计算回归曲线的MSE

import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LabeledPoint, LinearRegressionWithSGD}
import org.apache.spark.{SparkConf, SparkContext}
object kimiYang {
  var conf = new SparkConf()
  .setMaster("local")
  .setAppName("kimiYang");
  var sc = new SparkContext(conf);

  def main(args: Array[String]): Unit = {
    val data = sc.textFile("kimi.txt");
    val parsedData = data.map{line =>
      val parts = line.split('|');
      LabeledPoint(parts(0).toDouble,Vectors.dense(parts(1).split(',').map(_.toDouble)))
    }.cache();
    val model = LinearRegressionWithSGD.train(parsedData,10,0.1);
    println("model Weight" + model.weights)
    val valuesAndPreds = parsedData.map{point => {
      val prediction = model.predict(point.features);
      (point.label,prediction);
      }
    }
    val MSE = valuesAndPreds.map{
   case(v,p) => math.pow((v - p),2)}.mean();
    println("MSE" + MSE);

  }
}

结果：

model Weight[-2.1793201852602822E42,-4.305555405890157E44]

MSE1.4628747951573787E95

数据

65|7,400
90|5,1300
100|4,1100
110|3,1300
60|9,300
100|5,1000
75|7,600
80|6,1200
70|6,500
50|8,30