使用 count 窗口功能。检查以下代码。

scala> val someDF = Seq(
     |   (4623874, "user1", "success"),
     |   (4623874, "user2","fail"),
     |   (4623874, "user3","success"),
     |   (1343244, "user4","fail"),
     |   (4235252, "user5", "fail")
     | ).toDF("primaryid", "user","status")

scala> import org.apache.spark.sql.expressions._
import org.apache.spark.sql.expressions._

someDF
.withColumn("count",
    count($"status")
    .over(
        Window
        .partitionBy($"primaryid",$"status")
        .orderBy($"primaryid".asc)
    )
).show(false)
+---------+-----+-------+-----+
|primaryid|user |status |count|
+---------+-----+-------+-----+
|4235252  |user5|fail   |1    |
|1343244  |user4|fail   |1    |
|4623874  |user2|fail   |1    |
|4623874  |user1|success|2    |
|4623874  |user3|success|2    |
+---------+-----+-------+-----+

scala> :paste
// Entering paste mode (ctrl-D to finish)

someDF
.withColumn("count",
    count($"status")
    .over(
        Window
        .partitionBy($"primaryid",$"status")
        .orderBy($"primaryid".asc)
    )
)
.filter($"status" === "success")
.show(false)

// Exiting paste mode, now interpreting.

+---------+-----+-------+-----+
|primaryid|user |status |count|
+---------+-----+-------+-----+
|4623874  |user1|success|2    |
|4623874  |user3|success|2    |
+---------+-----+-------+-----+