update rule_rank_h_by_24h & region_rule_rank_h_by24h

config.py

@@ -128,14 +128,14 @@ class BaseConfig(object):
 
     # ##### 区分appType数据
     DATA_PARAMS = {
-        'data1': [APP_TYPE['VLOG'], ],  # vlog
-        'data2': [APP_TYPE['VLOG'], APP_TYPE['LONG_VIDEO'], ],  # [vlog, 内容精选]
-        'data3': [APP_TYPE['VLOG'], APP_TYPE['LOVE_LIVE'], ],  # [vlog, 票圈视频]
-        'data4': [APP_TYPE['VLOG'], APP_TYPE['SHORT_VIDEO'], ],  # [vlog, 票圈短视频]
-        'data5': [APP_TYPE['VLOG'], APP_TYPE['ZUI_JING_QI']],  # [vlog, 最惊奇]
-        'data6': [APP_TYPE['VLOG'], APP_TYPE['LOVE_LIVE'], APP_TYPE['LONG_VIDEO'], APP_TYPE['SHORT_VIDEO']],
-        'data7': [APP_TYPE['VLOG'], APP_TYPE['LOVE_LIVE'], APP_TYPE['LONG_VIDEO'], APP_TYPE['SHORT_VIDEO'],
-                  APP_TYPE['APP']],
+        'data1': {APP_TYPE['VLOG']: 0},  # vlog
+        'data2': {APP_TYPE['VLOG']: 0, APP_TYPE['LONG_VIDEO']: 0},  # [vlog, 内容精选]
+        # 'data3': [APP_TYPE['VLOG'], APP_TYPE['LOVE_LIVE'], ],  # [vlog, 票圈视频]
+        # 'data4': [APP_TYPE['VLOG'], APP_TYPE['SHORT_VIDEO'], ],  # [vlog, 票圈短视频]
+        # 'data5': [APP_TYPE['VLOG'], APP_TYPE['ZUI_JING_QI']],  # [vlog, 最惊奇]
+        'data6': {APP_TYPE['VLOG']: 0.25, APP_TYPE['LOVE_LIVE']: 0.25, APP_TYPE['LONG_VIDEO']: 0.25, APP_TYPE['SHORT_VIDEO']: 0.25},
+        # 'data7': [APP_TYPE['VLOG'], APP_TYPE['LOVE_LIVE'], APP_TYPE['LONG_VIDEO'], APP_TYPE['SHORT_VIDEO'],
+        #           APP_TYPE['APP']],
     }
 
     # 小时级更新过去48h数据 loghubods.video_data_each_hour_dataset_48h_total_apptype
@@ -166,6 +166,8 @@ class BaseConfig(object):
                       'view_type': 'preview'},
             'rule3': {'cal_score_func': 2, 'return_count': 100, 'platform_return_rate': 0.001,
                       'view_type': 'preview'},
+            'rule4': {'cal_score_func': 2, 'return_count': 100, 'platform_return_rate': 0.001,
+                      'view_type': 'preview', 'merge_func': 2},
         },
         'data_params': DATA_PARAMS,
         'params_list': [
@@ -177,6 +179,7 @@ class BaseConfig(object):
             # {'data': 'data4', 'rule': 'rule2'},
             # {'data': 'data7', 'rule': 'rule2'},
             # {'data': 'data6', 'rule': 'rule2'},
+            {'data': 'data6', 'rule': 'rule4'},
         ]
     }
 
@@ -191,6 +194,8 @@ class BaseConfig(object):
                       'platform_return_rate': 0.001},
             'rule3': {'view_type': 'preview', 'return_count': 21, 'score_rule': 0,
                       'platform_return_rate': 0.001},
+            'rule4': {'view_type': 'video-show', 'return_count': 21, 'score_rule': 0,
+                      'platform_return_rate': 0.001, 'merge_func': 2},
         },
         'data_params': DATA_PARAMS,
         'params_list': [
@@ -200,6 +205,7 @@ class BaseConfig(object):
             # {'data': 'data4', 'rule': 'rule2'},
             # {'data': 'data6', 'rule': 'rule2'},
             # {'data': 'data7', 'rule': 'rule3'},
+            {'data': 'data6', 'rule': 'rule4'},
         ]
     }
 
@@ -767,8 +773,8 @@ class ProductionConfig(BaseConfig):
 
 def set_config():
     # 获取环境变量 ROV_OFFLINE_ENV
-    env = os.environ.get('ROV_OFFLINE_ENV')
-    # env = 'dev'
+    # env = os.environ.get('ROV_OFFLINE_ENV')
+    env = 'dev'
     if env is None:
         # log_.error('ENV ERROR: is None!')
         return

region_rule_rank_h_by24h.py

@@ -197,6 +197,21 @@ def merge_df(df_left, df_right):
     return df_merged[feature_list]
 
 
+def merge_df_with_score(df_left, df_right):
+    """
+    df 按照videoid合并，平台回流人数、回流人数、分数 分别求和
+    :param df_left:
+    :param df_right:
+    :return:
+    """
+    df_merged = pd.merge(df_left, df_right, on=['videoid', 'code'], how='outer', suffixes=['_x', '_y'])
+    df_merged.fillna(0, inplace=True)
+    feature_list = ['videoid', 'code', 'lastday_return', 'platform_return', 'score']
+    for feature in feature_list[2:]:
+        df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y']
+    return df_merged[feature_list]
+
+
 def process_with_region(region, df_merged, data_key, rule_key, rule_param, now_date, now_h):
     log_.info(f"region = {region} start...")
     # 计算score
@@ -208,6 +223,15 @@ def process_with_region(region, df_merged, data_key, rule_key, rule_param, now_d
     log_.info(f"region = {region} end!")
 
 
+def process_with_region2(region, df_merged, data_key, rule_key, rule_param, now_date, now_h):
+    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)
+    log_.info(f"region = {region} end!")
+
+
 def process_with_app_type(app_type, params, region_code_list, feature_df, now_date, now_h):
     log_.info(f"app_type = {app_type} start...")
     data_params_item = params.get('data_params')
@@ -233,22 +257,38 @@ def process_with_app_type(app_type, params, region_code_list, feature_df, now_da
 
 def process_with_param(param, data_params_item, rule_params_item, region_code_list, feature_df, now_date, now_h):
     log_.info(f"param = {param} start...")
-
     data_key = param.get('data')
     data_param = data_params_item.get(data_key)
     log_.info(f"data_key = {data_key}, data_param = {data_param}")
-    df_list = [feature_df[feature_df['apptype'] == apptype] for apptype in data_param]
-    df_merged = reduce(merge_df, df_list)
-
     rule_key = param.get('rule')
     rule_param = rule_params_item.get(rule_key)
     log_.info(f"rule_key = {rule_key}, rule_param = {rule_param}")
-    task_list = [
-        gevent.spawn(process_with_region, region, df_merged, data_key, rule_key, rule_param, now_date, now_h)
-        for region in region_code_list
-    ]
-    gevent.joinall(task_list)
+    merge_func = rule_param.get('merge_func', None)
+    if merge_func == 2:
+        score_df_list = []
+        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['score'] = score_df['score'] * weight
+            score_df_list.append(score_df)
+        # 分数合并
+        df_merged = reduce(merge_df_with_score, score_df_list)
+        # 更新平台回流比
+        df_merged['platform_return_rate'] = df_merged['platform_return'] / df_merged['lastday_return']
+        task_list = [
+            gevent.spawn(process_with_region2, region, df_merged, data_key, rule_key, rule_param, now_date, now_h)
+            for region in region_code_list
+        ]
+    else:
+        df_list = [feature_df[feature_df['apptype'] == apptype] for apptype in data_param]
+        df_merged = reduce(merge_df, df_list)
+        task_list = [
+            gevent.spawn(process_with_region, region, df_merged, data_key, rule_key, rule_param, now_date, now_h)
+            for region in region_code_list
+        ]
 
+    gevent.joinall(task_list)
     log_.info(f"param = {param} end!")
 
 
@@ -261,7 +301,7 @@ def rank_by_24h(project, table, now_date, now_h, rule_params, region_code_list):
     rule_params_item = rule_params.get('rule_params')
     params_list = rule_params.get('params_list')
     pool = multiprocessing.Pool(processes=len(params_list))
-    for param in params_list:
+    for param in params_list[1:]:
         pool.apply_async(
             func=process_with_param,
             args=(param, data_params_item, rule_params_item, region_code_list, feature_df, now_date, now_h)

rule_rank_h_by_24h.py

@@ -178,7 +178,7 @@ def video_rank_h(df, now_date, now_h, rule_key, param, data_key):
         # 清空线上过滤应用列表
         # redis_helper.del_keys(key_name=f"{config_.H_VIDEO_FILER_24H}{app_type}.{data_key}.{rule_key}")
 
-    if rule_key == 'rule3':
+    if rule_key in ['rule3', 'rule4']:
         # 去重筛选结果，保留剩余数据并写入Redis
         all_videos = df['videoid'].to_list()
         log_.info(f'h_by24h_recall all videos count = {len(all_videos)}')
@@ -232,6 +232,21 @@ def merge_df(df_left, df_right):
     return df_merged[feature_list]
 
 
+def merge_df_with_score(df_left, df_right):
+    """
+    df 按照videoid合并，平台回流人数、回流人数、分数 分别求和
+    :param df_left:
+    :param df_right:
+    :return:
+    """
+    df_merged = pd.merge(df_left, df_right, on=['videoid'], how='outer', suffixes=['_x', '_y'])
+    df_merged.fillna(0, inplace=True)
+    feature_list = ['videoid', '回流人数', 'platform_return', 'score']
+    for feature in feature_list[1:]:
+        df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y']
+    return df_merged[feature_list]
+
+
 def rank_by_h(now_date, now_h, rule_params, project, table):
     # 获取特征数据
     feature_df = get_feature_data(now_date=now_date, now_h=now_h, project=project, table=table)
@@ -239,6 +254,7 @@ def rank_by_h(now_date, now_h, rule_params, project, table):
     # rank
     data_params_item = rule_params.get('data_params')
     rule_params_item = rule_params.get('rule_params')
+    """
     for param in rule_params.get('params_list'):
         data_key = param.get('data')
         data_param = data_params_item.get(data_key)
@@ -257,31 +273,46 @@ def rank_by_h(now_date, now_h, rule_params, project, table):
             score_df = cal_score1(df=df_merged)
         video_rank_h(df=score_df, now_date=now_date, now_h=now_h,
                      rule_key=rule_key, param=rule_param, data_key=data_key)
-
     """
-    for app_type, params in rule_params.items():
-        log_.info(f"app_type = {app_type}")
-        data_params_item = params.get('data_params')
-        rule_params_item = params.get('rule_params')
-        for param in params.get('params_list'):
-            data_key = param.get('data')
-            data_param = data_params_item.get(data_key)
-            log_.info(f"data_key = {data_key}, data_param = {data_param}")
-            df_list = [feature_df[feature_df['apptype'] == apptype] for apptype in data_param]
-            df_merged = reduce(merge_df, df_list)
 
-            rule_key = param.get('rule')
-            rule_param = rule_params_item.get(rule_key)
-            log_.info(f"rule_key = {rule_key}, rule_param = {rule_param}")
-            # 计算score
-            cal_score_func = rule_param.get('cal_score_func', 1)
+    for param in rule_params.get('params_list'):
+        score_df_list = []
+        data_key = param.get('data')
+        data_param = data_params_item.get(data_key)
+        log_.info(f"data_key = {data_key}, data_param = {data_param}")
+        rule_key = param.get('rule')
+        rule_param = rule_params_item.get(rule_key)
+        log_.info(f"rule_key = {rule_key}, rule_param = {rule_param}")
+        cal_score_func = rule_param.get('cal_score_func', 1)
+        merge_func = rule_param.get('merge_func', 1)
+
+        if merge_func == 2:
+            for apptype, weight in data_param.items():
+                df = feature_df[feature_df['apptype'] == apptype]
+                # 计算score
+                if cal_score_func == 2:
+                    score_df = cal_score2(df=df, param=rule_param)
+                else:
+                    score_df = cal_score1(df=df)
+                score_df['score'] = score_df['score'] * weight
+                score_df_list.append(score_df)
+            # 分数合并
+            df_merged = reduce(merge_df_with_score, score_df_list)
+            # 更新平台回流比
+            df_merged['platform_return_rate'] = df_merged['platform_return'] / df_merged['回流人数']
+            video_rank_h(df=df_merged, now_date=now_date, now_h=now_h,
+                         rule_key=rule_key, param=rule_param, data_key=data_key)
+
+        else:
+            df_list = [feature_df[feature_df['apptype'] == apptype] for apptype, _ in data_param.items()]
+            df_merged = reduce(merge_df, df_list)
             if cal_score_func == 2:
                 score_df = cal_score2(df=df_merged, param=rule_param)
             else:
                 score_df = cal_score1(df=df_merged)
-            video_rank_h(df=score_df, now_date=now_date, now_h=now_h, rule_key=rule_key, param=rule_param,
-                         app_type=app_type, data_key=data_key)
-    """
+            video_rank_h(df=score_df, now_date=now_date, now_h=now_h,
+                         rule_key=rule_key, param=rule_param, data_key=data_key)
+
     #     # to-csv
     #     score_filename = f"score_by24h_{key}_{datetime.strftime(now_date, '%Y%m%d%H')}.csv"
     #     score_df.to_csv(f'./data/{score_filename}')