You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
65 lines
2.2 KiB
65 lines
2.2 KiB
5 months ago
|
from datetime import datetime
|
||
|
|
import pickle
|
||
|
|
import json
|
||
|
|
from config import logger
|
||
|
|
from config import subject_xdeepfm_rank_dict
|
||
|
|
from config import subject_bst_rank_dict
|
||
|
|
from config import test_user_id
|
||
|
|
from matching.subject.cold_start_recall import cold_start_user_recall
|
||
|
|
|
||
|
|
|
||
|
|
logger.info('加载实训推荐离线排序字典')
|
||
|
|
xdeepfm_rank_dict = pickle.load(open(subject_xdeepfm_rank_dict, 'rb'))
|
||
|
|
bst_rank_dict = pickle.load(open(subject_bst_rank_dict, 'rb'))
|
||
|
|
|
||
|
|
def subject_recommend_offline(user_id, disciplines_id_list=None, topk=100, rank_method='1'):
|
||
|
|
"""
|
||
|
|
根据用户ID获取推荐的实训ID列表
|
||
|
|
直接从计算好的离线排序字典中取出数据返回
|
||
|
|
"""
|
||
|
|
start_time = datetime.now()
|
||
|
|
|
||
|
|
logger.info(f"本次需要进行推荐的用户ID: {user_id}")
|
||
|
|
|
||
|
|
has_data = False
|
||
|
|
rank_list = []
|
||
|
|
rank_list.clear()
|
||
|
|
recommend_results = {}
|
||
|
|
recommend_results.clear()
|
||
|
|
|
||
|
|
# 如果离线排序字典中有此用户则直接取出
|
||
|
|
if rank_method == '1':
|
||
|
|
if user_id in xdeepfm_rank_dict:
|
||
|
|
has_data = True
|
||
|
|
rank_list = xdeepfm_rank_dict[user_id]
|
||
|
|
else:
|
||
|
|
if user_id in bst_rank_dict:
|
||
|
|
has_data = True
|
||
|
|
rank_list = bst_rank_dict[user_id]
|
||
|
|
|
||
|
|
# 没有召回数据则根据兴趣标签使用冷启动召回推荐
|
||
|
|
if has_data == False:
|
||
|
|
recommend_results = cold_start_user_recall(user_id,disciplines_id_list, topk=topk)
|
||
|
|
else:
|
||
|
|
if topk > len(rank_list):
|
||
|
|
topk = len(rank_list)
|
||
|
|
|
||
|
|
# 取topk个返回
|
||
|
|
rank_list = rank_list[:topk]
|
||
|
|
|
||
|
|
recommend_results = {subject_id: subject_name for subject_id, subject_name in rank_list}
|
||
|
|
|
||
|
|
# 计算耗时毫秒
|
||
|
|
end_time = datetime.utcnow()
|
||
|
|
cost_time_millisecond = round(float((end_time - start_time).microseconds / 1000.0), 3)
|
||
|
|
|
||
|
|
logger.info(f"本次推荐总耗时: {cost_time_millisecond} 毫秒")
|
||
|
|
return recommend_results
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
recommend_results = subject_recommend_offline(user_id=test_user_id,
|
||
|
|
disciplines_id_list=[1,2],
|
||
|
|
topk=100,
|
||
|
|
rank_method=1)
|
||
|
|
print(json.dumps(recommend_results, ensure_ascii=False, indent=4))
|