how to run evaluation.py by myself?

[greatofdream]

The evalution.py in demo doesn't contain any main program, should I configure one function to run evalution.py？

https://github.com/PaddlePaddle/PaddleSpatial/blob/main/apps/wpf_baseline_gru/kddcup22-sdwpf-evaluation/paddlepaddle/evaluation.py

[ramber1836]

You can add the initial statements in the evaluation.py to invoke the eval() interface and run this script by yourself.

[shaido987]

You can add the following to the evaluation.py file:

if __name__ == '__main__':
    evaluate("./initial-test-run"

Then put the prepare.py, predict file, etc. in a subfolder called initial-test-run (or whatever you want to call it). Now you can run the evaluation.py file to make sure that your submission code works.

It is also possible to use the eval function but then you need to create a zip file with the code first.