Dylan Sherry

Yep this seems quite helpful. Don't we already support this in automl search via `pipeline_parameters`? Or would that not work for the time series params?

@ParthivNaresh noticed that we're getting a similar but slightly different message for sktime. "Could not optimize". He's gonna file a separate issue for that.

> This could be broken up into 3 issues, one for each estimator class. Let's start with one of our tree-based estimators and demonstrate a performance improvement. Then we can...

This is related to #2396 and #2397

@angela97lin what's the status of this?

Lightgbm also has a plot method https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.plot_tree.html Perhaps xgboost does too

@BoopBoopBeepBoop yeah good questions! I think the physical type for logical type "Currency" should be a float. @thehomebrewnerd could something like [this library](http://babel.pocoo.org/en/latest/api/numbers.html) help with parsing and with internationalization? I...

@gsheni can you explain why the example you gave is currently inferred as categorical? I wonder if this should get classified as a bug instead, and the fix is simply...

Got it. So these ```python [True, False, True, True, np.nan] [True, False, True, True, pd.NA] ``` would also end up as boolean logical type, converted to `pd.BooleanDtype` resulting in ```python...

Let's do the copy for now. I agree this has performance implications, but its important to keep our API contract clear. This only happens when one or more cols is...