{ "id":1 ,"name":" Ella","age":36 } { "id":2,"name":"Bob","age":29 } { "id":3 ,"name":"Jack","age":29 } { "id":4 ,"name":"Jim","age":28 } { "id":5 ,"name":"Damon" } { "id":5 ,"name":"Damon" }
1,Ella,36 2,Bob,29 3,Jack,29
假设当前目录为/usr/local/spark/mycode/rddtodf,在当前目录下新建一个目录 mkdir -p
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder import org.apache.spark.sql.Encoder import spark.implicits._ object RDDtoDF { def main(args: Array[String]) { case class Employee(id:Long,name: String, age: Long) val employeeDF = spark.sparkContext.textFile("file:///usr/local/spark/employee.txt").map(_.split(",")).map(at tributes => Employee(attributes(0).trim.toInt,attributes(1), attributes(2).trim.toInt)).toDF() employeeDF.createOrReplaceTempView("employee") val employeeRDD = spark.sql("select id,name,age from employee") employeeRDD.map(t => "id:"+t(0)+","+"name:"+t(1)+","+"age:"+t(2)).show() } }
原文:https://www.cnblogs.com/sonofdemon/p/12289410.html