Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19479#discussion_r149803550
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/Statistics.scala
---
@@ -275,6 +317,123 @@ object ColumnStat extends Logging {
avgLen = row.getLong(4),
maxLen = row.getLong(5)
)
+ if (row.isNullAt(6)) {
+ cs
+ } else {
+ val ndvs = row.getArray(6).toLongArray()
+ assert(percentiles.get.numElements() == ndvs.length + 1)
+ val endpoints =
percentiles.get.toArray[Any](attr.dataType).map(_.toString.toDouble)
+ // Construct equi-height histogram
+ val buckets = ndvs.zipWithIndex.map { case (ndv, i) =>
+ EquiHeightBucket(endpoints(i), endpoints(i + 1), ndv)
+ }
+ val nonNullRows = rowCount - cs.nullCount
+ val ehHistogram = EquiHeightHistogram(nonNullRows.toDouble /
ndvs.length, buckets)
+ cs.copy(histogram = Some(ehHistogram))
+ }
+ }
+
+}
+
+/**
+ * Equi-height histogram represents the distribution of a column's values
by a sequence of buckets.
+ * Each bucket has a value range and contains approximately the same
number of rows.
+ * In the context of Spark SQL statistics, we may use "histogram" to
denote "equi-height histogram"
+ * for simplicity.
+ * @param height number of rows in each bucket
+ * @param buckets equi-height histogram buckets
+ */
+case class EquiHeightHistogram(height: Double, buckets:
Array[EquiHeightBucket]) {
--- End diff --
How about just call it `Histogram` and in document say it's equi-height?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
