【spark系列5】回归之LinearRegressionWithSGD

scala程序

import org.apache.spark.mllib.regression.LinearRegressionWithSGD
import org.apache.spark.mllib.regression.LabeledPoint

object ObLinearRegressionWithSGD{
def run() {
// Load and parse the data file
val data = sc.textFile("D:/schoolar_tool/spark-0.9.1/mllib/data/ridge-data/lpsa.data")
val parsedData = data.map { line =>
val parts = line.split(',')
LabeledPoint(parts(0).toDouble, parts(1).split(' ').map(x => x.toDouble).toArray)
}

// Building the model
val numIterations = 20
val model = LinearRegressionWithSGD.train(parsedData, numIterations)

// Evaluate model on training examples and compute training error
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)}.reduce(_ + _)/valuesAndPreds.count
println("training Mean Squared Error = " + MSE)
}
}

运行

ObLinearRegressionWithSGD.run

效果