rov-offline/rule_rank_h.py

import datetime
import pandas as pd
import math
from odps import ODPS
from threading import Timer
from get_data import get_data_from_odps
from db_helper import RedisHelper
from config import set_config
from log import Log

config_, _ = set_config()
log_ = Log()

project = 'loghubods'
table = 'video_each_hour_update'
features = [
    'videoid',
    'lastonehour_view',  # 过去1小时曝光
    'lastonehour_play',  # 过去1小时播放
    'lastonehour_share',  # 过去1小时分享
    'lastonehour_return',  # 过去1小时分享，过去1小时回流
]


def h_data_check(project, table, now_date):
    """检查数据是否准备好"""
    odps = ODPS(
        access_id=config_.ODPS_CONFIG['ACCESSID'],
        secret_access_key=config_.ODPS_CONFIG['ACCESSKEY'],
        project=project,
        endpoint=config_.ODPS_CONFIG['ENDPOINT'],
        connect_timeout=3000,
        read_timeout=500000,
        pool_maxsize=1000,
        pool_connections=1000
    )

    try:
        dt = datetime.datetime.strftime(now_date, '%Y%m%d%H')
        sql = f'select * from {project}.{table} where dt = {dt}'
        with odps.execute_sql(sql=sql).open_reader() as reader:
            data_count = reader.count
    except Exception as e:
        data_count = 0
    return data_count


def get_rov_redis_key(now_date):
    # 获取rov模型结果存放key
    redis_helper = RedisHelper()
    now_dt = datetime.datetime.strftime(now_date, '%Y%m%d')
    key_name = f'{config_.RECALL_KEY_NAME_PREFIX}{now_dt}'
    if not redis_helper.key_exists(key_name=key_name):
        pre_dt = datetime.datetime.strftime(now_date - datetime.timedelta(days=1), '%Y%m%d')
        key_name = f'{config_.RECALL_KEY_NAME_PREFIX}{pre_dt}'
    return key_name


def get_feature_data(now_date):
    """获取特征数据"""
    dt = datetime.datetime.strftime(now_date, '%Y%m%d%H')
    # dt = '2022041310'
    records = get_data_from_odps(date=dt, project=project, table=table)
    feature_data = []
    for record in records:
        item = {}
        for feature_name in features:
            item[feature_name] = record[feature_name]
        feature_data.append(item)
    feature_df = pd.DataFrame(feature_data)
    return feature_df


def cal_score(df):
    """
    计算score
    :param df: 特征数据
    :return:
    """
    # score计算公式: sharerate*backrate*logback*ctr
    # sharerate = lastonehour_share/(lastonehour_play+1000)
    # backrate = lastonehour_return/(lastonehour_share+10)
    # ctr = lastonehour_play/(lastonehour_view+1000), 对ctr限最大值：K2 = 0.6 if ctr > 0.6 else ctr
    # 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)
    df['ctr'] = df['lastonehour_play'] / (df['lastonehour_view'] + 1000)
    df['K2'] = df['ctr'].apply(lambda x: 0.6 if x > 0.6 else x)
    df['score'] = df['share_rate'] * df['back_rate'] * df['log_back'] * df['K2']
    df = df.sort_values(by=['score'], ascending=False)
    return df


def video_rank(df, now_date, now_h):
    """
    获取符合进入召回源条件的视频，与每日更新的rov模型结果视频列表进行合并
    :param df:
    :param now_date:
    :param now_h:
    :return:
    """
    # 获取rov模型结果
    redis_helper = RedisHelper()
    key_name = get_rov_redis_key(now_date=now_date)
    initial_data = redis_helper.get_data_zset_with_index(key_name=key_name, start=0, end=-1, with_scores=True)
    log_.info(f'initial data count = {len(initial_data)}')

    # 获取符合进入召回源条件的视频，进入条件：小时级回流>=20 && score>=0.005
    h_recall_df = df[(df['lastonehour_return'] >= 20) & (df['score'] >= 0.005)]
    h_recall_videos = h_recall_df['videoid'].to_list()
    log_.info(f'h_recall videos count = {len(h_recall_videos)}')

    # 去重合并
    final_videos = [int(item) for item in h_recall_videos]
    temp_videos = [int(video_id) for video_id, _ in initial_data if int(video_id) not in final_videos]
    final_videos = final_videos + temp_videos
    log_.info(f'final videos count = {len(final_videos)}')

    # 重新给定score
    final_data = {}
    for i, video_id in enumerate(final_videos):
        score = 100 - i * config_.ROV_SCORE_D
        final_data[video_id] = score

    # 存入对应的redis
    final_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_BY_H}{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}"
    redis_helper.add_data_with_zset(key_name=final_key_name, data=final_data, expire_time=24 * 3600)


def rank_by_h(now_date, now_h):
    # 获取特征数据
    feature_df = get_feature_data(now_date=now_date)
    # 计算score
    score_df = cal_score(df=feature_df)
    # rank
    video_rank(df=score_df, now_date=now_date, now_h=now_h)
    # to-csv
    score_filename = f"score_{datetime.datetime.strftime(now_date, '%Y%m%d%H')}.csv"
    score_df.to_csv(f'./data/{score_filename}')


def h_rank_bottom(now_date, now_h):
    """未按时更新数据，用rov模型结果作为当前小时的数据"""
    # 获取rov模型结果
    redis_helper = RedisHelper()
    key_name = get_rov_redis_key(now_date=now_date)
    initial_data = redis_helper.get_data_zset_with_index(key_name=key_name, start=0, end=-1, with_scores=True)
    final_data = dict()
    for video_id, score in initial_data:
        final_data[video_id] = score
    # 存入对应的redis
    final_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_BY_H}{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}"
    redis_helper.add_data_with_zset(key_name=final_key_name, data=final_data, expire_time=24 * 3600)


def h_timer_check():
    now_date = datetime.datetime.today()
    log_.info(f"now_date: {datetime.datetime.strftime(now_date, '%Y%m%d%H')}")
    now_h = datetime.datetime.now().hour
    now_min = datetime.datetime.now().minute
    # 查看当前小时更新的数据是否已准备好
    op_data_count = h_data_check(project=project, table=table, now_date=now_date)
    if op_data_count > 0:
        # 数据准备好，进行更新
        rank_by_h(now_date=now_date, now_h=now_h)
    elif now_min > 50:
        log_.info('h_recall data is None, use bottom data!')
        h_rank_bottom(now_date=now_date, now_h=now_h)
    else:
        # 数据没准备好，1分钟后重新检查
        Timer(60, h_timer_check).start()


if __name__ == '__main__':
    # df1 = get_feature_data()
    # res = cal_score(df=df1)
    # video_rank(df=res, now_date=datetime.datetime.today())
    # rank_by_h()
    h_timer_check()