Java学习笔记（day58）

一、学习内容

主题：
符号型数据的 NB 算法
定义：
朴素贝叶斯方法是在贝叶斯算法的基础上进行了相应的简化，即假定给定目标值时属性之间相互条件独立。也就是说没有哪个属性变量对于决策结果来说占有着较大的比重，也没有哪个属性变量对于决策结果占有着较小的比重。虽然这个简化方式在一定程度上降低了贝叶斯分类算法的分类效果，但是在实际的应用场景中，极大地简化了贝叶斯方法的复杂性。
算法原理：
朴素贝叶斯分类（NBC）是以贝叶斯定理为基础并且假设特征条件之间相互独立的方法，先通过已给定的训练集，以特征词之间独立作为前提假设，学习从输入到输出的联合概率分布，再基于学习到的模型，输入X求出使得后验概率最大的输出Y。
优缺点：
优点
朴素贝叶斯算法假设了数据集属性之间是相互独立的，因此算法的逻辑性十分简单，并且算法较为稳定，当数据呈现不同的特点时，朴素贝叶斯的分类性能不会有太大的差异。换句话说就是朴素贝叶斯算法的健壮性比较好，对于不同类型的数据集不会呈现出太大的差异性。当数据集属性之间的关系相对比较独立时，朴素贝叶斯分类算法会有较好的效果。
缺点
属性独立性的条件同时也是朴素贝叶斯分类器的不足之处。数据集属性的独立性在很多情况下是很难满足的，因为数据集的属性之间往往都存在着相互关联，如果在分类过程中出现这种问题，会导致分类的效果大大降低。

二、代码编写

package machinelearning.bayes;

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

import weka.core.*;

/**
 * The Naive Bayes algorithm.
 * 
 * @author WeiZe 1025976860@qq.com
 */

public class NaiveBayes {
	/**
	 ************************* 
	 * An inner class to store parameters.
	 ************************* 
	 */
	private class GaussianParamters {
		double mu;
		double sigma;

		public GaussianParamters(double paraMu, double paraSigma) {
			mu = paraMu;
			sigma = paraSigma;
		}// Of the constructor

		public String toString() {
			return "(" + mu + ", " + sigma + ")";
		}// Of toString
	}// Of GaussianParamters

	/**
	 * The data.
	 */
	Instances dataset;

	/**
	 * 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;

	/**
	 * The prediction, including queried and predicted labels.
	 */
	int[] predicts;

	/**
	 * Class distribution.
	 */
	double[] classDistribution;

	/**
	 * Class distribution with Laplacian smooth.
	 */
	double[] classDistributionLaplacian;

	/**
	 * The conditional probabilities for all classes over all attributes on all
	 * values.
	 */
	double[][][] conditionalProbabilities;

	/**
	 * The conditional probabilities with Laplacian smooth.
	 */
	double[][][] conditionalProbabilitiesLaplacian;

	/**
	 * The Guassian parameters.
	 */
	GaussianParamters[][] gaussianParameters;

	/**
	 * Data type.
	 */
	int dataType;

	/**
	 * Nominal.
	 */
	public static final int NOMINAL = 0;

	/**
	 * Numerical.
	 */
	public static final int NUMERICAL = 1;

	/**
	 ********************
	 * The constructor.
	 * 
	 * @param paraFilename
	 *            The given file.
	 ********************
	 */
	public NaiveBayes(String paraFilename) {
		dataset = null;
		try {
			FileReader fileReader = new FileReader(paraFilename);
			dataset = new Instances(fileReader);
			fileReader.close();
		} catch (Exception ee) {
			System.out.println("Cannot read the file: " + paraFilename + "\r\n" + ee);
			System.exit(0);
		} // Of try

		dataset.setClassIndex(dataset.numAttributes() - 1);
		numConditions = dataset.numAttributes() - 1;
		numInstances = dataset.numInstances();
		numClasses = dataset.attribute(numConditions).numValues();
	}// Of the constructor

	/**
	 ********************
	 * Set the data type.
	 ********************
	 */
	public void setDataType(int paraDataType) {
		dataType = paraDataType;
	}// Of setDataType

	/**
	 ********************
	 * Calculate the class distribution with Laplacian smooth.
	 ********************
	 */
	public void calculateClassDistribution() {
		classDistribution = new double[numClasses];
		classDistributionLaplacian = new double[numClasses];

		double[] tempCounts = new double[numClasses];
		for (int i = 0; i < numInstances; i++) {
			int tempClassValue = (int) dataset.instance(i).classValue();
			tempCounts[tempClassValue]++;
		} // Of for i

		for (int i = 0; i < numClasses; i++) {
			classDistribution[i] = tempCounts[i] / numInstances;
			classDistributionLaplacian[i] = (tempCounts[i] + 1) / (numInstances + numClasses);
		} // Of for i

		System.out.println("Class distribution: " + Arrays.toString(classDistribution));
		System.out.println(
				"Class distribution Laplacian: " + Arrays.toString(classDistributionLaplacian));
	}// Of calculateClassDistribution

	/**
	 ********************
	 * Calculate the conditional probabilities with Laplacian smooth. ONLY scan
	 * the dataset once. There was a simpler one, I have removed it because the
	 * time complexity is higher.
	 ********************
	 */
	public void calculateConditionalProbabilities() {
		conditionalProbabilities = new double[numClasses][numConditions][];
		conditionalProbabilitiesLaplacian = new double[numClasses][numConditions][];

		// Allocate space
		for (int i = 0; i < numClasses; i++) {
			for (int j = 0; j < numConditions; j++) {
				int tempNumValues = (int) dataset.attribute(j).numValues();
				conditionalProbabilities[i][j] = new double[tempNumValues];
				conditionalProbabilitiesLaplacian[i][j] = new double[tempNumValues];
			} // Of for j
		} // Of for i

		// Count the numbers
		int[] tempClassCounts = new int[numClasses];
		for (int i = 0; i < numInstances; i++) {
			int tempClass = (int) dataset.instance(i).classValue();
			tempClassCounts[tempClass]++;
			for (int j = 0; j < numConditions; j++) {
				int tempValue = (int) dataset.instance(i).value(j);
				conditionalProbabilities[tempClass][j][tempValue]++;
			} // Of for j
		} // Of for i

		// Now for the real probability with Laplacian
		for (int i = 0; i < numClasses; i++) {
			for (int j = 0; j < numConditions; j++) {
				int tempNumValues = (int) dataset.attribute(j).numValues();
				for (int k = 0; k < tempNumValues; k++) {
					conditionalProbabilitiesLaplacian[i][j][k] = (conditionalProbabilities[i][j][k]
							+ 1) / (tempClassCounts[i] + numClasses);
				} // Of for k
			} // Of for j
		} // Of for i

		System.out.println(Arrays.deepToString(conditionalProbabilities));
	}// Of calculateConditionalProbabilities

	/**
	 ********************
	 * Calculate the conditional probabilities with Laplacian smooth.
	 ********************
	 */
	public void calculateGausssianParameters() {
		gaussianParameters = new GaussianParamters[numClasses][numConditions];

		double[] tempValuesArray = new double[numInstances];
		int tempNumValues = 0;
		double tempSum = 0;

		for (int i = 0; i < numClasses; i++) {
			for (int j = 0; j < numConditions; j++) {
				tempSum = 0;

				// Obtain values for this class.
				tempNumValues = 0;
				for (int k = 0; k < numInstances; k++) {
					if ((int) dataset.instance(k).classValue() != i) {
						continue;
					} // Of if

					tempValuesArray[tempNumValues] = dataset.instance(k).value(j);
					tempSum += tempValuesArray[tempNumValues];
					tempNumValues++;
				} // Of for k

				// Obtain parameters.
				double tempMu = tempSum / tempNumValues;

				double tempSigma = 0;
				for (int k = 0; k < tempNumValues; k++) {
					tempSigma += (tempValuesArray[k] - tempMu) * (tempValuesArray[k] - tempMu);
				} // Of for k
				tempSigma /= tempNumValues;
				tempSigma = Math.sqrt(tempSigma);

				gaussianParameters[i][j] = new GaussianParamters(tempMu, tempSigma);
			} // Of for j
		} // Of for i

		System.out.println(Arrays.deepToString(gaussianParameters));
	}// Of calculateGausssianParameters

	/**
	 ********************
	 * Classify all instances, the results are stored in predicts[].
	 ********************
	 */
	public void classify() {
		predicts = new int[numInstances];
		for (int i = 0; i < numInstances; i++) {
			predicts[i] = classify(dataset.instance(i));
		} // Of for i
	}// Of classify

	/**
	 ********************
	 * Classify an instances.
	 ********************
	 */
	public int classify(Instance paraInstance) {
		if (dataType == NOMINAL) {
			return classifyNominal(paraInstance);
		} else if (dataType == NUMERICAL) {
			return classifyNumerical(paraInstance);
		} // Of if

		return -1;
	}// Of classify

	/**
	 ********************
	 * Classify an instances with nominal data.
	 ********************
	 */
	public int classifyNominal(Instance paraInstance) {
		// Find the biggest one
		double tempBiggest = -10000;
		int resultBestIndex = 0;
		for (int i = 0; i < numClasses; i++) {
			double tempPseudoProbability = Math.log(classDistributionLaplacian[i]);
			for (int j = 0; j < numConditions; j++) {
				int tempAttributeValue = (int) paraInstance.value(j);

				// Laplacian smooth.
				tempPseudoProbability += Math
						.log(conditionalProbabilities[i][j][tempAttributeValue]);
			} // Of for j

			if (tempBiggest < tempPseudoProbability) {
				tempBiggest = tempPseudoProbability;
				resultBestIndex = i;
			} // Of if
		} // Of for i

		return resultBestIndex;
	}// Of classifyNominal

	/**
	 ********************
	 * Classify an instances with numerical data.
	 ********************
	 */
	public int classifyNumerical(Instance paraInstance) {
		// Find the biggest one
		double tempBiggest = -10000;
		int resultBestIndex = 0;

		for (int i = 0; i < numClasses; i++) {
			double tempPseudoProbability = Math.log(classDistributionLaplacian[i]);
			for (int j = 0; j < numConditions; j++) {
				double tempAttributeValue = paraInstance.value(j);
				double tempSigma = gaussianParameters[i][j].sigma;
				double tempMu = gaussianParameters[i][j].mu;

				tempPseudoProbability += -Math.log(tempSigma) - (tempAttributeValue - tempMu)
						* (tempAttributeValue - tempMu) / (2 * tempSigma * tempSigma);
			} // Of for j

			if (tempBiggest < tempPseudoProbability) {
				tempBiggest = tempPseudoProbability;
				resultBestIndex = i;
			} // Of if
		} // Of for i

		return resultBestIndex;
	}// Of classifyNumerical

	/**
	 ********************
	 * Compute accuracy.
	 ********************
	 */
	public double computeAccuracy() {
		double tempCorrect = 0;
		for (int i = 0; i < numInstances; i++) {
			if (predicts[i] == (int) dataset.instance(i).classValue()) {
				tempCorrect++;
			} // Of if
		} // Of for i

		double resultAccuracy = tempCorrect / numInstances;
		return resultAccuracy;
	}// Of computeAccuracy

	/**
	 ************************* 
	 * Test nominal data.
	 ************************* 
	 */
	public static void testNominal() {
		System.out.println("Hello, Naive Bayes. I only want to test the nominal data.");
		String tempFilename = "D:/data/mushroom.arff";

		NaiveBayes tempLearner = new NaiveBayes(tempFilename);
		tempLearner.setDataType(NOMINAL);
		tempLearner.calculateClassDistribution();
		tempLearner.calculateConditionalProbabilities();
		tempLearner.classify();

		System.out.println("The accuracy is: " + tempLearner.computeAccuracy());
	}// Of testNominal

	/**
	 ************************* 
	 * Test numerical data.
	 ************************* 
	 */
	public static void testNumerical() {
		System.out.println(
				"Hello, Naive Bayes. I only want to test the numerical data with Gaussian assumption.");
		String tempFilename = "D:/data/iris.arff";

		NaiveBayes tempLearner = new NaiveBayes(tempFilename);
		tempLearner.setDataType(NUMERICAL);
		tempLearner.calculateClassDistribution();
		tempLearner.calculateGausssianParameters();
		tempLearner.classify();

		System.out.println("The accuracy is: " + tempLearner.computeAccuracy());
	}// Of testNominal

	/**
	 ************************* 
	 * Test this class.
	 * 
	 * @param args
	 *            Not used now.
	 ************************* 
	 */
	public static void main(String[] args) {
		testNominal();
		testNumerical();
	}// Of main

}// Of class NaiveBayes