_df.sort_values(by=['score'], ascending=False)