# -*- coding: utf-8 -*- import multiprocessing import traceback import gevent import datetime import pandas as pd import math from functools import reduce from odps import ODPS from threading import Timer, Thread from my_utils import RedisHelper, get_data_from_odps, filter_video_status, check_table_partition_exits, \ filter_video_status_app, send_msg_to_feishu from my_config import set_config from log import Log # os.environ['NUMEXPR_MAX_THREADS'] = '16' config_, _ = set_config() log_ = Log() region_code = config_.REGION_CODE RULE_PARAMS = { 'rule_params': { 'rule66': {'view_type': 'video-show', 'return_count': 21, 'score_rule': 0, 'platform_return_rate': 0.001}, }, 'data_params': config_.DATA_PARAMS, 'params_list': [ {'data': 'data66', 'rule': 'rule66'}, ] } features = [ 'apptype', 'code', # 省份编码 'videoid', 'lastday_preview', # 昨日预曝光人数 'lastday_view', # 昨日曝光人数 'lastday_play', # 昨日播放人数 'lastday_share', # 昨日分享人数 'lastday_return', # 昨日回流人数 'lastday_preview_total', # 昨日预曝光次数 'lastday_view_total', # 昨日曝光次数 'lastday_play_total', # 昨日播放次数 'lastday_share_total', # 昨日分享次数 '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.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 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') 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(project, table, 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, param): """ 计算score :param df: 特征数据 :param param: :return: """ # score计算公式: sharerate*backrate*logback*ctr # sharerate = lastday_share/(lastday_play+1000) # backrate = lastday_return/(lastday_share+10) # ctr = lastday_play/(lastday_preview+1000), 对ctr限最大值：K2 = 0.6 if ctr > 0.6 else ctr # score = sharerate * backrate * LOG(lastday_return+1) * K2 df = df.fillna(0) df['share_rate'] = df['lastday_share'] / (df['lastday_play'] + 1000) df['back_rate'] = df['lastday_return'] / (df['lastday_share'] + 10) df['log_back'] = (df['lastday_return'] + 1).apply(math.log) if param.get('view_type', None) == 'video-show': df['ctr'] = df['lastday_play'] / (df['platform_show'] + 1000) else: df['ctr'] = df['lastday_play'] / (df['lastday_preview'] + 1000) df['K2'] = df['ctr'].apply(lambda x: 0.6 if x > 0.6 else x) df['platform_return_rate'] = df['platform_return'] / df['lastday_return'] df['score1'] = df['share_rate'] * df['back_rate'] * df['log_back'] * df['K2'] click_score_rate = param.get('click_score_rate', None) back_score_rate = param.get('click_score_rate', None) if click_score_rate is not None: df['score'] = (1 - click_score_rate) * df['score1'] + click_score_rate * df['K2'] elif back_score_rate is not None: df['score'] = (1 - back_score_rate) * df['score1'] + back_score_rate * df['back_rate'] else: df['score'] = df['score1'] df = df.sort_values(by=['score'], ascending=False) return df def video_rank(df, now_date, now_h, rule_key, param, region, data_key): """ 获取符合进入召回源条件的视频 :param df: :param now_date: :param now_h: :param rule_key: 小时级数据进入条件 :param param: 小时级数据进入条件参数 :param region: 所属地域 :return: """ redis_helper = RedisHelper() # 获取符合进入召回源条件的视频 return_count = param.get('return_count', 1) score_value = param.get('score_rule', 0) platform_return_rate = param.get('platform_return_rate', 0) h_recall_df = df[(df['lastday_return'] >= return_count) & (df['score'] >= score_value) & (df['platform_return_rate'] >= platform_return_rate)] # videoid重复时，保留分值高 h_recall_df = h_recall_df.sort_values(by=['score'], ascending=False) h_recall_df = h_recall_df.drop_duplicates(subset=['videoid'], keep='first') h_recall_df['videoid'] = h_recall_df['videoid'].astype(int) h_recall_videos = h_recall_df['videoid'].to_list() log_.info(f"各种规则过滤后，一共有多少个视频 = {len(h_recall_videos)}") # 视频状态过滤 if data_key in ['data7', ]: filtered_videos = filter_video_status_app(h_recall_videos) else: filtered_videos = filter_video_status(h_recall_videos) log_.info(f"视频状态-过滤后，一共有多少个视频 = {len(filtered_videos)}") # 写入对应的redis h_video_ids = [] day_recall_result = {} for video_id in filtered_videos: score = h_recall_df[h_recall_df['videoid'] == video_id]['score'] day_recall_result[int(video_id)] = float(score) h_video_ids.append(int(video_id)) day_recall_key_name = \ f"{config_.RECALL_KEY_NAME_PREFIX_REGION_BY_24H}{region}:{data_key}:{rule_key}:" \ f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}" log_.info("打印地域24小时的某个地域{},redis key:{}".format(region, day_recall_key_name)) if len(day_recall_result) > 0: log_.info(f"开始写入头部数据：count = {len(day_recall_result)}, key = {day_recall_key_name}") redis_helper.add_data_with_zset(key_name=day_recall_key_name, data=day_recall_result, expire_time=2 * 3600) else: log_.info(f"无数据，不写入。") # 清空线上过滤应用列表 # redis_helper.del_keys(key_name=f"{config_.REGION_H_VIDEO_FILER_24H}{region}.{app_type}.{data_key}.{rule_key}") # 与其他召回视频池去重，存入对应的redis # dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h, rule_key=rule_key, region=region) def merge_df(df_left, df_right): """ df按照videoid, code 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', 'code'], how='outer', suffixes=['_x', '_y']) df_merged.fillna(0, inplace=True) feature_list = ['videoid', 'code'] for feature in features: if feature in ['apptype', 'videoid', 'code']: continue df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y'] feature_list.append(feature) return df_merged[feature_list] def merge_df_with_score(df_left, df_right): """ df 按照[videoid, code]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"多协程的region = {region} 开始执行") region_df = df_merged[df_merged['code'] == region] log_.info(f'该区域region = {region}, 下有多少数据量 = {len(region_df)}') score_df = cal_score(df=region_df, param=rule_param) video_rank(df=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"多协程的region = {region} 完成执行") 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') 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}") task_list = [ gevent.spawn(process_with_region, region, df_merged, app_type, data_key, rule_key, rule_param, now_date, now_h) for region in region_code_list ] gevent.joinall(task_list) log_.info(f"app_type = {app_type} end!") def process_with_param(param, data_params_item, rule_params_item, region_code_list, feature_df, now_date, now_h): data_key = param.get('data') data_param = data_params_item.get(data_key) rule_key = param.get('rule') rule_param = rule_params_item.get(rule_key) merge_func = rule_param.get('merge_func', None) log_.info("数据采用:{},统计采用{}.".format(data_key, rule_key)) log_.info("具体的规则是:{}.".format(rule_param)) 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.items()] 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"多进程的 param = {param} 完成执行!") def rank_by_24h(project, table, now_date, now_h, rule_params, region_code_list): # 获取特征数据 feature_df = get_feature_data(project=project, table=table, now_date=now_date) 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') params_list = rule_params.get('params_list') pool = multiprocessing.Pool(processes=len(params_list)) for param in params_list: pool.apply_async( func=process_with_param, args=(param, data_params_item, rule_params_item, region_code_list, feature_df, now_date, now_h) ) pool.close() pool.join() """ pool = multiprocessing.Pool(processes=len(config_.APP_TYPE)) for app_type, params in rule_params.items(): pool.apply_async(func=process_with_app_type, args=(app_type, params, region_code_list, feature_df, now_date, now_h)) pool.close() pool.join() """ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region): """将地域分组小时级数据与其他召回视频池去重，存入对应的redis""" redis_helper = RedisHelper() # ##### 去重小程序天级更新结果，并另存为redis中 day_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_BY_DAY}rule2.{datetime.datetime.strftime(now_date, '%Y%m%d')}" if redis_helper.key_exists(key_name=day_key_name): day_data = redis_helper.get_all_data_from_zset(key_name=day_key_name, with_scores=True) log_.info(f'day data count = {len(day_data)}') day_dup = {} for video_id, score in day_data: if int(video_id) not in h_video_ids: day_dup[int(video_id)] = score h_video_ids.append(int(video_id)) log_.info(f"day data dup count = {len(day_dup)}") day_dup_key_name = \ f"{config_.RECALL_KEY_NAME_PREFIX_DUP_REGION_DAY_24H}{region}.{rule_key}." \ f"{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}" if len(day_dup) > 0: redis_helper.add_data_with_zset(key_name=day_dup_key_name, data=day_dup, expire_time=23 * 3600) # ##### 去重小程序模型更新结果，并另存为redis中 model_key_name = get_rov_redis_key(now_date=now_date) model_data = redis_helper.get_all_data_from_zset(key_name=model_key_name, with_scores=True) log_.info(f'model data count = {len(model_data)}') model_data_dup = {} for video_id, score in model_data: if int(video_id) not in h_video_ids: model_data_dup[int(video_id)] = score h_video_ids.append(int(video_id)) log_.info(f"model data dup count = {len(model_data_dup)}") model_data_dup_key_name = \ f"{config_.RECALL_KEY_NAME_PREFIX_DUP_REGION_24H}{region}.{rule_key}." \ f"{datetime.datetime.strftime(now_date, '%Y%m%d')}.{now_h}" if len(model_data_dup) > 0: redis_helper.add_data_with_zset(key_name=model_data_dup_key_name, data=model_data_dup, expire_time=23 * 3600) def h_rank_bottom(now_date, now_h, rule_params, region_code_list): """未按时更新数据，用上一小时结果作为当前小时的数据""" redis_helper = RedisHelper() if now_h == 0: redis_dt = datetime.datetime.strftime(now_date - datetime.timedelta(days=1), '%Y%m%d') redis_h = 23 else: redis_dt = datetime.datetime.strftime(now_date, '%Y%m%d') redis_h = now_h - 1 # 以上一小时的地域分组数据作为当前小时的数据 key_prefix = config_.RECALL_KEY_NAME_PREFIX_REGION_BY_24H 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 region in region_code_list: log_.info(f"region = {region}") key_name = f"{key_prefix}{region}:{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() h_video_ids = [] for video_id, score in initial_data: final_data[video_id] = score h_video_ids.append(int(video_id)) # 存入对应的redis final_key_name = \ f"{key_prefix}{region}:{data_key}:{rule_key}:{datetime.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) def h_timer_check(): try: rule_params = RULE_PARAMS project = config_.PROJECT_REGION_24H_APP_TYPE table = config_.TABLE_REGION_24H_APP_TYPE region_code_list = [code for region, code in region_code.items() if code != '-1'] now_date = datetime.datetime.today() now_h = datetime.datetime.now().hour now_min = datetime.datetime.now().minute log_.info(f"开始执行: {datetime.datetime.strftime(now_date, '%Y%m%d%H')}") # 查看当天更新的数据是否已准备好 h_data_count = data_check(project=project, table=table, now_date=now_date) if h_data_count > 0: log_.info('上游数据表查询数据条数 h_data_count = {}，开始计算。'.format(h_data_count)) rank_by_24h(now_date=now_date, now_h=now_h, rule_params=rule_params, project=project, table=table, region_code_list=region_code_list) log_.info("数据3----------正常完成----------") elif now_min > 40: log_.info('当前分钟超过40，预计执行无法完成，使用 bottom data!') h_rank_bottom(now_date=now_date, now_h=now_h, rule_params=rule_params, region_code_list=region_code_list) log_.info('----------当前分钟超过40，使用bottom的data，完成----------') else: # 数据没准备好，1分钟后重新检查 log_.info("上游数据未就绪，等待...") Timer(60, h_timer_check).start() except Exception as e: log_.error(f"地域分组24h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} - 地域分组24h数据更新失败\n" f"exception: {e}\n" f"traceback: {traceback.format_exc()}" ) if __name__ == '__main__': log_.info("文件alg_recsys_recall_24h_region.py:「24小时地域」 开始执行") h_timer_check()