[SPARK-55969][SQL] regr_r2 should treat first param as dependent variable

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/linearRegression.scala

@@ -147,8 +147,10 @@ case class RegrR2(y: Expression, x: Expression) extends PearsonCorrelation(y, x,
   override def prettyName: String = "regr_r2"
   override val evaluateExpression: Expression = {
     val corr = ck / sqrt(xMk * yMk)
-    If(xMk === 0.0, Literal.create(null, DoubleType),
-      If(yMk === 0.0, Literal.create(1.0, DoubleType), corr * corr))
+    // In PearsonCorrelation, x and y are swapped, so here xMk refers to the dependent variable
+    // and yMk to the independent variable
+    If(yMk === 0.0, Literal.create(null, DoubleType),
+      If(xMk === 0.0, Literal.create(1.0, DoubleType), corr * corr))
   }
   override protected def withNewChildrenInternal(
       newLeft: Expression, newRight: Expression): RegrR2 =

sql/core/src/test/resources/sql-tests/analyzer-results/linear-regression.sql.out

@@ -407,3 +407,29 @@ Aggregate [k#x], [k#x, regr_intercept(cast(y#x as double), cast(x#x as double))
             +- Project [k#x, y#x, x#x]
                +- SubqueryAlias testRegression
                   +- LocalRelation [k#x, y#x, x#x]
+
+
+-- !query
+SELECT regr_r2(k, x) FROM testRegression where k=2
+-- !query analysis
+Aggregate [regr_r2(cast(k#x as double), cast(x#x as double)) AS regr_r2(k, x)#x]
++- Filter (k#x = 2)
+   +- SubqueryAlias testregression
+      +- View (`testRegression`, [k#x, y#x, x#x])
+         +- Project [cast(k#x as int) AS k#x, cast(y#x as int) AS y#x, cast(x#x as int) AS x#x]
+            +- Project [k#x, y#x, x#x]
+               +- SubqueryAlias testRegression
+                  +- LocalRelation [k#x, y#x, x#x]
+
+
+-- !query
+SELECT regr_r2(y, k) FROM testRegression where k=2
+-- !query analysis
+Aggregate [regr_r2(cast(y#x as double), cast(k#x as double)) AS regr_r2(y, k)#x]
++- Filter (k#x = 2)
+   +- SubqueryAlias testregression
+      +- View (`testRegression`, [k#x, y#x, x#x])
+         +- Project [cast(k#x as int) AS k#x, cast(y#x as int) AS y#x, cast(x#x as int) AS x#x]
+            +- Project [k#x, y#x, x#x]
+               +- SubqueryAlias testRegression
+                  +- LocalRelation [k#x, y#x, x#x]

sql/core/src/test/resources/sql-tests/inputs/linear-regression.sql

@@ -50,3 +50,7 @@ SELECT regr_intercept(y, x) FROM testRegression;
 SELECT regr_intercept(y, x) FROM testRegression WHERE x IS NOT NULL AND y IS NOT NULL;
 SELECT k, regr_intercept(y, x) FROM testRegression GROUP BY k;
 SELECT k, regr_intercept(y, x) FROM testRegression WHERE x IS NOT NULL AND y IS NOT NULL GROUP BY k;
+
+-- SPARK-55969: regr_r2 should treat first param as dependent variable
+SELECT regr_r2(k, x) FROM testRegression where k=2;
+SELECT regr_r2(y, k) FROM testRegression where k=2;

sql/core/src/test/resources/sql-tests/results/linear-regression.sql.out

@@ -274,3 +274,19 @@ SELECT k, regr_intercept(y, x) FROM testRegression WHERE x IS NOT NULL AND y IS
 struct<k:int,regr_intercept(y, x):double>
 -- !query output
 2	1.1547344110854496
+
+
+-- !query
+SELECT regr_r2(k, x) FROM testRegression where k=2
+-- !query schema
+struct<regr_r2(k, x):double>
+-- !query output
+1.0
+
+
+-- !query
+SELECT regr_r2(y, k) FROM testRegression where k=2
+-- !query schema
+struct<regr_r2(y, k):double>
+-- !query output
+NULL