Mahmoud Rawas created SPARK-15858:
-------------------------------------
Summary: "evaluateEachIteration" will fail on trying to run it on
a model with 500+ trees
Key: SPARK-15858
URL: https://issues.apache.org/jira/browse/SPARK-15858
Project: Spark
Issue Type: Bug
Affects Versions: 1.6.1, 2.0.0
Reporter: Mahmoud Rawas
this line:
remappedData.zip(predictionAndError).mapPartitions
causing a stack over flow exception on executors after nearly 300 iterations
also with this number of trees having a var RDD will have needless memory
allocation.
this functionality tested on version 1.6.1
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
