GitHub user rawataaryan9 opened a pull request:
https://github.com/apache/spark/pull/18390
SPARK-21178 : Add support for label specific metrics in MulticlassClaâ¦
â¦ssificationEvaluator
## What changes were proposed in this pull request?
Added support for providing a label value (optional) in
MulticlassClassificationEvaluator
Added support for following metrics, when a label value is provided -
f1, precision, recall, true positive rate, false positive rate.
This allows for optimizing on a label specific metric when learning a model.
## How was this patch tested?
Added unit-tests in accordance with the existing tests on
MulticlassClassificationEvaluator
Done manual testing to verify it's working correctly.
Please review http://spark.apache.org/contributing.html before opening a
pull request.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/rawataaryan9/spark SPARK-21178
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/18390.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 #18390
----
commit 7be699310ae8a34eef57e1a9e6aa470dee4c859f
Author: aman rawat <aman.ra...@snapdeal.com>
Date: 2017-06-22T12:04:08Z
SPARK-21178 : Add support for label specific metrics in
MulticlassClassificationEvaluator
----
---
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
