spark mlib NaiveBayes 笔记

import org.apache.log4j.{Level, Logger}
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.{SparkConf, SparkContext}
object spark_mllib {
  def main(args: Array[String]): Unit = {
    Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
    Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF)
    val conf = new SparkConf().setAppName("spark_mllib").setMaster("local[2]")
    val sc =new  SparkContext(conf)
//    val spark = SparkSession.builder().getOrCreate()
    val data = sc.textFile("C:/Users/Lenovo/Desktop/data.txt")
    //将数据转换为Rating类型，即[Int,Int,Double]的Rdd
    val parsedData =data.map {
      line => val parts = line.split(',')
        LabeledPoint(parts(0).toDouble,Vectors.dense(parts(1).split(' ').map(_.toDouble)))
    }
//    parsedData.foreach(println)

    //将原始数据划分为训练数据和测试数据，其中60% 为训练集 40 % 的为测试集
      val splits = parsedData.randomSplit(Array(0.7,0.3),seed = 11L)
      val training =splits(0)
      val test =splits(1)
      //获得训练参数模型，第一个为数据，第二个参数为平滑参数
      val model =NaiveBayes.train(training,lambda = 1.0)
      //对测试样本进行测试
      val predictionAndLabel= test.map(p => (model.predict(p.features),p.label))
  //    //对模型进行准确度分析
      val accuracy =1.0 *predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()
     println("NaiveBayes精度----->" + accuracy)
     //我们这里特地打印一个预测值：假如一天是 晴天(0)凉(2)高(0)高(1) 是否训练
      println("test:0, 2, 0, 1--->" + model.predict(Vectors.dense(0.0,2.0,0.0,1.0)))
  }

}
//原始数据
//0,0 0 0 0
//0,0 0 0 1
//1,1 0 0 0
//1,2 1 0 0
//1,2 2 1 0
//0,2 2 1 1
//1,1 2 1 1
//0,0 1 0 0
//1,0 2 1 0
//1,2 1 1 0
//1,0 1 1 1