Github user wzhfy commented on a diff in the pull request:
https://github.com/apache/spark/pull/19783#discussion_r153977529
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/EstimationUtils.scala
---
@@ -114,4 +114,197 @@ object EstimationUtils {
}
}
+ /**
+ * Returns the number of the first bin into which a column values falls
for a specified
+ * numeric equi-height histogram.
+ *
+ * @param value a literal value of a column
+ * @param histogram a numeric equi-height histogram
+ * @return the number of the first bin into which a column values falls.
+ */
+
+ def findFirstBinForValue(value: Double, histogram: Histogram): Int = {
+ var binId = 0
+ histogram.bins.foreach { bin =>
+ if (value > bin.hi) binId += 1
+ }
+ binId
+ }
+
+ /**
+ * Returns the number of the last bin into which a column values falls
for a specified
+ * numeric equi-height histogram.
+ *
+ * @param value a literal value of a column
+ * @param histogram a numeric equi-height histogram
+ * @return the number of the last bin into which a column values falls.
+ */
+
+ def findLastBinForValue(value: Double, histogram: Histogram): Int = {
+ var binId = 0
+ for (i <- 0 until histogram.bins.length) {
+ if (value > histogram.bins(i).hi) {
+ // increment binId to point to next bin
+ binId += 1
+ }
+ if ((value == histogram.bins(i).hi) && (i < histogram.bins.length -
1)) {
+ if (value == histogram.bins(i + 1).lo) {
+ // increment binId since the value appears into this bin and
next bin
--- End diff --
appears in both this bin and the next bin
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
