Github user sethah commented on the pull request:
https://github.com/apache/spark/pull/12370#issuecomment-209669616
In a previous "TODO" it was proposed that we could incorporate sample
weights by simply multiplying the subsample counts by the sample weight and
storing them in an array. I chose not to do this because of the need to have
both _raw counts_ and _weighted counts_ when adding weights to decision trees.
If we simply store the weighted counts, we lose the information about the raw
counts, which makes it impossible to track `minInstancesPerNode` for decision
trees.
---
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]
