Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/13440#discussion_r218209453 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala --- @@ -52,6 +52,49 @@ trait Impurity extends Serializable { @Since("1.0.0") @DeveloperApi def calculate(count: Double, sum: Double, sumSquares: Double): Double + + /** + * :: DeveloperApi :: + * Compute a test-statistic p-value quality measure from left and right split populations + * @param calcL impurity calculator for the left split population + * @param calcR impurity calculator for the right split population + * @return The p-value for the null hypothesis; that left and right split populations + * represent the same distribution + * @note Unless overridden this method will fail with an exception, for backward compatability + */ + @Since("2.2.0") + @DeveloperApi + def calculate(calcL: ImpurityCalculator, calcR: ImpurityCalculator): Double + + /** + * :: DeveloperApi :: + * Determine if this impurity measure is a test-statistic measure + * @return True if this is a split quality measure based on a test statistic (i.e. returns a + * p-value) or false otherwise. + * @note Unless overridden this method returns false by default, for backward compatability + */ + @Since("2.2.0") + @DeveloperApi + def isTestStatistic: Boolean --- End diff -- Adding methods to a public trait is technically an API breaking change. This might be considered a Developer API even though it's not labeled that way. Still if we can avoid adding to the API here, it'd be better.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org