GitHub user noel-smith opened a pull request:
https://github.com/apache/spark/pull/8399
[SPARK-10188] [Pyspark] Pyspark CrossValidator with RMSE selects incorrect
model
* Added isLargerBetter() method to Pyspark Evaluator to match the Scala
version.
* JavaEvaluator delegates isLargerBetter() to underlying Scala object.
* Added check for isLargerBetter() in CrossValidator to determine whether
to use argmin or argmax.
* Added test cases for where smaller is better (RMSE) and larger is better
(R-Squared).
(This contribution is my original work and that I license the work to the
project under Sparks' open source license)
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/noel-smith/spark pyspark-rmse-xval-fix
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/8399.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #8399
----
commit d00357e40cef090c20ed4089d1cc23ebdaba2918
Author: noelsmith <m...@noelsmith.com>
Date: 2015-08-24T17:02:13Z
Added test for cross validation
commit 6cd4ed12e4c37e80a3f88f93cb4255a1c011f5af
Author: noelsmith <m...@noelsmith.com>
Date: 2015-08-24T18:03:18Z
Added/fixed tests for cross validation
commit 63b3835b3676d8c1c19f756d4e9dba5575ef9d3f
Author: noelsmith <m...@noelsmith.com>
Date: 2015-08-24T18:24:48Z
Removed print statements
commit 7794cf73e10f2b5c57cfff1a2ea4a175e282c33c
Author: noelsmith <m...@noelsmith.com>
Date: 2015-08-24T18:25:33Z
Added checks for isLargerBetter()
----
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
