Github user gdfm commented on the pull request:
https://github.com/apache/incubator-samoa/commit/af25e7d1f464323dcd0e2bb5729dc70e5ad36887#commitcomment-16522965
Hi,
Yes, the idea is that the trees are in synch.
However, it also depends on the underlying streaming engine: if it can
guarantee the message delivery (in this case, the split message broadcast from
the LearningNode to the ModelTrees), then the models will be the same.
We still don't handle the possibility of losing a message, so the algorithm
is not entirely fault-tolerant.
---
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.
---
