|
@@ -111,13 +111,13 @@ def video_rank(df, now_date, now_h):
|
|
# 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
|
|
# 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_df = df[(df['lastonehour_return'] >= 20) & (df['score'] >= 0.005)]
|
|
h_recall_videos = h_recall_df['videoid'].to_list()
|
|
h_recall_videos = h_recall_df['videoid'].to_list()
|
|
- print(len(h_recall_videos))
|
|
|
|
|
|
+ log_.info(f'h_recall videos count = {len(h_recall_videos)}')
|
|
|
|
|
|
# 去重合并
|
|
# 去重合并
|
|
final_videos = [int(item) for item in h_recall_videos]
|
|
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]
|
|
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
|
|
final_videos = final_videos + temp_videos
|
|
- print(len(final_videos))
|
|
|
|
|
|
+ log_.info(f'final videos count = {len(final_videos)}')
|
|
|
|
|
|
# 重新给定score
|
|
# 重新给定score
|
|
final_data = {}
|
|
final_data = {}
|
|
@@ -158,7 +158,7 @@ def h_rank_bottom(now_date, now_h):
|
|
|
|
|
|
def h_timer_check():
|
|
def h_timer_check():
|
|
now_date = datetime.datetime.today()
|
|
now_date = datetime.datetime.today()
|
|
- log_.info(f"now_date: {datetime.datetime.strftime(now_date, '%Y%m%d')}")
|
|
|
|
|
|
+ log_.info(f"now_date: {datetime.datetime.strftime(now_date, '%Y%m%d%h')}")
|
|
now_h = datetime.datetime.now().hour
|
|
now_h = datetime.datetime.now().hour
|
|
now_min = datetime.datetime.now().minute
|
|
now_min = datetime.datetime.now().minute
|
|
# 查看当前小时更新的数据是否已准备好
|
|
# 查看当前小时更新的数据是否已准备好
|
|
@@ -167,7 +167,7 @@ def h_timer_check():
|
|
# 数据准备好,进行更新
|
|
# 数据准备好,进行更新
|
|
rank_by_h(now_date=now_date, now_h=now_h)
|
|
rank_by_h(now_date=now_date, now_h=now_h)
|
|
elif now_min > 50:
|
|
elif now_min > 50:
|
|
- log_.info('op data is None, use bottom data!')
|
|
|
|
|
|
+ log_.info('h_recall data is None, use bottom data!')
|
|
h_rank_bottom(now_date=now_date, now_h=now_h)
|
|
h_rank_bottom(now_date=now_date, now_h=now_h)
|
|
else:
|
|
else:
|
|
# 数据没准备好,1分钟后重新检查
|
|
# 数据没准备好,1分钟后重新检查
|