Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/3637#issuecomment-71713330
@petro-rudenko It is possible to get the state, but not in a single
object. It's a good question whether a model and its state should be different
concepts. In the current MLlib code, they are the same concept, so the
functionality you're mentioning is supported in slightly different ways:
* Saving will happen through save/load methods (which I'm working on:
[https://issues.apache.org/jira/browse/SPARK-4587])
* Passing to prediction front-ends can happen through save, or by manually
taking the needed elements of the state.
* Copying the model can be done by copy().
* Printing/viewing the state can be done by casting the bestModel to the
correct type:
```
cvModel.bestModel.asInstanceOf[LogisticRegressionModel].weights
...
```
---
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]
