wzhe06 / sparkctr Goto Github PK
View Code? Open in Web Editor NEWCTR prediction model based on spark(LR, GBDT, DNN)
Home Page: https://github.com/wzhe06/SparkCTR
License: Apache License 2.0
CTR prediction model based on spark(LR, GBDT, DNN)
Home Page: https://github.com/wzhe06/SparkCTR
License: Apache License 2.0
请问测试数据是哪一份,之前没有搞过ctr,不知道对应什么经典数据集?
比如有user有1000W,item有1000W,那么要有 1000W*1000W = 1000000亿 的特征数据?
请问LZ能否展示一下9种不同CTR models的performance?就是基于当前的训练,测试集,PR curve 和 ROC curve 的AUC值?有没有哪种model会明显优于其他的models?
你好,我用mvn install
打包完成后,找不到class.
生成的jar文件只有4K,用反编译工具打开后,只有如下目录结果
-META-INF
--maven/com.ggstar/CTRmodel
---pom.properties
---pom.xml
--MANIFEST.MF
请问这是什么原因,谢谢。
首先非常感谢将论文和模型整理的这么详细,正在研读中,如题,ctr一般不就是将用户特征向量item特征向量和上下文特征concat后输入模型的吗?
非常感谢如此全面而具体的实现,我在idea导入项目并安装完成依赖之后运行modelselectionExample显示如下错误,请问是什么问题
错误: 找不到或无法加载主类 com.ggstar.example.ModelSelection
原因: java.lang.ClassNotFoundException: com.ggstar.example.ModelSelection
Process finished with exit code 1
Parameter Server架构还是All Reduce架构?
CPU还是GPU?
有没有开源代码参考?
用不用改TensorFlow源码?
性价比最高的方案是?
从您公众号来,测试数据有吗?
GBDT+LR怎么没有实现啊
对于我们的数据,在保持正负样本平衡的情况下,fm能够好于lr,但是在大量测试(意味着有大量没有见过的负样本)的情况下,lr反而超出fm几个点,请问您能否给出意见
您好,
我是scala spark的新手。刚git clone 下了CTRmodel的source code。我想要run 不同的example function(LR, GBDT, NN etc.),看到README上面的usage是说"After dependencies are imported by maven automatically, you can simple run the example function"。请问这个具体怎么做?
谢谢
您好,请问能提供一下samples.snappy.orc文件吗,谢谢!
val instr = Instrumentation.create(this, oldDataset) instr.logParams(params: _*) instr.logNumFeatures(numFeatures) instr.logNumClasses(2)
spark 2.3.2,官方文档地址:http://spark.apache.org/docs/2.3.2/api/scala/index.html,并没有这几个类可以用
这套框架能支持多少特征,多大的模型?
谢谢。
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.