Github user MLnick commented on the issue:

    https://github.com/apache/spark/pull/11119
  
    For the `KMeansModel` saving the `initialModel` - it still seems weird to 
me. Another factor to consider: the main use case in my view is continually 
re-training a model with the result from the previous training run. This makes 
up a model chain. Since each model saves the initial model, you'll end up with 
a recursive set of models all the way back to the beginning.
    
    In a way this is useful I guess since it would allow tracking the lineage. 
But what if the models are large (say large `k` and high-dimensional features, 
or later a large LoR model)? It is needlessly saving a bunch of data. If 
someone actually wants that tracking, I'd imagine they would explicitly save 
each trained model.
    
    Happy to hear dissenting thoughts on this point. 


---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to