掌握Spark机器学习库-07.14-保序回归算法实现房价预测

数据集

house.csv

数据集概览

代码

package org.apache.spark.examples.examplesforml

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

import scala.util.Random
/*
日期：2018.10.15
描述：
7-14
保序回归算法
实现房价预测
数据集：
house.csv
 */
object IstonicRegression {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf()
      .setAppName("linear")
      .setMaster("local")
    val sc = new SparkContext(conf)
    val spark = SparkSession
      .builder()
      .config(conf)
      .getOrCreate()

    val file = spark.read
      .format("csv")
      .option("sep",";")
      .option("header","true")
      .load("D:\\7-6线性回归-预测房价\\house.csv")
    import spark.implicits._
    //打乱顺序
    val rand = new Random()
    val data = file.select("square","price")
      .map(
      row => (row.getAs[String](0).toDouble,row.getString(1).toDouble,rand.nextDouble()))
      .toDF("square","price","rand").sort("rand") //强制类型转换过程

    val ass = new VectorAssembler()
      .setInputCols(Array("square"))
      .setOutputCol("features")
    val dataset = ass.transform(data)//特征包装
    val Array(train,test) = dataset.randomSplit(Array(0.8,0.2))//拆分成训练数据集和测试数据集

    val isotonic = new IsotonicRegression()
      .setFeaturesCol("features")
      .setLabelCol("price")
    val model = isotonic.fit(train)
    model.transform(test).show()
  }
}

输出结果