[
https://issues.apache.org/jira/browse/SPARK-11439?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14993308#comment-14993308
]
holdenk commented on SPARK-11439:
---------------------------------
I could see this, earlier versions of that test compared the model MSE against
the MSE of evaluating the model on the same input data, but the current version
of the test uses hardcoded values. The values are based on some R code thats
included in the comments, you should print out the new randomly generated
values and recompute the expected values using the provided R code.
> Optimization of creating sparse feature without dense one
> ---------------------------------------------------------
>
> Key: SPARK-11439
> URL: https://issues.apache.org/jira/browse/SPARK-11439
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Reporter: Kai Sasaki
> Priority: Minor
>
> Currently, sparse feature generated in {{LinearDataGenerator}} needs to
> create dense vectors once. It is cost efficient to prevent from generating
> dense feature when creating sparse features.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
