web-dev-qa-db-fra.com

la 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]

Voici le fichier TestApp.scala:

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 Fichier SBT 

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"
sbtapache-spark-sql
13
Ashish Aggarwal

Dans Spark 2, vous devez importer les implications de SparkSession:

val spark = SparkSession.builder().appName(appName).getOrCreate()
import spark.implicits._

Voir la documentation Spark pour plus d'options lors de la création de SparkSession.

2
Paul

Il y a deux problèmes avec votre code

  1. Vous devez importer sqlContext.implicits._ pour Spark V 1.0 ou importer spark.implicits._ si vous utilisez Spark V 2.0 ou une version ultérieure. 

  2. Deuxièmement, la classe de cas Record1 (k: Int, v: String) doit être à l'intérieur de la fonction principale mais à l'extérieur de def main (arguments: Array [String]) { val conf = new SparkConf (). setAppName ("RDD To DF") ….

}

1
saad
i.  scala> case class Employee(id: Int, name: String, age: Int)
defined class Employee
scala> val sqlContext= new org.Apache.spark.sql.SQLContext(sc)
warning: there was one deprecation warning; re-run with -deprecation for details
sqlContext: org.Apache.spark.sql.SQLContext = org.Apache.spark.sql.SQLContext@1f94e3a

scala> import sqlContext.implicits._
import sqlContext.implicits._
scala> var empl1=   empl.map(_.split(",")).map(e=>Employee(e(0).trim.toInt,e(1),e(2).trim.toInt)).toDF
empl1: org.Apache.spark.sql.DataFrame = [id: int, name: string ... 1 more field]
scala> val allrecords = sqlContext.sql("SELECT * FROM employee")
allrecords: org.Apache.spark.sql.DataFrame = [id: int, name: string ... 1 more field]

scala> allrecords.show();
+----+--------+---+
|  id|    name|age|
+----+--------+---+
|1201|  satish| 25|
|1202| krishna| 28|
|1203|   amith| 39|
|1204|   javed| 23|
|1205|  prudvi| 23|
+----+--------+---+
0
Shyam Gupta