java 新词发现_java_java使用Nagao算法实现新词发现、热门词的挖掘，采用Nagao算法统计各个子字符 - phpStudy...

java使用Nagao算法实现新词发现、热门词的挖掘

采用Nagao算法统计各个子字符串的频次，然后基于这些频次统计每个字符串的词频、左右邻个数、左右熵、交互信息(内部凝聚度)。

名词解释：

Nagao算法：一种快速的统计文本里所有子字符串频次的算法。详细算法可见http://www.doc88.com/p-664123446503.html

词频：该字符串在文档中出现的次数。出现次数越多越重要。

左右邻个数：文档中该字符串的左边和右边出现的不同的字的个数。左右邻越多，说明字符串成词概率越高。

左右熵：文档中该字符串的左边和右边出现的不同的字的数量分布的熵。类似上面的指标，有一定区别。

交互信息：每次将某字符串分成两部分，左半部分字符串和右半部分字符串，计算其同时出现的概率除于其各自独立出现的概率，最后取所有的划分里面概率最小值。这个值越大，说明字符串内部凝聚度越高，越可能成词。

算法具体流程：

1.  将输入文件逐行读入，按照非汉字([^\u4E00-\u9FA5]+)以及停词“的很了么呢是嘛个都也比还这于不与才上用就好在和对挺去后没说”，

分成一个个字符串，代码如下：

String[] phrases = line.split("[^\u4E00-\u9FA5]+|["+stopwords+"]");

停用词可以修改。

2.  获取所有切分后的字符串的左子串和右子串，分别加入左、右PTable

3.  对PTable排序，并计算LTable。LTable记录的是，排序后的PTable中，下一个子串同上一个子串具有相同字符的数量

4.  遍历PTable和LTable，即可得到所有子字符串的词频、左右邻

5.  根据所有子字符串的词频、左右邻结果，输出字符串的词频、左右邻个数、左右熵、交互信息

1.  NagaoAlgorithm.java

package com.algo.word;

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.FileNotFoundException;

import java.io.FileReader;

import java.io.FileWriter;

import java.io.IOException;

import java.util.ArrayList;

import java.util.Arrays;

import java.util.Collections;

import java.util.HashMap;

import java.util.HashSet;

import java.util.List;

import java.util.Map;

import java.util.Set;

public class NagaoAlgorithm {

private int N;

private List leftPTable;

private int[] leftLTable;

private List rightPTable;

private int[] rightLTable;

private double wordNumber;

private Map wordTFNeighbor;

private final static String stopwords = "的很了么呢是嘛个都也比还这于不与才上用就好在和对挺去后没说";

private NagaoAlgorithm(){

//default N = 5

N = 5;

leftPTable = new ArrayList();

rightPTable = new ArrayList();

wordTFNeighbor = new HashMap();

}

//reverse phrase

private String reverse(String phrase) {

StringBuilder reversePhrase = new StringBuilder();

for (int i = phrase.length() - 1; i >= 0; i--)

reversePhrase.append(phrase.charAt(i));

return reversePhrase.toString();

}

//co-prefix length of s1 and s2

private int coPrefixLength(String s1, String s2){

int coPrefixLength = 0;

for(int i = 0; i < Math.min(s1.length(), s2.length()); i++){

if(s1.charAt(i) == s2.charAt(i)) coPrefixLength++;

else break;

}

return coPrefixLength;

}

//add substring of line to pTable

private void addToPTable(String line){

//split line according to consecutive none Chinese character

String[] phrases = line.split("[^\u4E00-\u9FA5]+|["+stopwords+"]");

for(String phrase : phrases){

for(int i = 0; i < phrase.length(); i++)

rightPTable.add(phrase.substring(i));

String reversePhrase = reverse(phrase);

for(int i = 0; i < reversePhrase.length(); i++)

leftPTable.add(reversePhrase.substring(i));

wordNumber += phrase.length();

}

}

//count lTable

private void countLTable(){

Collections.sort(rightPTable);

rightLTable = new int[rightPTable.size()];

for(int i = 1; i < rightPTable.size(); i++)

rightLTable[i] = coPrefixLength(rightPTable.get(i-1), rightPTable.get(i));

Collections.sort(leftPTable);

leftLTable = new int[leftPTable.size()];

for(int i = 1; i < leftPTable.size(); i++)

leftLTable[i] = coPrefixLength(leftPTable.get(i-1), leftPTable.get(i));

System.out.println("Info: [Nagao Algorithm Step 2]: having sorted PTable and counted left and right LTable");

}

//according to pTable and lTable, count statistical result: TF, neighbor distribution

private void countTFNeighbor(){

//get TF and right neighbor

for(int pIndex = 0; pIndex < rightPTable.size(); pIndex++){

String phrase = rightPTable.get(pIndex);

for(int length = 1 + rightLTable[pIndex]; length <= N && length <= phrase.length(); length++){

String word = phrase.substring(0, length);

TFNeighbor tfNeighbor = new TFNeighbor();

tfNeighbor.incrementTF();

if(phrase.length() > length)

tfNeighbor.addToRightNeighbor(phrase.charAt(length));

for(int lIndex = pIndex+1; lIndex < rightLTable.length; lIndex++){

if(rightLTable[lIndex] >= length){

tfNeighbor.incrementTF();

String coPhrase = rightPTable.get(lIndex);

if(coPhrase.length() > length)

tfNeighbor.addToRightNeighbor(coPhrase.charAt(length));

}

else break;

}

wordTFNeighbor.put(word, tfNeighbor);

}

}

//get left neighbor

for(int pIndex = 0; pIndex < leftPTable.size(); pIndex++){

String phrase = leftPTable.get(pIndex);

for(int length = 1 + leftLTable[pIndex]; length <= N && length <= phrase.length(); length++){

String word = reverse(phrase.substring(0, length));

TFNeighbor tfNeighbor = wordTFNeighbor.get(word);

if(phrase.length() > length)

tfNeighbor.addToLeftNeighbor(phrase.charAt(length));

for(int lIndex = pIndex + 1; lIndex < leftLTable.length; lIndex++){

if(leftLTable[lIndex] >= length){

String coPhrase = leftPTable.get(lIndex);

if(coPhrase.length() > length)

tfNeighbor.addToLeftNeighbor(coPhrase.charAt(length));

}

else break;

}

}

}

System.out.println("Info: [Nagao Algorithm Step 3]: having counted TF and Neighbor");

}

//according to wordTFNeighbor, count MI of word

private double countMI(String word){

if(word.length() <= 1) return 0;

double coProbability = wordTFNeighbor.get(word).getTF()/wordNumber;

List mi = new ArrayList(word.length());

for(int pos = 1; pos < word.length(); pos++){

String leftPart = word.substring(0, pos);

String rightPart = word.substring(pos);

double leftProbability = wordTFNeighbor.get(leftPart).getTF()/wordNumber;

double rightProbability = wordTFNeighbor.get(rightPart).getTF()/wordNumber;

mi.add(coProbability/(leftProbability*rightProbability));

}

return Collections.min(mi);

}

//save TF, (left and right) neighbor number, neighbor entropy, mutual information

private void saveTFNeighborInfoMI(String out, String stopList, String[] threshold){

try {

//read stop words file

Set stopWords = new HashSet();

BufferedReader br = new BufferedReader(new FileReader(stopList));

String line;

while((line = br.readLine()) != null){

if(line.length() > 1)

stopWords.add(line);

}

br.close();

//output words TF, neighbor info, MI

BufferedWriter bw = new BufferedWriter(new FileWriter(out));

for(Map.Entry entry : wordTFNeighbor.entrySet()){

if( entry.getKey().length() <= 1 || stopWords.contains(entry.getKey()) ) continue;

TFNeighbor tfNeighbor = entry.getValue();

int tf, leftNeighborNumber, rightNeighborNumber;

double mi;

tf = tfNeighbor.getTF();

leftNeighborNumber = tfNeighbor.getLeftNeighborNumber();

rightNeighborNumber = tfNeighbor.getRightNeighborNumber();

mi = countMI(entry.getKey());

if(tf > Integer.parseInt(threshold[0]) && leftNeighborNumber > Integer.parseInt(threshold[1]) &&

rightNeighborNumber > Integer.parseInt(threshold[2]) && mi > Integer.parseInt(threshold[3]) ){

StringBuilder sb = new StringBuilder();

sb.append(entry.getKey());

sb.append(",").append(tf);

sb.append(",").append(leftNeighborNumber);

sb.append(",").append(rightNeighborNumber);

sb.append(",").append(tfNeighbor.getLeftNeighborEntropy());

sb.append(",").append(tfNeighbor.getRightNeighborEntropy());

sb.append(",").append(mi).append("\n");

bw.write(sb.toString());

}

}

bw.close();

} catch (IOException e) {

throw new RuntimeException(e);

}

System.out.println("Info: [Nagao Algorithm Step 4]: having saved to file");

}

//apply nagao algorithm to input file

public static void applyNagao(String[] inputs, String out, String stopList){

NagaoAlgorithm nagao = new NagaoAlgorithm();

//step 1: add phrases to PTable

String line;

for(String in : inputs){

try {

BufferedReader br = new BufferedReader(new FileReader(in));

while((line = br.readLine()) != null){

nagao.addToPTable(line);

}

br.close();

} catch (IOException e) {

throw new RuntimeException();

}

}

System.out.println("Info: [Nagao Algorithm Step 1]: having added all left and right substrings to PTable");

//step 2: sort PTable and count LTable

nagao.countLTable();

//step3: count TF and Neighbor

nagao.countTFNeighbor();

//step4: save TF NeighborInfo and MI

nagao.saveTFNeighborInfoMI(out, stopList, "20,3,3,5".split(","));

}

public static void applyNagao(String[] inputs, String out, String stopList, int n, String filter){

NagaoAlgorithm nagao = new NagaoAlgorithm();

nagao.setN(n);

String[] threshold = filter.split(",");

if(threshold.length != 4){

System.out.println("ERROR: filter must have 4 numbers, seperated with ',' ");

return;

}

//step 1: add phrases to PTable

String line;

for(String in : inputs){

try {

BufferedReader br = new BufferedReader(new FileReader(in));

while((line = br.readLine()) != null){

nagao.addToPTable(line);

}

br.close();

} catch (IOException e) {

throw new RuntimeException();

}

}

System.out.println("Info: [Nagao Algorithm Step 1]: having added all left and right substrings to PTable");

//step 2: sort PTable and count LTable

nagao.countLTable();

//step3: count TF and Neighbor

nagao.countTFNeighbor();

//step4: save TF NeighborInfo and MI

nagao.saveTFNeighborInfoMI(out, stopList, threshold);

}

private void setN(int n){

N = n;

}

public static void main(String[] args) {

String[] ins = {"E://test//ganfen.txt"};

applyNagao(ins, "E://test//out.txt", "E://test//stoplist.txt");

}

}

2. TFNeighbor.java

package com.algo.word;

import java.util.HashMap;

import java.util.Map;

public class TFNeighbor {

private int tf;

private Map leftNeighbor;

private Map rightNeighbor;

TFNeighbor(){

leftNeighbor = new HashMap();

rightNeighbor = new HashMap();

}

//add word to leftNeighbor

public void addToLeftNeighbor(char word){

//leftNeighbor.put(word, 1 + leftNeighbor.getOrDefault(word, 0));

Integer number = leftNeighbor.get(word);

leftNeighbor.put(word, number == null? 1: 1+number);

}

//add word to rightNeighbor

public void addToRightNeighbor(char word){

//rightNeighbor.put(word, 1 + rightNeighbor.getOrDefault(word, 0));

Integer number = rightNeighbor.get(word);

rightNeighbor.put(word, number == null? 1: 1+number);

}

//increment tf

public void incrementTF(){

tf++;

}

public int getLeftNeighborNumber(){

return leftNeighbor.size();

}

public int getRightNeighborNumber(){

return rightNeighbor.size();

}

public double getLeftNeighborEntropy(){

double entropy = 0;

int sum = 0;

for(int number : leftNeighbor.values()){

entropy += number*Math.log(number);

sum += number;

}

if(sum == 0) return 0;

return Math.log(sum) - entropy/sum;

}

public double getRightNeighborEntropy(){

double entropy = 0;

int sum = 0;

for(int number : rightNeighbor.values()){

entropy += number*Math.log(number);

sum += number;

}

if(sum == 0) return 0;

return Math.log(sum) - entropy/sum;

}

public int getTF(){

return tf;

}

}

3. Main.java

package com.algo.word;

public class Main {

public static void main(String[] args) {

//if 3 arguments, first argument is input files splitting with ','

//second argument is output file

//output 7 columns split with ',' , like below:

//word, term frequency, left neighbor number, right neighbor number, left neighbor entropy, right neighbor entropy, mutual information

//third argument is stop words list

if(args.length == 3)

NagaoAlgorithm.applyNagao(args[0].split(","), args[1], args[2]);

//if 4 arguments, forth argument is the NGram parameter N

//5th argument is threshold of output words, default is "20,3,3,5"

//output TF > 20 && (left | right) neighbor number > 3 && MI > 5

else if(args.length == 5)

NagaoAlgorithm.applyNagao(args[0].split(","), args[1], args[2], Integer.parseInt(args[3]), args[4]);

}

}

以上所述就是本文的全部内容了，希望大家能够喜欢。相关阅读:

js中replace的用法总结

javascript每日必学之继承

Android-App增量更新的使用姿势

详谈JS中实现种子随机数及作用

php数组添加与删除单元的常用函数实例分析

Win7怎么更换扫雷游戏的外观让其与众不同

Eclipse中php插件安装及Xdebug配置的使用详解

PHP魔术引号所带来的安全问题分析

JS使用eval解析JSON的注意事项分析

php实现带读写分离功能的MySQL类完整实例

不让tomcat显示目录文件列表的配置方法

自定义刻度jQuery进度条及插件

div清除浮动css样式代码分享(4种方法)

ie7+背景透明文字不透明超级简单的实现方法