urosstan-db commented on code in PR #59615:
URL: https://github.com/apache/spark/pull/59615#discussion_r4362098150
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/VectorAggSuite.scala:
##########
@@ -405,6 +405,151 @@ class VectorAggSuite extends SparkFunSuite {
assert(result(1) === 3.0f)
}
+ test("VectorAvg - opposite extreme values do not overflow") {
+ val (agg, buffer, _) = createVectorAvg()
+ agg.update(buffer, createInputRow(Array(Float.MaxValue, -Float.MaxValue)))
+ agg.update(buffer, createInputRow(Array(-Float.MaxValue, Float.MaxValue)))
+ assertResult(Array(0.0f, 0.0f))(evalAsFloatArray(agg, buffer))
+
+ val (_, buffer1, _) = createVectorAvg()
+ val (_, buffer2, _) = createVectorAvg()
+ agg.update(buffer1, createInputRow(Array(Float.MaxValue, -Float.MaxValue)))
+ agg.update(buffer2, createInputRow(Array(-Float.MaxValue, Float.MaxValue)))
+ agg.merge(buffer1, buffer2)
+ assertResult(Array(0.0f, 0.0f))(evalAsFloatArray(agg, buffer1))
+ }
+
+ test("VectorAvg - finite overflow preserves cumulative weights") {
+ val (agg, buffer, _) = createVectorAvg()
+ val first = Array(Float.MaxValue, -Float.MaxValue)
+ agg.update(buffer, createInputRow(first))
+ agg.update(buffer, createInputRow(first))
+ // The third update overflows the delta. An unweighted midpoint would
incorrectly return zero.
+ agg.update(buffer, createInputRow(first.map(-_)))
+ val expected = (Float.MaxValue.toDouble / 3).toFloat
+ assertFloatArrayEquals(
+ evalAsFloatArray(agg, buffer),
+ Array(expected, -expected),
+ tolerance = math.ulp(expected) * 2)
+ }
+
+ test("VectorAvg - non-finite results do not depend on input order") {
+ val first =
+ Array(Float.PositiveInfinity, 1.0f, Float.NegativeInfinity,
Float.PositiveInfinity)
+ val second = Array(1.0f, Float.PositiveInfinity, 1.0f,
Float.NegativeInfinity)
+ def checkResult(result: Array[Float]): Unit = {
+ assertResult(Float.PositiveInfinity)(result(0))
+ assertResult(Float.PositiveInfinity)(result(1))
+ assertResult(Float.NegativeInfinity)(result(2))
+ assert(result(3).isNaN)
+ }
+
+ Seq(Seq(first, second), Seq(second, first)).foreach { vectors =>
+ val (agg, buffer, _) = createVectorAvg()
+ vectors.foreach(v => agg.update(buffer, createInputRow(v)))
+ checkResult(evalAsFloatArray(agg, buffer))
+ agg.update(buffer, createInputRow(Array(2.0f, 2.0f, 2.0f, 2.0f)))
+ checkResult(evalAsFloatArray(agg, buffer))
+
+ val (_, buffer1, _) = createVectorAvg()
+ val (_, buffer2, _) = createVectorAvg()
+ agg.update(buffer1, createInputRow(vectors.head))
+ agg.update(buffer2, createInputRow(vectors(1)))
+ agg.merge(buffer1, buffer2)
+ checkResult(evalAsFloatArray(agg, buffer1))
+ }
+ }
+
+ test("VectorAvg - finite elements around non-finite deltas") {
+ val first = Array(1.0f, Float.MaxValue, 3.0f, Float.PositiveInfinity, 5.0f,
+ Float.NegativeInfinity, 7.0f, Float.PositiveInfinity, 9.0f, Float.NaN,
11.0f)
+ val second = Array(3.0f, -Float.MaxValue, 5.0f, 1.0f, 7.0f, 1.0f, 9.0f,
+ Float.NegativeInfinity, 11.0f, 2.0f, 13.0f)
+ val expected = Array(2.0f, 0.0f, 4.0f, Float.PositiveInfinity, 6.0f,
+ Float.NegativeInfinity, 8.0f, Float.NaN, 10.0f, Float.NaN, 12.0f)
+
+ Seq(false, true).foreach { useGenericArray =>
+ val (agg, buffer, _) = createVectorAvg()
+ Seq(first, second).foreach { values =>
+ val array = if (useGenericArray) {
+ new GenericArrayData(values)
+ } else {
+ ArrayData.toArrayData(values)
+ }
+ agg.update(buffer, InternalRow(array))
+ }
+ assertResult(expected.map(JFloat.floatToIntBits))(
+ evalAsFloatArray(agg, buffer).map(JFloat.floatToIntBits))
+ }
+ }
+
+ test("VectorAvg - finite updates preserve running-average rounding") {
+ Seq(false, true).foreach { includeInfinity =>
+ val (agg, buffer, _) = createVectorAvg()
+ val first = Array.tabulate(17)(i => if (i % 2 == 0) 1.0f else -1.0f)
+ val last = first.map(-_)
Review Comment:
Good catch, resolved now
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
