创建包含具有整数属性的case类实例的DataFrame

case class Person(id: Int, name: String, age: Int)

case class Employee(id: Int, departmentId: Int, salary: Int)

import org.apache.spark.sql.{SparkSession, DataFrame}
import org.apache.spark.sql.types.{StructType, StructField, IntegerType}

object CreateDataFrameExample {
  def main(args: Array[String]): Unit = {
    // 创建SparkSession
    val spark = SparkSession.builder()
      .appName("Create DataFrame from Case Class")
      .master("local[*]")
      .getOrCreate()

    // 定义case class
    case class Employee(id: Int, departmentId: Int, salary: Int)

    // 创建一些实例
    val employees = Seq(
      Employee(1, 101, 50000),
      Employee(2, 102, 60000),
      Employee(3, 101, 55000)
    )

    // 将case class实例转换为DataFrame
    import spark.implicits._
    val employeeDF: DataFrame = employees.toDF()

    // 显示DataFrame内容
    employeeDF.show()

    // 停止SparkSession
    spark.stop()
  }
}

val schema = StructType(Seq(
  StructField("id", IntegerType, nullable = false),
  StructField("departmentId", IntegerType, nullable = false),
  StructField("salary", IntegerType, nullable = false)
))

val employeeDF = spark.createDataFrame(employees, schema)