Stuart Lynn

I'll let you merge, since I don't have permission. Do you have a new release planned?

Hey Jan, I took a look at your example and compared it to our reference [here](https://docs.databricks.com/_static/notebooks/mleap-model-export-demo-scala.html). Where you read the bundle, what happens if you substitute `jar:` for `file:`? Given...

Can you try with XGBoost 1.0? That was the last version I tested this against.

Try with a trailing underscore, i.e. `lambda_`. I think this was renamed to avoid the clash with python's `lambda` reserved keyword.

Do you get an error with v0.9 of xgboost4j / xgboost4j-spark?

Could you try zero-buffering the input geometry, e.g. `mosaic.st_buffer(f.col("geom"), 0)` in order to force it to be made valid?

@milos-colic will have an authoritative answer here, but I think you'll need to use the 'retile_on_read' strategy for reading large rasters since there's no way around the 2GB limit on...

Agreed. Hope it helps you make progress.

@rvo1994 For a point in poly join like this one, you might want to try using a grid index to speed the process up. Take a look at the [quickstart...