java代码实现Kmeans聚类算法，训练集的文件类型为xls，java所有代码都写在k4.java中

好的，我了解了您的要求。以下是Java代码实现K-means聚类算法，可以读取xls格式的训练集文件，并且所有代码都写在k4.java中：

import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.WorkbookFactory;

public class k4 {

    public static void main(String[] args) throws IOException {
        int k = 3; // 聚类数
        int maxIter = 100; // 最大迭代次数
        double[][] dataSet = readExcel("data.xls"); // 读取训练集
        int m = dataSet.length; // 样本数
        int n = dataSet[0].length; // 特征数
        int[] clusterAssment = new int[m]; // 记录每个样本所属的簇
        double[][] centroids = randCent(dataSet, k); // 随机初始化簇质心
        for (int i = 0; i < maxIter; i++) {
            boolean clusterChanged = false;
            // 遍历每个样本，将其归入最近的簇
            for (int j = 0; j < m; j++) {
                double minDist = Double.MAX_VALUE;
                int minIndex = -1;
                for (int l = 0; l < k; l++) {
                    double dist = euclDistance(dataSet[j], centroids[l]);
                    if (dist < minDist) {
                        minDist = dist;
                        minIndex = l;
                    }
                }
                if (clusterAssment[j] != minIndex) {
                    clusterChanged = true;
                    clusterAssment[j] = minIndex;
                }
            }
            // 重新计算每个簇的质心
            for (int l = 0; l < k; l++) {
                List<double[]> pointsInCluster = new ArrayList<double[]>();
                for (int j = 0; j < m; j++) {
                    if (clusterAssment[j] == l) {
                        pointsInCluster.add(dataSet[j]);
                    }
                }
                if (!pointsInCluster.isEmpty()) {
                    centroids[l] = mean(pointsInCluster.toArray(new double[pointsInCluster.size()][n]));
                }
            }
            // 如果簇分配不再变化，退出循环
            if (!clusterChanged) {
                break;
            }
        }
        // 输出最终结果
        System.out.println("Cluster centroids:\n");
        for (int i = 0; i < k; i++) {
            System.out.print("(");
            for (int j = 0; j < n; j++) {
                System.out.print(centroids[i][j]);
                if (j < n - 1) {
                    System.out.print(", ");
                }
            }
            System.out.println(")");
        }
        System.out.println("\nCluster assignments:");
        for (int i = 0; i < m; i++) {
            System.out.printf("Sample %d -> Cluster %d%n", i + 1, clusterAssment[i] + 1);
        }
    }

    // 计算两个样本之间的欧氏距离
    private static double euclDistance(double[] vec1, double[] vec2) {
        double sum = 0.0;
        for (int i = 0; i < vec1.length; i++) {
            sum += Math.pow(vec1[i] - vec2[i], 2);
        }
        return Math.sqrt(sum);
    }

    // 随机初始化簇质心
    private static double[][] randCent(double[][] dataSet, int k) {
        int n = dataSet[0].length;
        double[][] centroids = new double[k][n];
        Random rand = new Random();
        for (int i = 0; i < k; i++) {
            int index = rand.nextInt(dataSet.length);
            for (int j = 0; j < n; j++) {
                centroids[i][j] = dataSet[index][j];
            }
        }
        return centroids;
    }

    // 计算一组样本的均值
    private static double[] mean(double[][] points) {
        int n = points[0].length;
        double[] mean = new double[n];
        for (int i = 0; i < n; i++) {
            double sum = 0.0;
            for (double[] point : points) {
                sum += point[i];
            }
            mean[i] = sum / points.length;
        }
        return mean;
    }

    // 从 Excel 文件中读取数据集
    private static double[][] readExcel(String filePath) throws IOException {
        FileInputStream file = new FileInputStream(filePath);
        Workbook workbook = WorkbookFactory.create(file);
        Sheet sheet = workbook.getSheetAt(0);
        int firstRowNum = sheet.getFirstRowNum();
        int lastRowNum = sheet.getLastRowNum();
        int firstCellNum = sheet.getRow(firstRowNum).getFirstCellNum();
        int lastCellNum = sheet.getRow(firstRowNum).getLastCellNum();
        double[][] dataSet = new double[lastRowNum - firstRowNum + 1][lastCellNum - firstCellNum];
        for (int i = firstRowNum; i <= lastRowNum; i++) {
            Row row = sheet.getRow(i);
            for (int j = firstCellNum; j < lastCellNum; j++) {
                Cell cell = row.getCell(j);
                if (cell.getCellType() == Cell.CELL_TYPE_NUMERIC) {
                    dataSet[i - firstRowNum][j - firstCellNum] = cell.getNumericCellValue();
                } else {
                    throw new IOException("Invalid cell type in data file");
                }
            }
        }
        return dataSet;
    }

}

注意：以上代码中使用了 Apache POI 库来读取 xls 文件，需要先下载并添加到项目中。另外，此代码实现的 K-means 算法是经典的 Lloyd 算法，对大数据集和高维数据的效果可能不佳，建议使用优化后的 K-means 算法或其他聚类算法。