Karin Hrovatin

@Scienfitz for RDKIt there is some ruggedness where it flattens off I checked the encoding statistics and RDKit does not seem to differ from ECFP in their distn. N of...

@Scienfitz I made the merge. Please check comments that are still open and lmk if I should change sth or close them if ok with you

With `tox -e fulltest-py312` I get - any ideas? ``` _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _...

> @Hrovatin the example picture is off, the curve for RDKIT is wrong, seem the batch size was influenced... something very strange here is going on. Ive noticed this in...

@Scienfitz I ran `pytest -fast` and there are two errs that I am not sure about - if you could provide some guidance that would be great ``` FAILED tests/test_searchspace.py::test_searchspace_memory_estimate[grid5-parameter_names0]...

Also, do I need to do sth to re-generate documentation svgs or will it be done automatically? I guess `examples/Backtesting/full_lookup.py` creates some of these - should I run it?

Test results. For mypy I need to do a few updates and will add once finished. ``` tox -p -e lint-py312 lint-py312: OK (19.49=setup[1.84]+cmd[0.01,17.63] seconds) congratulations :) (19.81 seconds) tox...

For mypy I have multiple issues with `SubstanceEncoding`, for which I would anyway suggest changes, as briefly mentioned above. So I did not resolve them for now. ``` baybe/parameters/enum.py:51: error:...

@Scienfitz another thing to potentially consider: If I understand correctly FPS only supports discrete subspaces. Would it be possible to internally discretize subspaces to make it more general?

As briefly discussed today maybe a good start would be the option to specify bins for discretization (as user probably knows best what may be a meaningful number/spacing) of bins