|
@@ -321,14 +321,16 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
|
|
|
region_24h_rule_key = param.get('region_24h_rule_key', 'rule1')
|
|
|
by_24h_rule_key = param.get('24h_rule_key', None)
|
|
|
by_48h_rule_key = param.get('48h_rule_key', None)
|
|
|
+ dup_remove = param.get('dup_remove', True)
|
|
|
# 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_24h_rule_key=region_24h_rule_key, by_24h_rule_key=by_24h_rule_key, by_48h_rule_key=by_48h_rule_key,
|
|
|
- region=region, data_key=data_key, rule_rank_h_flag=rule_rank_h_flag, political_filter=political_filter,
|
|
|
- shield_config=shield_config)
|
|
|
+ region_24h_rule_key=region_24h_rule_key, by_24h_rule_key=by_24h_rule_key,
|
|
|
+ by_48h_rule_key=by_48h_rule_key, region=region, data_key=data_key,
|
|
|
+ rule_rank_h_flag=rule_rank_h_flag, political_filter=political_filter,
|
|
|
+ shield_config=shield_config, dup_remove=dup_remove)
|
|
|
|
|
|
|
|
|
-def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filter, shield_config):
|
|
|
+def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filter, shield_config, dup_remove):
|
|
|
redis_helper = RedisHelper()
|
|
|
if redis_helper.key_exists(key_name=initial_key_name):
|
|
|
initial_data = redis_helper.get_all_data_from_zset(key_name=initial_key_name, with_scores=True)
|
|
@@ -343,10 +345,16 @@ def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filt
|
|
|
initial_video_ids = filter_political_videos(video_ids=initial_video_ids)
|
|
|
|
|
|
dup_data = {}
|
|
|
- for video_id, score in initial_data:
|
|
|
- if int(video_id) not in h_video_ids and int(video_id) in initial_video_ids:
|
|
|
- dup_data[int(video_id)] = score
|
|
|
- h_video_ids.append(int(video_id))
|
|
|
+ # 视频去重逻辑
|
|
|
+ if dup_remove is True:
|
|
|
+ for video_id, score in initial_data:
|
|
|
+ if int(video_id) not in h_video_ids and int(video_id) in initial_video_ids:
|
|
|
+ dup_data[int(video_id)] = score
|
|
|
+ h_video_ids.append(int(video_id))
|
|
|
+ else:
|
|
|
+ for video_id, score in initial_data:
|
|
|
+ if int(video_id) in initial_video_ids:
|
|
|
+ dup_data[int(video_id)] = score
|
|
|
|
|
|
if len(dup_data) > 0:
|
|
|
redis_helper.add_data_with_zset(key_name=dup_key_name, data=dup_data, expire_time=2 * 24 * 3600)
|
|
@@ -356,7 +364,7 @@ def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filt
|
|
|
|
|
|
|
|
|
def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by_24h_rule_key, by_48h_rule_key,
|
|
|
- region, data_key, rule_rank_h_flag, political_filter, shield_config):
|
|
|
+ region, data_key, rule_rank_h_flag, political_filter, shield_config, dup_remove):
|
|
|
"""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"""
|
|
|
# ##### 去重更新地域分组小时级24h列表,并另存为redis中
|
|
|
region_24h_key_name = \
|
|
@@ -367,7 +375,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=region_24h_key_name,
|
|
|
dup_key_name=region_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
- shield_config=shield_config)
|
|
|
+ shield_config=shield_config, dup_remove=dup_remove)
|
|
|
|
|
|
if rule_rank_h_flag == '48h':
|
|
|
|
|
@@ -379,7 +387,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=h_48h_key_name,
|
|
|
dup_key_name=h_48h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
- shield_config=shield_config)
|
|
|
+ shield_config=shield_config, dup_remove=dup_remove)
|
|
|
|
|
|
# ##### 去重小程序相对48h 筛选后剩余数据 更新结果,并另存为redis中
|
|
|
if by_48h_rule_key == 'rule1':
|
|
@@ -390,7 +398,8 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=other_h_48h_key_name,
|
|
|
dup_key_name=other_h_48h_dup_key_name, region=region,
|
|
|
- political_filter=political_filter, shield_config=shield_config)
|
|
|
+ political_filter=political_filter, shield_config=shield_config,
|
|
|
+ dup_remove=dup_remove)
|
|
|
|
|
|
else:
|
|
|
# ##### 去重小程序相对24h更新结果,并另存为redis中
|
|
@@ -401,7 +410,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=h_24h_key_name,
|
|
|
dup_key_name=h_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
- shield_config=shield_config)
|
|
|
+ shield_config=shield_config, dup_remove=dup_remove)
|
|
|
|
|
|
# ##### 去重小程序相对24h 筛选后剩余数据 更新结果,并另存为redis中
|
|
|
# if by_24h_rule_key in ['rule3', 'rule4']:
|
|
@@ -412,7 +421,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=other_h_24h_key_name,
|
|
|
dup_key_name=other_h_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
- shield_config=shield_config)
|
|
|
+ shield_config=shield_config, dup_remove=dup_remove)
|
|
|
|
|
|
# ##### 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)
|
|
@@ -729,6 +738,7 @@ def h_bottom_process(param, rule_params_item, region_code_list, key_prefix, redi
|
|
|
political_filter = param.get('political_filter', None)
|
|
|
# 屏蔽视频过滤
|
|
|
shield_config = param.get('shield_config', config_.SHIELD_CONFIG)
|
|
|
+ dup_remove = param.get('dup_remove', True)
|
|
|
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}"
|
|
@@ -750,7 +760,7 @@ def h_bottom_process(param, rule_params_item, region_code_list, key_prefix, redi
|
|
|
region_24h_rule_key=region_24h_rule_key, region=region,
|
|
|
data_key=data_key, by_24h_rule_key=by_24h_rule_key,
|
|
|
by_48h_rule_key=by_48h_rule_key, rule_rank_h_flag=rule_rank_h_flag,
|
|
|
- political_filter=political_filter, shield_config=shield_config)
|
|
|
+ political_filter=political_filter, shield_config=shield_config, dup_remove=dup_remove)
|
|
|
# 特殊城市视频数据准备
|
|
|
for region, city_list in config_.REGION_CITY_MAPPING.items():
|
|
|
t = [
|