我们正在尝试实现一个简单的 spark 作业,它读取 CSV 文件(1 行数据)并使用预构建的随机森林模型对象进行预测。这项工作不包括任何数据预处理或数据操作。
我们以独立模式运行 spark,应用程序在本地运行。配置如下: RAM:8GB 内存:40GB 内核数:2 Spark 版本:1.5.2 Scala 版本:2.10.5 输入文件大小:1KB(1行数据) 模型文件大小:1,595 KB(400棵树)随机森林)
目前,spark-submit 中的实现大约需要 13 秒。然而,运行时间是这个应用程序的一个巨大问题,因此
有没有办法优化代码以将运行时间缩短到 1 或 2 秒?(高优先级)
我们注意到实际代码的执行大约需要 7-8 秒,而启动和设置上下文大约需要 5-6 秒,所以有没有办法在我们运行 spark-submit 时保持 spark 上下文运行。
这是应用程序代码
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
object RF_model_App {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("Simple Application")
val sc = new SparkContext(conf)
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.feature4.{RandomForestfeature4Model, RandomForestClassifier}
import org.apache.spark.ml.evaluation.Multiclassfeature4Evaluator
import org.apache.spark.ml.feature.{IndexToString, StringIndexer, VectorIndexer}
import org.apache.spark.sql.functions.udf
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.feature.StringIndexer
import sqlContext.implicits._
val Test = sqlContext.read.format("com.databricks.spark.csv").option("header","true").load("/home/ubuntu/Test.csv")
Test.registerTempTable("Test")
val model_L1 = sc.objectFile[RandomForestfeature4Model]("/home/ubuntu/RF_L1.model").first()
val toInt = udf[Int, String]( _.toInt)
val toDouble = udf[Double, String]( _.toDouble)
val featureDf = Test.withColumn("id1", toInt(Test("id1"))) .withColumn("id2", toInt(Test("id2"))) .withColumn("id3", toInt(Test("id3"))) .withColumn("id4", toInt(Test("id4"))) .withColumn("feature3", toInt(Test("feature3"))) .withColumn("feature9", toInt(Test("feature9"))) .withColumn("feature10", toInt(Test("feature10"))) .withColumn("feature12", toInt(Test("feature12"))) .withColumn("feature14", toDouble(Test("feature14"))) .withColumn("feature15", toDouble(Test("feature15"))) .withColumn("feature16", toInt(Test("feature16"))) .withColumn("feature17", toDouble(Test("feature17"))) .withColumn("feature18", toInt(Test("feature18")))
val feature4_index = new StringIndexer() .setInputCol("feature4") .setOutputCol("feature4_index")
val feature6_index = new StringIndexer() .setInputCol("feature6") .setOutputCol("feature6_index")
val feature11_index = new StringIndexer() .setInputCol("feature11") .setOutputCol("feature11_index")
val feature8_index = new StringIndexer() .setInputCol("feature8") .setOutputCol("feature8_index")
val feature13_index = new StringIndexer() .setInputCol("feature13") .setOutputCol("feature13_index")
val feature2_index = new StringIndexer() .setInputCol("feature2") .setOutputCol("feature2_index")
val feature5_index = new StringIndexer() .setInputCol("feature5") .setOutputCol("feature5_index")
val feature7_index = new StringIndexer() .setInputCol("feature7") .setOutputCol("feature7_index")
val vectorizer_L1 = new VectorAssembler() .setInputCols(Array("feature3", "feature2_index", "feature6_index", "feature4_index", "feature8_index", "feature7_index", "feature5_index", "feature10", "feature9", "feature12", "feature11_index", "feature13_index", "feature14", "feature15", "feature18", "feature17", "feature16")).setOutputCol("features_L1")
val feature_pipeline_L1 = new Pipeline() .setStages(Array( feature4_index, feature6_index, feature11_index,feature8_index, feature13_index, feature2_index, feature5_index, feature7_index,vectorizer_L1))
val testPredict= feature_pipeline_L1.fit(featureDf).transform(featureDf)
val getPOne = udf((v: org.apache.spark.mllib.linalg.Vector) => v(1))
val getid2 = udf((v: Int) => v)
val L1_output = model_L1.transform(testPredict).select(getid2($"id2") as "id2",getid2($"prediction") as "L1_prediction",getPOne($"probability") as "probability")
L1_output.repartition(1).write.format("com.databricks.spark.csv").option("header", "true").mode("overwrite").save("/home/L1_output")
}
};