✔️ Linting Passed

All linting checks passed. Your pull request is in excellent shape! ☀️

_{Generated for commit: 9ec90ad. Link to the linter CI: here}

O_o a bit confused. If the test sets are not different, then the train sets also would be the same, wouldn't they?

So my understanding (which may be wrong) is that when we say the test sets are 'different', we mean that test sets do not overlap between folds (i.e. no sample appears in more than one test set across folds). With train set, there is generally always overlap between folds.

I don't think it means simply that the test/train sets are 'different' between folds because, generally they are not exactly the same.

I noticed this after reading:

(which is the only 'shuffle' splitter where we use the term 'with replacement')

So I think instead of saying "different" we can say, "test test are not guaranteed to be mutually exclusive, and might include overlapping samples".

Thanks @adrinjalali , I agree that 'different' is too vague and slightly mis-leading but couldn't think of something better. I've made the changes!