rov-offline/rule_rank_h_by_24h.py

import pandas as pd
import math
from functools import reduce
from odps import ODPS
from threading import Timer
from datetime import datetime, timedelta
from get_data import get_data_from_odps
from db_helper import RedisHelper
from utils import filter_video_status, check_table_partition_exits
from config import set_config
from log import Log

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

features = [
    'apptype',
    'videoid',
    'preview人数',  # 过去24h预曝光人数
    'view人数',  # 过去24h曝光人数
    'play人数',  # 过去24h播放人数
    'share人数',  # 过去24h分享人数
    '回流人数',  # 过去24h分享，过去24h回流人数
    'preview次数',  # 过去24h预曝光次数
    'view次数',  # 过去24h曝光次数
    'play次数',  # 过去24h播放次数
    'share次数',  # 过去24h分享次数
    'platform_return',
    'platform_preview',
    'platform_preview_total',
    'platform_show',
    'platform_show_total',
    'platform_view',
    'platform_view_total',
]


def get_rov_redis_key(now_date):
    # 获取rov模型结果存放key
    redis_helper = RedisHelper()
    now_dt = 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.strftime(now_date - timedelta(days=1), '%Y%m%d')
        key_name = f'{config_.RECALL_KEY_NAME_PREFIX}{pre_dt}'
    return key_name


def h_data_check(project, table, now_date, now_h):
    """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:
        # 23点开始到8点之前（不含8点），全部用22点生成那个列表
        if now_h == 23:
            dt = datetime.strftime(now_date - timedelta(hours=1), '%Y%m%d%H')
        elif now_h < 8:
            dt = f"{datetime.strftime(now_date - timedelta(days=1), '%Y%m%d')}22"
        else:
            dt = datetime.strftime(now_date, '%Y%m%d%H')
        check_res = check_table_partition_exits(date=dt, project=project, table=table)
        if check_res:
            sql = f'select * from {project}.{table} where dt = {dt}'
            with odps.execute_sql(sql=sql).open_reader() as reader:
                data_count = reader.count
        else:
            data_count = 0
    except Exception as e:
        data_count = 0
    return data_count


def get_feature_data(now_date, now_h, project, table):
    """获取特征数据"""
    # 23点开始到8点之前（不含8点），全部用22点生成那个列表
    if now_h == 23:
        dt = datetime.strftime(now_date - timedelta(hours=1), '%Y%m%d%H')
    elif now_h < 8:
        dt = f"{datetime.strftime(now_date - timedelta(days=1), '%Y%m%d')}22"
    else:
        dt = datetime.strftime(now_date, '%Y%m%d%H')
    log_.info({'feature_dt': dt})
    # dt = '20220425'
    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_score1(df):
    # score1计算公式: score = 回流人数/(view人数+10000)
    df = df.fillna(0)
    df['score'] = df['回流人数'] / (df['view人数'] + 1000)
    df = df.sort_values(by=['score'], ascending=False)
    return df


def cal_score2(df, param):
    # score2计算公式: score = share次数/(view+1000)+0.01*return/(share次数+100)
    df = df.fillna(0)
    if param.get('view_type', None) == 'video-show':
        df['share_rate'] = df['share次数'] / (df['platform_show'] + 1000)
    elif param.get('view_type', None) == 'preview':
        df['share_rate'] = df['share次数'] / (df['preview人数'] + 1000)
    else:
        df['share_rate'] = df['share次数'] / (df['view人数'] + 1000)
    df['back_rate'] = df['回流人数'] / (df['share次数'] + 100)
    df['score'] = df['share_rate'] + 0.01 * df['back_rate']
    df['platform_return_rate'] = df['platform_return'] / df['回流人数']
    df = df.sort_values(by=['score'], ascending=False)
    return df


def video_rank_h(df, now_date, now_h, rule_key, param, data_key):
    """
    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:
    :param rule_key: 天级规则数据进入条件
    :param param: 天级规则数据进入条件参数
    :param data_key: 使用数据标识
    :return:
    """
    redis_helper = RedisHelper()
    log_.info(f"videos_count = {len(df)}")

    # videoid重复时，保留分值高
    df = df.sort_values(by=['score'], ascending=False)
    df = df.drop_duplicates(subset=['videoid'], keep='first')
    df['videoid'] = df['videoid'].astype(int)

    # 获取符合进入召回源条件的视频
    return_count = param.get('return_count')
    if return_count:
        day_recall_df = df[df['回流人数'] > return_count]
    else:
        day_recall_df = df
    platform_return_rate = param.get('platform_return_rate', 0)
    day_recall_df = day_recall_df[day_recall_df['platform_return_rate'] > platform_return_rate]
    day_recall_videos = day_recall_df['videoid'].to_list()
    log_.info(f'h_by24h_recall videos count = {len(day_recall_videos)}')

    # 视频状态过滤
    filtered_videos = filter_video_status(day_recall_videos)
    log_.info('filtered_videos count = {}'.format(len(filtered_videos)))

    # 写入对应的redis
    now_dt = datetime.strftime(now_date, '%Y%m%d')
    day_video_ids = []
    day_recall_result = {}
    for video_id in filtered_videos:
        score = day_recall_df[day_recall_df['videoid'] == video_id]['score']
        day_recall_result[int(video_id)] = float(score)
        day_video_ids.append(int(video_id))
    # h_24h_recall_key_name = \
    #     f"{config_.RECALL_KEY_NAME_PREFIX_BY_24H}{app_type}:{data_key}:{rule_key}:{now_dt}:{now_h}"
    h_24h_recall_key_name = \
        f"{config_.RECALL_KEY_NAME_PREFIX_BY_24H}{data_key}:{rule_key}:{now_dt}:{now_h}"

    if len(day_recall_result) > 0:
        log_.info(f"count = {len(day_recall_result)}, key = {h_24h_recall_key_name}")
        redis_helper.add_data_with_zset(key_name=h_24h_recall_key_name, data=day_recall_result, expire_time=2 * 3600)
        # 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':
        # 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)}')
        # 视频状态过滤
        all_filtered_videos = filter_video_status(all_videos)
        log_.info(f'all_filtered_videos count = {len(all_filtered_videos)}')
        # 与筛选结果去重
        other_videos = [video for video in all_filtered_videos if video not in day_video_ids]
        log_.info(f'other_videos count = {len(other_videos)}')
        # 写入对应的redis
        other_24h_recall_result = {}
        for video_id in other_videos:
            score = df[df['videoid'] == video_id]['score']
            other_24h_recall_result[int(video_id)] = float(score)
        # other_h_24h_recall_key_name = \
        #     f"{config_.RECALL_KEY_NAME_PREFIX_BY_24H_OTHER}{app_type}:{data_key}:{rule_key}:{now_dt}:{now_h}"
        other_h_24h_recall_key_name = \
            f"{config_.RECALL_KEY_NAME_PREFIX_BY_24H_OTHER}{data_key}:{rule_key}:{now_dt}:{now_h}"
        if len(other_24h_recall_result) > 0:
            log_.info(f"count = {len(other_24h_recall_result)}")
            redis_helper.add_data_with_zset(key_name=other_h_24h_recall_key_name, data=other_24h_recall_result,
                                            expire_time=2 * 3600)

    # 去重更新rov模型结果，并另存为redis中
    # initial_data_dup = {}
    # for video_id, score in initial_data:
    #     if int(video_id) not in day_video_ids:
    #         initial_data_dup[int(video_id)] = score
    # log_.info(f"initial data dup count = {len(initial_data_dup)}")
    #
    # initial_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_DUP_24H}{rule_key}.{now_dt}.{now_h}"
    # if len(initial_data_dup) > 0:
    #     redis_helper.add_data_with_zset(key_name=initial_key_name, data=initial_data_dup, expire_time=23 * 3600)


def merge_df(df_left, df_right):
    """
    df按照videoid 合并，对应特征求和
    :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']
    for feature in features:
        if feature in ['apptype', 'videoid']:
            continue
        df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y']
        feature_list.append(feature)
    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)
    feature_df['apptype'] = feature_df['apptype'].astype(int)
    # 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)
        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)
        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, 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)
            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)
    """
    #     # 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}')
    #     # to-logs
    #     log_.info({"date": datetime.strftime(now_date, '%Y%m%d%H'),
    #                "redis_key_prefix": config_.RECALL_KEY_NAME_PREFIX_BY_24H,
    #                "rule_key": key,
    #                # "score_df": score_df[['videoid', 'score']]
    #                })


def h_rank_bottom(now_date, now_h, rule_params):
    """未按时更新数据，用模型召回数据作为当前的数据"""
    redis_helper = RedisHelper()
    if now_h == 0:
        redis_dt = datetime.strftime(now_date - timedelta(days=1), '%Y%m%d')
        redis_h = 23
    else:
        redis_dt = datetime.strftime(now_date, '%Y%m%d')
        redis_h = now_h - 1
    key_prefix_list = [config_.RECALL_KEY_NAME_PREFIX_BY_24H, config_.RECALL_KEY_NAME_PREFIX_BY_24H_OTHER]

    for param in rule_params.get('params_list'):
        data_key = param.get('data')
        rule_key = param.get('rule')
        log_.info(f"data_key = {data_key}, rule_key = {rule_key}")
        for key_prefix in key_prefix_list:
            key_name = f"{key_prefix}{data_key}:{rule_key}:{redis_dt}:{redis_h}"
            initial_data = redis_helper.get_all_data_from_zset(key_name=key_name, with_scores=True)
            if initial_data is None:
                initial_data = []
            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"{key_prefix}{data_key}:{rule_key}:{datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
            if len(final_data) > 0:
                redis_helper.add_data_with_zset(key_name=final_key_name, data=final_data, expire_time=2 * 3600)

    """
    for app_type, params in rule_params.items():
        log_.info(f"app_type = {app_type}")
        for param in params.get('params_list'):
            data_key = param.get('data')
            rule_key = param.get('rule')
            log_.info(f"data_key = {data_key}, rule_key = {rule_key}")
            for key_prefix in key_prefix_list:
                key_name = f"{key_prefix}{app_type}:{data_key}:{rule_key}:{redis_dt}:{redis_h}"
                initial_data = redis_helper.get_all_data_from_zset(key_name=key_name, with_scores=True)
                if initial_data is None:
                    initial_data = []
                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"{key_prefix}{app_type}:{data_key}:{rule_key}:{datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
                if len(final_data) > 0:
                    redis_helper.add_data_with_zset(key_name=final_key_name, data=final_data, expire_time=2 * 3600)
                # 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}")
    """


def h_timer_check():
    project = config_.PROJECT_24H_APP_TYPE
    table = config_.TABLE_24H_APP_TYPE
    rule_params = config_.RULE_PARAMS_24H_APP_TYPE
    now_date = datetime.today()
    log_.info(f"now_date: {datetime.strftime(now_date, '%Y%m%d%H')}")
    now_min = datetime.now().minute
    now_h = datetime.now().hour
    # 查看当前天级更新的数据是否已准备好
    h_data_count = h_data_check(project=project, table=table, now_date=now_date, now_h=now_h)
    if h_data_count > 0:
        log_.info(f'h_by24h_data_count = {h_data_count}')
        # 数据准备好，进行更新
        rank_by_h(now_date=now_date, now_h=now_h, rule_params=rule_params, project=project, table=table)
    elif now_min > 50:
        log_.info('h_by24h_recall data is None!')
        h_rank_bottom(now_date=now_date, now_h=now_h, rule_params=rule_params)
    else:
        # 数据没准备好，1分钟后重新检查
        Timer(60, h_timer_check).start()


if __name__ == '__main__':
    h_timer_check()