Java学习第56天： kMeans 聚类

k均值聚类算法（k-means clustering algorithm）是一种迭代求解的聚类分析算法，其步骤是，预将数据分为K组，则随机选取K个对象作为初始的聚类中心，然后计算每个对象与各个种子聚类中心之间的距离，把每个对象分配给距离它最近的聚类中心。聚类中心以及分配给它们的对象就代表一个聚类。每分配一个样本，聚类的聚类中心会根据聚类中现有的对象被重新计算。这个过程将不断重复直到满足某个终止条件。终止条件可以是没有（或最小数目）对象被重新分配给不同的聚类，没有（或最小数目）聚类中心再发生变化，误差平方和局部最小。

K-means 的算法步骤为：

1.选择初始化的 k 个样本作为初始聚类中心 a=a1,a2,…ak;
2.针对数据集中每个样本xi计算它到 k 个聚类中心的距离并将其分到距离最小的聚类中心所对应的类中；
3.针对每个类别aj ，重新计算它的聚类中心;

 （即属于该类的所有样本的质心）；
4.重复上面 2 3 两步操作，直到达到某个中止条件（迭代次数、最小误差变化等）。

getRandomIndices() 和 kMeans 的完全相同, 拷贝过来. 本来应该写在 SimpleTools.java 里面的, 代码不多, 为保证独立性就放这里了.
distance() 和 kMeans 的相似, 注意不要用决策属性, 而且参数不同. 第 2 个参数为实数向量, 这是类为中心可能为虚拟的, 而中心点那里并没有对象.
代码如下：

package machinelearning.knn;

import java.util.Random;
import java.util.Arrays;
import java.io.FileReader;
import java.util.Random;

import weka.core.*;

/**
 * @description:kMeans聚类
 * @author: Qing Zhang
 * @time: 2021/7/5
 */
public class KMeans {
    //曼哈顿距离，|x|+|y|
    public static final int MANHATTAN = 0;

    //欧氏距离
    public static final int EUCLIDEAN = 1;

    //距离衡量方式
    public int distanceMeasure = EUCLIDEAN;

    //一个随机实例
    public static final Random random = new Random();

    //存储整个数据集
    Instances dataset;

    //聚类个数
    int numClusters = 2;

    //聚类
    int[][] clusters;

    /**
     * @Description: 构造函数
     * @Param: [paraFilename]
     * @return:
     */
    public KMeans(String paraFilename) {
        dataset = null;
        try {
            FileReader fileReader = new FileReader(paraFilename);
            dataset = new Instances(fileReader);
            fileReader.close();
        } catch (Exception ee) {
            System.out.println("Cannot read the file: " + paraFilename + "\r\n" + ee);
            System.exit(0);
        }
    }

    /**
     * @Description: 设置聚类数量
     * @Param: [paraNumClusters]
     * @return: void
     */
    public void setNumClusters(int paraNumClusters) {
        numClusters = paraNumClusters;
    }

    /**
     * @Description: 获得一个随机的索引用于数据随机化
     * @Param: [paraLength: 序列的长度]
     * @return: int[] e.g., {4, 3, 1, 5, 0, 2} with length 6.
     */
    public static int[] getRandomIndices(int paraLength) {
        int[] resultIndices = new int[paraLength];

        //第一步：初始化
        for (int i = 0; i < paraLength; i++) {
            resultIndices[i] = i;
        }

        //第二步：随机交换
        int tempFirst, tempSecond, tempValue;
        for (int i = 0; i < paraLength; i++) {
            //产生两个随机的索引
            tempFirst = random.nextInt(paraLength);
            tempSecond = random.nextInt(paraLength);

            //交换
            tempValue = resultIndices[tempFirst];
            resultIndices[tempFirst] = resultIndices[tempSecond];
            resultIndices[tempSecond] = tempValue;
        }

        return resultIndices;
    }


    /**
     * @Description: 两个实例的距离
     * @Param: [paraI, paraArray：表示空间中的一个点]
     * @return: double
     */
    public double distance(int paraI, double[] paraArray) {
        int resultDistance = 0;
        double tempDifference;
        switch (distanceMeasure) {
            case MANHATTAN:
                //numAttributes??属性数量
                for (int i = 0; i < dataset.numAttributes() - 1; i++) {
                    tempDifference = dataset.instance(paraI).value(i) - paraArray[i];
                    if (tempDifference < 0) {
                        resultDistance -= tempDifference;
                    } else {
                        resultDistance += tempDifference;
                    }
                }
                break;
            case EUCLIDEAN:
                for (int i = 0; i < dataset.numAttributes() - 1; i++) {
                    tempDifference = dataset.instance(paraI).value(i) - paraArray[i];
                    //这里为什么直接是平方？？应该是为了效率，将开根省略了
                    resultDistance += tempDifference * tempDifference;
                }
                break;
            default:
                System.out.println("Unsupported distance measure: " + distanceMeasure);
        }

        return resultDistance;
    }

    public void clustering() {
        int[] tempOldClusterArray = new int[dataset.numInstances()];
        tempOldClusterArray[0] = -1;
        int[] tempClusterArray = new int[dataset.numInstances()];
        Arrays.fill(tempClusterArray, 0);
        double[][] tempCenters = new double[numClusters][dataset.numAttributes() - 1];

        // 初始化，设置中心
        int[] tempRandomOrders = getRandomIndices(dataset.numInstances());
        for (int i = 0; i < numClusters; i++) {
            for (int j = 0; j < tempCenters[0].length; j++) {
                tempCenters[i][j] = dataset.instance(tempRandomOrders[i]).value(j);
            }
        }

        int[] tempClusterLengths = null;
        //当当前聚类结果与上次相同时，说明已经拟合了
        while (!Arrays.equals(tempOldClusterArray, tempClusterArray)) {
            System.out.println("New loop ...");
            tempOldClusterArray = tempClusterArray;
            tempClusterArray = new int[dataset.numInstances()];

            // 2.1 让每一个实例都被聚类
            int tempNearestCenter;
            double tempNearestDistance;
            double tempDistance;

            for (int i = 0; i < dataset.numInstances(); i++) {
                tempNearestCenter = -1;
                tempNearestDistance = Double.MAX_VALUE;

                //与每个中心比较，取最近的作为聚类结果
                for (int j = 0; j < numClusters; j++) {
                    tempDistance = distance(i, tempCenters[j]);
                    if (tempNearestDistance > tempDistance) {
                        tempNearestDistance = tempDistance;
                        tempNearestCenter = j;
                    }
                }
                tempClusterArray[i] = tempNearestCenter;
            }

            // 2.2 取每类的平均值，重新获得中心点
            //每种类别的数量
            tempClusterLengths = new int[numClusters];
            Arrays.fill(tempClusterLengths, 0);
            double[][] tempNewCenters = new double[numClusters][dataset.numAttributes() - 1];
            // 将每个类别中每个实例的单个属性值加在一起
            for (int i = 0; i < dataset.numInstances(); i++) {
                for (int j = 0; j < tempNewCenters[0].length; j++) {
                    tempNewCenters[tempClusterArray[i]][j] += dataset.instance(i).value(j);
                }
                tempClusterLengths[tempClusterArray[i]]++;
            }

            // 2.3 计算平均中心
            for (int i = 0; i < tempNewCenters.length; i++) {
                for (int j = 0; j < tempNewCenters[0].length; j++) {
                    tempNewCenters[i][j] /= tempClusterLengths[i];
                }
            }

            System.out.println("Now the new centers are: " + Arrays.deepToString(tempNewCenters));
            tempCenters = tempNewCenters;
        }

        // 3. 形成最终的聚类
        clusters = new int[numClusters][];
        int[] tempCounters = new int[numClusters];
        for (int i = 0; i < numClusters; i++) {
            clusters[i] = new int[tempClusterLengths[i]];
        }

        for (int i = 0; i < tempClusterArray.length; i++) {
            clusters[tempClusterArray[i]][tempCounters[tempClusterArray[i]]] = i;
            tempCounters[tempClusterArray[i]]++;
        }

        System.out.println("The clusters are: " + Arrays.deepToString(clusters));
    }

    /**
     * @Description: 聚类测试
     * @Param: []
     * @return: void
     */
    public static void testClustering() {
        KMeans tempKMeans = new KMeans("D:\\Java\\Java学习\\data_set\\iris.arff");
        tempKMeans.setNumClusters(3);
        tempKMeans.clustering();
    }

    public static void main(String arags[]) {
        testClustering();
    }
}

运行结果:

New loop ...
Now the new centers are: [[6.017142857142856, 2.7971428571428567, 4.545714285714286, 1.5214285714285716], [6.964285714285715, 3.089285714285714, 5.932142857142857, 2.107142857142857], [5.005769230769231, 3.3807692307692316, 1.5288461538461537, 0.2749999999999999]]
New loop ...
Now the new centers are: [[6.022666666666666, 2.804, 4.544, 1.5333333333333332], [6.980000000000001, 3.0759999999999996, 5.991999999999998, 2.1039999999999996], [5.005999999999999, 3.4180000000000006, 1.464, 0.2439999999999999]]
New loop ...
Now the new centers are: [[6.022666666666666, 2.804, 4.544, 1.5333333333333332], [6.980000000000001, 3.0759999999999996, 5.991999999999998, 2.1039999999999996], [5.005999999999999, 3.4180000000000006, 1.464, 0.2439999999999999]]
The clusters are: [[50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 101, 106, 110, 111, 112, 113, 114, 115, 116, 119, 121, 123, 126, 127, 133, 137, 138, 139, 141, 142, 145, 146, 147, 148, 149], [100, 102, 103, 104, 105, 107, 108, 109, 117, 118, 120, 122, 124, 125, 128, 129, 130, 131, 132, 134, 135, 136, 140, 143, 144], [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49]