日撸代码300行：第63天(集成学习之 AdaBoosting-1)

 代码来自闵老师”日撸 Java 三百行（61-70天）

日撸 Java 三百行（61-70天，决策树与集成学习）_闵帆的博客-优快云博客

学习过程中理解算法参考了：（十三）通俗易懂理解——Adaboost算法原理 - 知乎 (zhihu.com)

 今天的代码的核心是方法adjustWeights(boolean[] paraCorrectArray, double paraAlpha)。分类正确的实例，权重调整为原值除以Math.exp(paraAlpha)；分类错误的调整为原值乘以Math.exp(paraAlpha)。

测试方法里，之所以for循环到tempCorrectArray长度的一半，仅仅是为了测试。相当于设置弱分类器分类正确了一半。

package machinelearning.adaboosting;

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

import weka.core.Instances;

/**
 * Weighted instances.<br>
 * 
 * @author WX873
 *
 */
public class WeightedInstances extends Instances{
	
	/**
	 * Just the requirement of some classes, any number is ok.
	 */
	private static final long serialVersionUID = 11087456L;
	
	/**
	 * Weights
	 */
	private double[] weights;
	
	/**
	 * **************************************************
	 * The first constructor.
	 * 
	 * @param paraFileReader   The given reader to read data from file.
	 * @throws Exception
	 * **************************************************
	 */
	public WeightedInstances(FileReader paraFileReader) throws Exception{
		// TODO Auto-generated constructor stub
		super(paraFileReader);
		setClassIndex(numAttributes() - 1);
		
		// Initialize weights
		weights = new double[numInstances()];
		double tempAverage = 1.0/numInstances();
		
		for (int i = 0; i < weights.length; i++) {
			weights[i] = tempAverage;
		}//of for i
		System.out.println("Instances weights are: " + Arrays.toString(weights));
	}//of the first constructor
	
	/**
	 * **********************************************************
	 * The second constructor.
	 * 
	 * @param paraInstances
	 * **********************************************************
	 */
	public WeightedInstances(Instances paraInstances) {
		// TODO Auto-generated constructor stub
		super(paraInstances);
		setClassIndex(numAttributes() - 1);
		
		//Initialize weights
		weights = new double[numInstances()];
		double tempAverage = 1.0/numInstances();
		
		for (int i = 0; i < weights.length; i++) {
			weights[i] = tempAverage;
		}//of for i
		System.out.println("Instances weights are: " + Arrays.toString(weights));
	}//of the second constructor
	
	/**
	 * ***************************************************
	 * Getter.
	 * 
	 * @param paraIndex   The given index.
	 * @return    The weight of the given index.
	 * ***************************************************
	 */
	public double getWeight(int paraIndex) {
		return weights[paraIndex];
	}//of getWeight
	
	/**
	 * *****************************************************
	 * Adjust the weights.
	 * 
	 * @param paraCorrectArray  Indicate which instances have been correctly classified.
	 * @param paraAlpha   The weight of the last classifier.
	 * *****************************************************
	 */
	public void adjustWeights(boolean[] paraCorrectArray, double paraAlpha) {
		//Step 1. Calculate alpha.
		double tempIncrease = Math.exp(paraAlpha);
		
		//Step 2. Adjust.
		double tempWeightsSum = 0;  // For normalization.
		for (int i = 0; i < weights.length; i++) {
			if (paraCorrectArray[i]) {
				weights[i] /= tempIncrease;
			} else {
				weights[i] *= tempIncrease;
			}//of if
			tempWeightsSum += weights[i];
		}//of for i
		
		// Step 3. Normalize.
		for (int i = 0; i < weights.length; i++) {
			weights[i] /= tempWeightsSum;
		}//of for i
		
		System.out.println("After adjusting, instances weights are: " + Arrays.toString(weights));
	}//of adjustWeights
	
	/**
	 * *********************************************
	 * Test the method.
	 * *********************************************
	 */
	public void adjustWeightsTest() {
		boolean[] tempCorrectArray = new boolean[numInstances()];
		for (int i = 0; i < tempCorrectArray.length / 2; i++) {    //仅仅是测试adjustWeights（）方法,因为还没有分类器，设置分类正确了一半
			tempCorrectArray[i] = true;
		}//of for i
		
		double tempWeightedError = 0.3;
		
		adjustWeights(tempCorrectArray, tempWeightedError);     //仅仅是测试adjustWeights（）方法,因为还没有分类器
		System.out.println("After adjusting");
		
		System.out.println(toString());
	}//of adjustWeightsTest
	
	/**
	 * ********************************************************
	 * For display.
	 * ********************************************************
	 */
	public String toString() {
		String resultString = "I am a weighted Instances object.\r\n" + "I have " + numInstances() + " instances and "
				+ (numAttributes() - 1) + " conditional attributes.\r\n" + "My weights are: " + Arrays.toString(weights)
				+ "\r\n" + "My data are: \r\n" + super.toString();
		
		return resultString;
	}//of toString
	
	/**
	 * ***********************************************************
	 * The entrance of the program.
	 * 
	 * @param args
	 * ***********************************************************
	 */
	public static void main(String args[]) {
		WeightedInstances tempWeightedInstances = null;
		String tempFilename = "E:/Datasets/UCIdatasets/其他数据集/iris.arff";
		try {
			FileReader tempFileReader = new FileReader(tempFilename);
			tempWeightedInstances = new WeightedInstances(tempFileReader);
			tempFileReader.close();
		} catch (Exception exception1) {
			// TODO: handle exception
			System.out.println("Cannot read the file: " + tempFilename + "\r\n" + exception1);
			System.exit(0);
		}//of try
		
		System.out.println(tempWeightedInstances.toString());
		
		tempWeightedInstances.adjustWeightsTest();
	}//of main

}//of WeightedInstances