Spark Mlib(一) svm

SVM(Support Vector Machine)指的是支持向量机，是常见的一种判别方法。在机器学习领域，是一个有监督的学习模型，通常用来进行模式识别、分类以及回归分析。下面是spark官网给出的例子。原网址为http://spark.apache.org/docs/latest/mllib-linear-methods.html#classification

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.{SVMModel, SVMWithSGD}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.util.MLUtils
object spark_svm {

  def main(args :Array[String]): Unit = {

    val sparkConf = new SparkConf().setMaster("local").setAppName("testTansformition")
    val sc = new SparkContext(sparkConf)

    //加载训练数据　LIBSVＭ数据格式.
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    // 划分训练集和测试机集（训练集６０％，测试集４０％）
    val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
    val training = splits(0).cache()
    val test = splits(1)

    // 训练模型
    val numIterations = 100
    val model = SVMWithSGD.train(training, numIterations)

    // 清楚默认阈值
    model.clearThreshold()

    // 对测试集进行预测
    val scoreAndLabels = test.map { point =>
      val score = model.predict(point.features)
      (score, point.label)
    }

    //获取评价指标
    val metrics = new BinaryClassificationMetrics(scoreAndLabels)
    val auROC = metrics.areaUnderROC()

    println(s"Area under ROC = $auROC")

    // 保存和加载模型示例
    model.save(sc, "target/tmp/scalaSVMWithSGDModel")
    val sameModel = SVMModel.load(sc, "target/tmp/scalaSVMWithSGDModel")

    Thread.sleep(30*30*1000);

  }

}