GraphX 无法正常工作 Spark / Scala
GraphX not working properly Spark / Scala
我正在尝试在 apache Spark/Scala 中创建一个 GraphX 对象,但由于某种原因它似乎无法正常工作。我已经附上示例输入文件的文件,实际程序代码是:
package SGraph
import org.apache.spark._
import org.apache.spark.SparkContext._
import org.apache.spark.sql._
import org.apache.log4j._
import org.apache.spark.rdd.RDD
import org.apache.spark.graphx._
`
object GooglePlusGraph {
/** Our main function where the action happens */
def main(args: Array[String]) {
// Set the log level to only print errors
Logger.getLogger("org").setLevel(Level.ERROR)
// Create a SparkContext using every core of the local machine
val sc = new SparkContext("local[*]", "GooglePlusGraphX")
val lines = sc.textFile("../Example.txt")
val ratings = lines.map(x => x.toString().split(":")(0))
val verts = ratings.map(line => (line.toLong,line))
val edges = lines.flatMap(makeEdges)
val default = "Nobody"
val graph = Graph(verts, edges, default).cache()
graph.degrees.join(verts).take(10).foreach(println)
}
def makeEdges(line: String) : List[Edge[Int]] = {
import scala.collection.mutable.ListBuffer
var edges = new ListBuffer[Edge[Int]]()
val fields = line.split(",").flatMap(a => a.split(":"))
val origin = fields(0)
for (x <- 1 to (fields.length - 1)) {
// Our attribute field is unused, but in other graphs could
// be used to deep track of physical distances etc.
edges += Edge(origin.toLong, fields(x).toLong, 0)
}
return edges.toList
}
}
我得到的第一个错误如下:
16/12/19 01:28:33 ERROR Executor: Exception in task 0.0 in stage 2.0 (TID 3)
java.lang.NumberFormatException: For input string: "935750800736168978117"
感谢您的帮助!
跟你下面的问题是一样的问题
给定的号码有 21 位超出了最大位数 Long
(19 位)。
我正在尝试在 apache Spark/Scala 中创建一个 GraphX 对象,但由于某种原因它似乎无法正常工作。我已经附上示例输入文件的文件,实际程序代码是:
package SGraph
import org.apache.spark._
import org.apache.spark.SparkContext._
import org.apache.spark.sql._
import org.apache.log4j._
import org.apache.spark.rdd.RDD
import org.apache.spark.graphx._
`
object GooglePlusGraph {
/** Our main function where the action happens */
def main(args: Array[String]) {
// Set the log level to only print errors
Logger.getLogger("org").setLevel(Level.ERROR)
// Create a SparkContext using every core of the local machine
val sc = new SparkContext("local[*]", "GooglePlusGraphX")
val lines = sc.textFile("../Example.txt")
val ratings = lines.map(x => x.toString().split(":")(0))
val verts = ratings.map(line => (line.toLong,line))
val edges = lines.flatMap(makeEdges)
val default = "Nobody"
val graph = Graph(verts, edges, default).cache()
graph.degrees.join(verts).take(10).foreach(println)
}
def makeEdges(line: String) : List[Edge[Int]] = {
import scala.collection.mutable.ListBuffer
var edges = new ListBuffer[Edge[Int]]()
val fields = line.split(",").flatMap(a => a.split(":"))
val origin = fields(0)
for (x <- 1 to (fields.length - 1)) {
// Our attribute field is unused, but in other graphs could
// be used to deep track of physical distances etc.
edges += Edge(origin.toLong, fields(x).toLong, 0)
}
return edges.toList
}
}
我得到的第一个错误如下:
16/12/19 01:28:33 ERROR Executor: Exception in task 0.0 in stage 2.0 (TID 3)
java.lang.NumberFormatException: For input string: "935750800736168978117"
感谢您的帮助!
跟你下面的问题是一样的问题
给定的号码有 21 位超出了最大位数 Long
(19 位)。