Github user wzhfy commented on a diff in the pull request: https://github.com/apache/spark/pull/19783#discussion_r154248457 --- 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 --- End diff -- If a user changes the data, statistics will be removed, or re-collected (only size currently), Spark already implements this.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org