-
Notifications
You must be signed in to change notification settings - Fork 393
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Property-based GLM test #427
Conversation
@michaelweilsalesforce please update PR description. also, is it ready for review? |
@@ -262,6 +261,7 @@ private[op] case object FitStagesUtil { | |||
val stages = stagesLayer.map(_._1) | |||
val (estimators, noFit) = stages.partition(_.isInstanceOf[Estimator[_]]) | |||
val fitEstimators = estimators.map { case e: Estimator[_] => | |||
println(e.getInputFeatures().toSeq) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
remove println
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
great tests!
@Jauntbox These tests are actually painful for our runtime (~15-20 mins/ unit test) |
Builds will be killed if not output is produced for 10 minutes, so we can’t have an individual test take longer than that. |
Codecov Report
@@ Coverage Diff @@
## master #427 +/- ##
==========================================
+ Coverage 86.94% 86.96% +0.01%
==========================================
Files 337 337
Lines 11082 11083 +1
Branches 355 356 +1
==========================================
+ Hits 9635 9638 +3
+ Misses 1447 1445 -2
Continue to review full report at Codecov.
|
Related issues
Adding more Tests for our ML capabilities (TDD)
Describe the proposed solution
Property based tests to check each of our the Regression Models (Linear Regression, Random Forest, GLM) will be picked based on the nature of the data (and response) generated
Describe alternatives you've considered
Doing the same tests on one single dataset instead