Narine Kokhlikyan created SPARK-13982:
-----------------------------------------
Summary: SparkR - KMeans predict: Output column name of features
is an unclear, automatic genetared text
Key: SPARK-13982
URL: https://issues.apache.org/jira/browse/SPARK-13982
Project: Spark
Issue Type: Bug
Reporter: Narine Kokhlikyan
Priority: Minor
Currently KMean-predict's features' output column name is set to something like
this: "vecAssembler_522ba59ea239__output", which is the default output column
name of the "VectorAssembler".
Example:
showDF(predict(model, training)) shows something like this:
DataFrame[Sepal_Length:double, Sepal_Width:double, Petal_Length:double,
Petal_Width:double, **vecAssembler_522ba59ea239__output:**vector,
prediction:int]
This name is automatically generated and very unclear from user perspective.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
