协同过滤算法 Java代码示例

协同过滤算法是一种常用的推荐算法，它通过分析用户的历史行为和与其他用户的相似度来进行推荐。下面是一个简单的协同过滤算法的Java代码示例：

import java.util.*;

public class CollaborativeFiltering {
    // 用户评分数据
    private static int[][] ratings = {
            {4, 5, 0, 2, 1},
            {0, 2, 4, 0, 5},
            {1, 0, 3, 4, 2},
            {5, 1, 2, 0, 4},
            {2, 4, 1, 5, 0}
    };

    // 计算用户之间的相似度
    private static double similarity(int user1, int user2) {
        double dotProduct = 0.0;
        double norm1 = 0.0;
        double norm2 = 0.0;

        for (int i = 0; i < ratings[user1].length; i++) {
            dotProduct += ratings[user1][i] * ratings[user2][i];
            norm1 += Math.pow(ratings[user1][i], 2);
            norm2 += Math.pow(ratings[user2][i], 2);
        }

        return dotProduct / (Math.sqrt(norm1) * Math.sqrt(norm2));
    }

    // 根据用户相似度进行推荐
    private static List<Integer> recommend(int user) {
        List<Integer> recommendations = new ArrayList<>();
        double[] similarities = new double[ratings.length];

        for (int i = 0; i < ratings.length; i++) {
            if (i != user) {
                similarities[i] = similarity(user, i);
            }
        }

        for (int i = 0; i < ratings[user].length; i++) {
            if (ratings[user][i] == 0) {
                double weightedSum = 0.0;
                double similaritySum = 0.0;

                for (int j = 0; j < ratings.length; j++) {
                    if (j != user && ratings[j][i] != 0) {
                        weightedSum += ratings[j][i] * similarities[j];
                        similaritySum += similarities[j];
                    }
                }

                if (similaritySum != 0) {
                    double recommendation = weightedSum / similaritySum;
                    recommendations.add((int) Math.round(recommendation));
                }
            }
        }

        return recommendations;
    }

    public static void main(String[] args) {
        int user = 0;
        List<Integer> recommendations = recommend(user);

        System.out.println("用户 " + user + " 的推荐结果：");
        for (int recommendation : recommendations) {
            System.out.println(recommendation);
        }
    }
}

这段代码实现了一个简单的协同过滤算法，其中包括计算用户之间的相似度和根据相似度进行推荐的功能。你可以根据自己的需求进行修改和扩展。