This is super exciting. In particular, I think for ibis ( http://docs.ibis-project.org/) building up expressions and executing them using gandiva would fit nicely as another in-memory backend alongside the pandas backend. I think it would also drive some use cases forward for more complex datatype support. I'm likely going to hack together a very basic POC using Philipp's bindings to see where I trip up and submit patches for any non-PEBKAC errors I encounter.
I think it would be wonderful if this code were donated to the arrow project as it would make the testing, release, deployment aspects of both pieces of software much easier. On Sat, Jun 23, 2018 at 11:11 AM Jacques Nadeau <jacq...@apache.org> wrote: > > > > I'd be willing to carve out some extra time to make sure patches are > > getting > > merged promptly until Ravindra or others become committers. > > > > Thanks! > > > > > I think the fact that Philipp incorporated Gandiva into the Arrow > > codebase and built Python bindings in less than 24 hours is a pretty > > strong indicator! > > > > Agreed >
