掌握Spark機器學習庫-07.6-線性迴歸實現房價預測

數據集

house.csv

數據概覽

代碼

package org.apache.spark.examples.examplesforml

import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.sql.SparkSession
import org.apache.spark.{SparkConf, SparkContext}

import scala.util.Random
/*
日期：2018.10.15
描述：
7-6
線性迴歸算法
預測房價
數據集：house.csv
 */
object Linear {
  def main(args:Array[String]): Unit ={
    val conf=new SparkConf().setMaster("local[*]").setAppName("LinearregRession")
    val sc=new SparkContext(conf)
    val spark=SparkSession.builder().config(conf).getOrCreate()
    val file=spark.read.format("csv")
      .option("header","true")//y
      .option("sep",";")//分隔符
      .load("D:\\機器學習算法準備\\7-6線性迴歸-預測房價\\house.csv")
    import spark.implicits._
    val random =new Random()
    val data=file.select("square","price")
      .map(row => (row.getAs[String](0).toDouble,row.getAs[String](1).toDouble,random.nextDouble()))
      .toDF("square","price","rand")
      .sort("rand")
    data.show()

    val assembler=new VectorAssembler()
      .setInputCols(Array("square"))
      .setOutputCol("features")
    val dataset=assembler.transform(data)
    var Array(train,test)=dataset.randomSplit(Array(0.8,0.2),1234L)
    train.show()
    println(test.count())

    var regression=new LinearRegression().setMaxIter(10).setRegParam(0.3).setElasticNetParam(0.8)
    val model=regression.setLabelCol("price").setFeaturesCol("features").fit(train)
    model.transform(test).show()

    val s = model.summary.totalIterations
    println(s"iter: ${s}")

  }
}

輸出：