Github user mengxr commented on the pull request:
https://github.com/apache/spark/pull/12299#issuecomment-208454483
@srowen Determining the sparsity by the first row is not very reliable. I
checked out the stable online covariance computation
(https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance#Covariance)
and making it work for sparse data is not trivial. I wonder whether we should
go with a possibly inaccurate sparse implementation or treating all vectors as
dense and implement a "correct" version.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
