Это то, что вы ожидаете?
val df = Seq(("foo", "one", "small", 1),
("foo", "one", "large", 2),
("foo", "one", "large", 2),
("foo", "two", "small", 3)).toDF("A","B","C","D")
scala> df.show
+---+---+-----+---+
| A| B| C| D|
+---+---+-----+---+
|foo|one|small| 1|
|foo|one|large| 2|
|foo|one|large| 2|
|foo|two|small| 3|
+---+---+-----+---+
scala> val df2 = df.groupBy('A,'B).pivot("C").sum("D")
df2: org.apache.spark.sql.DataFrame = [A: string, B: string ... 2 more fields]
scala> val df3 = df.groupBy('A as "A1",'B as "B1").agg(sum('D) as "sumd")
df3: org.apache.spark.sql.DataFrame = [A1: string, B1: string ... 1 more field]
scala> df3.join(df2,'A==='A1 and 'B==='B1,"inner").select("A","B","sumd","large","small").show
+---+---+----+-----+-----+
| A| B|sumd|large|small|
+---+---+----+-----+-----+
|foo|one| 5| 4| 1|
|foo|two| 3| null| 3|
+---+---+----+-----+-----+
scala>