当我尝试使用图框生成连接的组件时,它花费的时间比我预期的要长得多。我在 spark 2.1、graphframes 0.5 和带有 3 个 r4.xlarge 实例的 AWS EMR 上运行。当为大约 1200 万条边的图生成连接组件时,大约需要 3 个小时。
代码如下。我对火花相当陌生,所以任何建议都会很棒。
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf()
.setMaster("yarn-cluster")
.setAppName("Connected Component")
val sc = new SparkContext(sparkConf)
sc.setCheckpointDir("s3a://......")
AWSUtils.setS3Credentials(sc.hadoopConfiguration)
implicit val sqlContext = SQLContext.getOrCreate(sc)
import sqlContext.implicits._
val historical = sqlContext
.read
.option("mergeSchema", "false")
.parquet("s3a://.....")
.map(x => (x(0).toString, x(2).toString, x(1).toString, x(3).toString, x(4).toString.toLong, x(5).toString.toLong))
// Complete graph
val g = GraphFrame(
historical.flatMap(e => List((e._1, e._3, e._5), (e._2, e._4, e._5))).toDF("id", "type", "timestamp"),
historical.toDF("src", "dst", "srcType", "dstType", "timestamp", "companyId")
)
val connectedComponents: DataFrame = g.connectedComponents.run()
connectedComponents.toDF().show(100, false)
sc.stop()
}