Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21054#discussion_r185461620
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala
---
@@ -22,18 +22,14 @@ import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.types._
/**
- * Compute Pearson correlation between two expressions.
+ * Base class for computing Pearson correlation between two expressions.
* When applied on empty data (i.e., count is zero), it returns NULL.
*
* Definition of Pearson correlation can be found at
*
http://en.wikipedia.org/wiki/Pearson_product-moment_correlation_coefficient
*/
-// scalastyle:off line.size.limit
-@ExpressionDescription(
- usage = "_FUNC_(expr1, expr2) - Returns Pearson coefficient of
correlation between a set of number pairs.")
-// scalastyle:on line.size.limit
-case class Corr(x: Expression, y: Expression)
- extends DeclarativeAggregate with ImplicitCastInputTypes {
+abstract class PearsonCorrelation(x: Expression, y: Expression)
+ extends DeclarativeAggregate with ImplicitCastInputTypes {
--- End diff --
nit: indent
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
