Spark SQL 笔记(8)—— Dataset 案例

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012292754/article/details/83662117

1 概述

• 静态类型（Static-typing） 和运行时类型安全（runtime type-safety）
  

2 测试代码

sales.csv

transactionId,customerId,itemId,amoutPaid
111,1,1,100.1
112,2,2,200.3
113,3,3,300.6
114,4,4,444.89
115,5,5,555.99
116,6,6,666.44
117,7,7,777.43
118,8,8,888.56

package com.tzb.demo2

import org.apache.spark.sql.SparkSession

object DatasetApp {
  def main(args: Array[String]): Unit = {

    val spark = SparkSession.builder().appName("DatasetApp")
      .master("local[2]").getOrCreate()

    import spark.implicits._

    val df = spark.read.option("header", "true").option("inferSchema", "true")
      .csv("file:///d://sales.csv")

    //df.show()

    val ds = df.as[Sales]
    ds.map(line=>line.itemId).show()

    spark.stop()

  }

  case class Sales(transactionId:Int,customerId:Int,itemId:Int,amoutPaid:Double)

}