Skip to content

P
physical
Commit 374fb99d authored by 段英荣's avatar 段英荣
Browse files
Options

Merge branch 'branch_0520' into 'test' 

Branch 0520

See merge request alpha/physical!334
parents c1b48f9f 92ec6cc3
Hide whitespace changes
Inline Side-by-side
Showing with 66 additions and 104 deletions
injection/data_sync/tasks.py
View file @ 374fb99d
......@@ -60,12 +60,21 @@ def sync_face_similar_data_to_redis():
item_list = list()
for item in similar_result_items:
weight_score = int(item.similarity * 100)
item_list.append(
{
"contrast_user_id": item.contrast_user_id,
"similarity": item.similarity
"filter":{
"constant_score":{
"filter":{
"term":{"user_id": item.contrast_user_id}
}
}
},
"weight": weight_score*2
}
)
if len(item_list)>=100:
break
redis_client.set(redis_key, json.dumps(item_list))
logging.info("participant_user_id:%d set data done!" % participant_user_id)
......
linucb/views/collect_data.py
View file @ 374fb99d
......@@ -68,7 +68,6 @@ class CollectData(object):
if len(recommend_tag_list) > 0:
tag_recommend_redis_key = self.linucb_recommend_redis_prefix + str(device_id)
redis_client.set(tag_recommend_redis_key, json.dumps(recommend_tag_list))
# Todo:设置过期时间，调研set是否支持
redis_client.expire(tag_recommend_redis_key, 7*24*60*60)
have_read_topic_id_list = Tools.get_have_read_topic_id_list(device_id,user_id,TopicPageType.HOME_RECOMMEND)
......@@ -80,38 +79,35 @@ class CollectData(object):
recommend_topic_id_list_click = list()
recommend_topic_id_list_click_dict = dict()
if click_topic_tag_list:
if len(click_topic_tag_list)>0:
recommend_topic_id_list_click,recommend_topic_id_list_click_dict = ESPerform.get_tag_topic_list_dict(click_topic_tag_list,
if click_topic_tag_list and len(click_topic_tag_list)>0:
recommend_topic_id_list_click,recommend_topic_id_list_click_dict = ESPerform.get_tag_topic_list_dict(click_topic_tag_list,
have_read_topic_id_list,size=2)
if len(recommend_topic_id_list_click) > 0:
recommend_topic_id_list.extend(recommend_topic_id_list_click)
recommend_topic_id_list_dict.update(recommend_topic_id_list_click_dict)
have_read_topic_id_list.extend(recommend_topic_id_list_click)
click_recommend_redis_key = self.click_recommend_redis_key_prefix + str(device_id)
click_redis_data_dict = {
"data": json.dumps(recommend_topic_id_list),
"datadict":json.dumps(recommend_topic_id_list_dict),
"cursor": 0
}
redis_client.hmset(click_recommend_redis_key, click_redis_data_dict)
# have_read_topic_id_list.extend(recommend_topic_id_list_click)
# click_recommend_redis_key = self.click_recommend_redis_key_prefix + str(device_id)
# click_redis_data_dict = {
# "data": json.dumps(recommend_topic_id_list),
# "datadict":json.dumps(recommend_topic_id_list_dict),
# "cursor": 0
# }
# redis_client.hmset(click_recommend_redis_key, click_redis_data_dict)
tag_id_list = recommend_tag_list[0:100]
topic_recommend_redis_key = self.linucb_recommend_topic_id_prefix + str(device_id)
redis_topic_data_dict = redis_client.hgetall(topic_recommend_redis_key)
redis_topic_list = list()
cursor = -1
if b"data" in redis_topic_data_dict:
redis_topic_list = json.loads(redis_topic_data_dict[b"data"]) if redis_topic_data_dict[
b"data"] else []
cursor = int(str(redis_topic_data_dict[b"cursor"], encoding="utf-8"))
if len(recommend_topic_id_list)==0 and cursor==0 and len(redis_topic_list)>0:
have_read_topic_id_list.extend(redis_topic_list[:2])
tag_topic_dict = dict()
# redis_topic_data_dict = redis_client.hgetall(topic_recommend_redis_key)
# redis_topic_list = list()
# cursor = -1
# if b"data" in redis_topic_data_dict:
# redis_topic_list = json.loads(redis_topic_data_dict[b"data"]) if redis_topic_data_dict[
# b"data"] else []
# cursor = int(str(redis_topic_data_dict[b"cursor"], encoding="utf-8"))
# if len(recommend_topic_id_list)==0 and cursor==0 and len(redis_topic_list)>0:
# have_read_topic_id_list.extend(redis_topic_list[:2])
if len(new_user_click_tag_list)>0:
tag_topic_id_list,tag_topic_dict = ESPerform.get_tag_topic_list_dict(new_user_click_tag_list, have_read_topic_id_list)
......@@ -119,7 +115,7 @@ class CollectData(object):
tag_topic_id_list,tag_topic_dict = ESPerform.get_tag_topic_list_dict(tag_id_list,have_read_topic_id_list)
if len(recommend_topic_id_list)>0 or len(new_user_click_tag_list) > 0:
if len(recommend_topic_id_list)>0 or len(tag_topic_id_list)>0 or len(new_user_click_tag_list) > 0:
tag_topic_id_list = recommend_topic_id_list + tag_topic_id_list
tag_topic_dict.update(recommend_topic_id_list_dict)
redis_data_dict = {
......@@ -128,11 +124,6 @@ class CollectData(object):
"cursor":0
}
redis_client.hmset(topic_recommend_redis_key,redis_data_dict)
else:
if cursor<=0 and len(redis_topic_list)>0:
tag_topic_dict = list()
tag_topic_dict = redis_topic_list[:2]
tag_topic_dict = list(set(tag_topic_dict))
return True
except:
......
search/utils/topic.py
View file @ 374fb99d
......@@ -11,6 +11,8 @@ from libs.es import ESPerform
from .common import TopicDocumentField
from search.utils.common import *
from trans2es.models.pictorial import PictorialTopics
from libs.cache import redis_client
class TopicUtils(object):
......@@ -161,14 +163,6 @@ class TopicUtils(object):
q["query"] = dict()
functions_list = [
# {
# "filter": {
# "term": {
# "language_type": 1
# }
# },
# "weight": 60
# },
{
"gauss": {
"create_time": {
......@@ -177,38 +171,22 @@ class TopicUtils(object):
}
},
"weight": 60
},
# {
# "filter": {
# "constant_score":{
# "filter":{
# "term": {
# "content_level": 6
# }
# }
# }
# },
# "weight": 600
# }
}
]
# if len(user_similar_score_list) > 0:
# for item in user_similar_score_list[:100]:
# score_item = 2 + item[1]
# functions_list.append(
# {
# "filter": {"bool": {
# "should": {"term": {"user_id": item[0]}}}},
# "weight": score_item,
# }
# )
if user_id and user_id>0:
redis_key_prefix = "physical:user_similar:participant_user_id:"
similar_redis_key = redis_key_prefix + str(user_id)
redis_user_similar_data = redis_client.get(similar_redis_key)
user_similar_list = json.loads(redis_user_similar_data) if redis_user_similar_data else []
if len(user_similar_list)>0:
functions_list.extend(user_similar_list)
if len(attention_user_id_list) > 0:
functions_list.append(
{
"filter": {"bool": {
"should": {"terms": {"user_id": attention_user_id_list}}}},
"weight": 30,
"filter": {"constant_score":{"filter":{"terms": {"user_id": attention_user_id_list}}}},
"weight": 100,
}
)
if len(attention_tag_list) > 0:
......@@ -224,8 +202,6 @@ class TopicUtils(object):
"query": {
"bool": {
"filter": [
# {"term": {"content_level": 6}},
# {"term": {"has_image":True}},
{"term": {"is_online": True}},
{"term": {"is_deleted": False}}
],
......@@ -297,7 +273,7 @@ class TopicUtils(object):
]
query_function_score["query"]["bool"]["minimum_should_match"] = 1
query_function_score["query"]["bool"]["filter"].append(
{"range": {"content_level": {"gte": 4, "lte": 6}}}
{"range": {"content_level": {"gte":3,"lte":6}}}
)
else:
if "must_not" in query_function_score["query"]["bool"]:
......@@ -321,7 +297,6 @@ class TopicUtils(object):
q["collapse"] = {
"field": "user_id"
}
# "includes": ["id", "pictorial_id", "offline_score", "user_id", "edit_tag_list"]
q["_source"] = {
"includes": ["id"]
}
......
search/views/topic.py
View file @ 374fb99d
......@@ -49,13 +49,15 @@ def get_home_recommend_topic_ids(user_id, device_id, tag_id, offset, size, query
query_type=TopicPageType.HOME_RECOMMEND,promote_topic_list = [],disable_collpase=False):
try:
topic_star_routing = "6"
index_type = "topic-high-star"
if query is None:
if user_id>0:
redis_key = "physical:home_recommend" + ":user_id:" + str(user_id) + ":query_type:" + str(query_type)
else:
redis_key = "physical:home_recommend" + ":device_id:" + device_id + ":query_type:" + str(query_type)
else:
topic_star_routing = "4,5,6"
topic_star_routing = "3,4,5,6"
index_type = "topic"
if user_id>0:
redis_key = "physical:home_query" + ":user_id:" + str(user_id) + ":query:" + str(query) + ":query_type:" + str(query_type)
else:
......@@ -89,22 +91,22 @@ def get_home_recommend_topic_ids(user_id, device_id, tag_id, offset, size, query
recommend_topic_dict = redis_client.hgetall(topic_recommend_redis_key)
if b"data" in recommend_topic_dict:
recommend_topic_id_list = json.loads(recommend_topic_dict[b"data"])
linucb_recommend_topic_id_list = json.loads(recommend_topic_dict[b"data"])
# 推荐帖子是强插的，要保证推荐帖子不在已读里
# recommend_topic_id_list = list(set(recommend_topic_id_list) - set(have_read_topic_id_list))
cursor = int(str(recommend_topic_dict[b"cursor"], encoding="utf-8"))
newcursor = cursor + 6
if len(recommend_topic_id_list) > newcursor:
recommend_topic_list = recommend_topic_id_list[cursor:newcursor]
redis_client.hset(topic_recommend_redis_key, "cursor", newcursor)
recommend_topic_id_list = list(set(linucb_recommend_topic_id_list) - set(have_read_topic_id_list))
recommend_topic_id_list.sort(key=linucb_recommend_topic_id_list.index)
# cursor = int(str(recommend_topic_dict[b"cursor"], encoding="utf-8"))
# newcursor = cursor + 6
if len(recommend_topic_id_list) > 0:
recommend_topic_list = recommend_topic_id_list[0:size]
# redis_client.hset(topic_recommend_redis_key, "cursor", newcursor)
if b"datadict" in recommend_topic_dict:
recommend_topic_id_dict = json.loads(recommend_topic_dict[b"datadict"])
if len(recommend_topic_list) == 6 and recommend_topic_id_dict is not None:
linucb_recommend_topic_id_dict = json.loads(recommend_topic_dict[b"datadict"])
if len(recommend_topic_list) == 6 and linucb_recommend_topic_id_dict is not None:
for i in recommend_topic_list:
recommend_topic_user_list.append(recommend_topic_id_dict[str(i)])
recommend_topic_user_list.append(linucb_recommend_topic_id_dict[str(i)])
# 用户关注标签
redis_tag_data = redis_client.hget("physical:linucb:register_user_tag_info", user_id)
attention_tag_list = json.loads(redis_tag_data) if redis_tag_data else []
......@@ -120,11 +122,12 @@ def get_home_recommend_topic_ids(user_id, device_id, tag_id, offset, size, query
# for topic_id in promote_recommend_topic_id_list:
# have_read_topic_id_list_add_promote.append(topic_id)
have_read_topic_id_list.extend(promote_topic_list)
topic_id_list = list()
rank_topic_id_list = TopicUtils.get_recommend_topic_ids(user_id=user_id, tag_id=tag_id, offset=0, size=size,
single_size=size,query=query, query_type=query_type,
filter_topic_id_list=have_read_topic_id_list,
index_type="topic-high-star",routing=topic_star_routing,attention_tag_list=attention_tag_list,linucb_user_id_list=recommend_topic_user_list,disable_collpase=disable_collpase)
rank_topic_id_list = list()
if size>0:
rank_topic_id_list = TopicUtils.get_recommend_topic_ids(user_id=user_id, tag_id=tag_id, offset=0, size=size,
single_size=size,query=query, query_type=query_type,
filter_topic_id_list=have_read_topic_id_list,
index_type=index_type,routing=topic_star_routing,attention_tag_list=attention_tag_list,linucb_user_id_list=recommend_topic_user_list,disable_collpase=disable_collpase)
# if len(recommend_topic_list) == 6 and query is None:
# if (size < 11):
......
trans2es/models/topic.py
View file @ 374fb99d
......@@ -227,10 +227,6 @@ class Topic(models.Model):
elif user_query_results[0].is_shadow:
user_is_shadow = True
# 是否官方推荐小组
# if self.group and self.group.is_recommend:
# offline_score += 4.0
# 帖子等级
if self.content_level == '5':
offline_score += 100.0 *3
......@@ -239,20 +235,8 @@ class Topic(models.Model):
elif self.content_level == '6':
offline_score += 200.0 *3
# is_excellent = self.judge_if_excellent_topic(self.id)
# if is_excellent:
# offline_score += 200.0
if self.language_type == 1:
offline_score += 60.0
# exposure_count = ActionSumAboutTopic.objects.using(settings.SLAVE_DB_NAME).filter(topic_id=self.id, data_type=1).count()
# click_count = ActionSumAboutTopic.objects.using(settings.SLAVE_DB_NAME).filter(topic_id=self.id, data_type=2).count()
# uv_num = ActionSumAboutTopic.objects.using(settings.SLAVE_DB_NAME).filter(topic_id=self.id, data_type=3).count()
#
# if exposure_count > 0:
# offline_score += click_count / exposure_count
# if uv_num > 0:
# offline_score += (self.vote_num / uv_num + self.reply_num / uv_num)
"""
1:马甲账号是否对总分降权？
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment