|
@@ -153,6 +153,7 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key):
|
|
|
:param region: 所属地域
|
|
|
:return:
|
|
|
"""
|
|
|
+ log_.info(f'df count = {len(df)}')
|
|
|
redis_helper = RedisHelper()
|
|
|
# 获取符合进入召回源条件的视频
|
|
|
return_count = param.get('return_count', 1)
|
|
@@ -160,19 +161,20 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key):
|
|
|
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)]
|
|
|
+ log_.info(f'h_recall_df count = {len(h_recall_df)}')
|
|
|
# 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'day_recall videos count = {len(h_recall_videos)}')
|
|
|
+ log_.info(f'h_recall_videos count = {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('filtered_videos count = {}'.format(len(filtered_videos)))
|
|
|
+ log_.info('filtered_videos count = {}'.format(len(filtered_videos)))
|
|
|
|
|
|
# 写入对应的redis
|
|
|
h_video_ids = []
|
|
@@ -182,14 +184,15 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key):
|
|
|
# print(score)
|
|
|
day_recall_result[int(video_id)] = float(score)
|
|
|
h_video_ids.append(int(video_id))
|
|
|
-
|
|
|
+ log_.info(f'day_recall_result count = {len(day_recall_result)}')
|
|
|
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("day_recall_key_name:{}".format(day_recall_key_name))
|
|
|
log_.info("day_recall_result.type:{}".format(str(type(day_recall_result))))
|
|
|
+ log_.info("begin to write redis for day_recall_key_name:{} with {}".format(day_recall_key_name,
|
|
|
+ str(len(day_recall_result))))
|
|
|
if len(day_recall_result) > 0:
|
|
|
- log_.info("begin to write redis for day_recall_key_name:{} with {}".format(day_recall_key_name, str(len(day_recall_result))))
|
|
|
redis_helper.add_data_with_zset(key_name=day_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_.REGION_H_VIDEO_FILER_24H}{region}.{app_type}.{data_key}.{rule_key}")
|