val df1 = (1 to 10).map(i => (s"str_$i", i)).toDF("i", "j")
val df2 =
df1
.join(df1.select(df1("i")), "i")
.select(df1("i"), df1("j"))
val df3 = df2.withColumnRenamed("i", "i1").withColumnRenamed("j", "j1")
val df4 =
df2
.join(df3, df2("i") === df3("i1"))
.withColumn("diff", $"j" - $"j1")
df4.show(100, false)
+------+---+------+---+----+
|i |j |i1 |j1 |diff|
+------+---+------+---+----+
|str_2 |2 |str_2 |2 |0 |
|str_7 |7 |str_2 |2 |5 |
|str_10|10 |str_10|10 |0 |
|str_3 |3 |str_3 |3 |0 |
|str_8 |8 |str_3 |3 |5 |
|str_4 |4 |str_4 |4 |0 |
|str_9 |9 |str_4 |4 |5 |
|str_5 |5 |str_5 |5 |0 |
|str_1 |1 |str_1 |1 |0 |
|str_6 |6 |str_1 |1 |5 |
+------+---+------+---+----+
Blocker 