Dataframe:如何在Scala中groupBy/count然后按count排序

import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions._

// 创建SparkSession
val spark = SparkSession.builder()
  .appName("Dataframe GroupBy and Count")
  .master("local")
  .getOrCreate()

// 创建示例数据
val data = Seq(
  ("Alice", "Math"),
  ("Bob", "Science"),
  ("Alice", "English"),
  ("Bob", "Math"),
  ("Alice", "Science")
)

// 将数据转换为Dataframe
val df = spark.createDataFrame(data).toDF("Name", "Subject")

// 使用groupBy和count进行分组和计数
val countDF = df.groupBy("Name").agg(count("Subject").as("Count"))

// 按照count进行排序
val sortedDF = countDF.orderBy(desc("Count"))

// 打印结果
sortedDF.show()