Spark DataFrame의 각 그룹에서 첫 번째 행을 선택하는 방법은 무엇입니까?

<code>import org.apache.spark.sql.functions._
import org.apache.spark.sql.expressions.Window

// 创建一个带有分组数据的 DataFrame
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")

// 创建窗口规范
val w = Window.partitionBy($"Hour").orderBy($"TotalValue".desc)

// 计算每个组的行号
val dfTop = df.withColumn("rn", row_number.over(w)).where($"rn" === 1).drop("rn")

// 显示每个组的第一行
dfTop.show</code>

<code>val dfMax = df.groupBy($"Hour".as("max_hour")).agg(max($"TotalValue").as("max_value"))

val dfTopByJoin = df.join(broadcast(dfMax), ($"Hour" === $"max_hour") && ($"TotalValue" === $"max_value"))
  .drop("max_hour")
  .drop("max_value")

dfTopByJoin.show</code>

<code>val dfTop = df.select($"Hour", struct($"TotalValue", $"Category").alias("vs"))
  .groupBy($"Hour")
  .agg(max("vs").alias("vs"))
  .select($"Hour", $"vs.Category", $"vs.TotalValue")

dfTop.show</code>

<code>case class Record(Hour: Integer, Category: String, TotalValue: Double)

df.as[Record]
  .groupBy($"Hour")
  .reduce((x, y) => if (x.TotalValue > y.TotalValue) x else y)
  .show</code>

<code>df.as[Record]
  .groupByKey(_.Hour)
  .reduceGroups((x, y) => if (x.TotalValue > y.TotalValue) x else y)</code>