JavaDay11

学习来源：日撸 Java 三百行（51-60天，kNN 与 NB）_闵帆的博客——CSDN博客

一、KNN分类器

        1. KNN是指当对目标进行预测的时候，根据k个最近邻居的投票来对目标的类别进行预测。

        2. KNN是没有学习过程的，直接根据已有数据进行预测。

        3. KNN的综合性能较好，在大多数情况下KNN都具有较好的效果。

        4. 以下是KNN算法的例子——对花朵进行分类

package JavaDay11;

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

import weka.core.*;

/**
 * @author Kexiong Wang
 *
 * @date 2022年5月2日
 *
 * KNN分类算法
 */

public class KnnClassification {
    //曼哈顿距离
    public static final int MANHATTAN = 0;

    //欧几里得距离
    public static final int EUCLIDEAN = 1;

    //测量距离
    public int distanceMeasure = EUCLIDEAN;

    //随机乱序
    public static final Random random = new Random();

    //邻居数（K）
    int numNeighbors = 7;

    //全数据集
    Instances dataset;

    //训练集
    int[] trainingSet;

    //测试集
    int[] testingSet;

    //预测分类
    int[] predictions;

    /**
     *********************
     * 构造函数
     *
     * @param paraFilename  文件名
     *********************
     */
    public KnnClassification(String paraFilename) {
        try {
            FileReader fileReader = new FileReader(paraFilename);
            dataset = new Instances(fileReader);
            //最后一个属性是种类
            dataset.setClassIndex(dataset.numAttributes() - 1);
            fileReader.close();
        } catch (Exception ee) {
            System.out.println("Error occurred while trying to read \'" + paraFilename + "\' in KnnClassification constructor.\r\n" + ee);
            System.exit(0);
        }//Of try
    }//Of KnnClassification

    /**
     *********************
     * 将数据集乱序
     *
     * @param paraLength  数据集长度
     * @return            乱序后的数据集
     *********************
     */
    public static int[] getRandomIndices(int paraLength) {
        int[] resultIndices = new int[paraLength];

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

        //随机交换数据项
        int tempFirst, tempSecond, tempValue;
        for (int i = 0; i < paraLength; i++) {
            //生成两个随机序号
            tempFirst = random.nextInt(paraLength);
            tempSecond = random.nextInt(paraLength);

            //交换序号对应的数据项
            tempValue = resultIndices[tempFirst];
            resultIndices[tempFirst] = resultIndices[tempSecond];
            resultIndices[tempSecond] = tempValue;
        }//Of for i

        return resultIndices;
    }//Of getRandomIndices

    /**
     *********************
     * 将数据集分为测试集和训练集
     *
     * @param paraTrainingFraction  训练集占数据集的比例
     *********************
     */
    public void splitTrainingTesting(double paraTrainingFraction) {
        //数据集长度
        int tempSize = dataset.numInstances();
        //乱序后的数据集序号
        int[] tempIndices = getRandomIndices(tempSize);
        //训练集长度
        int tempTrainingSize = (int) (tempSize * paraTrainingFraction);

        //初始化训练集和测试集空间
        trainingSet = new int[tempTrainingSize];
        testingSet = new int[tempSize - tempTrainingSize];

        for (int i = 0; i < tempTrainingSize; i++) {
            trainingSet[i] = tempIndices[i];
        }//Of for i

        for (int i = 0; i < tempSize - tempTrainingSize; i++) {
            testingSet[i] = tempIndices[tempTrainingSize + i];
        }//Of for i
    }//Of splitTrainingTesting

    /**
     *********************
     * 对所有测试集进行预测，结果保存在prediction数组中
     *********************
     */
    public void predict() {
        predictions = new int[testingSet.length];
        for (int i = 0; i < predictions.length; i++) {
            predictions[i] = predict(testingSet[i]);
        }//Of for i
    }//Of predict

    /**
     *********************
     * 对给定数据项进行预测
     *
     * @return 返回预测结果
     *********************
     */
    public int predict(int paraIndex) {
        int[] tempNeighbors = computeNearests(paraIndex);
        int resultPrediction = simpleVoting(tempNeighbors);

        return resultPrediction;
    }//Of predict

    /**
     *********************
     * 两个数据项的距离
     *
     * @param paraI  第一个数据项下标
     * @param paraJ  第二个数据项下标
     * @return       距离
     *********************
     */
    public double distance(int paraI, int paraJ) {
        double resultDistance = 0;
        double tempDifference;
        switch (distanceMeasure) {
            case MANHATTAN:
                for (int i = 0; i < dataset.numAttributes() - 1; i++) {
                    tempDifference = dataset.instance(paraI).value(i) - dataset.instance(paraJ).value(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) - dataset.instance(paraJ).value(i);
                    resultDistance += tempDifference * tempDifference;
                }//Of for i
                break;
            default:
                System.out.println("Unsupported distance measure: " + distanceMeasure);
        }//Of switch

        return resultDistance;
    }//Of distance

    /**
     *********************
     * 预测分类的准确度
     *
     * @return 准确度
     *********************
     */
    public double getAccuracy() {
        double tempCorrect = 0;
        for (int i = 0; i < predictions.length; i++) {
            if (predictions[i] == dataset.instance(testingSet[i]).classValue()) {
                tempCorrect++;
            }//Of if
        }//Of for i

        return tempCorrect / testingSet.length;
    }//Of getAccuracy

    /**
     ************************************
     * 寻找最近的k个邻居，每次扫描找到一个邻居
     *
     * @param paraCurrent  要计算的当前数据项
     * @return             最近的数据项下标
     ************************************
     */
    public int[] computeNearests(int paraCurrent) {
        int[] resultNearests = new int[numNeighbors];
        boolean[] tempSelected = new boolean[trainingSet.length];
        double tempMinimalDistance;
        int tempMinimalIndex = 0;

        //计算到所有其他数据项的距离
        double[] tempDistances = new double[trainingSet.length];
        for (int i = 0; i < trainingSet.length; i ++) {
            tempDistances[i] = distance(paraCurrent, trainingSet[i]);
        }//Of for i

        //选择最近的k个数据项
        for (int i = 0; i < numNeighbors; i++) {
            tempMinimalDistance = Double.MAX_VALUE;

            for (int j = 0; j < trainingSet.length; j++) {
                if (tempSelected[j]) {
                    continue;
                }//Of if

                if (tempDistances[j] < tempMinimalDistance) {
                    tempMinimalDistance = tempDistances[j];
                    tempMinimalIndex = j;
                }//Of if
            }//Of for j

            resultNearests[i] = trainingSet[tempMinimalIndex];
            tempSelected[tempMinimalIndex] = true;
        }//Of for i

        System.out.println("The nearest of " + paraCurrent + " are: " + Arrays.toString(resultNearests));
        return resultNearests;
    }//Of computeNearests

    /**
     ************************************
     * 由邻居投票决定分类
     *
     * @param paraNeighbors  邻居的下标
     * @return               预测的分类
     ************************************
     */
    public int simpleVoting(int[] paraNeighbors) {
        int[] tempVotes = new int[dataset.numClasses()];
        for (int i = 0; i < paraNeighbors.length; i++) {
            tempVotes[(int) dataset.instance(paraNeighbors[i]).classValue()]++;
        }//Of for i

        int tempMaximalVotingIndex = 0;
        int tempMaximalVoting = 0;
        for (int i = 0; i < dataset.numClasses(); i++) {
            if (tempVotes[i] > tempMaximalVoting) {
                tempMaximalVoting = tempVotes[i];
                tempMaximalVotingIndex = i;
            }//Of if
        }//Of for i

        return tempMaximalVotingIndex;
    }//Of simpleVoting

    /**
     *********************
     * 程序入口
     *
     * @param args  暂未使用
     *********************
     */
    public static void main(String args[]) {
        KnnClassification tempClassifier = new KnnClassification("D:/iris.arff");
        tempClassifier.splitTrainingTesting(0.8);
        tempClassifier.predict();
        System.out.println("The accuracy of the classifier is: " + tempClassifier.getAccuracy());
    }//Of main
}//Of class KnnClassification

其中用到的数据集iris.arff为

@RELATION iris

@ATTRIBUTE sepallength	REAL
@ATTRIBUTE sepalwidth 	REAL
@ATTRIBUTE petallength 	REAL
@ATTRIBUTE petalwidth	REAL
@ATTRIBUTE class 	{Iris-setosa,Iris-versicolor,Iris-virginica}

@DATA
5.1,3.5,1.4,0.2,Iris-setosa
4.9,3.0,1.4,0.2,Iris-setosa
4.7,3.2,1.3,0.2,Iris-setosa
4.6,3.1,1.5,0.2,Iris-setosa
5.0,3.6,1.4,0.2,Iris-setosa
5.4,3.9,1.7,0.4,Iris-setosa
4.6,3.4,1.4,0.3,Iris-setosa
5.0,3.4,1.5,0.2,Iris-setosa
4.4,2.9,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.4,3.7,1.5,0.2,Iris-setosa
4.8,3.4,1.6,0.2,Iris-setosa
4.8,3.0,1.4,0.1,Iris-setosa
4.3,3.0,1.1,0.1,Iris-setosa
5.8,4.0,1.2,0.2,Iris-setosa
5.7,4.4,1.5,0.4,Iris-setosa
5.4,3.9,1.3,0.4,Iris-setosa
5.1,3.5,1.4,0.3,Iris-setosa
5.7,3.8,1.7,0.3,Iris-setosa
5.1,3.8,1.5,0.3,Iris-setosa
5.4,3.4,1.7,0.2,Iris-setosa
5.1,3.7,1.5,0.4,Iris-setosa
4.6,3.6,1.0,0.2,Iris-setosa
5.1,3.3,1.7,0.5,Iris-setosa
4.8,3.4,1.9,0.2,Iris-setosa
5.0,3.0,1.6,0.2,Iris-setosa
5.0,3.4,1.6,0.4,Iris-setosa
5.2,3.5,1.5,0.2,Iris-setosa
5.2,3.4,1.4,0.2,Iris-setosa
4.7,3.2,1.6,0.2,Iris-setosa
4.8,3.1,1.6,0.2,Iris-setosa
5.4,3.4,1.5,0.4,Iris-setosa
5.2,4.1,1.5,0.1,Iris-setosa
5.5,4.2,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.0,3.2,1.2,0.2,Iris-setosa
5.5,3.5,1.3,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
4.4,3.0,1.3,0.2,Iris-setosa
5.1,3.4,1.5,0.2,Iris-setosa
5.0,3.5,1.3,0.3,Iris-setosa
4.5,2.3,1.3,0.3,Iris-setosa
4.4,3.2,1.3,0.2,Iris-setosa
5.0,3.5,1.6,0.6,Iris-setosa
5.1,3.8,1.9,0.4,Iris-setosa
4.8,3.0,1.4,0.3,Iris-setosa
5.1,3.8,1.6,0.2,Iris-setosa
4.6,3.2,1.4,0.2,Iris-setosa
5.3,3.7,1.5,0.2,Iris-setosa
5.0,3.3,1.4,0.2,Iris-setosa
7.0,3.2,4.7,1.4,Iris-versicolor
6.4,3.2,4.5,1.5,Iris-versicolor
6.9,3.1,4.9,1.5,Iris-versicolor
5.5,2.3,4.0,1.3,Iris-versicolor
6.5,2.8,4.6,1.5,Iris-versicolor
5.7,2.8,4.5,1.3,Iris-versicolor
6.3,3.3,4.7,1.6,Iris-versicolor
4.9,2.4,3.3,1.0,Iris-versicolor
6.6,2.9,4.6,1.3,Iris-versicolor
5.2,2.7,3.9,1.4,Iris-versicolor
5.0,2.0,3.5,1.0,Iris-versicolor
5.9,3.0,4.2,1.5,Iris-versicolor
6.0,2.2,4.0,1.0,Iris-versicolor
6.1,2.9,4.7,1.4,Iris-versicolor
5.6,2.9,3.6,1.3,Iris-versicolor
6.7,3.1,4.4,1.4,Iris-versicolor
5.6,3.0,4.5,1.5,Iris-versicolor
5.8,2.7,4.1,1.0,Iris-versicolor
6.2,2.2,4.5,1.5,Iris-versicolor
5.6,2.5,3.9,1.1,Iris-versicolor
5.9,3.2,4.8,1.8,Iris-versicolor
6.1,2.8,4.0,1.3,Iris-versicolor
6.3,2.5,4.9,1.5,Iris-versicolor
6.1,2.8,4.7,1.2,Iris-versicolor
6.4,2.9,4.3,1.3,Iris-versicolor
6.6,3.0,4.4,1.4,Iris-versicolor
6.8,2.8,4.8,1.4,Iris-versicolor
6.7,3.0,5.0,1.7,Iris-versicolor
6.0,2.9,4.5,1.5,Iris-versicolor
5.7,2.6,3.5,1.0,Iris-versicolor
5.5,2.4,3.8,1.1,Iris-versicolor
5.5,2.4,3.7,1.0,Iris-versicolor
5.8,2.7,3.9,1.2,Iris-versicolor
6.0,2.7,5.1,1.6,Iris-versicolor
5.4,3.0,4.5,1.5,Iris-versicolor
6.0,3.4,4.5,1.6,Iris-versicolor
6.7,3.1,4.7,1.5,Iris-versicolor
6.3,2.3,4.4,1.3,Iris-versicolor
5.6,3.0,4.1,1.3,Iris-versicolor
5.5,2.5,4.0,1.3,Iris-versicolor
5.5,2.6,4.4,1.2,Iris-versicolor
6.1,3.0,4.6,1.4,Iris-versicolor
5.8,2.6,4.0,1.2,Iris-versicolor
5.0,2.3,3.3,1.0,Iris-versicolor
5.6,2.7,4.2,1.3,Iris-versicolor
5.7,3.0,4.2,1.2,Iris-versicolor
5.7,2.9,4.2,1.3,Iris-versicolor
6.2,2.9,4.3,1.3,Iris-versicolor
5.1,2.5,3.0,1.1,Iris-versicolor
5.7,2.8,4.1,1.3,Iris-versicolor
6.3,3.3,6.0,2.5,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
7.1,3.0,5.9,2.1,Iris-virginica
6.3,2.9,5.6,1.8,Iris-virginica
6.5,3.0,5.8,2.2,Iris-virginica
7.6,3.0,6.6,2.1,Iris-virginica
4.9,2.5,4.5,1.7,Iris-virginica
7.3,2.9,6.3,1.8,Iris-virginica
6.7,2.5,5.8,1.8,Iris-virginica
7.2,3.6,6.1,2.5,Iris-virginica
6.5,3.2,5.1,2.0,Iris-virginica
6.4,2.7,5.3,1.9,Iris-virginica
6.8,3.0,5.5,2.1,Iris-virginica
5.7,2.5,5.0,2.0,Iris-virginica
5.8,2.8,5.1,2.4,Iris-virginica
6.4,3.2,5.3,2.3,Iris-virginica
6.5,3.0,5.5,1.8,Iris-virginica
7.7,3.8,6.7,2.2,Iris-virginica
7.7,2.6,6.9,2.3,Iris-virginica
6.0,2.2,5.0,1.5,Iris-virginica
6.9,3.2,5.7,2.3,Iris-virginica
5.6,2.8,4.9,2.0,Iris-virginica
7.7,2.8,6.7,2.0,Iris-virginica
6.3,2.7,4.9,1.8,Iris-virginica
6.7,3.3,5.7,2.1,Iris-virginica
7.2,3.2,6.0,1.8,Iris-virginica
6.2,2.8,4.8,1.8,Iris-virginica
6.1,3.0,4.9,1.8,Iris-virginica
6.4,2.8,5.6,2.1,Iris-virginica
7.2,3.0,5.8,1.6,Iris-virginica
7.4,2.8,6.1,1.9,Iris-virginica
7.9,3.8,6.4,2.0,Iris-virginica
6.4,2.8,5.6,2.2,Iris-virginica
6.3,2.8,5.1,1.5,Iris-virginica
6.1,2.6,5.6,1.4,Iris-virginica
7.7,3.0,6.1,2.3,Iris-virginica
6.3,3.4,5.6,2.4,Iris-virginica
6.4,3.1,5.5,1.8,Iris-virginica
6.0,3.0,4.8,1.8,Iris-virginica
6.9,3.1,5.4,2.1,Iris-virginica
6.7,3.1,5.6,2.4,Iris-virginica
6.9,3.1,5.1,2.3,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
6.8,3.2,5.9,2.3,Iris-virginica
6.7,3.3,5.7,2.5,Iris-virginica
6.7,3.0,5.2,2.3,Iris-virginica
6.3,2.5,5.0,1.9,Iris-virginica
6.5,3.0,5.2,2.0,Iris-virginica
6.2,3.4,5.4,2.3,Iris-virginica
5.9,3.0,5.1,1.8,Iris-virginica

运行结果