rov-offline/ad_user_data_update_with_new_strategy.py

import datetime
import traceback
from threading import Timer
from my_utils import RedisHelper, data_check, get_feature_data, send_msg_to_feishu
from my_config import set_config
from log import Log
config_, _ = set_config()
log_ = Log()
redis_helper = RedisHelper()

features = [
    'apptype',
    'group',
    'ad_type',  # 0: all, 1: 自营，2: 微信
    'sharerate',  # 分享的概率
    'no_ad_rate',  # 不出广告的概率
    'no_adrate_share',  # 分享的情况下且不出广告的概率
    'ad_rate',  # 出广告的概率
    'adrate_share',  # 分享的情况下且出广告的概率
]


def predict_user_group_share_rate_with_ad(user_group_initial_df, dt, data_params, rule_params, param):
    """预估用户组有广告时的分享率"""
    # 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()
    # print(user_group_df)
    # 获取所有广告类型对应的数据
    user_group_df['ad_type'] = user_group_df['ad_type'].astype(int)
    user_group_df = user_group_df[user_group_df['ad_type'] == 0]
    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['ad_rate'].fillna(0, inplace=True)
    user_group_df['sharerate'].fillna(0, inplace=True)
    user_group_df['adrate_share'].fillna(0, inplace=True)
    user_group_df['ad_rate'] = user_group_df['ad_rate'].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)]

    # 计算用户组有广告时分享率
    user_group_df = user_group_df[user_group_df['ad_rate'] != 0]
    user_group_df['group_ad_share_rate'] = \
        user_group_df['adrate_share'] * user_group_df['sharerate'] / user_group_df['ad_rate']
    user_group_df['group_ad_share_rate'].fillna(0, inplace=True)

    # 结果写入redis
    key_name = f"{config_.KEY_NAME_PREFIX_GROUP_WITH_AD}{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 predict_user_group_share_rate_no_ad(user_group_initial_df, dt, data_params, rule_params, param):
    """预估用户组无广告时的分享率"""
    # 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()
    # 获取所有广告类型对应的数据
    user_group_df['ad_type'] = user_group_df['ad_type'].astype(int)
    user_group_df = user_group_df[user_group_df['ad_type'] == 0]
    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['no_ad_rate'].fillna(0, inplace=True)
    user_group_df['sharerate'].fillna(0, inplace=True)
    user_group_df['no_adrate_share'].fillna(0, inplace=True)
    user_group_df['no_ad_rate'] = user_group_df['no_ad_rate'].astype(float)
    user_group_df['sharerate'] = user_group_df['sharerate'].astype(float)
    user_group_df['no_adrate_share'] = user_group_df['no_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)]

    # 计算用户组有广告时分享率
    user_group_df = user_group_df[user_group_df['no_ad_rate'] != 0]
    user_group_df['group_no_ad_share_rate'] = \
        user_group_df['no_adrate_share'] * user_group_df['sharerate'] / user_group_df['no_ad_rate']
    user_group_df['group_no_ad_share_rate'].fillna(0, inplace=True)

    # 结果写入redis
    key_name = f"{config_.KEY_NAME_PREFIX_GROUP_NO_AD}{data_key}:{rule_key}:{dt}"
    redis_data = {}
    for index, item in user_group_df.iterrows():
        redis_data[item['group']] = item['group_no_ad_share_rate']
    group_ad_share_rate_mean = user_group_df['group_no_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_with_ad(user_group_initial_df=user_group_initial_df,
                                              dt=dt,
                                              data_params=data_params,
                                              rule_params=rule_params,
                                              param=param)
        predict_user_group_share_rate_no_ad(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"新策略 -- 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} - 新策略 -- 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()