数据挖掘—K-Means算法（Java实现）

算法描述

（1）任意选择k个数据对象作为初始聚类中心
（2）根据簇中对象的平均值，将每个对象赋给最类似的簇
（3）更新簇的平均值，即计算每个对象簇中对象的平均值
（4）计算聚类准则函数E
（5）重复2-4步骤，直到准则函数E值不再进行变化

代码


public class Cluster {public String clusterName; // 类簇名private Medoid medoid; // 类簇的质点private ArrayList<DataPoint> dataPoints; // 类簇中各样本点public Cluster(String clusterName) {this.clusterName = clusterName;this.medoid = null; // will be set by calling setCentroid()dataPoints = new ArrayList<DataPoint>();}public void setMedoid(Medoid c) {medoid = c;}public Medoid getMedoid() {return medoid;}public void addDataPoint(DataPoint dp) { // called from CAInstancedp.setCluster(this);// 标注该类簇属于某点,计算欧式距离this.dataPoints.add(dp);}public void removeDataPoint(DataPoint dp) {this.dataPoints.remove(dp);}public int getNumDataPoints() {return this.dataPoints.size();}public DataPoint getDataPoint(int pos) {return (DataPoint) this.dataPoints.get(pos);}public String getName() {return this.clusterName;}public ArrayList<DataPoint> getDataPoints() {return this.dataPoints;}
}


public class ClusterAnalysis {public Cluster[] clusters;// 所有类簇private int miter;// 迭代次数private ArrayList<DataPoint> dataPoints = new ArrayList<DataPoint>();// 所有样本点private int dimNum;//维度public ClusterAnalysis(int k, int iter, ArrayList<DataPoint> dataPoints,int dimNum) {clusters = new Cluster[k];// 类簇种类数for (int i = 0; i < k; i++) {clusters[i] = new Cluster(i+"");}this.miter = iter;this.dataPoints = dataPoints;this.dimNum=dimNum;}public int getIterations() {return miter;}public ArrayList<DataPoint>[] getClusterOutput() {ArrayList<DataPoint> v[] = new ArrayList[clusters.length];for (int i = 0; i < clusters.length; i++) {v[i] = clusters[i].getDataPoints();}return v;}public void startAnalysis(double[][] medoids) {setInitialMedoids(medoids);double[][] newMedoids=medoids;double[][] oldMedoids=new double[medoids.length][this.dimNum];while(!isEqual(oldMedoids,newMedoids)){for(int m = 0; m < clusters.length; m++){//每次迭代开始情况各类簇的点clusters[m].getDataPoints().clear();}for (int j = 0; j < dataPoints.size(); j++) {int clusterIndex=0;double minDistance=Double.MAX_VALUE;for (int k = 0; k < clusters.length; k++) {//判断样本点属于哪个类簇double eucDistance=dataPoints.get(j).testEuclideanDistance(clusters[k].getMedoid());if(eucDistance<minDistance){minDistance=eucDistance;clusterIndex=k;}}//将该样本点添加到该类簇clusters[clusterIndex].addDataPoint(dataPoints.get(j));}for(int m = 0; m < clusters.length; m++){clusters[m].getMedoid().calcMedoid();//重新计算各类簇的质点}for(int i=0;i<medoids.length;i++){for(int j=0;j<this.dimNum;j++){oldMedoids[i][j]=newMedoids[i][j];}}for(int n=0;n<clusters.length;n++){newMedoids[n]=clusters[n].getMedoid().getDimensioin();}this.miter++;}}private void setInitialMedoids(double[][] medoids) {for (int n = 0; n < clusters.length; n++) {Medoid medoid = new Medoid(medoids[n]);clusters[n].setMedoid(medoid);medoid.setCluster(clusters[n]);}}private boolean isEqual(double[][] oldMedoids,double[][] newMedoids){boolean flag=false;for(int i=0;i<oldMedoids.length;i++){for(int j=0;j<oldMedoids[i].length;j++){if(oldMedoids[i][j]!=newMedoids[i][j]){return flag;}}}flag=true;return flag;}
}


public class DataPoint {private double dimension[]; //样本点的维度private String pointName; //样本点名字private Cluster cluster; //类簇private double euDt;//样本点到质点的距离public DataPoint(double dimension[], String pointName) {this.dimension = dimension;this.pointName = pointName;this.cluster = null;}@Overridepublic String toString() {String result = "Point_id=" + pointName + "  [";for (int i = 0; i < dimension.length; i++) {result += String.format("%.2f",dimension[i]) + " ";}return result.trim()+"] clusterId: "+cluster.clusterName;}public void setCluster(Cluster cluster) {this.cluster = cluster;}public double calEuclideanDistanceSum() {double sum=0.0;Cluster cluster=this.getCluster();ArrayList<DataPoint> dataPoints=cluster.getDataPoints();for(int i=0;i<dataPoints.size();i++){double[] dims=dataPoints.get(i).getDimensioin();for(int j=0;j<dims.length;j++){double temp=Math.pow((dims[j]-this.dimension[j]),2);sum=sum+temp;}}return Math.sqrt(sum);}public double testEuclideanDistance(Medoid c) {double sum=0.0;double[] cDim=c.getDimensioin();for(int i=0;i<dimension.length;i++){double temp=Math.pow((dimension[i]-cDim[i]),2);sum=sum+temp;}return Math.sqrt(sum);}public double[] getDimensioin() {return this.dimension;}public Cluster getCluster() {return this.cluster;}public double getCurrentEuDt() {return this.euDt;}public String getPointName() {return this.pointName;}
}

public class Medoid{private double dimension[]; // 质点的维度private Cluster cluster; //所属类簇private double etdDisSum;//Medoid到本类簇中所有的欧式距离之和public String toString() {String result ="  [";DecimalFormat decimalFormat=new DecimalFormat("0.000000");for (int i = 0; i < dimension.length; i++) {result += decimalFormat.format(dimension[i]) + " ";}return result.trim()+"] clusterId: "+cluster.clusterName;}public Medoid(double dimension[]) {this.dimension = dimension;}public void setCluster(Cluster c) {this.cluster = c;}public double[] getDimensioin() {return this.dimension;}public Cluster getCluster() {return this.cluster;}public void calcMedoid() {// 取代价最小的点calcEtdDisSum();double minEucDisSum = this.etdDisSum;ArrayList<DataPoint> dps = this.cluster.getDataPoints();for (int i = 0; i < dps.size(); i++) {double tempeucDisSum = dps.get(i).calEuclideanDistanceSum();if (tempeucDisSum < minEucDisSum) {dimension = dps.get(i).getDimensioin();minEucDisSum=tempeucDisSum;}}}// 计算该Medoid到同类簇所有样本点的欧斯距离和private void calcEtdDisSum() {double sum=0.0;Cluster cluster=this.getCluster();ArrayList<DataPoint> dataPoints=cluster.getDataPoints();for(int i=0;i<dataPoints.size();i++){double[] dims=dataPoints.get(i).getDimensioin();for(int j=0;j<dims.length;j++){double temp=Math.abs(dims[j]-this.dimension[j]);sum=sum+temp;}}etdDisSum= sum;}
}


public class TestMain {public static List<double[]> readTxt(String fileName){List<double[]> list=new ArrayList<>();try {File filename = new File(fileName); // 读取input.txt文件InputStreamReader reader = new InputStreamReader(new FileInputStream(filename)); // 建立一个输入流对象readerBufferedReader br = new BufferedReader(reader);String line = "";line = br.readLine();while (true) {line = br.readLine();if(line==null) break;String[] temp=line.split(",");double[] c=new double[temp.length];for(int i=0;i<temp.length;i++){c[i]=Float.parseFloat(temp[i]);}list.add(c);}} catch (Exception e) {e.printStackTrace();}return list;}public static void writeTxt(String content){try { // 防止文件建立或读取失败，用catch捕捉错误并打印，也可以throw/* 读入TXT文件 */File writename = new File("src/km/output.txt"); // 相对路径，如果没有则要建立一个新的output。txt文件BufferedWriter out = new BufferedWriter(new FileWriter(writename));out.write(content); // \r\n即为换行out.flush(); // 把缓存区内容压入文件out.close(); // 最后记得关闭文件} catch (Exception e) {e.printStackTrace();}}public static void main (String args[]){ArrayList<DataPoint> dataPoints = new ArrayList<DataPoint>();List<double[]> list=readTxt("src/km/t2.txt");for(int i=0;i<list.size();i++){dataPoints.add(new DataPoint(list.get(i),String.valueOf(i)));}long s=System.currentTimeMillis();ClusterAnalysis ca=new ClusterAnalysis(5,200,dataPoints,5);double[][] cen={list.get(22),list.get(3),list.get(45),list.get(156),list.get(96)};ca.startAnalysis(cen);StringBuilder stringBuilder=new StringBuilder();ArrayList<DataPoint>[] v = ca.getClusterOutput();System.out.println("K-中心点聚类算法运行时间"+(System.currentTimeMillis()-s)+"ms");for (int ii=0; ii<v.length; ii++){ArrayList tempV = v[ii];stringBuilder.append("\n").append("-----------Cluster").append(ii).append("---------").append("\n");stringBuilder.append("Mid_Point:  ").append(ca.clusters[ii].getMedoid()).append("  Points_num:  "+ca.clusters[ii].getDataPoints().size()).append("\n");System.out.println(ca.clusters[ii].getMedoid()+"  Points_num:  "+ca.clusters[ii].getDataPoints().size());Iterator iter = tempV.iterator();while(iter.hasNext()){DataPoint dpTemp = (DataPoint)iter.next();stringBuilder.append(dpTemp).append("\n");}}writeTxt(stringBuilder.toString());}}

数据挖掘—K-Means算法（Java实现）相关推荐

kmeans改进 matlab,基于距离函数的改进k―means 算法
摘要:聚类算法在自然科学和和社会科学中都有很普遍的应用,而K-means算法是聚类算法中经典的划分方法之一.但如果数据集内相邻的簇之间离散度相差较大,或者是属性分布区间相差较大,则算法的聚类效果十分有 ...
k means算法C语言伪代码,K均值算法（K-Means）
1. K-Means算法步骤算法步骤收敛性定义,畸变函数(distortion function): 伪代码: 1) 创建k个点作为K个簇的起始质心(经常随机选择) 2) 当任意一个点的蔟分配结果 ...
k均值聚类算法(K Means)及其实战案例
算法说明 K均值聚类算法其实就是根据距离来看属性,近朱者赤近墨者黑.其中K表示要聚类的数量,就是说样本要被划分成几个类别.而均值则是因为需要求得每个类别的中心点,比如一维样本的中心点一般就是求这些样本 ...
数据挖掘10大算法详细介绍
想初步了解下怎样数据挖掘,看到一篇不错的文章转载过来啦~ 转自:http://blog.jobbole.com/89037/ 在一份调查问卷中,三个独立专家小组投票选出的十大最有影响力的数据挖掘算法, ...
K means 图片压缩
k-means的基本原理较为清晰,这里不多赘述,本次博客主要通过基础的k means算法进行图像的压缩处理. 原理分析在彩色图像中,每个像素的大小为3字节(RGB),可以表示的颜色总数为256 * ...
java实现 k nn算法_数据挖掘(二)——Knn算法的java实现
本文接数据挖掘-基于Kmeans算法.MBSAS算法及DBSCAN算法的newsgroup18828文本聚类器的JAVA实现(上). (update 2012.12.28 关于本项目下载及运行的常见问 ...
数据挖掘各种算法JAVA的实现方法
数据挖掘-关联分析频繁模式挖掘Apriori.FP-Growth及Eclat算法的JAVA及C++实现: 网址:http://blog.csdn.net/yangliuy/article/detail ...
Leetcode算法Java全解答--60. 第k个排列
Leetcode算法Java全解答–60. 第k个排列文章目录 Leetcode算法Java全解答--60. 第k个排列题目想法结果总结代码我的答案大佬们的答案测试用例其他题目 ...
机器学习算法：18大数据挖掘的经典算法以及代码Java实现
https://python.ctolib.com/article/wiki/95851 数据挖掘十大类经典算法基于Java8实现. 算法目录常用的标准数据挖掘算法包名目录名算法名 Asso ...
数据挖掘--“聚类”详解、K-means、K-平均值算法、K均值算法
一. 什么是聚类二. 聚类步骤三. 聚类算法有哪些 1 层次聚类算法 2 划分聚类算法 3 基于密度的聚类算法 4 基于网格的聚类算法 5 基于模型的聚类算法一. 什么是聚类? 物以类聚,人以群 ...

数据挖掘—K-Means算法（Java实现）

算法描述

代码

数据挖掘—K-Means算法（Java实现）相关推荐

最新文章

热门文章