add ad_user_data_update_with_new_strategy

ad_user_data_update_with_new_strategy.py

@@ -0,0 +1,113 @@
+import datetime
+import traceback
+from threading import Timer
+from utils import RedisHelper, data_check, get_feature_data, send_msg_to_feishu
+from config import set_config
+from log import Log
+config_, _ = set_config()
+log_ = Log()
+redis_helper = RedisHelper()
+
+features = [
+    'apptype',
+    'group',
+    'adrate',
+    'sharerate',
+    'adrate_share'
+]
+
+
+def predict_user_group_share_rate(user_group_initial_df, dt, data_params, rule_params, param):
+    """预估用户组对应的有广告时分享率"""
+    # 获取对应的参数
+    data_key = param.get('data')
+    data_param = data_params.get(data_key)
+    rule_key = param.get('rule')
+    rule_param = rule_params.get(rule_key)
+
+    # 获取对应的用户组特征
+    user_group_df = user_group_initial_df.copy()
+    user_group_df['apptype'] = user_group_df['apptype'].astype(int)
+    user_group_df = user_group_df[user_group_df['apptype'] == data_param]
+    user_group_df['adrate'].fillna(0, inplace=True)
+    user_group_df['sharerate'].fillna(0, inplace=True)
+    user_group_df['adrate_share'].fillna(0, inplace=True)
+    user_group_df['adrate'] = user_group_df['adrate'].astype(float)
+    user_group_df['sharerate'] = user_group_df['sharerate'].astype(float)
+    user_group_df['adrate_share'] = user_group_df['adrate_share'].astype(float)
+
+    # 获取对应的用户分组数据
+    user_group_list = rule_param.get('group_list')
+    user_group_df = user_group_df[user_group_df['group'].isin(user_group_list)]
+
+    # 去除对应无广告用户组
+    if rule_param.get('remove_no_ad_group') is True:
+        user_group_df = user_group_df[~user_group_df['group'].isin(rule_param.get('no_ad_mid_group_list'))]
+
+    # 计算用户组有广告时分享率
+    user_group_df = user_group_df[user_group_df['adrate'] != 0]
+    user_group_df['group_ad_share_rate'] = \
+        user_group_df['adrate_share'] * user_group_df['sharerate'] / user_group_df['adrate']
+    user_group_df['group_ad_share_rate'].fillna(0, inplace=True)
+
+    # 结果写入redis
+    key_name = f"{config_.KEY_NAME_PREFIX_AD_GROUP}{data_key}:{rule_key}:{dt}"
+    redis_data = {}
+    for index, item in user_group_df.iterrows():
+        redis_data[item['group']] = item['group_ad_share_rate']
+    group_ad_share_rate_mean = user_group_df['group_ad_share_rate'].mean()
+    redis_data['mean_group'] = group_ad_share_rate_mean
+    if len(redis_data) > 0:
+        redis_helper = RedisHelper()
+        redis_helper.add_data_with_zset(key_name=key_name, data=redis_data, expire_time=2 * 24 * 3600)
+    return user_group_df
+
+
+def update_users_data(project, table, dt, update_params):
+    """预估用户组有广告时分享率"""
+    # 获取用户组特征
+    user_group_initial_df = get_feature_data(project=project, table=table, features=features, dt=dt)
+    data_params = update_params.get('data_params')
+    rule_params = update_params.get('rule_params')
+    for param in update_params.get('params_list'):
+        log_.info(f"param = {param} update start...")
+        predict_user_group_share_rate(user_group_initial_df=user_group_initial_df,
+                                      dt=dt,
+                                      data_params=data_params,
+                                      rule_params=rule_params,
+                                      param=param)
+        log_.info(f"param = {param} update end!")
+
+
+def timer_check():
+    try:
+        update_params = config_.AD_USER_PARAMS_NEW_STRATEGY
+        project = config_.ad_model_data['users_share_rate_new_strategy'].get('project')
+        table = config_.ad_model_data['users_share_rate_new_strategy'].get('table')
+        now_date = datetime.datetime.today()
+        dt = datetime.datetime.strftime(now_date, '%Y%m%d')
+        log_.info(f"now_date: {dt}")
+        # 查看当前更新的数据是否已准备好
+        data_count = data_check(project=project, table=table, dt=dt)
+        if data_count > 0:
+            log_.info(f"ad user group data count = {data_count}")
+            # 数据准备好，进行更新
+            update_users_data(project=project, table=table, dt=dt, update_params=update_params)
+            log_.info(f"ad user group data update end!")
+        else:
+            # 数据没准备好，1分钟后重新检查
+            Timer(60, timer_check).start()
+
+    except Exception as e:
+        log_.error(f"用户组分享率预测数据更新失败, exception: {e}, traceback: {traceback.format_exc()}")
+        send_msg_to_feishu(
+            webhook=config_.FEISHU_ROBOT['server_robot'].get('webhook'),
+            key_word=config_.FEISHU_ROBOT['server_robot'].get('key_word'),
+            msg_text=f"rov-offline{config_.ENV_TEXT} - 用户组分享率预测数据更新失败\n"
+                     f"exception: {e}\n"
+                     f"traceback: {traceback.format_exc()}"
+        )
+
+
+if __name__ == '__main__':
+    timer_check()

config.py

@@ -1109,6 +1109,33 @@ class BaseConfig(object):
         ]
     }
 
+    # 新策略使用 - 广告模型用户数据
+    AD_USER_PARAMS_NEW_STRATEGY = {
+        'data_params': {
+            'user0': APP_TYPE['VLOG'],  # vlog
+            'user3': APP_TYPE['BLESSING_YEAR'],  # 票圈福年
+            'user4': APP_TYPE['LOVE_LIVE'],  # 票圈视频
+            'user5': APP_TYPE['LONG_VIDEO'],  # 内容精选
+            'user6': APP_TYPE['SHORT_VIDEO'],  # 票圈短视频
+            'user18': APP_TYPE['LAO_HAO_KAN_VIDEO'],  # 老好看视频
+            'user19': APP_TYPE['ZUI_JING_QI'],  # 票圈最惊奇
+            'user21': APP_TYPE['PIAO_QUAN_VIDEO_PLUS'],  # 票圈视频+
+            'user22': APP_TYPE['JOURNEY'],  # 票圈足迹
+        },
+        'rule_params': {
+            'rule1': {
+                'group_list': AD_MID_GROUP['class1'],
+                'no_ad_mid_group_list': [],
+                'remove_no_ad_group': True,  # mean_group 预测&计算阈值时，去除不出广告的用户组
+            },  # 优化阈值计算方式
+        },
+        'params_list': [
+            {'data': 'user0', 'rule': 'rule1'},  # 票圈vlog + 优化阈值计算方式
+            {'data': 'user4', 'rule': 'rule1'},  # 票圈视频 + 优化阈值计算方式
+            {'data': 'user5', 'rule': 'rule1'},  # 内容精选 + 优化阈值计算方式
+        ]
+    }
+
     # 广告模型abtest配置
     AD_ABTEST_CONFIG = {
         # 票圈vlog