机器学习-10-矩阵分解

学习来源：日撸 Java 三百行（61-70天，决策树与集成学习）_闵帆的博客-CSDN博客

梯度下降

如同所示，梯度下降就是沿着下降最快的方向移动一定距离，距离为梯度乘以学习率。直到下降到最底部。

该代码中的梯度：

对于用户向量和电影向量的偏导：

其中，表示真实评分和预测评分的差值。

矩阵分解

1.数据：“用户ID 电影ID 评分（1-5）”。电影看得多的用户排在前面。

2.思想：可以将用户-电影的评分矩阵，转化为两个包含隐含因子的低维矩阵。一个是用户低维矩阵，一个是电影低维矩阵。并且使。

其中：表示用户对电影的评分。假设低维为3维，所以表示用户对第个隐含因子的重视程度，表示电影对第个隐含因子的满足程度。隐含因子可以是电影流行度、导演水平、演员演技。

例如：第个用户相应的向量为[0.8，0.1，0.3]，第个电影相应的向量为[0.3，0.9，0.6]。预测评分就是两个向量的内积：0.8*0.3+0.1*0.9+0.3*0.6=0.51

3.和的初始化都是随机值，并且采用梯度下降的方法对其中的值进行调整。 梯度下降直到收敛。

4.算法思路：

1）对 和初始化。（矩阵中全部值为0-1的随机值）

2）利用梯度下降对  和 的值进行调整（调整公式如上方梯度下降中的公式所示）。

3）调整2000（人为规定）次，结束。

代码：

package 日撸Java300行_61_70;

import java.io.*;
import java.util.Random;

/*
 * Matrix factorization for recommender systems.
 * 
 * @author Hui Xiao
 */

public class MatrixFactorization {
	/**
	 * Used to generate random numbers.
	 */
	Random rand = new Random();

	/**
	 * Number of users.
	 */
	int numUsers;

	/**
	 * Number of items.
	 */
	int numItems;

	/**
	 * Number of ratings.
	 */
	int numRatings;

	/**
	 * Training data.
	 */
	Triple[] dataset;

	/**
	 * A parameter for controlling learning regular.
	 */
	double alpha;

	/**
	 * A parameter for controlling the learning speed.
	 */
	double lambda;

	/**
	 * The low rank of the small matrices.
	 */
	int rank;

	/**
	 * The user matrix U.
	 */
	double[][] userSubspace;

	/**
	 * The item matrix V.
	 */
	double[][] itemSubspace;

	/**
	 * The lower bound of the rating value.
	 */
	double ratingLowerBound;

	/**
	 * The upper bound of the rating value.
	 */
	double ratingUpperBound;

	/**
	 ************************ 
	 * The first constructor.
	 * 
	 * @param paraFilename
	 *            The data filename.
	 * @param paraNumUsers
	 *            The number of users.
	 * @param paraNumItems
	 *            The number of items.
	 * @param paraNumRatings
	 *            The number of ratings.
	 ************************ 
	 */
	public MatrixFactorization(String paraFilename, int paraNumUsers, int paraNumItems,
			int paraNumRatings, double paraRatingLowerBound, double paraRatingUpperBound) {
		numUsers = paraNumUsers;
		numItems = paraNumItems;
		numRatings = paraNumRatings;
		ratingLowerBound = paraRatingLowerBound;
		ratingUpperBound = paraRatingUpperBound;

		try {
			readData(paraFilename, paraNumUsers, paraNumItems, paraNumRatings);
			// adjustUsingMeanRating();
		} catch (Exception ee) {
			System.out.println("File " + paraFilename + " cannot be read! " + ee);
			System.exit(0);
		} // Of try
	}// Of the first constructor

	/**
	 ************************ 
	 * Set parameters.
	 * 
	 * @param paraRank
	 *            The given rank.
	 * @throws IOException
	 ************************ 
	 */
	public void setParameters(int paraRank, double paraAlpha, double paraLambda) {
		rank = paraRank;
		alpha = paraAlpha;
		lambda = paraLambda;
	}// Of setParameters

	/**
	 ************************ 
	 * Read the data from the file.
	 * 
	 * @param paraFilename
	 *            The given file.
	 * @throws IOException
	 ************************ 
	 */
	public void readData(String paraFilename, int paraNumUsers, int paraNumItems,
			int paraNumRatings) throws IOException {
		File tempFile = new File(paraFilename);
		if (!tempFile.exists()) {
			System.out.println("File " + paraFilename + " does not exists.");
			System.exit(0);
		} // Of if
		BufferedReader tempBufferReader = new BufferedReader(new FileReader(tempFile));

		// Allocate space.
		dataset = new Triple[paraNumRatings];
		String tempString;
		String[] tempStringArray;
		for (int i = 0; i < paraNumRatings; i++) {
			tempString = tempBufferReader.readLine();
			tempStringArray = tempString.split(",");
			dataset[i] = new Triple(Integer.parseInt(tempStringArray[0]),
					Integer.parseInt(tempStringArray[1]), Double.parseDouble(tempStringArray[2]));
		} // Of for i

		tempBufferReader.close();
	}// Of readData

	/**
	 ************************ 
	 * Initialize subspaces. Each value is in [0, 1].
	 ************************ 
	 */
	void initializeSubspaces() {
		userSubspace = new double[numUsers][rank];

		for (int i = 0; i < numUsers; i++) {
			for (int j = 0; j < rank; j++) {
				userSubspace[i][j] = rand.nextDouble();
			} // Of for j
		} // Of for i

		itemSubspace = new double[numItems][rank];
		for (int i = 0; i < numItems; i++) {
			for (int j = 0; j < rank; j++) {
				itemSubspace[i][j] = rand.nextDouble();
			} // Of for j
		} // Of for i
	}// Of initializeSubspaces

	/**
	 ************************ 
	 * Predict the rating of the user to the item
	 * 
	 * @param paraUser
	 *            The user index.
	 ************************ 
	 */
	public double predict(int paraUser, int paraItem) {
		double resultValue = 0;
		for (int i = 0; i < rank; i++) {
			// The row vector of an user and the column vector of an item
			resultValue += userSubspace[paraUser][i] * itemSubspace[paraItem][i];
		} // Of for i
		return resultValue;
	}// Of predict

	/**
	 ************************ 
	 * Train.
	 * 
	 * @param paraRounds
	 *            The number of rounds.
	 ************************ 
	 */
	public void train(int paraRounds) {
		initializeSubspaces();

		for (int i = 0; i < paraRounds; i++) {
			updateNoRegular();
			if (i % 50 == 0) {
				// Show the process
				System.out.println("Round " + i);
				System.out.println("MAE: " + mae());
			} // Of if
		} // Of for i
	}// Of train

	/**
	 ************************ 
	 * Update sub-spaces using the training data.
	 ************************ 
	 */
	public void updateNoRegular() {
		for (int i = 0; i < numRatings; i++) {
			int tempUserId = dataset[i].user;
			int tempItemId = dataset[i].item;
			double tempRate = dataset[i].rating;

			double tempResidual = tempRate - predict(tempUserId, tempItemId); // Residual

			// Update user subspace
			double tempValue = 0;
			for (int j = 0; j < rank; j++) {
				tempValue = 2 * tempResidual * itemSubspace[tempItemId][j];
				userSubspace[tempUserId][j] += alpha * tempValue;
			} // Of for j

			// Update item subspace
			for (int j = 0; j < rank; j++) {
				tempValue = 2 * tempResidual * userSubspace[tempUserId][j];

				itemSubspace[tempItemId][j] += alpha * tempValue;
			} // Of for j
		} // Of for i
	}// Of updateNoRegular

	/**
	 ************************ 
	 * Compute the RSME.
	 * 
	 * @return RSME of the current factorization.
	 ************************ 
	 */
	public double rsme() {
		double resultRsme = 0;
		int tempTestCount = 0;

		for (int i = 0; i < numRatings; i++) {
			int tempUserIndex = dataset[i].user;
			int tempItemIndex = dataset[i].item;
			double tempRate = dataset[i].rating;

			double tempPrediction = predict(tempUserIndex, tempItemIndex);// +
																			// DataInfo.mean_rating;

			if (tempPrediction < ratingLowerBound) {
				tempPrediction = ratingLowerBound;
			} else if (tempPrediction > ratingUpperBound) {
				tempPrediction = ratingUpperBound;
			} // Of if

			double tempError = tempRate - tempPrediction;
			resultRsme += tempError * tempError;
			tempTestCount++;
		} // Of for i

		return Math.sqrt(resultRsme / tempTestCount);
	}// Of rsme

	/**
	 ************************ 
	 * Compute the MAE.
	 * 
	 * @return MAE of the current factorization.
	 ************************ 
	 */
	public double mae() {
		double resultMae = 0;
		int tempTestCount = 0;

		for (int i = 0; i < numRatings; i++) {
			int tempUserIndex = dataset[i].user;
			int tempItemIndex = dataset[i].item;
			double tempRate = dataset[i].rating;

			double tempPrediction = predict(tempUserIndex, tempItemIndex);

			if (tempPrediction < ratingLowerBound) {
				tempPrediction = ratingLowerBound;
			} // Of if
			if (tempPrediction > ratingUpperBound) {
				tempPrediction = ratingUpperBound;
			} // Of if

			double tempError = tempRate - tempPrediction;

			resultMae += Math.abs(tempError);
			// System.out.println("resultMae: " + resultMae);
			tempTestCount++;
		} // Of for i

		return (resultMae / tempTestCount);
	}// Of mae

	/**
	 ************************ 
	 * Compute the MAE.
	 * 
	 * @return MAE of the current factorization.
	 ************************ 
	 */
	public static void testTrainingTesting(String paraFilename, int paraNumUsers, int paraNumItems,
			int paraNumRatings, double paraRatingLowerBound, double paraRatingUpperBound,
			int paraRounds) {
		try {
			// Step 1. read the training and testing data
			MatrixFactorization tempMF = new MatrixFactorization(paraFilename, paraNumUsers,
					paraNumItems, paraNumRatings, paraRatingLowerBound, paraRatingUpperBound);

			tempMF.setParameters(5, 0.0001, 0.005);

			// Step 3. update and predict
			System.out.println("Begin Training ! ! !");
			tempMF.train(paraRounds);

			double tempMAE = tempMF.mae();
			double tempRSME = tempMF.rsme();
			System.out.println("Finally, MAE = " + tempMAE + ", RSME = " + tempRSME);
		} catch (Exception e) {
			e.printStackTrace();
		} // Of try
	}// Of testTrainingTesting

	/**
	 ************************ 
	 * @param args
	 ************************ 
	 */
	public static void main(String args[]) {
		testTrainingTesting("D:/data/movielens-943u1682m.txt", 943, 1682, 10000, 1, 5, 2000);
	}// Of main

	public class Triple {
		public int user;
		public int item;
		public double rating;

		/**
		 *********************
		 * The constructor.
		 *********************
		 */
		public Triple() {
			user = -1;
			item = -1;
			rating = -1;
		}// Of the first constructor

		/**
		 *********************
		 * The constructor.
		 *********************
		 */
		public Triple(int paraUser, int paraItem, double paraRating) {
			user = paraUser;
			item = paraItem;
			rating = paraRating;
		}// Of the first constructor

		/**
		 *********************
		 * Show me.
		 *********************
		 */
		public String toString() {
			return "" + user + ", " + item + ", " + rating;
		}// Of toString
	}// Of class Triple

}// Of class MatrixFactorization

截图：

 说明更新2000次MAE达0.5190206081496164，RMSE达0.6844411201166227。