数据分析案例 4 电影数据分析统计

其他 2018-05-12 18:27:45 阅读次数: 1
数据样例：
movie：电影id
rate：用户评分
timeStamp:评分时间
uid：用户id

{"movie":"2804","rate":"5","timeStamp":"978300719","uid":"1"}
{"movie":"594","rate":"4","timeStamp":"978302268","uid":"1"}
{"movie":"919","rate":"4","timeStamp":"978301368","uid":"1"}
需求：
1.每个用户评分最高的3部电影评分信息
2.每个用户的uid和评分的平均值
3.最大方(评分平均值高)的3个用户的uid和评分平均值
    排序
4.最热门的3部电影id和评价次数
5.评价最高的3部电影id和评分均值    
并将统计结果输出到结果文件中(或数据库中)

步骤：
1读文件，赋值到bean中
2按评分排序
3 取前3电影
4.最热门的3部电影id和评价次数  
热门定义 ：评价次数最多的

5.评价最高的3部电影id和评分均值 评价最高（评分最高）

并将统计结果输出到结果文件中（或数据库中）


由于数据文件太大，只上传一部分

rate.txt

{"movie":"1193","rate":"5","timeStamp":"978300760","uid":"1"}
{"movie":"661","rate":"3","timeStamp":"978302109","uid":"1"}
{"movie":"914","rate":"3","timeStamp":"978301968","uid":"1"}
{"movie":"3408","rate":"4","timeStamp":"978300275","uid":"1"}
{"movie":"2355","rate":"5","timeStamp":"978824291","uid":"1"}
{"movie":"1197","rate":"3","timeStamp":"978302268","uid":"1"}
{"movie":"1287","rate":"5","timeStamp":"978302039","uid":"1"}
{"movie":"2804","rate":"5","timeStamp":"978300719","uid":"1"}
{"movie":"594","rate":"4","timeStamp":"978302268","uid":"1"}
{"movie":"919","rate":"4","timeStamp":"978301368","uid":"1"}
{"movie":"595","rate":"5","timeStamp":"978824268","uid":"1"}
{"movie":"938","rate":"4","timeStamp":"978301752","uid":"1"}
{"movie":"2398","rate":"4","timeStamp":"978302281","uid":"1"}
{"movie":"2918","rate":"4","timeStamp":"978302124","uid":"1"}
{"movie":"1035","rate":"5","timeStamp":"978301753","uid":"1"}
{"movie":"2791","rate":"4","timeStamp":"978302188","uid":"1"}
{"movie":"2687","rate":"3","timeStamp":"978824268","uid":"1"}
{"movie":"2018","rate":"4","timeStamp":"978301777","uid":"1"}
{"movie":"3105","rate":"5","timeStamp":"978301713","uid":"1"}
{"movie":"2797","rate":"4","timeStamp":"978302039","uid":"1"}
{"movie":"2321","rate":"3","timeStamp":"978302205","uid":"1"}
{"movie":"720","rate":"3","timeStamp":"978300760","uid":"1"}
{"movie":"1270","rate":"5","timeStamp":"978300055","uid":"1"}
{"movie":"527","rate":"5","timeStamp":"978824195","uid":"1"}
{"movie":"2340","rate":"3","timeStamp":"978300103","uid":"1"}
{"movie":"48","rate":"5","timeStamp":"978824351","uid":"1"}
{"movie":"1097","rate":"4","timeStamp":"978301953","uid":"1"}
{"movie":"1721","rate":"4","timeStamp":"978300055","uid":"1"}
{"movie":"2321","rate":"3","timeStamp":"978302205","uid":"1"}
{"movie":"1545","rate":"4","timeStamp":"978824139","uid":"1"}
{"movie":"745","rate":"3","timeStamp":"978824268","uid":"1"}
{"movie":"2294","rate":"4","timeStamp":"978824291","uid":"1"}
{"movie":"3186","rate":"4","timeStamp":"978300019","uid":"1"}
{"movie":"1566","rate":"4","timeStamp":"978824330","uid":"1"}
{"movie":"588","rate":"4","timeStamp":"978824268","uid":"1"}
{"movie":"1907","rate":"4","timeStamp":"978824330","uid":"1"}
{"movie":"783","rate":"4","timeStamp":"978824291","uid":"1"}
{"movie":"1836","rate":"5","timeStamp":"978300172","uid":"1"}
{"movie":"1022","rate":"5","timeStamp":"978300055","uid":"1"}

{"movie":"2762","rate":"4","timeStamp":"978302091","uid":"1"}

以上是数据文件100万条

HotMovie.java

package ch04;

public class HotMovie implements Comparable<HotMovie> {
	private int movie;
	private int count;

	public HotMovie() {
		super();
	}

	public HotMovie(int movie, int count) {
		super();
		this.movie = movie;
		this.count = count;
	}

	public int getMovie() {
		return movie;
	}

	public void setMovie(int movie) {
		this.movie = movie;
	}

	public int getCount() {
		return count;
	}

	public void setCount(int count) {
		this.count = count;
	}

	@Override
	public String toString() {
		return "HotMovie [movie=" + movie + ", count=" + count + "]";
	}

	@Override
	public int compareTo(HotMovie o) {
		return o.getCount()-this.getCount();
	}
}

Movie.java

//电影评分信息
public class Movie implements Comparable<Movie> {
	private int movie;
	private int rate;
	private long timeStamp;
	private int uid;

	public Movie() {
		super();
	}

	public Movie(int movie, int rate, long timeStamp, int uid) {
		super();
		this.movie = movie;
		this.rate = rate;
		this.timeStamp = timeStamp;
		this.uid = uid;
	}

	public int getMovie() {
		return movie;
	}

	public void setMovie(int movie) {
		this.movie = movie;
	}

	public int getRate() {
		return rate;
	}

	public void setRate(int rate) {
		this.rate = rate;
	}

	public long getTimeStamp() {
		return timeStamp;
	}

	public void setTimeStamp(long timeStamp) {
		this.timeStamp = timeStamp;
	}

	public int getUid() {
		return uid;
	}

	public void setUid(int uid) {
		this.uid = uid;
	}

	@Override
	public String toString() {
		return "[movie=" + movie + ", rate=" + rate + ", timeStamp=" + timeStamp + ", uid=" + uid + "]";
	}

	@Override
	public int compareTo(Movie o) {
		return o.getRate() - this.getRate();
	}

}
rate.java 
public class Rate implements Comparable<Rate> {
	private int uid;
	private float rate;

	public Rate() {
		super();
	}

	public Rate(int uid, float rate) {
		super();
		this.uid = uid;
		this.rate = rate;
	}

	public int getUid() {
		return uid;
	}

	public void setUid(int uid) {
		this.uid = uid;
	}

	public float getRate() {
		return rate;
	}

	public void setRate(float rate) {
		this.rate = rate;
	}

	@Override
	public String toString() {
		return "[uid=" + uid + ", rate=" + rate + "]";
	}

	@Override
	public int compareTo(Rate o) {
		if (o.getRate() == this.getRate()) {
			return 0;
		} else if (o.getRate() > this.getRate()) {
			return 1;
		} else {
			return -1;
		}
	}

}

RateMovie.java

public class RateMovie implements Comparable<RateMovie> {
	private int movie;
	private float rate;

	public RateMovie() {
		super();
	}

	public RateMovie(int movie, float rate) {
		super();
		this.movie = movie;
		this.rate = rate;
	}

	public int getMovie() {
		return movie;
	}

	public void setMovie(int movie) {
		this.movie = movie;
	}

	public float getRate() {
		return rate;
	}

	public void setRate(float rate) {
		this.rate = rate;
	}

	@Override
	public String toString() {
		return "[movie=" + movie + ", rate=" + rate + "]";
	}

	@Override
	public int compareTo(RateMovie o) {
		if (o.getRate() == this.getRate()) {
			return 0;
		} else if (o.getRate() > this.getRate()) {
			return 1;
		} else {
			return -1;
		}
	}
}
Test.java(主类) 
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map.Entry;

import com.alibaba.fastjson.JSON;

/*
	movie：电影id
	rate：用户评分
	timeStamp:评分时间
	uid：用户id
	
	{"movie":"2804","rate":"5","timeStamp":"978300719","uid":"1"}
	{"movie":"594","rate":"4","timeStamp":"978302268","uid":"1"}
	{"movie":"919","rate":"4","timeStamp":"978301368","uid":"1"}
需求：
		1.每个用户评分最高的3部电影评分信息
		2.每个用户的uid和评分的平均值
		3.最大方(评分平均值高)的3个用户的uid和评分平均值
		4.最热门的3部电影id和评价次数
		5.评价最高的3部电影id和评分均值
	
	并将统计结果输出到结果文件中(或数据库中)
 */
public class Test {
	public static void main(String[] args) {
		// 保存uid对应的电影评分信息
		HashMap<Integer, ArrayList<Movie>> map = new HashMap<Integer, ArrayList<Movie>>();

		// 保存movie对应的电影评分信息
		HashMap<Integer, ArrayList<Movie>> map2 = new HashMap<Integer, ArrayList<Movie>>();

		// 把rating.txt中的数据读取出来，封装到java对象中
		try (BufferedReader br = new BufferedReader(new FileReader("../案例1/src/qq/rating.txt"));) {
			String line;
			while ((line = br.readLine()) != null) {
				// 把读取的数据转换成Movie对象
				Movie movie = JSON.parseObject(line, Movie.class);

				// 判断map集合中是否存有对应uid电影评分信息
				if (map.containsKey(movie.getUid())) {
					// 取出用户对应电影评分信息的集合
					map.get(movie.getUid()).add(movie);
				} else {
					// 如果不包含用户的评分信息就自己创建一个集合然后放进map集合中
					ArrayList<Movie> list = new ArrayList<Movie>();
					list.add(movie);
					map.put(movie.getUid(), list);
				}

				// 判断map2集合中是否有对应movie对应的电影评分信息
				if (map2.containsKey(movie.getMovie())) {
					// 如果有就拿出对应的集合，然后把当前的电影评分对象添加进去
					map2.get(movie.getMovie()).add(movie);
				} else {
					// 创建一个存放电影信息的list集合
					ArrayList<Movie> list = new ArrayList<Movie>();
					// 把电影评分对象添加进list集合中
					list.add(movie);
					// 再把movie对应的list集合添加进map2集合中
					map2.put(movie.getMovie(), list);
				}
			}
		} catch (Exception e) {
			e.printStackTrace();
		}

		// 1.每个用户评分最高的3部电影评分信息
		// 把每个用户的电影信息集合降序排序
		for (Entry<Integer, ArrayList<Movie>> entry : map.entrySet()) {
			ArrayList<Movie> list = entry.getValue();
			Collections.sort(list);
		}
		try (BufferedWriter bw = new BufferedWriter(new FileWriter("D:/1.每个用户评分最高的3部电影评分信息.txt"));) {
			for (Entry<Integer, ArrayList<Movie>> entry : map.entrySet()) {
				bw.write(entry.getKey() + "：");
				bw.newLine();
				ArrayList<Movie> list = entry.getValue();
				bw.write(list.get(0).toString());
				bw.newLine();
				bw.write(list.get(1).toString());
				bw.newLine();
				bw.write(list.get(2).toString());
				bw.newLine();
			}
			System.out.println(" 1.每个用户评分最高的3部电影评分信息保存完毕");
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("1.每个用户评分最高的3部电影评分信息保存失败");
		}

		// 2.每个用户的uid和评分的平均值
		ArrayList<Rate> avgRateList = getAvgRateList(map);
		try (BufferedWriter bw = new BufferedWriter(new FileWriter("D:/2.每个用户的uid和评分的平均值.txt"));) {
			for (Rate rate : avgRateList) {
				bw.write(rate.toString());
				bw.newLine();
			}
			System.out.println("2.每个用户的uid和评分的平均值保存完毕");
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("2.每个用户的uid和评分的平均值失败");
		}

		// 3.最大方(评分平均值高)的3个用户的uid和评分平均值
		Collections.sort(avgRateList);
		try (BufferedWriter bw = new BufferedWriter(new FileWriter("D:/3.最大方(评分平均值高)的3个用户的uid和评分平均值.txt"));) {
			for (int i = 0; i < 3; i++) {
				Rate rate = avgRateList.get(i);
				bw.write(rate.toString());
				bw.newLine();
			}
			System.out.println("3.最大方(评分平均值高)的3个用户的uid和评分平均值保存完毕");
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("3.最大方(评分平均值高)的3个用户的uid和评分平均值保存失败");
		}

		// 4.最热门的3部电影id和评价次数
		ArrayList<HotMovie> hotMovieList = getHotMovieList(map2);
		try (BufferedWriter bw = new BufferedWriter(new FileWriter("D:/4.最热门的3部电影id和评价次数.txt"));) {
			for (int i = 0; i < 3; i++) {
				HotMovie hotMovie = hotMovieList.get(i);
				bw.write(hotMovie.toString());
				bw.newLine();
			}
			System.out.println("4.最热门的3部电影id和评价次数保存完毕");
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("4.最热门的3部电影id和评价次数保存失败");
		}

		// 5.评价最高的3部电影id和评分均值
		ArrayList<RateMovie> rateMovieList = tetRateMovieList(map2);
		try (BufferedWriter bw = new BufferedWriter(new FileWriter("D:/5.评价最高的3部电影id和评分均值.txt"));) {
			for (int i = 0; i < 3; i++) {
				RateMovie rateMovie = rateMovieList.get(i);
				bw.write(rateMovie.toString());
				bw.newLine();
			}
			System.out.println("5.评价最高的3部电影id和评分均值保存完毕");
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("5.评价最高的3部电影id和评分均值保存失败");
		}
	}

	private static ArrayList<RateMovie> tetRateMovieList(HashMap<Integer, ArrayList<Movie>> map2) {
		// 创建保存电影的历史评价分对象集合
		ArrayList<RateMovie> list = new ArrayList<RateMovie>();

		// 遍历电影对应的电影评分信息集合
		for (Entry<Integer, ArrayList<Movie>> entry : map2.entrySet()) {
			Integer movie = entry.getKey();// 电影的id
			ArrayList<Movie> list2 = entry.getValue();// 电影评分信息集合
			float rate = 0;
			for (Movie m : list2) {
				rate += m.getRate();
			}
			rate /= list2.size();
			list.add(new RateMovie(movie, rate));
		}

		Collections.sort(list);
		return list;
	}

	private static ArrayList<HotMovie> getHotMovieList(HashMap<Integer, ArrayList<Movie>> map2) {
		// 创建保存电影被评论次数对象的集合
		ArrayList<HotMovie> list = new ArrayList<HotMovie>();

		// 遍历电影对应的电影评分信息集合
		for (Entry<Integer, ArrayList<Movie>> entry : map2.entrySet()) {
			Integer movie = entry.getKey();// 电影的id
			ArrayList<Movie> list2 = entry.getValue();// 电影评分信息集合
			list.add(new HotMovie(movie, list2.size()));
		}

		Collections.sort(list);
		return list;
	}

	private static ArrayList<Rate> getAvgRateList(HashMap<Integer, ArrayList<Movie>> map) {
		// 存储用户评分的平均值信息
		ArrayList<Rate> list = new ArrayList<Rate>();
		// DecimalFormat df = new DecimalFormat("#.00");
		// df.format(number)
		// 遍历map集合，算出每一个用户的平均值，然后存储到list集合中
		for (Entry<Integer, ArrayList<Movie>> entry : map.entrySet()) {
			Integer uid = entry.getKey();
			float rate = 0;
			// 遍历电影评分信息然后累加评分
			ArrayList<Movie> list2 = entry.getValue();
			for (Movie m : list2) {
				rate += m.getRate();
			}
			rate /= list2.size();
			list.add(new Rate(uid, rate));
		}
		return list;
	}
}


猜你喜欢

转载自blog.csdn.net/a331685690/article/details/80230057
今日推荐
基于大语言模型的开源知识库问答系统 MaxKB GitHub Star 数量突破 5,000 个！
美国拟限制 AI 大模型出口中国和俄罗斯
苹果将与 OpenAI 达成协议，将 ChatGPT 应用于 iPhone
openKylin 社区生态委员会第六次会议圆满召开
阿里云正式发布通义千问 2.5
Python 3.13 发布首个 Beta：实验性自由线程模式和 JIT、改进交互式解释器
Stack Overflow 拿我的代码去训练 AI 大模型，还封了我的账号
Pop!_OS 的 COSMIC 桌面完成 App Store 上架工作
《2024 年一季度互联网投融资运行情况》研究报告
报告：Django 仍然是 74% 开发者的首选
15 年前上了“FFmpeg 耻辱柱”，今天他还得谢谢咱——腾讯QQPlayer一雪前耻？
TIOBE 5 月榜单：Fortran “复活”进入 Top 10
周排行
记一下去大梅沙的准备（2018-05-26）
Spring 注解 事务
基于HTTP协议的客户端缓存
阿里云rds 备份和还原
[PHP] 几个拖慢 PHP 程序/API 运行速度的点
python 代码风格------------PEP8规则
js控制json生成菜单——自制菜单（一）
将字符串: 'k:1|k1:2|k2:3|k3:4 ' ,处理成 python 字典: {'k':1, 'k1':2, ...}
微信小程序转支付宝小程序
Qt551.窗口滚动条
每日归档
更多
2024-05-13(18)
2024-05-12(0)
2024-05-11(38)
2024-05-10(38)
2024-05-09(35)
2024-05-08(42)
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022