Github user huaxingao commented on a diff in the pull request: https://github.com/apache/spark/pull/20400#discussion_r165270774 --- Diff: python/pyspark/sql/window.py --- @@ -129,11 +131,34 @@ def rangeBetween(start, end): :param end: boundary end, inclusive. The frame is unbounded if this is ``Window.unboundedFollowing``, or any value greater than or equal to min(sys.maxsize, 9223372036854775807). + + >>> from pyspark.sql import functions as F, SparkSession, Window + >>> spark = SparkSession.builder.getOrCreate() + >>> df = spark.createDataFrame([(1, "a"), (1, "a"), (2, "a"), (1, "b"), (2, "b"), + ... (3, "b")], ["id", "category"]) + >>> window = Window.orderBy("id").partitionBy("category").rangeBetween(F.currentRow(), + ... F.lit(1)) + >>> df.withColumn("sum", F.sum("id").over(window)).show() + +---+--------+---+ + | id|category|sum| + +---+--------+---+ + | 1| b| 3| + | 2| b| 5| + | 3| b| 3| + | 1| a| 4| + | 1| a| 4| + | 2| a| 2| + +---+--------+---+ + <BLANKLINE> --- End diff -- Seems to me this <BLANKLINE> is required. I will change the rest except this one.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org