Group by considers null as seperate row

val simpleData = Seq(("James","Sales","NY",90000,34,10000),
    ("Michael","Sales","NY",86000,56,20000),
    ("Robert","Sales","CA",81000,30,23000),
    ("Maria","Finance","CA",90000,24,23000),
    ("Raman","Finance","CA",99000,40,24000),
    ("Scott","Finance","NY",83000,36,19000),
    ("Jen","Finance","NY",79000,53,15000),
    ("Jeff","Marketing","CA",80000,25,18000),
    ("Kumar","Marketing","NY",91000,50,21000)
  )
  val df = simpleData.toDF("employee_name","department","state","salary","age","bonus")
  df.show()

+-------------+----------+-----+------+---+-----+
|employee_name|department|state|salary|age|bonus|
+-------------+----------+-----+------+---+-----+
|        James|     Sales|   NY| 90000| 34|10000|
|      Michael|     Sales|   NY| 86000| 56|20000|
|       Robert|     Sales|   CA| 81000| 30|23000|
|        Maria|   Finance|   CA| 90000| 24|23000|
|        Raman|   Finance|   CA| 99000| 40|24000|
|        Scott|   Finance|   NY| 83000| 36|19000|
|          Jen|   Finance|   NY| 79000| 53|15000|
|         Jeff| Marketing|   CA| 80000| 25|18000|
|        Kumar| Marketing|   NY| 91000| 50|21000|
+-------------+----------+-----+------+---+-----+



    //using agg function
  df.groupBy("department")
    .agg(
      sum("salary").as("sum_salary"),
      avg("salary").as("avg_salary"),
      sum("bonus").as("sum_bonus"),
      max("bonus").as("max_bonus"))
    .show(false)

+----------+----------+-----------------+---------+---------+
|department|sum_salary|avg_salary       |sum_bonus|max_bonus|
+----------+----------+-----------------+---------+---------+
|Sales     |257000    |85666.66666666667|53000    |23000    |
|Finance   |351000    |87750.0          |81000    |24000    |
|Marketing |171000    |85500.0          |39000    |21000    |
+----------+----------+-----------------+---------+---------+


=====

val simpleData = Seq(("James","Sales","NY",90000,34,10000),
    ("Michael","Sales","NY",86000,56,20000),
    ("Robert","Sales","CA",81000,30,23000),
    ("Maria","Finance","CA",90000,24,23000),
    ("Raman","Finance","CA",99000,40,24000),
    ("Scott","Finance","NY",83000,36,19000),
    ("Jen","Finance","NY",79000,53,15000),
    ("Jeff","Marketing","CA",80000,25,18000),
    ("Kumar",null,"NY",91000,50,21000)
  )
  val df = simpleData.toDF("employee_name","department","state","salary","age","bonus")
  df.show()


  +-------------+----------+-----+------+---+-----+
|employee_name|department|state|salary|age|bonus|
+-------------+----------+-----+------+---+-----+
|        James|     Sales|   NY| 90000| 34|10000|
|      Michael|     Sales|   NY| 86000| 56|20000|
|       Robert|     Sales|   CA| 81000| 30|23000|
|        Maria|   Finance|   CA| 90000| 24|23000|
|        Raman|   Finance|   CA| 99000| 40|24000|
|        Scott|   Finance|   NY| 83000| 36|19000|
|          Jen|   Finance|   NY| 79000| 53|15000|
|         Jeff| Marketing|   CA| 80000| 25|18000|
|        Kumar|      null|   NY| 91000| 50|21000|
+-------------+----------+-----+------+---+-----+

Observe null is treated as seperate row

+----------+----------+-----------------+---------+---------+
|department|sum_salary|avg_salary       |sum_bonus|max_bonus|
+----------+----------+-----------------+---------+---------+
|Sales     |257000    |85666.66666666667|53000    |23000    |
|null      |91000     |91000.0          |21000    |21000    |
|Finance   |351000    |87750.0          |81000    |24000    |
|Marketing |80000     |80000.0          |18000    |18000    |
+----------+----------+-----------------+---------+---------+