Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/11866#discussion_r57026496
--- Diff: python/pyspark/ml/pipeline.py ---
@@ -206,49 +167,65 @@ def save(self, path):
@classmethod
@since("2.0.0")
def read(cls):
- """Returns an JavaMLReader instance for this class."""
+ """Returns an MLReader instance for this class."""
return PipelineMLReader(cls)
@classmethod
- @since("2.0.0")
- def load(cls, path):
- """Reads an ML instance from the input path, a shortcut of
`read().load(path)`."""
- return cls.read().load(path)
+ def _transfer_stage_from_java(cls, java_stage):
+ """
+ Given a Java Pipeline, create and return a Python wrapper of it.
+ Used for ML persistence.
+ """
+ # Create a new instance of this stage.
+ py_stage = cls()
+ # Load information from java_stage to the instance.
+ py_stages = [JavaWrapper._transfer_stage_from_java(s) for s in
java_stage.getStages()]
+ py_stage.setStages(py_stages)
+ py_stage._resetUid(java_stage.uid())
+ return py_stage
+
+ def _transfer_stage_to_java(self):
+ """
+ Transfer this instance to a Java object. Used for ML persistence.
--- End diff --
Done
---
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]
