From 783415c9424cb6db1333aa5bc3ccd3cd1b227204 Mon Sep 17 00:00:00 2001 From: Mortada Mehyar Date: Thu, 9 Jun 2016 19:34:16 -0700 Subject: [PATCH] [Documentation] fixed groupby aggregation example for pyspark --- docs/sql-programming-guide.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/sql-programming-guide.md b/docs/sql-programming-guide.md index 940c1d77045ad..efdf873c34556 100644 --- a/docs/sql-programming-guide.md +++ b/docs/sql-programming-guide.md @@ -2221,7 +2221,7 @@ import pyspark.sql.functions as func # In 1.3.x, in order for the grouping column "department" to show up, # it must be included explicitly as part of the agg function call. -df.groupBy("department").agg("department"), func.max("age"), func.sum("expense")) +df.groupBy("department").agg(df["department"], func.max("age"), func.sum("expense")) # In 1.4+, grouping column "department" is included automatically. df.groupBy("department").agg(func.max("age"), func.sum("expense"))