valeur toDF n'est pas membre de org.apache.spark.rdd.RDD

Exception :

val people = sc.textFile("resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF()
value toDF is not a member of org.apache.spark.rdd.RDD[Person]

Ici est TestApp.scala fichier:

package main.scala

import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf


case class Record1(k: Int, v: String)


object RDDToDataFramesWithCaseClasses {

    def main(args: Array[String]) {
        val conf = new SparkConf().setAppName("Simple Spark SQL Application With RDD To DF")

        //sc is an existing SparkContext.
        val sc = new SparkContext(conf)

        val sqlContext = new SQLContext(sc)

        //this is used to implicitly convert an RDD to a DataFrame.
        import sqlContext.implicits._

        //Define the schema using a case class.
        //Note: Case classes in Scala 2.10 can support only up to 22 fields. To work around this limit,package main.scala

Et TestApp.scala

import org.apache.spark.SparkContext    
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf


case class Record1(k: Int, v: String)


object RDDToDataFramesWithCaseClasses {
    def main(args: Array[String]) {
        val conf = new SparkConf().setAppName("RDD To DF")

        //sc is an existing SparkContext.
        //you can use custom classes that implement the Product interface.
        case class Person(name: String, age: Int)

        //Create an RDD of Person objects and register it as a table.
        val people = sc.textFile("resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF() 
        people.registerTempTable("people")

        //SQL statements can be run by using the sql methods provided by sqlContext.
        val teenagers = sqlContext.sql("SELECT name, age FROM people WHERE age >= 13 AND age <= 19")

        //The results of SQL queries are DataFrames and support all the normal RDD operations.
        //The columns of a row in the result can be accessed by field index:
        teenagers.map(t => "Name: " + t(0)).collect().foreach(println)

        //or by field name:
        teenagers.map(t => "Name: " + t.getAs[String]("name")).collect().foreach(println)

        //row.getValuesMap[T] retrieves multiple columns at once into a Map[String, T]

        teenagers.map(_.getValuesMap[Any](List("name", "age"))).collect().foreach(println)

        //Map("name" -> "Justin", "age" -> 19)

    }
}

Et SBT Fichier

name := "SparkScalaRDBMS"
version := "1.0"
scalaVersion := "2.11.7"
libraryDependencies += "org.apache.spark" %% "spark-core" % "1.5.1"
libraryDependencies += "org.apache.spark" %% "spark-sql" % "1.5.1"

source d'informationauteur Ashish Aggarwal