microsoft / adaptive-testing

Find and fix bugs in natural language machine learning models using adaptive testing.
MIT License
182 stars 30 forks source link

Data files are not available for notebooks to run #15

Open guanqun-yang opened 2 years ago

guanqun-yang commented 2 years ago

Hi,

Thanks for the great system you designed! It is a great improvement over your previous CheckList system. I can not wait to try our your system into my project!

However, running the sample notebooks requires some external .csv files that do not seem to be provided in the notebooks/ directory or anywhere else in your repository. Specifically,

Could these two files be provided? If this is not possible, could you explain how we create a .csv with same schema from existing sentiment classification or NLI dataset?

Best, Guanqun

Harsha-Nori commented 2 years ago

Hi @guanqun-yang,

Thanks for your excitement about the project, and great question! The .csv files in the example notebooks are completely optional -- if AdaTest is provided with a path to a .csv that doesn't exist, the code will just initialize with an empty set of tests. Once you've used the interface to create tests, you'll find the file automatically created for you on disk (and you'll be able to re-use it in the future by passing it to the adatest.TestTree constructor). We could definitely make this more clear in the documentation/notebooks, so thanks for the feedback too. Hope this helps!