Spark DataFrame分组后选取第一行

import org.apache.spark.sql.functions.{row_number, max, broadcast}
import org.apache.spark.sql.expressions.Window

val df = sc.parallelize(Seq(
  (0,"cat26",30.9), (0,"cat13",22.1), (0,"cat95",19.6), (0,"cat105",1.3),
  (1,"cat67",28.5), (1,"cat4",26.8), (1,"cat13",12.6), (1,"cat23",5.3),
  (2,"cat56",39.6), (2,"cat40",29.7), (2,"cat187",27.9), (2,"cat68",9.8),
  (3,"cat8",35.6))).toDF("Hour", "Category", "TotalValue")

//+----+--------+----------+
//|Hour|Category|TotalValue|
//+----+--------+----------+
//| 0| cat26| 30.9|
//| 0| cat13| 22.1|
//| 0| cat95| 19.6|
//| 0| cat105| 1.3|
//| 1| cat67| 28.5|
//| 1| cat4| 26.8|
//| 1| cat13| 12.6|
//| 1| cat23| 5.3|
//| 2| cat56| 39.6|
//| 2| cat40| 29.7|
//| 2| cat187| 27.9|
//| 2| cat68| 9.8|
//| 3| cat8| 35.6|
//| ...| ....| ....|
//+----+--------+----------+

val w = Window.partitionBy($"hour").orderBy($"TotalValue".desc)

val dfTop = df.withColumn("rn", row_number.over(w)).where($"rn" === 1).drop("rn")

dfTop.show
// +----+--------+----------+
// |Hour|Category|TotalValue|
// +----+--------+----------+
// |   0|   cat26|      30.9|
// |   1|   cat67|      28.5|
// |   2|   cat56|      39.6|
// |   3|    cat8|      35.6|
// +----+--------+----------+

其它效率更高的方法,参考:

https://stackoverflow.com/questions/33878370/how-to-select-the-first-row-of-each-group