Riccardo Cappuzzo

> Formatting is now broken in jupyter:  I must have committed some changes that broke it, now it should be fixed.

> Two questions: > > 1. could we mark conversations/threads that are done (or outdated) as resolved? This would help collapse comments that don't need reading > 2. can you...

I am trying to push some changes to address @betatim's comment, but mypy is stopping me... I am getting this error: ``` sklearn/externals/_arff.py:782: note: By default the bodies of untyped...

> Ok. So the result of "highest level estimator is checked" would be that if you have a stateless estimator in your pipeline then it will be displayed as "fitted",...

Hello, thanks for tagging me! In fact, there are a few things that I think are worth considering. Specifically, there various issues involved in using a simple threshold that I...

Thanks for the work and for putting together the notes! I agree with @LeoGrin on having both relative and absolute metrics: a relative metric should work better if the user...

Hello! We talked about holidays as features during this week's meeting, and I found this API that might be useful for adding holidays as features: https://api-ninjas.com/api/holidays Of course this would...

Yep, I'm finding some more things I'd like to change in the doc page, but everything I mentioned in the original post has been fixed so we can close this...

Hey @ancri, thanks for the issue. Yes, it's a good idea, and shouldn't be too difficult to add in. The `TableReport` class can carry additional arguments to be forwarded to...

> In my opinion, we should only use the `float_precision` kwarg for displaying the value of the table, not for computing statistics or plotting. So, this value should be passed...