大数据之spark_spark SQL的建表语句

1.通过RDD+case class创建DataFrame

package com.doit.spark.day10

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{
   
   DataFrame, SparkSession}

object CaseClassCreateDataFrame {
   
   
  def main(args: Array[String]): Unit = {
   
   
    //构建SparkSession
    val sparkSession: SparkSession = SparkSession.builder().appName(this.getClass().getSimpleName).master("local[*]").getOrCreate()
    //使用RDD读取切分数据,放入case class中
    val lineRDD: RDD[String] = sparkSession.sparkContext.textFile("C:\\Users\\WoBo\\Desktop\\user.txt")

    val userRDD: RDD[User] = lineRDD.map(x => {
   
   
      val arr: Array[String] = x.split(",")
      val name: String = arr(0)
      val age: Int = arr(1).toInt
      val fv: Double = arr(2).toDouble
      User(name, age, fv)
    })

    //通过RDD创建DataFrame
    val dataFrame: DataFrame = sparkSession.createDataFrame(userRDD)
    //创建好DataFrame之后,就能通过RDD获取到表格结构信息和表内数据
    dataFrame.printSchema() //打印表结构
    dataFrame.show()  //展示表内数据,默认show前20行
  }
}
case class User(name:String,age:Int,fv :Double)

2.通过RowRDD+StructType创建DataFrame

package com.doit.spark.day10

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types.{
   
   DataTypes, StructField, StructType}
import org.apache.spark.sql.{
   
   DataFrame, Row, SparkSession}

object DataStructTypeCreateDataFrame {
   
   
  def main(args: Array[String]): Unit = {
   
   
    //构建SparkSession
    val sparkSession: SparkSession = SparkSession.builder().appName(this.getClass().getSimpleName).master("local[*]").getOrCreate()
    //使用RDD读取切分数据,放入Row中
    val lineRDD: RDD[String] = sparkSession.sparkContext.textFile("C:\\Users\\WoBo\\Desktop\\user.txt")
    val rowRDD: RDD[Row] = lineRDD.map(x => {
   
   
      val arr: Array[String] = x.split(",")
      val name: String = arr(0)
      val age: Int = arr<