seb.

Hi @gabrielasuchopar, if the setup is interrupted during the creation of the virtual env, I agree that it's better to simply delete it... usually enforcing setup is enough (using `--setup...

@gabrielasuchopar thanks a lot for your feedback, I'll add an entry in the troubleshooting guide (and also make it more visible/accessible from the README) for now, and create a ticket...

very possible, I don't think anyone has tried `hyperoptsklearn` for a long time now. It's not even included in our validation test suite. Thanks for raising this, we'll look at...

Hi @pplonski, currently the only published results are 1 year old: you can find them on the [application website](https://openml.github.io/automlbenchmark/), and in the [reports folder](https://github.com/openml/automlbenchmark/tree/master/reports). Those same results are also available...

It's Python core library's decision to log to `stderr` by default. It's common for logs to be redirected to `stderr` as `stdout` is usually reserved for a program's output/result: e.g....

@eddiebergman instead of fixing the logger, it rather looks like you expect the result scores to be printed to `stdout`, which is a fair expectation, we can add a `print()`...

@eddiebergman, yes, there are basically 2 common practices for command line apps. A common one—who lead to Python's decision—is to redirect logs to `stderr` and reserve `stdout` for result or...

@PGijsbers another one for you when you find some review time.

@mfeurer in this case both `X` and `y` are indeed sparse, not sure this makes sense for `y`. I currently fixed this by turning both into arrays as I thought...

@mfeurer for autosklearn, sparse `X` with dense `y` seems to work fine (and faster), meaning that in your case, sparse `y` was the issue. Thanks for noticing this: ideally we'd...