[大数据]spark指定类型+列名 将RDD转化成DataFrame

package lambda.sql

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

/**
  * 演示sparksql-rdd-DATAFRAME --指定类型和列名
  *
  * @Author wangyijie
  * @Date 2021/7/15 20:42
  * @Version 1.0
  */
object Demo03 {
  def main(args: Array[String]): Unit = {

    // TODO 0.准备环境
    val spark: SparkSession = SparkSession.builder().appName("Demo02").master("local[*]").getOrCreate()
    val sc: SparkContext = spark.sparkContext
    sc.setLogLevel("WARN")

    // TODO 1.加载数据
    val lines: RDD[String] = sc.textFile("")

    // TODO 2.处理数据
    val tupleRDD:RDD[(Int,String,Int)] = lines.map(line => {
      val arr: Array[String] = line.split(" ")
      (arr(0).toInt, arr(1), arr(2).toInt)
    })       //获取到了PersonrRDD

    // RDD->DF
    import spark.implicits._ // 这里的spark是上面的定义生产的spark对象
    val personDF:DataFrame = tupleRDD.toDF("id","name","age")

    // TODO 3.输出结果
    personDF.printSchema()
    personDF.show()


    sc.stop()
  }

}