summary for circular variables

[aloctavodia]

Summary used to have a circ_var_names argument in order to specify for which variables to compute circular statistics instead of the regular ones (#45). This argument was replaced by include_circ, this accept booleans, when True it will compute the regular statistics plus the circular statistics for all variables. I think we should revert this and have circ_var_names again, or maybe some other alternative.

The ideal behavior will be to automatically compute the proper statistics based on the variable type, but at least for the moment that information is not available for ArviZ

[shivam7569]

Is this issue open for work? I would like to work on this. Thanks!

[aloctavodia]

Yeah, this is still an issue. Thanks for your offer.

[smit-s]

@aloctavodia If this issue is still open, can I work on it please?

[aloctavodia]

Is still open, I think @agustinaarroyuelo was planning to work on this as part of the GSoC (but she also is proposing many other tasks).

[smit-s]

No problem at all. I will pick up regression plot and time-series.