决策树与集成学习day4

学习来源：https://blog.csdn.net/minfanphd/article/details/116974889

集成学习之 AdaBoosting (树桩分类器)

1、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)。
2、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。
3、做了一个超类, 用于支持不同的基础分类器. 这里为了减少代码量, 只实现了树桩分类器。
4、树桩分类器每次只将数据分成两堆, 与决策树相比, 简单至极。
5、抽象分类器代码。
6、今天对代码再次进行了理解。

package 决策树与集成学习;
 
/**
 * @time 2022/5/19
 * @author Liang Huang
 */

import java.util.Random;
import weka.core.Instance;

public abstract class SimpleClassifier {

	/**
	 * The index of the current attribute.
	 */
	int selectedAttribute;

	/**
	 * Weighted data.
	 */
	WeightedInstances weightedInstances;

	/**
	 * The accuracy on the training set.
	 */
	double trainingAccuracy;

	/**
	 * The number of classes. For binary classification it is 2.
	 */
	int numClasses;

	/**
	 * The number of instances.
	 */
	int numInstances;

	/**
	 * The number of conditional attributes.
	 */
	int numConditions;

	/**
	 * For random number generation.
	 */
	Random random = new Random();

	/**
	 ****************** 
	 * The first constructor.
	 * 
	 * @param paraWeightedInstances The given instances.
	 ****************** 
	 */
	public SimpleClassifier(WeightedInstances paraWeightedInstances) {
		weightedInstances = paraWeightedInstances;

		numConditions = weightedInstances.numAttributes() - 1;
		numInstances = weightedInstances.numInstances();
		numClasses = weightedInstances.classAttribute().numValues();
	}// Of the first constructor

	/**
	 ****************** 
	 * Train the classifier.
	 ****************** 
	 */
	public abstract void train();

	/**
	 ****************** 
	 * Classify an instance.
	 * 
	 * @param paraInstance The given instance.
	 * @return Predicted label.
	 ****************** 
	 */
	public abstract int classify(Instance paraInstance);

	/**
	 ****************** 
	 * Which instances in the training set are correctly classified.
	 * 
	 * @return The correctness array.
	 ****************** 
	 */
	public boolean[] computeCorrectnessArray() {
		boolean[] resultCorrectnessArray = new boolean[weightedInstances.numInstances()];
		for (int i = 0; i < resultCorrectnessArray.length; i++) {
			Instance tempInstance = weightedInstances.instance(i);
			if ((int) (tempInstance.classValue()) == classify(tempInstance)) {
				resultCorrectnessArray[i] = true;
			} // Of if

			// System.out.print("\t" + classify(tempInstance));
		} // Of for i
			// System.out.println();
		return resultCorrectnessArray;
	}// Of computeCorrectnessArray

	/**
	 ****************** 
	 * Compute the accuracy on the training set.
	 * 
	 * @return The training accuracy.
	 ****************** 
	 */
	public double computeTrainingAccuracy() {
		double tempCorrect = 0;
		boolean[] tempCorrectnessArray = computeCorrectnessArray();
		for (int i = 0; i < tempCorrectnessArray.length; i++) {
			if (tempCorrectnessArray[i]) {
				tempCorrect++;
			} // Of if
		} // Of for i

		double resultAccuracy = tempCorrect / tempCorrectnessArray.length;

		return resultAccuracy;
	}// Of computeTrainingAccuracy

	/**
	 ****************** 
	 * Compute the weighted error on the training set. It is at least 1e-6 to
	 * avoid NaN.
	 * 
	 * @return The weighted error.
	 ****************** 
	 */
	public double computeWeightedError() {
		double resultError = 0;
		boolean[] tempCorrectnessArray = computeCorrectnessArray();
		for (int i = 0; i < tempCorrectnessArray.length; i++) {
			if (!tempCorrectnessArray[i]) {
				resultError += weightedInstances.getWeight(i);
			} // Of if
		} // Of for i

		if (resultError < 1e-6) {
			resultError = 1e-6;
		} // Of if

		return resultError;
	}// Of computeWeightedError
} // Of class SimpleClassifier

6、树桩分类器代码.

package 决策树与集成学习;
 
/**
 * @time 2022/5/19
 * @author Liang Huang
 */
import weka.core.Instance;
import java.io.FileReader;
import java.util.*;

public class StumpClassifier extends SimpleClassifier {

	/**
	 * The best cut for the current attribute on weightedInstances.
	 */
	double bestCut;

	/**
	 * The class label for attribute value less than bestCut.
	 */
	int leftLeafLabel;

	/**
	 * The class label for attribute value no less than bestCut.
	 */
	int rightLeafLabel;

	/**
	 ****************** 
	 * The only constructor.
	 * 
	 * @param paraWeightedInstances The given instances.
	 ****************** 
	 */
	public StumpClassifier(WeightedInstances paraWeightedInstances) {
		super(paraWeightedInstances);
	}// Of the only constructor

	/**
	 ****************** 
	 * Train the classifier.
	 ****************** 
	 */
	public void train() {
		// Step 1. Randomly choose an attribute.
		selectedAttribute = random.nextInt(numConditions);

		// Step 2. Find all attribute values and sort.
		double[] tempValuesArray = new double[numInstances];
		for (int i = 0; i < tempValuesArray.length; i++) {
			tempValuesArray[i] = weightedInstances.instance(i).value(selectedAttribute);
		} // Of for i
		Arrays.sort(tempValuesArray);

		// Step 3. Initialize, classify all instances as the same with the
		// original cut.
		int tempNumLabels = numClasses;
		double[] tempLabelCountArray = new double[tempNumLabels];
		int tempCurrentLabel;

		// Step 3.1 Scan all labels to obtain their counts.
		for (int i = 0; i < numInstances; i++) {
			// The label of the ith instance
			tempCurrentLabel = (int) weightedInstances.instance(i).classValue();
			tempLabelCountArray[tempCurrentLabel] += weightedInstances.getWeight(i);
		} // Of for i

		// Step 3.2 Find the label with the maximal count.
		double tempMaxCorrect = 0;
		int tempBestLabel = -1;
		for (int i = 0; i < tempLabelCountArray.length; i++) {
			if (tempMaxCorrect < tempLabelCountArray[i]) {
				tempMaxCorrect = tempLabelCountArray[i];
				tempBestLabel = i;
			} // Of if
		} // Of for i

		// Step 3.3 The cut is a little bit smaller than the minimal value.
		bestCut = tempValuesArray[0] - 0.1;
		leftLeafLabel = tempBestLabel;
		rightLeafLabel = tempBestLabel;

		// Step 4. Check candidate cuts one by one.
		// Step 4.1 To handle multi-class data, left and right.
		double tempCut;
		double[][] tempLabelCountMatrix = new double[2][tempNumLabels];

		for (int i = 0; i < tempValuesArray.length - 1; i++) {
			// Step 4.1 Some attribute values are identical, ignore them.
			if (tempValuesArray[i] == tempValuesArray[i + 1]) {
				continue;
			} // Of if
			tempCut = (tempValuesArray[i] + tempValuesArray[i + 1]) / 2;

			// Step 4.2 Scan all labels to obtain their counts wrt. the cut.
			// Initialize again since it is used many times.
			for (int j = 0; j < 2; j++) {
				for (int k = 0; k < tempNumLabels; k++) {
					tempLabelCountMatrix[j][k] = 0;
				} // Of for k
			} // Of for j

			for (int j = 0; j < numInstances; j++) {
				// The label of the jth instance
				tempCurrentLabel = (int) weightedInstances.instance(j).classValue();
				if (weightedInstances.instance(j).value(selectedAttribute) < tempCut) {
					tempLabelCountMatrix[0][tempCurrentLabel] += weightedInstances.getWeight(j);
				} else {
					tempLabelCountMatrix[1][tempCurrentLabel] += weightedInstances.getWeight(j);
				} // Of if
			} // Of for i

			// Step 4.3 Left leaf.
			double tempLeftMaxCorrect = 0;
			int tempLeftBestLabel = 0;
			for (int j = 0; j < tempLabelCountMatrix[0].length; j++) {
				if (tempLeftMaxCorrect < tempLabelCountMatrix[0][j]) {
					tempLeftMaxCorrect = tempLabelCountMatrix[0][j];
					tempLeftBestLabel = j;
				} // Of if
			} // Of for i

			// Step 4.4 Right leaf.
			double tempRightMaxCorrect = 0;
			int tempRightBestLabel = 0;
			for (int j = 0; j < tempLabelCountMatrix[1].length; j++) {
				if (tempRightMaxCorrect < tempLabelCountMatrix[1][j]) {
					tempRightMaxCorrect = tempLabelCountMatrix[1][j];
					tempRightBestLabel = j;
				} // Of if
			} // Of for i

			// Step 4.5 Compare with the current best.
			if (tempMaxCorrect < tempLeftMaxCorrect + tempRightMaxCorrect) {
				tempMaxCorrect = tempLeftMaxCorrect + tempRightMaxCorrect;
				bestCut = tempCut;
				leftLeafLabel = tempLeftBestLabel;
				rightLeafLabel = tempRightBestLabel;
			} // Of if
		} // Of for i

		System.out.println("Attribute = " + selectedAttribute + ", cut = " + bestCut + ", leftLeafLabel = "
				+ leftLeafLabel + ", rightLeafLabel = " + rightLeafLabel);
	}// Of train

	/**
	 ****************** 
	 * Classify an instance.
	 * 
	 * @param paraInstance The given instance.
	 * @return Predicted label.
	 ****************** 
	 */
	public int classify(Instance paraInstance) {
		int resultLabel = -1;
		if (paraInstance.value(selectedAttribute) < bestCut) {
			resultLabel = leftLeafLabel;
		} else {
			resultLabel = rightLeafLabel;
		} // Of if
		return resultLabel;
	}// Of classify

	/**
	 ****************** 
	 * For display.
	 ****************** 
	 */
	public String toString() {
		String resultString = "I am a stump classifier.\r\n" + "I choose attribute #" + selectedAttribute
				+ " with cut value " + bestCut + ".\r\n" + "The left and right leaf labels are " + leftLeafLabel
				+ " and " + rightLeafLabel + ", respectively.\r\n" + "My weighted error is: " + computeWeightedError()
				+ ".\r\n" + "My weighted accuracy is : " + computeTrainingAccuracy() + ".";

		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 ee) {
			System.out.println("Cannot read the file: " + tempFilename + "\r\n" + ee);
			System.exit(0);
		} // Of try

		StumpClassifier tempClassifier = new StumpClassifier(tempWeightedInstances);
		tempClassifier.train();
		System.out.println(tempClassifier);

		System.out.println(Arrays.toString(tempClassifier.computeCorrectnessArray()));
	}// Of main
}// Of class StumpClassifier

集成学习之 AdaBoosting (集成器)

1、核心代码在写在 train() 函数里.
2、为了简化代码, 直接使用训练集做测试.

package 决策树与集成学习;
 
/**
 * @time 2022/5/19
 * @author Liang Huang
 */
import java.io.FileReader;
import weka.core.Instance;
import weka.core.Instances;

public class Booster {

	/**
	 * Classifiers.
	 */
	SimpleClassifier[] classifiers;

	/**
	 * Number of classifiers.
	 */
	int numClassifiers;

	/**
	 * Whether or not stop after the training error is 0.
	 */
	boolean stopAfterConverge = false;

	/**
	 * The weights of classifiers.
	 */
	double[] classifierWeights;

	/**
	 * The training data.
	 */
	Instances trainingData;

	/**
	 * The testing data.
	 */
	Instances testingData;

	/**
	 ****************** 
	 * The first constructor. The testing set is the same as the training set.
	 * 
	 * @param paraTrainingFilename The data filename.
	 ****************** 
	 */
	public Booster(String paraTrainingFilename) {
		// Step 1. Read training set.
		try {
			FileReader tempFileReader = new FileReader(paraTrainingFilename);
			trainingData = new Instances(tempFileReader);
			tempFileReader.close();
		} catch (Exception ee) {
			System.out.println("Cannot read the file: " + paraTrainingFilename + "\r\n" + ee);
			System.exit(0);
		} // Of try

		// Step 2. Set the last attribute as the class index.
		trainingData.setClassIndex(trainingData.numAttributes() - 1);

		// Step 3. The testing data is the same as the training data.
		testingData = trainingData;

		stopAfterConverge = true;

		System.out.println("****************Data**********\r\n" + trainingData);
	}// Of the first constructor

	/**
	 ****************** 
	 * Set the number of base classifier, and allocate space for them.
	 * 
	 * @param paraNumBaseClassifiers The number of base classifier.
	 ****************** 
	 */
	public void setNumBaseClassifiers(int paraNumBaseClassifiers) {
		numClassifiers = paraNumBaseClassifiers;

		// Step 1. Allocate space (only reference) for classifiers
		classifiers = new SimpleClassifier[numClassifiers];

		// Step 2. Initialize classifier weights.
		classifierWeights = new double[numClassifiers];
	}// Of setNumBaseClassifiers

	/**
	 ****************** 
	 * Train the booster.
	 * 
	 * @see algorithm.StumpClassifier#train()
	 ****************** 
	 */
	public void train() {
		// Step 1. Initialize.
		WeightedInstances tempWeightedInstances = null;
		double tempError;
		numClassifiers = 0;

		// Step 2. Build other classifiers.
		for (int i = 0; i < classifiers.length; i++) {
			// Step 2.1 Key code: Construct or adjust the weightedInstances
			if (i == 0) {
				tempWeightedInstances = new WeightedInstances(trainingData);
			} else {
				// Adjust the weights of the data.
				tempWeightedInstances.adjustWeights(classifiers[i - 1].computeCorrectnessArray(),
						classifierWeights[i - 1]);
			} // Of if

			// Step 2.2 Train the next classifier.
			classifiers[i] = new StumpClassifier(tempWeightedInstances);
			classifiers[i].train();

			tempError = classifiers[i].computeWeightedError();

			// Key code: Set the classifier weight.
			classifierWeights[i] = 0.5 * Math.log(1 / tempError - 1);
			if (classifierWeights[i] < 1e-6) {
				classifierWeights[i] = 0;
			} // Of if

			System.out.println("Classifier #" + i + " , weighted error = " + tempError + ", weight = "
					+ classifierWeights[i] + "\r\n");

			numClassifiers++;

			// The accuracy is enough.
			if (stopAfterConverge) {
				double tempTrainingAccuracy = computeTrainingAccuray();
				System.out.println("The accuracy of the booster is: " + tempTrainingAccuracy + "\r\n");
				if (tempTrainingAccuracy > 0.999999) {
					System.out.println("Stop at the round: " + i + " due to converge.\r\n");
					break;
				} // Of if
			} // Of if
		} // Of for i
	}// Of train

	/**
	 ****************** 
	 * Classify an instance.
	 * 
	 * @param paraInstance  The given instance.
	 * @return The predicted label.
	 ****************** 
	 */
	public int classify(Instance paraInstance) {
		double[] tempLabelsCountArray = new double[trainingData.classAttribute().numValues()];
		for (int i = 0; i < numClassifiers; i++) {
			int tempLabel = classifiers[i].classify(paraInstance);
			tempLabelsCountArray[tempLabel] += classifierWeights[i];
		} // Of for i

		int resultLabel = -1;
		double tempMax = -1;
		for (int i = 0; i < tempLabelsCountArray.length; i++) {
			if (tempMax < tempLabelsCountArray[i]) {
				tempMax = tempLabelsCountArray[i];
				resultLabel = i;
			} // Of if
		} // Of for

		return resultLabel;
	}// Of classify

	/**
	 ****************** 
	 * Test the booster on the training data.
	 * 
	 * @return The classification accuracy.
	 ****************** 
	 */
	public double test() {
		System.out.println("Testing on " + testingData.numInstances() + " instances.\r\n");

		return test(testingData);
	}// Of test

	/**
	 ****************** 
	 * Test the booster.
	 * 
	 * @param paraInstances  The testing set.
	 * @return The classification accuracy.
	 ****************** 
	 */
	public double test(Instances paraInstances) {
		double tempCorrect = 0;
		paraInstances.setClassIndex(paraInstances.numAttributes() - 1);

		for (int i = 0; i < paraInstances.numInstances(); i++) {
			Instance tempInstance = paraInstances.instance(i);
			if (classify(tempInstance) == (int) tempInstance.classValue()) {
				tempCorrect++;
			} // Of if
		} // Of for i

		double resultAccuracy = tempCorrect / paraInstances.numInstances();
		System.out.println("The accuracy is: " + resultAccuracy);

		return resultAccuracy;
	} // Of test

	/**
	 ****************** 
	 * Compute the training accuracy of the booster. It is not weighted.
	 * 
	 * @return The training accuracy.
	 ****************** 
	 */
	public double computeTrainingAccuray() {
		double tempCorrect = 0;

		for (int i = 0; i < trainingData.numInstances(); i++) {
			if (classify(trainingData.instance(i)) == (int) trainingData.instance(i).classValue()) {
				tempCorrect++;
			} // Of if
		} // Of for i

		double tempAccuracy = tempCorrect / trainingData.numInstances();

		return tempAccuracy;
	}// Of computeTrainingAccuray

	/**
	 ****************** 
	 * For integration test.
	 * 
	 * @param args Not provided.
	 ****************** 
	 */
	public static void main(String args[]) {
		System.out.println("Starting AdaBoosting...");
		Booster tempBooster = new Booster("D:/data/iris.arff");
		// Booster tempBooster = new Booster("src/data/smalliris.arff");

		tempBooster.setNumBaseClassifiers(100);
		tempBooster.train();

		System.out.println("The training accuracy is: " + tempBooster.computeTrainingAccuray());
		tempBooster.test();
	}// Of main
}// Of class Booster