yongqyu / dien-tf2 Goto Github PK
View Code? Open in Web Editor NEWDeep Interest Network for Click-Through Rate Prediction / Deep Interest Evolution Network for Click-Through Rate Prediction
Deep Interest Network for Click-Through Rate Prediction / Deep Interest Evolution Network for Click-Through Rate Prediction
I would like to replicate your work but the dataset of Amazon, I am not sure which you are using. Can you direct me to datasets you are using?
Thanks.
hi,dear
from the codes, we can know the neg item is from random choice,
random.seed(1234)
train_set = []
test_set = []
for reviewerID, hist in reviews_df.groupby('reviewerID'):
pos_list = hist['asin'].tolist()
neg_list = []
for _ in range(len(pos_list)):
neg = pos_list[0]
while neg in pos_list + neg_list :
neg = random.randint(0, item_count-1)
neg_list.append(neg)
and the test_set's label is tuple, one item is pos never seen before , another is neg
for i in range(1, len(pos_list)-1):
hist = pos_list[:i]
train_set.append((reviewerID, hist, pos_list[i], 1))
train_set.append((reviewerID, hist, neg_list[i], 0))
label = (pos_list[-1], neg_list[-1])
test_set.append((reviewerID, hist, label))
测试集中选择一个没见过的item,与随机选择一个负样本item,这个两个item作为测试?
一般排序的测试集都是这么构建的吗?
多谢大佬。
您提到这个代码跑出来的auc与论文中大概相同,我使用了您的代码却未能得到论文中的 效果,所以想问下您跑出来的结果?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.