display-advertising-challenge - GitLite

KO | EN

gitlite — search

#python #ai #typescript #golang #machine-learning #deep-learning #docker #macos #java #vue #pytorch #ios #mcp #openai

display-advertising-challenge

(★ 130)

Criteo/Kaggle Competition of CTR prediction

파일 탐색기

최종 버전 다운로드 (.zip)

- .gitignore
- .gitignore
- pom.xml
- shuffle.py
- submit.py
- vw_run.py
- .gitignore
.gitignore
LICENSE
README.md
run.sh

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/songgc/display-advertising-challenge

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd display-advertising-challenge

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Maven (Java)

보통 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
JDK (Java) Java 프로젝트를 빌드/실행하려면 필요합니다.
Maven mvn 명령어를 쓰기 위한 빌드 도구입니다.

$ mvn package # or mvn install

Maven으로 의존성 설치와 빌드를 진행합니다.

✅ BUILD SUCCESS 메시지가 뜨면 성공입니다. target/ 폴더에 결과물이 생성됩니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Display Advertising Challenge
=============================

Description
-----------
This is the code was written for the [Kaggle Criteo Competition of CTR prediction](https://www.kaggle.com/c/criteo-display-ad-challenge).

Since the data are highly sparse, the basic methodology is to use logistic regression with appropriate quadratic/polynomial feature generation and regularization to make sophisticated and over-fitting-tractable models. [Vowpal Wabbit](https://github.com/JohnLangford/vowpal_wabbit) is the major machine learning software used for this project. Since the data size is challenging in terms of my personal workstation (a single quad-core CPU), the techniques of feature selection and model training are selected based on the trade off between performance and CPU/RAM resource limit.

Dependencies and requirements
-----------------------------
Please note that the code was written for my personal learning and practice in new features of Java 8 and Python 3.4 in Ubuntu 14.04. The code cannot be run in early versions of these two languages or other OSs. Compatibility is not considered here.

* Java 8
* Python 3.4
* Maven 3
* Redis 2.8
* Pandas 0.14
* Vowpal Wabbit 7.7
* Java-based open source projects: (Maven will install them automatically)
  - guava 17.0
  - jedis 2.5.1
  - commons-lang3 3.3.2

How to run
----------
- Copy train and test data file (train.csv, test.csv) to data folder
- Compile the Java code by
```
$ cd display-ad-java
$ mvn package # or mvn install
```
- Make sure a redis instance running at localhost:6379
- Set the path of binary vw (VW_BIN) in run.sh, such as 
```
export VW_BIN=/path/to/vw/binary
```
- Finally, 
```
$ cd work
$ ../run.sh
```