you are scored by ans_simple order doesn't matter we expect for you to write the evaluation code\
The evaluation metric is hard accuracy based on ans_simple we will also ask you to present to me the model and approach you took to ensure that you didn't over fit the test set or cheat
You can use any dataset as long as it doesn't contain any values in the test set
The test set has already been provided see the attached notebook
There is no evaluation tool but you can come find me and I will be happy to guide, provide advice and tell you how you are doing