srowen commented on a change in pull request #17084: [SPARK-24103][ML][MLLIB]
ML Evaluators should use weight column - added weight column for binary
classification evaluator
URL: https://github.com/apache/spark/pull/17084#discussion_r259648418
##########
File path:
mllib/src/test/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluatorSuite.scala
##########
@@ -71,6 +71,33 @@ class BinaryClassificationEvaluatorSuite
assert(thrown.getMessage.replace("\n", "") contains "but was actually of
type string.")
}
+ test("should accept weight column") {
+ val weightCol = "weight"
+ // get metric with weight column
+ val evaluator = new BinaryClassificationEvaluator()
+ .setMetricName("areaUnderROC").setWeightCol(weightCol)
+ val vectorDF = Seq(
+ (0d, Vectors.dense(2.5, 12), 1.0),
Review comment:
Nit: 0.0 instead of 0d. The "d" or "D" suffix I think might read for a
moment like hex or something.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
