If I want to test the type of vulnerability in a piece of code, how should I preprocess the test data?

Question

If I want to test the type of vulnerability in a piece of code, how should I preprocess the test data?

zhang-zrq opened this issue a year ago · 2 comments

I followed the method provided in this link for preprocessing, but I was unable to obtain the test. jsonl file
link：【 https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Defect-detection/dataset】

Answer 1 · 2023-05-08T04:16:11.000Z

Sincerely hope that you can provide an test.sh for testing

Answer 2 · 2023-05-08T04:21:44.000Z

Hi ,
You can use this file and split into train test and evaluation file.
Or you can use the train_test_split() method from sklearn to split the file into 80:10:10 for train eval and test.