加入收藏 | 设为首页 | 会员中心 | 我要投稿 PHP编程网 - 金华站长网 (https://www.0579zz.com/)- 科技、建站、经验、云计算、5G、大数据,站长网!
当前位置: 首页 > 大数据 > 正文

利用文本挖掘技术来找出网络中的“小鲜词”

发布时间:2021-01-17 20:43:35 所属栏目:大数据 来源:网络整理
导读:副标题#e# 开始之前,先看一下从人人网中发现的90后用户爱用的词 是不是很好玩,哈哈。写这篇文章就是让你简单的自动的从文本中找出新的词,这样就知道现在的年轻人喜欢什么了(对于博主这种上了年纪的人来说,真的是很有用,呜呜) 项目结构 当然,text.da

用来做文本处理,如判断是否为空、匹配字符等

package grid.common;


public class TextUtils {

    public static boolean isCnLetter(char c) {
        return c >= 0x4E00 && c <= 0x9FCB;
    }

    public static boolean isNumeric(char c) {
        return c >= '0' && c <= '9';
    }

    public static boolean isEnLetter(char c) {
        return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
    }

    public static boolean match(String src,int off,String dest) {
        int len = dest.length();
        int srcLen = src.length();
        for (int i = 0; i < len; i++) {
            if (srcLen <= off + i) {
                return false;
            }
            if (dest.charAt(i) != src.charAt(off + i)) {
                return false;
            }
        }
        return true;
    }

    public static boolean isBlank(String str) {
        return null == str || str.isEmpty() || str.trim().isEmpty();
    }
}

Tree.java

语法树

package grid.common;


public class Tree<T> extends Node<T> {

    public Tree(T value) {
        super(value);
    }

}

dic

里边包含CnDictionary类

这里写图片描述

CnDictionary.java

词典处理

package grid.text.dic;

import grid.common.CountMap;
import grid.common.TextDatReader;
import grid.common.TextUtils;

import java.io.IOException;
import java.util.HashSet;
import java.util.Set;


public class CnDictionary {

    private final String COMMON_WORD_DIC_PATH = "common.dic";

    /** * This text data is for character statistic. Change to your own if you * like. */
    private final String COMMON_LETTER_RESOURCE_PATH = "text.dat";

    private Set<String> dictionary = new HashSet<String>();

    private CountMap<Character> letterCountMap = new CountMap<Character>();

    private int totalLetterCount;

    private static CnDictionary instance;
//单例模式
    public static CnDictionary Instance() {
        if (null == instance) {
            try {
                instance = new CnDictionary();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return instance;
    }

    private CnDictionary() throws IOException {
        initWordDic();
        initLetterCountMap();
    }

    private void initLetterCountMap() throws IOException {
        String letterResource = TextDatReader.read(COMMON_LETTER_RESOURCE_PATH);//读取语料数据 text.dat
        final int len = letterResource.length();
        char c;
        for (int i = 0; i < len; i++) {
            c = letterResource.charAt(i);
            if (TextUtils.isCnLetter(c)) {
                letterCountMap.increase(c);
            }
        }
        totalLetterCount = letterCountMap.count();

    }

    private void initWordDic() throws IOException {

        String bytes = TextDatReader.read(COMMON_WORD_DIC_PATH);//读取词典commondic
        final int len = bytes.length();
        String s = "";
        char c;
        for (int i = 0; i < len; i++) {
            c = bytes.charAt(i);

            if ('n' == c || 'r' == c || 0 == c) {
                if (!TextUtils.isBlank(s)) {
                    dictionary.add(s.trim());
                }
                s = "";
            } else {
                s += c;
            }
            if (0 == c) {
                break;
            }
        }
    }

    public boolean contains(String word) {
        return dictionary.contains(word);
    }

    public double rate(char c) {
        return (double) letterCountMap.get(c) / totalLetterCount;
    }

    public int size() {
        return dictionary.size();
    }
}

evolution

(编辑:PHP编程网 - 金华站长网)

【声明】本站内容均来自网络,其相关言论仅代表作者个人观点,不代表本站立场。若无意侵犯到您的权利,请及时与联系站长删除相关内容!