diff --git a/python/pyspark/sql/group.py b/python/pyspark/sql/group.py index d8ed7eb2dda649c510460ef71743a485ec813b61..1911588309affdb0b03dc5c9f16ad79101912fb6 100644 --- a/python/pyspark/sql/group.py +++ b/python/pyspark/sql/group.py @@ -169,11 +169,11 @@ class GroupedData(object): @since(1.6) def pivot(self, pivot_col, values=None): - """Pivots a column of the current DataFrame and preform the specified aggregation. + """Pivots a column of the current DataFrame and perform the specified aggregation. :param pivot_col: 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 + :param values: Optional list of values of pivot column that will be translated to columns in + the output DataFrame. If values are not provided the method will do an immediate call to .distinct() on the pivot column. >>> df4.groupBy("year").pivot("course", ["dotNET", "Java"]).sum("earnings").collect() diff --git a/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala b/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala index abd531c4ba5417203c6a720c3983244b813e6994..13341a88a6b740f92605eb0d0c843f9e2cb0d9a7 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/GroupedData.scala @@ -282,7 +282,7 @@ class GroupedData protected[sql]( } /** - * Pivots a column of the current [[DataFrame]] and preform the specified aggregation. + * Pivots a column of the current [[DataFrame]] and perform the specified aggregation. * There are two versions of pivot function: one that requires the caller to specify the list * of distinct values to pivot on, and one that does not. The latter is more concise but less * efficient, because Spark needs to first compute the list of distinct values internally. @@ -321,7 +321,7 @@ class GroupedData protected[sql]( } /** - * Pivots a column of the current [[DataFrame]] and preform the specified aggregation. + * Pivots a column of the current [[DataFrame]] and perform the specified aggregation. * There are two versions of pivot function: one that requires the caller to specify the list * of distinct values to pivot on, and one that does not. The latter is more concise but less * efficient, because Spark needs to first compute the list of distinct values internally. @@ -353,7 +353,7 @@ class GroupedData protected[sql]( } /** - * Pivots a column of the current [[DataFrame]] and preform the specified aggregation. + * Pivots a column of the current [[DataFrame]] and perform the specified aggregation. * There are two versions of pivot function: one that requires the caller to specify the list * of distinct values to pivot on, and one that does not. The latter is more concise but less * efficient, because Spark needs to first compute the list of distinct values internally.