头歌-旅游网站之数据可视化 第3关:获取酒店评论数据生成词云
·
代码如下:
package com.showdata;
import com.kennycason.kumo.CollisionMode;
import com.kennycason.kumo.WordCloud;
import com.kennycason.kumo.WordFrequency;
import com.kennycason.kumo.bg.PixelBoundryBackground;
import com.kennycason.kumo.font.KumoFont;
import com.kennycason.kumo.image.AngleGenerator;
import com.kennycason.kumo.palette.LinearGradientColorPalette;
import com.kennycason.kumo.wordstart.CenterWordStart;
import com.util.HBaseUtil;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import java.awt.*;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
/**
* 词云
*/
public class CommentWordCloud {
public WordCloud get() throws IOException {
Connection conn = HBaseUtil.getConnection();
/********** Begin **********/
//1.读取Hbase表中数据显示
TableName tableName = TableName.valueOf(Bytes.toBytes("comment_word_count"));
Table table = conn.getTable(tableName); // 连接表
Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
List<WordFrequency> words = new ArrayList<>();
for (Result result : scanner) {
String word = new String(result.getRow(), "UTF-8");
int count = Bytes.toInt(result.getValue("word_info".getBytes(), "count".getBytes())); // 获取词频
WordFrequency wordFrequency = new WordFrequency(word, count);
if (count > 10) {
words.add(wordFrequency); // 由于文件中词汇过多,将大于10个的存进去将会大量减少运行时间
}
}
//2.生成并渲染图片
Dimension dimension = new Dimension(500, 312);
WordCloud wordCloud = new WordCloud(dimension, CollisionMode.PIXEL_PERFECT);
wordCloud.setPadding(2);
// 修正字体定义,使用Font类常量
Font font = new Font("宋体", Font.ITALIC, 24);
wordCloud.setKumoFont(new KumoFont(font));
// 设置渐变色板
wordCloud.setColorPalette(new LinearGradientColorPalette(Color.RED, Color.BLUE, Color.GREEN, 30, 30));
// 修正背景设置
wordCloud.setBackgroundColor(Color.WHITE);
wordCloud.setBackground(new PixelBoundryBackground("myImgs/whale_small.png"));
wordCloud.setWordStartStrategy(new CenterWordStart());
// 修正类名拼写
wordCloud.setAngleGenerator(new AngleGenerator(0));
// 修正变量名拼写
wordCloud.build(words);
/********** End **********/
wordCloud.writeToFile("imgs/wordcloud_comment.png");
return wordCloud;
}
public static void main(String[] args) {
try {
CommentWordCloud wordCloudGenerator = new CommentWordCloud();
wordCloudGenerator.get();
System.out.println("词云生成成功!");
} catch (IOException e) {
System.err.println("生成词云时出错: " + e.getMessage());
e.printStackTrace();
}
}
}
DAMO开发者矩阵,由阿里巴巴达摩院和中国互联网协会联合发起,致力于探讨最前沿的技术趋势与应用成果,搭建高质量的交流与分享平台,推动技术创新与产业应用链接,围绕“人工智能与新型计算”构建开放共享的开发者生态。
更多推荐

所有评论(0)