Scala StreamingLinearRegressionWithSGD类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Scala›Scala教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Scala中org.apache.spark.mllib.regression.StreamingLinearRegressionWithSGD类的典型用法代码示例。如果您正苦于以下问题：Scala StreamingLinearRegressionWithSGD类的具体用法？Scala StreamingLinearRegressionWithSGD怎么用？Scala StreamingLinearRegressionWithSGD使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

在下文中一共展示了StreamingLinearRegressionWithSGD类的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: StreamingSimpleModel

//设置package包名称以及导入依赖的类
package com.bigchange.streaming

import breeze.linalg.DenseVector
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LabeledPoint, StreamingLinearRegressionWithSGD}
import org.apache.spark.streaming.{Seconds, StreamingContext}


object StreamingSimpleModel {

  def main(args: Array[String]) {

    val ssc = new StreamingContext("local","test",Seconds(10))
    val stream = ssc.socketTextStream("localhost",9999)
    val numberFeatures = 100
    val zeroVector = DenseVector.zeros[Double](numberFeatures)
    val model = new StreamingLinearRegressionWithSGD()
      .setInitialWeights(Vectors.dense(zeroVector.data))
      .setNumIterations(1)
      .setStepSize(0.01)


    val labeledStream = stream.map { event =>
      val split = event.split("\t")
      val y = split(0).toDouble
      val features = split(1).split(",").map(_.toDouble)
      LabeledPoint(label = y, features = Vectors.dense(features))
    }

    model.trainOn(labeledStream)
    // ??DStream?????
    val predictAndTrue = labeledStream.transform { rdd =>
     val latestModel = model.latestModel()
      rdd.map { point =>
        val predict = latestModel.predict(point.features)
        predict - point.label
      }
    }
    // ??MSE
    predictAndTrue.foreachRDD { rdd =>
      val  mse = rdd.map(x => x * x).mean()
      val rmse = math.sqrt(mse)
      println(s"current batch, MSE: $mse, RMSE:$rmse")

    }
    ssc.start()
    ssc.awaitTermination()

  }
}

开发者ID:bigchange，项目名称:AI，代码行数:51，代码来源:StreamingSimpleModel.scala

示例2: LinearRegressionApp

//设置package包名称以及导入依赖的类
package org.apress.prospark

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.regression.StreamingLinearRegressionWithSGD
import org.apache.spark.rdd.RDD
import org.apache.spark.rdd.RDD.doubleRDDToDoubleRDDFunctions
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.StreamingContext

object LinearRegressionApp {

  def main(args: Array[String]) {
    if (args.length != 4) {
      System.err.println(
        "Usage: LinearRegressionApp <appname> <batchInterval> <hostname> <port>")
      System.exit(1)
    }
    val Seq(appName, batchInterval, hostname, port) = args.toSeq

    val conf = new SparkConf()
      .setAppName(appName)
      .setJars(SparkContext.jarOfClass(this.getClass).toSeq)

    val ssc = new StreamingContext(conf, Seconds(batchInterval.toInt))

    val substream = ssc.socketTextStream(hostname, port.toInt)
      .filter(!_.contains("NaN"))
      .map(_.split(" "))
      .filter(f => f(1) != "0")

    val datastream = substream.map(f => Array(f(2).toDouble, f(3).toDouble, f(4).toDouble, f(5).toDouble, f(6).toDouble))
      .map(f => LabeledPoint(f(0), Vectors.dense(f.slice(1, 5))))
    val test = datastream.transform(rdd => rdd.randomSplit(Array(0.3, 0.7))(0))
    val train = datastream.transformWith(test, (r1: RDD[LabeledPoint], r2: RDD[LabeledPoint]) => r1.subtract(r2)).cache()
    val model = new StreamingLinearRegressionWithSGD()
      .setInitialWeights(Vectors.zeros(4))
      .setStepSize(0.0001)
      .setNumIterations(1)

    model.trainOn(train)
    model.predictOnValues(test.map(v => (v.label, v.features))).foreachRDD(rdd => println("MSE: %f".format(rdd
      .map(v => math.pow((v._1 - v._2), 2)).mean())))

    ssc.start()
    ssc.awaitTermination()
  }

}

开发者ID:ZubairNabi，项目名称:prosparkstreaming，代码行数:52，代码来源:L9-1LinearRegression.scala

注：本文中的org.apache.spark.mllib.regression.StreamingLinearRegressionWithSGD类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。