决策树与集成学习day3

集成学习之 AdaBoosting (1. 带权数据集)

1、AdaBoosting的基本思想

Adaboost是一种迭代算法，其核心思想是针对同一个训练集训练不同的分类器(弱分类器)，然后把这些弱分类器集合起来，构成一个更强的最终分类器(强分类器)。

其算法本身是通过改变数据分布来实现的，它根据每次训练集之中每个样本的分类是否正确，以及上次的总体分类的准确率，来确定每个样本的权值。将修改过权值的新数据集送给下层分类器进行训练，最后将每次训练得到的分类器最后融合起来，作为最后的决策分类器。使用adaboost分类器可以排除一些不必要的训练数据特徵，并将关键放在关键的训练数据上面。

2、整体流程

（1）先通过对N个训练样本的学习得到第一个弱分类器 ；

（2）将 分错的样本和其他的新数据一起构成一个新的N个的训练样本，通过对这个样本的学习得到第二个弱分类器 ；

 （3）将 和 都分错了的样本加上其他的新样本构成另一个新的N个的训练样本，通过对这个样本的学习得到第三个弱分类器 ；

 （4）最终得到经过提升的强分类器 。

3、实验代码(java版)

package 决策树与集成学习;
 
/**
 * @time 2022/5/15
 * @author Liang Huang
 */

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

import weka.core.Instances;

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.
	 ****************** 
	 */
	public WeightedInstances(FileReader paraFileReader) throws Exception {
		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 The given instance.
	 ****************** 
	 */
	public WeightedInstances(Instances paraInstances) {
		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++) {
			tempCorrectArray[i] = true;
		} // Of for i

		double tempWeightedError = 0.3;

		adjustWeights(tempCorrectArray, tempWeightedError);

		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

	/**
	 ****************** 
	 * For unit test.
	 * 
	 * @param args Not provided.
	 ****************** 
	 */
	public static void main(String args[]) {
		WeightedInstances tempWeightedInstances = null;
		String tempFilename = "d:/data/iris.arff";
		try {
			FileReader tempFileReader = new FileReader(tempFilename);
			tempWeightedInstances = new WeightedInstances(tempFileReader);
			tempFileReader.close();
		} catch (Exception exception1) {
			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 class WeightedInstances