hwang7308/kdd_cup_challenge_2009

KDD Cup Challenge 2009

How to Run The Code

1.cd code/

2.python preprocessing.py

3.cd ../scripts/

4.bash test.sh

There will be more detailed guide on usage.

After running, the graph results with be in "result/graph", some text results will be in "result/text".

How we contribute to our code

Preprocessing data on numerical features

rushingdragging and S1887468 provide files in folder './data_preprocessing_temp'

Preprocessing data on categorical features & PCA

philipppp000 provides code in 'preprocessing.py'

Classification method & integration of all code files

HWANG7308 provides code for classification model and organizes all our code with other necessary part to make our code running better

References

1.New website for the KDD-cup

https://www.kdd.org/kdd-cup/view/kdd-cup-2009/Data

2.Datasets here

http://www.vincentlemaire-labs.fr/kddcup2009/#data

3.Proceedings of KDD-Cup 2009 competition

http://proceedings.mlr.press/v7/

4.KDD-Cup 2009 competition web site (Note post-challenge entries still ranked on the leaderboard!)

https://www.hugedomains.com/domain_profile.cfm?d=kddcup-orange&e=com

5.Kaggle competition

https://www.kaggle.com/asminalev/kdd-cup-2009-customer-relationship-prediction/kernels