[GitHub] 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

[GitBox <gi...@apache.org>]

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_r256590880
 
 

 ##########
 File path: mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
 ##########
 @@ -68,21 +74,33 @@ class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override va
   @Since("1.2.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
+  /** @group setParam */
+  @Since("3.0.0")
+  def setWeightCol(value: String): this.type = set(weightCol, value)
+
   setDefault(metricName -> "areaUnderROC")
 
   @Since("2.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {
     val schema = dataset.schema
     SchemaUtils.checkColumnTypes(schema, $(rawPredictionCol), Seq(DoubleType, new VectorUDT))
     SchemaUtils.checkNumericType(schema, $(labelCol))
+    if (isDefined(weightCol)) {
+      SchemaUtils.checkNumericType(schema, $(weightCol))
+    }
 
     // TODO: When dataset metadata has been implemented, check rawPredictionCol vector length = 2.
-    val scoreAndLabels =
-      dataset.select(col($(rawPredictionCol)), col($(labelCol)).cast(DoubleType)).rdd.map {
-        case Row(rawPrediction: Vector, label: Double) => (rawPrediction(1), label)
-        case Row(rawPrediction: Double, label: Double) => (rawPrediction, label)
+    val scoreAndLabelsWithWeights =
+      dataset.select(col($(rawPredictionCol)), col($(labelCol)).cast(DoubleType),
+        if (!isDefined(weightCol) || $(weightCol).isEmpty) lit(1.0)
 
 Review comment:
   We might need to wrap this differently for clarity, like
   ```
   dataset.select(
     col(...),
     ...
     if () else ...).rdd.map {
       case ...
   ```

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org