机器学习-06-AdaBoosting-1带权数据集

Boosting算法

Boosting算法的工作机制是首先从训练集用初始权重训练出一个弱学习器1，根据弱学习的学习误差率表现来更新训练样本的权重，使得之前弱学习器1学习误差率高的训练样本点的权重变高，使得这些误差率高的点在后面的弱学习器2中得到更多的重视。然后基于调整权重后的训练集来训练弱学习器2.，如此重复进行，直到弱学习器数达到事先指定的数目T，最终将这T个弱学习器通过集合策略进行整合，得到最终的强学习器。主要思想是“三个臭皮匠顶个诸葛亮”。

弱学习器

指泛化性能略优于随机猜测的学习器：例如在二分类问题的精度略高于50%的分类器。

强学习器

指分类精度90%以上的学习器。

函数：调整数据集权重。

输入：分类正确数组和权重调整大小参数。

输出：无。

数据集的权重

对每一条数据赋予一定权重。

分类正确数组

[true, true, false, false, true]表示对第1，2，5条数据分类成功。第3，4条数据分类失败。

函数步骤：

1.计算权重变化大小：

2.对每个权重值：

3.        如果分类成功，就权重除以

4.        如果分类失败，就权重乘以

5.将所有权重值归一化。 

代码：

package 日撸Java300行_61_70;


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

import weka.core.Instances;


public class WeightedInstances extends Instances {

	
	private static final long serialVersionUID = 11087456L;

	
	private double[] weights;

	
	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

	
	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

	
	public double getWeight(int paraIndex) {
		return weights[paraIndex];
	} // Of getWeight

	
	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

	
	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");

	} // Of adjustWeightsTest

	
	public String toString() {
		String resultString = "I am a weighted Instances object.rn" + "I have " + numInstances() + " instances and "
				+ (numAttributes() - 1) + " conditional attributes.rn" + "My weights are: " + Arrays.toString(weights)
				+ "rn" ;

		return resultString;
	} // Of toString

	
	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 + "rn" + exception1);
			System.exit(0);
		} // Of try

		System.out.println(tempWeightedInstances.toString());

		tempWeightedInstances.adjustWeightsTest();
	} // Of main

} // Of class WeightedInstances

截图：