Documentation on PCA expected max memory usage
Open
- Dominant language
- Python
- Stars
- 951
- Forks
- 262
- PR merge metrics
- No merged PRs in 30d
Description
While running the distributed PCA defined here, I've found that I need to tune my cluster so that I can accommodate the `finalize` task without nodes crashing out due to memory usage.
It would be nice to be able to estimate what amount of memory is required for a particular data size ahead of time.
Contributor guide
Assessment
This issue has not been assessed yet.