dongjoon-hyun commented on a change in pull request #28764:
URL: https://github.com/apache/spark/pull/28764#discussion_r438501422
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala
##########
@@ -1325,3 +1325,94 @@ case class BRound(child: Expression, scale: Expression)
with Serializable with ImplicitCastInputTypes {
def this(child: Expression) = this(child, Literal(0))
}
+
+object WidthBucket {
+
+ def computeBucketNumber(value: Double, min: Double, max: Double, numBucket:
Long): jl.Long = {
+ if (numBucket <= 0 || numBucket == Long.MaxValue || jl.Double.isNaN(value)
|| min == max ||
+ jl.Double.isNaN(min) || jl.Double.isInfinite(min) ||
+ jl.Double.isNaN(max) || jl.Double.isInfinite(max)) {
+ return null
+ }
+
+ val lower = Math.min(min, max)
+ val upper = Math.max(min, max)
+
+ if (min < max) {
+ if (value < lower) {
+ 0L
+ } else if (value >= upper) {
+ numBucket + 1L
+ } else {
+ (numBucket.toDouble * (value - lower) / (upper - lower)).toLong + 1L
+ }
+ } else { // `min > max` case
+ if (value > upper) {
+ 0L
+ } else if (value <= lower) {
+ numBucket + 1L
+ } else {
+ (numBucket.toDouble * (upper - value) / (upper - lower)).toLong + 1L
+ }
+ }
+ }
+}
+
+/**
+ * Returns the bucket number into which the value of this expression would fall
+ * after being evaluated. Note that input arguments must follow conditions
listed below;
+ * otherwise, the method will return null.
+ * - `numBucket` must be greater than zero and be less than Long.MaxValue
+ * - `value`, `min`, and `max` cannot be NaN
+ * - `min` bound cannot equal `max
+ * - `min` and `max` must be finite
+ *
+ * @param expr is the expression to compute a bucket number in the histogram
+ * @param minValue is the minimum value of the histogram
+ * @param maxValue is the maximum value of the histogram
+ * @param numBucket is the number of buckets
+ */
+@ExpressionDescription(
+ usage = """
+ _FUNC_(expr, min_value, max_value, num_bucket) - Returns the `bucket` to
which
+ operand would be assigned in an equiwidth histogram with `num_bucket`
buckets,
Review comment:
Technically, in `PostgreSQL` , their argument name is `operand` while
this PR uses `expr`.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
