Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/6088#discussion_r30377478
--- Diff: python/pyspark/ml/pipeline.py ---
@@ -165,16 +215,27 @@ class PipelineModel(Model):
Represents a compiled pipeline with transformers and fitted models.
"""
- def __init__(self, transformers):
+ def __init__(self, stages):
super(PipelineModel, self).__init__()
- self.transformers = transformers
+ self.stages = stages
- def transform(self, dataset, params={}):
- paramMap = self.extractParamMap(params)
- for t in self.transformers:
- dataset = t.transform(dataset, paramMap)
+ def _transform(self, dataset):
+ for t in self.stages:
+ dataset = t.transform(dataset)
return dataset
+ def copy(self, extra={}):
+ """
+ Creates a copy of this instance with a randomly generated uid
--- End diff --
not random
---
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]
