SparkSql RDD转DataFrame (scala语言)

代码

demo01是对象 demo02是基本类型

package com

import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

/**
 * 定义一个对象
 *
 * @param name
 * @param age
 */
case class User(name: String, age: Int)

object RDD2DF {
  /** 对象
   */
  def demo01(): Unit = {
    val spark: SparkSession = SparkSession.builder()
      .master("local[2]")
      .appName("RDD2DF")
      .getOrCreate()
    import spark.implicits._
    val sc: SparkContext = spark.sparkContext
    //        val rdd = sc.parallelize(1 to 10)

    val rdd = sc.parallelize(Array(User("lisi", 10), User("zs", 20), User("ww", 15)))

    rdd.toDF("name", "age").show

    spark.stop()
  }

  /**
   * 基本数据类型
   */
  def demo02(): Unit = {
    val spark: SparkSession = SparkSession.builder()
      .master("local[2]")
      .appName("RDD2DF")
      .getOrCreate()
    import spark.implicits._
    val sc: SparkContext = spark.sparkContext

    val rdd: RDD[(String, Int)] = sc.parallelize(("lisi", 10) :: ("zs", 20) :: Nil)


    rdd.toDF("name", "name").show

    spark.stop()
  }

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

    demo01() //对象

    //   demo02() // 基本类型
  }
}

demo01输出

+----+---+
|name|age|
+----+---+
|lisi| 10|
|  zs| 20|
|  ww| 15|
+----+---+

demo02 输出

+----+----+
|name|name|
+----+----+
|lisi|  10|
|  zs|  20|
+----+----+