机器学习:决策树算法实战

object DecisionTreeTest {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("DesionTrain").setMaster("local[2]")
    val sc = new SparkContext(conf)
    //    加载数据
    val data = sc.textFile("f://dt.csv").map(lines => {
      val fields = lines.split(",")
      val lable = fields(fields.length - 1).toDouble
      val features = fields.slice(1, fields.length - 1).map(x => x.toDouble)
      LabeledPoint(lable, Vectors.dense(features))
    })
    val labe = data.map(_.label)
    //    了解决策树的参数
    val model = DecisionTree.train(data, Algo.Classification, Entropy, 5, 9)
    val predictionAndLabel = data.map { point =>
      val score = model.predict(point.features)
      (score)
    }
    println(predictionAndLabel.collect().toBuffer)
    val acc = labe.zip(predictionAndLabel).filter(x => {
      x._1.equals(x._2)
    }).count() / labe.count().toDouble
    println(acc)
  }
}

dt.csv格式如下:

1,1,1,30,2201,0,1,20,210105,51,3,5,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3.2,0,3.2,3.2,3.2,3.2,0,1,0,1,1,0,10,4680,1,1,80,0,1,2,2,5,0,1,2101,1,1,2101,3,1,1,1,1,1,1,0,0,0,0,1,5467,3253,300133,300133,13,1,300102,4535,0,0,0,0,75357,8907.53,1,1,1,1,1,1,1,1,1,1,1,0,0,1,1,0,0,1,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,55

你可能感兴趣的:(机器学习实战)