The data source can be downloaded here
Front-end visualization
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>词云</title>
</head>
<body>
<div class="btn-group">
<button onclick="loadAndShowWordcloud('正面')">正面</button>
<button onclick="loadAndShowWordcloud('负面')">负面</button>
</div>
<div id="main" style="width: 500px;height: 500px;"></div>
</body>
</html>
<script src="js/echarts.min.js"></script>
<script src="js/echarts-wordcloud.min.js"></script>
<script>
function loadAndShowWordcloud(type='正面'){
var chart = echarts.init(document.getElementById('main'));
// 1.新建请求对象
var request = new XMLHttpRequest();
//2.设置请求对象url
request.open('get','/wordcloud?type=' + type)
//3.发送请求
request.send()
//4.等待响应
request.onreadystatechange = function (){
if(request.readyState === 4){
var chart = echarts.init(document.getElementById("main"))
chart.setOption({
series: [{
type: 'wordCloud',
shape: 'circle',
keepAspect: false,
left: 'center',
top: 'center',
width: '100%',
height: '100%',
// sizeRange: [12, 60],
// rotationRange: [-90, 90],
// rotationStep: 45,
// drawOutOfBound: false,
// shrinkToFit: false,
textStyle: {
fontFamily: 'sans-serif',
fontWeight: 'bold',
// Color can be a callback function or a color string
color: function () {
// Random color
return 'rgb(' + [
Math.round(Math.random() * 160),
Math.round(Math.random() * 160),
Math.round(Math.random() * 160)
].join(',') + ')';
}
},
// Data is an array. Each array item must have name and value property.
data: JSON.parse(request.responseText)
}]
});
}
}
}
loadAndShowWordcloud()
</script>backend processing
First build an entity class Word
Note: To use annotations such as @Data, first import the configuration file of lombok
package com.example.springbootdemo1.entity;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import java.io.Serializable;
@Data
@NoArgsConstructor
@AllArgsConstructor
public class Word implements Serializable {
private String name;
private int value;
}
package com.example.springbootdemo1.contorller;
import com.example.springbootdemo1.entity.Word;
import com.example.springbootdemo1.util.StopWordUtil;
import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.seg.common.Term;
import lombok.extern.slf4j.Slf4j;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RestController;
import java.io.*;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
import java.util.function.Predicate;
import java.util.stream.Collectors;
@Slf4j
@RestController
public class WordCloudContorller {
@GetMapping("/wordcloud")
public List<Word> wordcloud(String type) throws IOException, ClassNotFoundException {
long l = System.currentTimeMillis();//记录开始时间
//=======================================================
//判断有没有被读取过,如果有读取，直接调用
//======================================================
File path = new File("D:\\word\\");
File file1 = new File(path,type);
//判断路径是否存在,如果不存在，就生成该路径
if (!path.exists()){
path.mkdirs();
}
//判断该文件是否已经存在，如果存在，直接读取
long s= System.currentTimeMillis();
if(file1.exists()){
//直接读取盘中内容
ObjectInputStream objectInputStream = new ObjectInputStream(new FileInputStream(file1));
LinkedList<Word>words =(LinkedList<Word>) objectInputStream.readObject();
if(words!=null){
objectInputStream.close();
long en= System.currentTimeMillis();
//读取本地花费时间
System.out.println(s-en);
return words;
}
}
//=========================================================
//没有生成结果，读取预料，并且分词统计次数
//=========================================================
if (type == null || type.equals("")) {
return new ArrayList<>(0);
}
File file = new File("C:\\Users\\luofei\\Desktop\\自然语言处理-张老师\\ChnSentiCorp情感分析酒店评论\\" + type);
File[] files = file.listFiles(File::isFile);
StringBuilder text = new StringBuilder();//线程不安全,相对于StringBuffer有速度优势
assert files != null;
for (File filess : files) {
try {
BufferedReader bufferedReader = new BufferedReader(new FileReader(filess));
String line = bufferedReader.readLine();
text.append(line);
bufferedReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
//分词
List<Term> segment = HanLP.segment(text.toString());
//保留分词类型为形容词
List<Term> termList = segment.stream().filter(new Predicate<Term>() {
@Override
public boolean test(Term term) {
return term.nature.toString().equalsIgnoreCase("n");
}
}).collect(Collectors.toList());
//转换成List<String>
List<String> collect = termList.stream().map(term -> term.word).collect(Collectors.toList());
//StopWordUtil.loadStopWord对停留词做预处理，判断是否存在，是否有值
List<String> stopWord = StopWordUtil.loadStopWord("C:\\Users\\luofei\\Desktop\\自然语言处理-张老师\\停留词.txt");
//去停留词
collect.removeAll(stopWord);
//统计分词次数
LinkedList<Word> words = new LinkedList<>();
for (Term word : termList) {
//第一次循环
if (words.size() == 0) {
words.add(new Word(word.word, 1));
}
//第二次循环
boolean exists = false;
Word word1 = null;
for (Word value : words) {
word1 = value;
if (word1.getName().equals(word.word)) {
exists = true;
break;
}
}
if (exists) {
word1.setValue(word1.getValue() + 1);
} else {
words.add(new Word(word.word, 1));
}
}
//========================================================
//将序列化结果，保存包文件中
//========================================================
ObjectOutputStream objectOutputStream = new ObjectOutputStream(new FileOutputStream(file1));
objectOutputStream.writeObject(words);
//清理缓存区
objectOutputStream.flush();
objectOutputStream.close();
//创建完成时间
long end = System.currentTimeMillis();
//计算总共花了多少时间
System.out.println(l - end);
return words;
}
}Show results
Note: just a classroom exercise