逻辑回归（LR）

package com.dianping.www

/**
* Created by sun on 16/7/19.
*/

import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS
import org.apache.spark.mllib.evaluation.MulticlassMetrics
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.{SparkConf, SparkContext}
object LR{
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("LR1.0")
val sc = new SparkContext(conf)

// split args
val para = args(0).split(',')
// load data and transform to LabeledPoint format.
val data_tmp = sc.textFile(para(0))
val data = data_tmp.map( line => line.split(',')).map { r =>
val label = r(r.size - 1).toInt
val features = r.slice(0,r.size -1).map(_.toDouble)
LabeledPoint(label,Vectors.dense(features))
}
// Split data into training (60%) and test (40%).
val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
val training = splits(0).cache()
val test = splits(1)

// Run training algorithm to build the model
val model = new LogisticRegressionWithLBFGS()
.setNumClasses(para(1).toInt) //two class.
.run(training)
 
// clear Threshold
// model.clearThreshold()
// Compute raw scores on the test set.
val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
val prediction = model.predict(features)
(prediction, label)
}

// Get evaluation metrics.
val metrics = new MulticlassMetrics(predictionAndLabels)
val precision = metrics.precision
val recall = metrics.recall
println("Precision = " + precision + ",Recall = " + recall)
 
// Get AUC
val metrics2 = new BinaryClassificationMetrics(predictionAndLabels)
println("AreaUnderPR = " + metrics2.areaUnderPR() + "AUC = " + metrics2.areaUnderROC())

// Save and load model
//    model.save(sc, para(2))
sc.stop()
}
}