How to quickly start to train and test my new model using a public dataset instead of a toy dataset, such as avazu, criteo?

reczoo / FuxiCTR

A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io

Apache License 2.0

914 stars 157 forks source link

How to quickly start to train and test my new model using a public dataset instead of a toy dataset, such as avazu, criteo? #71

Closed Zeng-B-B closed 1 year ago

Zeng-B-B commented 1 year ago

Hello, I don't know how to modify the code detailly for running my model on avazu dataset.I have three csv file(train, valid, test) for avazu, which are placed in "data" directory.which files do I need to modify?please tell me how to transform "avazu" dataset to the format(H5) we want?

zhujiem commented 1 year ago

Please check the benchmark links in the model table in README. Then you could find some examples to run your model. Say https://github.com/openbenchmark/BARS/tree/main/ctr_prediction/benchmarks/FinalMLP

zhujiem commented 1 year ago

The full example can be also found at https://github.com/xue-pai/FinalMLP