SparkSQL运用

package sql

import org.apache.avro.ipc.specific.Person
import org.apache.spark
import org.apache.spark.rdd.RDD
import org.apache.spark.sql
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}
import org.junit.Test

class Intro {
  @Test
  def dsIntro(): Unit ={
    val spark: SparkSession = new sql.SparkSession.Builder()
      .appName("ds intro")
      .master("local[6]")
      .getOrCreate()

    //导入隐算是shi转换
    import spark.implicits._

    val sourceRDD: RDD[Person] =spark.sparkContext.parallelize(Seq(Person("张三",10),Person("李四",15)))
    val personDS: Dataset[Person] =sourceRDD.toDS();
//personDS.printSchema()打印出错信息

    val resultDS: Dataset[Person] =personDS.where('age>10)
      .select('name,'age)
      .as[Person]
    resultDS.show()

  }
  @Test
  def dfIntro(): Unit ={
    val spark: SparkSession =new SparkSession.Builder()
      .appName("ds intro")
      .master("local")
      .getOrCreate()

    import spark.implicits._
    val sourceRDD: RDD[Person] = spark.sparkContext.parallelize(Seq(Person("张三",10),Person("李四",15)))
    val df: DataFrame = sourceRDD.toDF()//隐shi转换

    df.createOrReplaceTempView("person")//创建表
    val resultDF: DataFrame =spark.sql("select name from person where age>=10 and age<=20")
    resultDF.show()

  }
  @Test
  def database1(): Unit ={
    //1.创建sparkSession
    val spark: SparkSession =new SparkSession.Builder()
      .appName("database1")
      .master("local[6]")
      .getOrCreate()
      //2.导入引入shi子转换
    import spark.implicits._

    //3.演示
    val sourceRDD: RDD[Person] =spark.sparkContext.parallelize(Seq(Person("张三",10),Person("李四",15)))
    val dataset: Dataset[Person] =sourceRDD.toDS()

    //Dataset 支持强类型的API
    dataset.filter(item => item.age >10).show()
    //Dataset 支持若弱类型的API
    dataset.filter('age>10).show()
    //Dataset 可以直接编写SQL表达式
    dataset.filter("age>10").show()
  }

  @Test
  def database2(): Unit ={
    val spark: SparkSession = new SparkSession.Builder()
      .master("local[6]")
      .appName("database2")
      .getOrCreate()
    import spark.implicits._

    val dataset: Dataset[Person] =spark.createDataset(Seq(Person("张三",10),Person("李四",20)))
    //无论Dataset中放置的是什么类型的对象,最终执行计划中的RDD上都是internalRow
    //直接获取到已经分析和解析过得Dataset的执行计划,从中拿到RDD
    val executionRdd: RDD[InternalRow] =dataset.queryExecution.toRdd

    //通过将Dataset底层的RDD通过Decoder转成了和Dataset一样的类型RDD
    val typedRdd:RDD[Person] = dataset.rdd

    println(executionRdd.toDebugString)
    println()
    println()
    println(typedRdd.toDebugString)
  }

  @Test
  def database3(): Unit = {
    //1.创建sparkSession
    val spark: SparkSession = new SparkSession.Builder()
      .appName("database1")
      .master("local[6]")
      .getOrCreate()
    //2.导入引入shi子转换
    import spark.implicits._

    val dataFrame: DataFrame = Seq(Person("zhangsan", 15), Person("lisi", 20)).toDF()
    //3.看看DataFrame可以玩出什么花样
    //select name from...
    dataFrame.where('age > 10)
      .select('name)
      .show()
  }
//  @Test
//  def database4(): Unit = {
//    //1.创建sparkSession
//    val spark: SparkSession = new SparkSession.Builder()
//      .appName("database1")
//      .master("local[6]")
//      .getOrCreate()
//    //2.导入引入shi子转换
//    import spark.implicits._
//    val personList=Seq(Person("zhangsan",15),Person("lisi",20))
//
//    //1.toDF
//    val df1: DataFrame =personList.toDF()
//    val df2: DataFrame =spark.sparkContext.parallelize(personList).toDF()
//      //2.createDataFrame
//    val df3: DataFrame =spark.createDataFrame(personList)
//
//    //3.read
//    val df4: DataFrame =spark.read.csv("")
//    df4.show()
//  }
  //toDF()是转成DataFrame,toDs是转成Dataset
  //  DataFrame就是Dataset[Row] 代表弱类型的操作,Dataset代表强类型的操作,中的类型永远是row,DataFrame可以做到运行时类型安全,Dataset可以做到 编译时和运行时都安全
@Test
def database4(): Unit = {
  //1.创建sparkSession
  val spark: SparkSession = new SparkSession.Builder()
    .appName("database1")
    .master("local[6]")
    .getOrCreate()
  //2.导入引入shi子转换
  import spark.implicits._
  val personList=Seq(Person("zhangsan",15),Person("lisi",20))
  //DataFrame代表弱类型操作是编译时不安全
  val df: DataFrame =personList.toDF()

  //Dataset是强类型的
  val ds: Dataset[Person] =personList.toDS()
  ds.map((person:Person) =>Person(person.name,person.age))
}
  @Test
  def row(): Unit ={
    //1.Row如何创建,它是什么
    //row对象必须配合Schema对象才会有列名
    val p: Person =Person("zhangsan",15)
    val row: Row =Row("zhangsan",15)
    //2.如何从row中获取数据
    row.getString(0)
    row.getInt(1)
    //3.Row也是样例类、
    row match {
      case Row(name,age) => println(name,age)
    }
  }

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