Github user zhengruifeng commented on a diff in the pull request: https://github.com/apache/spark/pull/16776#discussion_r100713371 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala --- @@ -63,44 +63,49 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * Note that values greater than 1 are accepted but give the same result as 1. * @return the approximate quantiles at the given probabilities * - * @note NaN values will be removed from the numerical column before calculation + * @note null and NaN values will be removed from the numerical column before calculation * * @since 2.0.0 */ def approxQuantile( col: String, probabilities: Array[Double], relativeError: Double): Array[Double] = { - StatFunctions.multipleApproxQuantiles(df.select(col).na.drop(), - Seq(col), probabilities, relativeError).head.toArray + val res = approxQuantile(Array(col), probabilities, relativeError) + if (res != null) { + res.head + } else { + null + } } /** * Calculates the approximate quantiles of numerical columns of a DataFrame. - * @see [[DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile]] for - * detailed description. + * @see `DataFrameStatsFunctions.approxQuantile` for detailed description. --- End diff -- @jkbradley Do you mean `@see [[DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile]])`? I am not sure whether it work for java docs. @HyukjinKwon Could you help review this?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org