值toDF不是org.apache.spark.rdd.RDD的成员

Question

例外:

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]

这是TestApp.scala文件:

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

和 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)

    }
}

和SBT文件

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"

Answer 1

现在我找到了原因,你应该在对象中定义case类,并在main函数中定义.看看这里

好的,我终于解决了这个问题.需要做的2件事:

1. 导入含义:请注意,只有在创建了org.apache.spark.sql.SQLContext实例后才能执行此操作.它应该写成:

   val sqlContext= new org.apache.spark.sql.SQLContext(sc)

   import sqlContext.implicits._

2. 将case类移到方法之外:case类,通过使用它来定义DataFrame的模式,应该在需要它的方法之外定义.你可以在这里阅读更多相关信息:https://issues.scala-lang.org/browse/SI-6649

Answer 2

在 Spark 2 中，您需要从 SparkSession 导入隐式：

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

创建 SparkSession 时，请参阅Spark 文档以获取更多选项。

Answer 3

你的代码有两个问题

1. 您需要为 Spark V 1.0 导入 import sqlContext.implicits._ 或如果您使用的是 Spark V 2.0 或更高版本，则导入 spark.implicits._

2. 第二种情况类 Record1(k: Int, v: String) 需要在 main 函数内部但在 def main(args: Array[String]) { val conf = new SparkConf().setAppName("RDD To DF") ...

}