Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/16776#discussion_r100727960 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala --- @@ -58,49 +58,54 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) { * @param probabilities a list of quantile probabilities * Each number must belong to [0, 1]. * For example 0 is the minimum, 0.5 is the median, 1 is the maximum. - * @param relativeError The relative target precision to achieve (greater or equal to 0). + * @param relativeError The relative target precision to achieve (greater than or equal to 0). * If set to zero, the exact quantiles are computed, which could be very expensive. * 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. If + * the dataframe is empty or all rows contain null or NaN, null is returned. * * @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) + Option(res).map(_.head).orNull } /** * Calculates the approximate quantiles of numerical columns of a DataFrame. - * @see [[DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile]] for - * detailed description. + * @see `[[DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile]]` for detailed --- End diff -- `DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile` -> `DataFrameStatsFunctions.approxQuantile(col:Str* approxQuantile)`
--- 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