Github user yhuai commented on a diff in the pull request: https://github.com/apache/spark/pull/7841#discussion_r44500928 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala --- @@ -273,6 +280,60 @@ class GroupedData protected[sql]( def sum(colNames: String*): DataFrame = { aggregateNumericColumns(colNames : _*)(Sum) } + + /** + * (Scala-specific) Pivots a column of the current [[DataFrame]] and preform the specified + * aggregation. + * {{{ + * // Compute the sum of earnings for each year by course with each course as a separate column + * df.groupBy($"year").pivot($"course", "dotNET", "Java").agg(sum($"earnings")) + * // Or without specifying column values + * df.groupBy($"year").pivot($"course").agg(sum($"earnings")) + * }}} + * @param pivotColumn Column to pivot + * @param values Optional list of values of pivotColumn that will be translated to columns in the + * output data frame. If values are not provided the method with do an immediate + * call to .distinct() on the pivot column. + * @since 1.6.0 + */ + @scala.annotation.varargs + def pivot(pivotColumn: Column, values: String*): GroupedData = groupType match { + case _: GroupedData.PivotType => + throw new UnsupportedOperationException("repeated pivots are not supported") + case GroupedData.GroupByType => + val pivotValues = if (values.nonEmpty) { + values + } else { + // Get the distinct values of the column and sort them so its consistent + df.select(pivotColumn.cast(StringType)) + .distinct() + .map(_.getString(0)) + .collect().sorted.toSeq + } + new GroupedData(df, groupingExprs, GroupedData.PivotType(pivotColumn.expr, pivotValues)) + case _ => + throw new UnsupportedOperationException("pivot is only supported after a groupBy") + } + + /** + * Pivots a column of the current [[DataFrame]] and preform the specified aggregation. + * {{{ + * // Compute the sum of earnings for each year by course with each course as a separate column + * df.groupBy("year").pivot("course", "dotNET", "Java").sum("earnings") + * // Or without specifying column values + * df.groupBy("year").pivot("course").sum("earnings") + * }}} + * @param pivotColumn Column to pivot + * @param values Optional list of values of pivotColumn that will be translated to columns in the + * output data frame. If values are not provided the method with do an immediate + * call to .distinct() on the pivot column. + * @since 1.6.0 + */ + @scala.annotation.varargs + def pivot(pivotColumn: String, values: String*): GroupedData = { + val resolvedPivotColumn = Column(df.resolve(pivotColumn)) + pivot(resolvedPivotColumn, values: _*) + } --- End diff -- For the first version, maybe we can just have the API using `Column` as the argument type? (I am thinking about the type of values. I am not sure String is the right type).
--- 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