Day 56

kMeans 聚类

一、学习内容

        K-means中心思想:事先确定常数K,常数K意味着最终的聚类类别数,首先随机选定初始点为质心,并通过计算每一个样本与质心之间的相似度(这里为欧式距离),将样本点归到最相似的类中,接着,重新计算每个类的质心(即为类中心),重复这样的过程,直到质心不再改变,最终就确定了每个样本所属的类别以及每个类的质心。

package machinelearning.kmeans;

import java.io.FileReader;
import java.util.Arrays;
import java.util.Random;
import weka.core.Instances;

/**
 * kMeans clustering.
 * @author Fan Min minfanphd@163.com.
 */
 public class KMeans {

	/**
	 * Manhattan distance.
	 */
	public static final int MANHATTAN = 0;

	/**
	 * Euclidean distance.
	 */
	public static final int EUCLIDEAN = 1;

	/**
	 * The distance measure.
	 */
	public int distanceMeasure = EUCLIDEAN;

	/**
	 * A random instance;
	 */
	public static final Random random = new Random();

	/**
	 * The data.
	 */
	Instances dataset;

	/**
	 * The number of clusters.
	 */
	int numClusters = 2;

	/**
	 * The clusters.
	 */
	int[][] clusters;

	/**
	 ******************************* 
	 * The first constructor.
	 * 
	 * @param paraFilename
	 *            The data filename.
	 ******************************* 
	 */
	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);
		} // Of try
	}// Of the first constructor

	/**
	 ******************************* 
	 * A setter.
	 ******************************* 
	 */
	public void setNumClusters(int paraNumClusters) {
		numClusters = paraNumClusters;
	}// Of the setter

	/**
	 *********************
	 * Get a random indices for data randomization.
	 * 
	 * @param paraLength
	 *            The length of the sequence.
	 * @return An array of indices, e.g., {4, 3, 1, 5, 0, 2} with length 6.
	 *********************
	 */
	public static int[] getRandomIndices(int paraLength) {
		int[] resultIndices = new int[paraLength];

		// Step 1. Initialize.
		for (int i = 0; i < paraLength; i++) {
			resultIndices[i] = i;
		} // Of for i

		// Step 2. Randomly swap.
		int tempFirst, tempSecond, tempValue;
		for (int i = 0; i < paraLength; i++) {
			// Generate two random indices.
			tempFirst = random.nextInt(paraLength);
			tempSecond = random.nextInt(paraLength);

			// Swap.
			tempValue = resultIndices[tempFirst];
			resultIndices[tempFirst] = resultIndices[tempSecond];
			resultIndices[tempSecond] = tempValue;
		} // Of for i

		return resultIndices;
	}// Of getRandomIndices

	/**
	 *********************
	 * The distance between two instances.
	 * 
	 * @param paraI
	 *            The index of the first instance.
	 * @param paraArray
	 *            The array representing a point in the space.
	 * @return The distance.
	 *********************
	 */
	public double distance(int paraI, double[] paraArray) {
		int resultDistance = 0;
		double tempDifference;
		switch (distanceMeasure) {
		case MANHATTAN:
			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;
				} // Of if
			} // Of for i
			break;

		case EUCLIDEAN:
			for (int i = 0; i < dataset.numAttributes() - 1; i++) {
				tempDifference = dataset.instance(paraI).value(i) - paraArray[i];
				resultDistance += tempDifference * tempDifference;
			} // Of for i
			break;
		default:
			System.out.println("Unsupported distance measure: " + distanceMeasure);
		}// Of switch

		return resultDistance;
	}// Of distance

	/**
	 ******************************* 
	 * Clustering.
	 ******************************* 
	 */
	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];

		// Step 1. Initialize centers.
		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);
			} // Of for j
		} // Of for i

		int[] tempClusterLengths = null;
		while (!Arrays.equals(tempOldClusterArray, tempClusterArray)) {
			System.out.println("New loop ...");
			tempOldClusterArray = tempClusterArray;
			tempClusterArray = new int[dataset.numInstances()];

			// Step 2.1 Minimization. Assign cluster to each instance.
			int tempNearestCenter;
			double tempNearestDistance;
			double tempDistance;

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

				for (int j = 0; j < numClusters; j++) {
					tempDistance = distance(i, tempCenters[j]);
					if (tempNearestDistance > tempDistance) {
						tempNearestDistance = tempDistance;
						tempNearestCenter = j;
					} // Of if
				} // Of for j
				tempClusterArray[i] = tempNearestCenter;
			} // Of for i

			// Step 2.2 Mean. Find new centers.
			tempClusterLengths = new int[numClusters];
			Arrays.fill(tempClusterLengths, 0);
			double[][] tempNewCenters = new double[numClusters][dataset.numAttributes() - 1];
			// Arrays.fill(tempNewCenters, 0);
			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);
				} // Of for j
				tempClusterLengths[tempClusterArray[i]]++;
			} // Of for i

			// Step 2.3 Now average
			for (int i = 0; i < tempNewCenters.length; i++) {
				for (int j = 0; j < tempNewCenters[0].length; j++) {
					tempNewCenters[i][j] /= tempClusterLengths[i];
				} // Of for j
			} // Of for i

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

		// Step 3. Form clusters.
		clusters = new int[numClusters][];
		int[] tempCounters = new int[numClusters];
		for (int i = 0; i < numClusters; i++) {
			clusters[i] = new int[tempClusterLengths[i]];
		} // Of for i

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

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

	/**
	 ******************************* 
	 * Clustering.
	 ******************************* 
	 */
	public static void testClustering() {
		KMeans tempKMeans = new KMeans("D:/data/iris.arff");
		tempKMeans.setNumClusters(3);
		tempKMeans.clustering();
	}// Of testClustering

	/**
	 ************************* 
	 * A testing method.
	 ************************* 
	 */
	public static void main(String arags[]) {
		testClustering();
	}// Of main

}// Of class KMeans

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值