Spark——KNN代码及注解

一、简介

KNN及K邻近分类算法，通过搜索K个最相似的实例（邻居）的整个训练集并总结那些K个实例的输出变量，对新数据点进行预测。而寻找邻近点的距离公式一般使用欧式距离公式。

二、示例

1、数据

该数据是根据鸢尾花特征来区分种类的数据。前四个特征为花萼长度，花萼宽度，花瓣长度，花瓣宽度，最后一个为种类。
该数据分为训练数据与测试数据。

训练数据

5.1,3.5,1.4,0.2,setosa
4.9,3,1.4,0.2,setosa
4.7,3.2,1.3,0.2,setosa
4.6,3.1,1.5,0.2,setosa
5,3.6,1.4,0.2,setosa
5.4,3.9,1.7,0.4,setosa
4.6,3.4,1.4,0.3,setosa
5,3.4,1.5,0.2,setosa
4.4,2.9,1.4,0.2,setosa
4.9,3.1,1.5,0.1,setosa
5.4,3.7,1.5,0.2,setosa
4.8,3.4,1.6,0.2,setosa
4.8,3,1.4,0.1,setosa
4.3,3,1.1,0.1,setosa
5.8,4,1.2,0.2,setosa
5.7,4.4,1.5,0.4,setosa
5.4,3.9,1.3,0.4,setosa
5.1,3.5,1.4,0.3,setosa
5.7,3.8,1.7,0.3,setosa
5.1,3.8,1.5,0.3,setosa
5.4,3.4,1.7,0.2,setosa
5.1,3.7,1.5,0.4,setosa
4.6,3.6,1,0.2,setosa
5.1,3.3,1.7,0.5,setosa
4.8,3.4,1.9,0.2,setosa
5,3,1.6,0.2,setosa
5,3.4,1.6,0.4,setosa
5.2,3.5,1.5,0.2,setosa
5.2,3.4,1.4,0.2,setosa
4.7,3.2,1.6,0.2,setosa
4.8,3.1,1.6,0.2,setosa
5.4,3.4,1.5,0.4,setosa
5.2,4.1,1.5,0.1,setosa
5.5,4.2,1.4,0.2,setosa
4.9,3.1,1.5,0.2,setosa
5,3.2,1.2,0.2,setosa
5.5,3.5,1.3,0.2,setosa
4.9,3.6,1.4,0.1,setosa
4.4,3,1.3,0.2,setosa
5.1,3.4,1.5,0.2,setosa
5,3.5,1.3,0.3,setosa
4.5,2.3,1.3,0.3,setosa
4.4,3.2,1.3,0.2,setosa
5,3.5,1.6,0.6,setosa
5.1,3.8,1.9,0.4,setosa
4.8,3,1.4,0.3,setosa
5.1,3.8,1.6,0.2,setosa
4.6,3.2,1.4,0.2,setosa
7,3.2,4.7,1.4,versicolor
6.4,3.2,4.5,1.5,versicolor
6.9,3.1,4.9,1.5,versicolor
5.5,2.3,4,1.3,versicolor
6.5,2.8,4.6,1.5,versicolor
5.7,2.8,4.5,1.3,versicolor
6.3,3.3,4.7,1.6,versicolor
4.9,2.4,3.3,1,versicolor
6.6,2.9,4.6,1.3,versicolor
5.2,2.7,3.9,1.4,versicolor
5,2,3.5,1,versicolor
5.9,3,4.2,1.5,versicolor
6,2.2,4,1,versicolor
6.1,2.9,4.7,1.4,versicolor
5.6,2.9,3.6,1.3,versicolor
6.7,3.1,4.4,1.4,versicolor
5.6,3,4.5,1.5,versicolor
5.8,2.7,4.1,1,versicolor
6.2,2.2,4.5,1.5,versicolor
5.6,2.5,3.9,1.1,versicolor
5.9,3.2,4.8,1.8,versicolor
6.1,2.8,4,1.3,versicolor
6.3,2.5,4.9,1.5,versicolor
6.1,2.8,4.7,1.2,versicolor
6.4,2.9,4.3,1.3,versicolor
6.6,3,4.4,1.4,versicolor
6.8,2.8,4.8,1.4,versicolor
6.7,3,5,1.7,versicolor
6,2.9,4.5,1.5,versicolor
5.7,2.6,3.5,1,versicolor
5.5,2.4,3.8,1.1,versicolor
5.5,2.4,3.7,1,versicolor
5.8,2.7,3.9,1.2,versicolor
6,2.7,5.1,1.6,versicolor
5.4,3,4.5,1.5,versicolor
6,3.4,4.5,1.6,versicolor
6.7,3.1,4.7,1.5,versicolor
6.3,2.3,4.4,1.3,versicolor
5.6,3,4.1,1.3,versicolor
5.5,2.5,4,1.3,versicolor
5.5,2.6,4.4,1.2,versicolor
6.1,3,4.6,1.4,versicolor
5.8,2.6,4,1.2,versicolor
5,2.3,3.3,1,versicolor
5.6,2.7,4.2,1.3,versicolor
5.7,3,4.2,1.2,versicolor
5.7,2.9,4.2,1.3,versicolor
6.2,2.9,4.3,1.3,versicolor
6.3,3.3,6,2.5,virginica
5.8,2.7,5.1,1.9,virginica
7.1,3,5.9,2.1,virginica
6.3,2.9,5.6,1.8,virginica
6.5,3,5.8,2.2,virginica
7.6,3,6.6,2.1,virginica
4.9,2.5,4.5,1.7,virginica
7.3,2.9,6.3,1.8,virginica
6.7,2.5,5.8,1.8,virginica
7.2,3.6,6.1,2.5,virginica
6.5,3.2,5.1,2,virginica
6.4,2.7,5.3,1.9,virginica
6.8,3,5.5,2.1,virginica
5.7,2.5,5,2,virginica
5.8,2.8,5.1,2.4,virginica
6.4,3.2,5.3,2.3,virginica
6.5,3,5.5,1.8,virginica
7.7,3.8,6.7,2.2,virginica
7.7,2.6,6.9,2.3,virginica
6,2.2,5,1.5,virginica
6.9,3.2,5.7,2.3,virginica
5.6,2.8,4.9,2,virginica
7.7,2.8,6.7,2,virginica
6.3,2.7,4.9,1.8,virginica
6.7,3.3,5.7,2.1,virginica
7.2,3.2,6,1.8,virginica
6.2,2.8,4.8,1.8,virginica
6.1,3,4.9,1.8,virginica
6.4,2.8,5.6,2.1,virginica
7.2,3,5.8,1.6,virginica
7.4,2.8,6.1,1.9,virginica
7.9,3.8,6.4,2,virginica
6.4,2.8,5.6,2.2,virginica
6.3,2.8,5.1,1.5,virginica
6.1,2.6,5.6,1.4,virginica
7.7,3,6.1,2.3,virginica
6.3,3.4,5.6,2.4,virginica
6.4,3.1,5.5,1.8,virginica
6,3,4.8,1.8,virginica
6.9,3.1,5.4,2.1,virginica
6.7,3.1,5.6,2.4,virginica
6.9,3.1,5.1,2.3,virginica
5.8,2.7,5.1,1.9,virginica
6.8,3.2,5.9,2.3,virginica
6.7,3.3,5.7,2.5,virginica
6.7,3,5.2,2.3,virginica
6.3,2.5,5,1.9,virginica
6.5,3,5.2,2,virginica

测试数据

5.1,2.5,3,1.1
5.7,2.8,4.1,1.3
5.3,3.7,1.5,0.2
5,3.3,1.4,0.2
6.2,3.4,5.4,2.3
5.9,3,5.1,1.8

2、代码

package com.knn

import org.apache.spark.{SparkConf, SparkContext}

object LrisDemo {
    def main(args: Array[String]): Unit = {
        val sc = new SparkContext(new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local"))
        val K = 9
        // 输入训练集转换为样例类
        val sample = sc.textFile("src/main/resources/knn/iris.txt")
                .map { line =>
                    val fields = line.split(",")
                    LabeledPoint(fields.last, fields.init.map(_.toDouble))
                }

        val test = sc.textFile("src/main/resources/knn/test.txt")
                .map { line =>
                    val features = line.split(",")
                    LabeledPoint("", features.map(_.toDouble))
                }

        val sampleData = sample.filter(_.label != "")
        val testData = test.map(_.features).collect()

        testData.foreach(elem => {
            val distance = sampleData.map(x => (getDistance(elem, x.features), x.label))
            // 获取距离最近的k个样本
            val minDistance = distance.sortBy(_._1).take(K)
            // 取出这k个样本的label，并获取出现最多的label视为最终确定的label
            val labels = minDistance.map(_._2)
                    .groupBy(x => x)
                    .mapValues(_.length)
                    .toList
                    .sortBy(_._2)
                    .take(1)
                    .map(_._1)
            println(elem.mkString(","), labels.mkString(","))
        })

        sc.stop()
    }

    import scala.math._

    // 求距离方法
    def getDistance(x: Array[Double], y: Array[Double]): Double = {
        // 每个数组中的元素的差的平方和，再sqrt开方就是距离，即欧式距离的计算
        // pow(a -b ,2) 即 （a - b）^ 2
        // sqrt 即 开方
        sqrt(x.zip(y).map(elem => pow(elem._1 - elem._2, 2)).sum)
    }
}

// 样例类 label标签 + 特征数组
case class LabeledPoint(label: String, features: Array[Double])