nealrichardson commented on pull request #9615:
URL: https://github.com/apache/arrow/pull/9615#issuecomment-853293852
Thanks @westonpace, I'll merge now and make a followup
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
nealrichardson commented on pull request #9615:
URL: https://github.com/apache/arrow/pull/9615#issuecomment-848297121
@romainfrancois @westonpace @jonkeane Is this ready to merge? (The rtools35
error is spurious)
--
This is an automated message from the Apache Git Service.
To respond to
nealrichardson commented on pull request #9615:
URL: https://github.com/apache/arrow/pull/9615#issuecomment-841545022
I think this needs rebase, and then that should expose the other place where
`Table__from_dots` is called that needs `options_use_threads()` passed to it
(which is the fail
nealrichardson commented on pull request #9615:
URL: https://github.com/apache/arrow/pull/9615#issuecomment-840145156
I wonder if the logic for "parallelize what you can, then do the rest in
serial" isn't working right. Maybe the natural datasets all have at least one
column (string, most
nealrichardson commented on pull request #9615:
URL: https://github.com/apache/arrow/pull/9615#issuecomment-833924620
I'm a little skeptical, with the exception of the big change on the
data.frames of factor columns, that this isn't just noise. I don't think
there's been any other changes