编写SparkSQL的API

IDEA中程序的打包和运行方式都和SparkCore类似，Maven依赖中需要添加新的依赖项：

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.11</artifactId>
    <version>2.1.1</version>
</dependency>

程序如下：

import org.apache.spark.SparkConf
import org.apache.spark.sql.SparkSession

object Spark03_Transform {
  def main(args: Array[String]): Unit = {
    //创建SparkConf
    val conf = new SparkConf().setMaster("local[*]").setAppName("Test")

    //创建SparkSession
    val spark = SparkSession.builder().config(conf).getOrCreate()

    //创建RDD
    //这里的spark不是包的含义，而是SparkSession对象的名字
    import spark.implicits._
    val rdd = spark.sparkContext.makeRDD(List((1,"zhangsan",23),(2,"lisi",24),(3,"wangwu",25)))

    //RDD转换为DataFarme(是结构)
    val df = rdd.toDF("id","name","age")

    //DataFrame转换为DataSet(是对象),转换为DataSet首先需要创建一个样例类
    val ds = df.as[User]

    //DataSet转换为DataFrame
    val df1 = ds.toDF()

    //DataFrame转换为RDD
    val rdd1 = df1.rdd

    rdd1.foreach{
      datas => {
        println(datas.getString(1))
      }
    }

    //释放资源
    spark.stop()

  }
}
 case class User(id:Int,name:String,age:Int