TF-IDF理解及其Java實現

TF-IDF

前言

前段時間，又具體看了自己以前整理的TF-IDF，這里把它發布在博客上，知識就是需要不斷的重復的，否則就感覺生疏了。

TF-IDF理解

TF-IDF（term frequency–inverse document frequency）是一種用於資訊檢索與資訊探勘的常用加權技術, TFIDF的主要思想是：如果某個詞或短語在一篇文章中出現的頻率TF高，並且在其他文章中很少出現，則認為此詞或者短語具有很好的類別區分能力，適合用來分類。TFIDF實際上是：TF * IDF，TF詞頻(Term Frequency)，IDF反文檔頻率(Inverse Document Frequency)。TF表示詞條在文檔d中出現的頻率。IDF的主要思想是：如果包含詞條t的文檔越少，也就是n越小，IDF越大，則說明詞條t具有很好的類別區分能力。如果某一類文檔C中包含詞條t的文檔數為m，而其它類包含t的文檔總數為k，顯然所有包含t的文檔數n=m + k，當m大的時候，n也大，按照IDF公式得到的IDF的值會小，就說明該詞條t類別區分能力不強。但是實際上，如果一個詞條在一個類的文檔中頻繁出現，則說明該詞條能夠很好代表這個類的文本的特征，這樣的詞條應該給它們賦予較高的權重，並選來作為該類文本的特征詞以區別與其它類文檔。這就是IDF的不足之處.

TF公式：

       

以上式子中  是該詞在文件中的出現次數，而分母則是在文件中所有字詞的出現次數之和。

IDF公式：

  

• |D|：語料庫中的文件總數
• ：包含詞語的文件數目（即的文件數目）如果該詞語不在語料庫中，就會導致被除數為零，因此一般情況下使用

然后

TF-IDF案例

案例：假如一篇文件的總詞語數是100個，而詞語“母牛”出現了3次，那么“母牛”一詞在該文件中的詞頻就是3/100=0.03。一個計算文件頻率 (DF) 的方法是測定有多少份文件出現過“母牛”一詞，然后除以文件集里包含的文件總數。所以，如果“母牛”一詞在1,000份文件出現過，而文件總數是10,000,000份的話，其逆向文件頻率就是 lg(10,000,000 / 1,000)=4。最后的TF-IDF的分數為0.03 * 4=0.12。

TF-IDF實現（Java）

這里采用了外部插件IKAnalyzer-2012.jar，用其進行分詞，插件和測試文件可以從這里下載：點擊

具體代碼如下：

package tfidf;

import java.io.*;
import java.util.*;

import org.wltea.analyzer.lucene.IKAnalyzer;

public class ReadFiles {

    /**
     * @param args
     */    
    private static ArrayList<String> FileList = new ArrayList<String>(); // the list of file

    //get list of file for the directory, including sub-directory of it
    public static List<String> readDirs(String filepath) throws FileNotFoundException, IOException
    {
        try
        {
            File file = new File(filepath);
            if(!file.isDirectory())
            {
                System.out.println("輸入的[]");
                System.out.println("filepath:" + file.getAbsolutePath());
            }
            else
            {
                String[] flist = file.list();
                for(int i = 0; i < flist.length; i++)
                {
                    File newfile = new File(filepath + "\\" + flist[i]);
                    if(!newfile.isDirectory())
                    {
                        FileList.add(newfile.getAbsolutePath());
                    }
                    else if(newfile.isDirectory()) //if file is a directory, call ReadDirs
                    {
                        readDirs(filepath + "\\" + flist[i]);
                    }                    
                }
            }
        }catch(FileNotFoundException e)
        {
            System.out.println(e.getMessage());
        }
        return FileList;
    }
    
    //read file
    public static String readFile(String file) throws FileNotFoundException, IOException
    {
        StringBuffer strSb = new StringBuffer(); //String is constant， StringBuffer can be changed.
        InputStreamReader inStrR = new InputStreamReader(new FileInputStream(file), "gbk"); //byte streams to character streams
        BufferedReader br = new BufferedReader(inStrR); 
        String line = br.readLine();
        while(line != null){
            strSb.append(line).append("\r\n");
            line = br.readLine();    
        }
        
        return strSb.toString();
    }
    
    //word segmentation
    public static ArrayList<String> cutWords(String file) throws IOException{
        
        ArrayList<String> words = new ArrayList<String>();
        String text = ReadFiles.readFile(file);
        IKAnalyzer analyzer = new IKAnalyzer();
        words = analyzer.split(text);
        
        return words;
    }
    
    //term frequency in a file, times for each word
    public static HashMap<String, Integer> normalTF(ArrayList<String> cutwords){
        HashMap<String, Integer> resTF = new HashMap<String, Integer>();
        
        for(String word : cutwords){
            if(resTF.get(word) == null){
                resTF.put(word, 1);
                System.out.println(word);
            }
            else{
                resTF.put(word, resTF.get(word) + 1);
                System.out.println(word.toString());
            }
        }
        return resTF;
    }
    
    //term frequency in a file, frequency of each word
    public static HashMap<String, Float> tf(ArrayList<String> cutwords){
        HashMap<String, Float> resTF = new HashMap<String, Float>();
        
        int wordLen = cutwords.size();
        HashMap<String, Integer> intTF = ReadFiles.normalTF(cutwords); 
        
        Iterator iter = intTF.entrySet().iterator(); //iterator for that get from TF
        while(iter.hasNext()){
            Map.Entry entry = (Map.Entry)iter.next();
            resTF.put(entry.getKey().toString(), Float.parseFloat(entry.getValue().toString()) / wordLen);
            System.out.println(entry.getKey().toString() + " = "+  Float.parseFloat(entry.getValue().toString()) / wordLen);
        }
        return resTF;
    } 
    
    //tf times for file
    public static HashMap<String, HashMap<String, Integer>> normalTFAllFiles(String dirc) throws IOException{
        HashMap<String, HashMap<String, Integer>> allNormalTF = new HashMap<String, HashMap<String,Integer>>();
        
        List<String> filelist = ReadFiles.readDirs(dirc);
        for(String file : filelist){
            HashMap<String, Integer> dict = new HashMap<String, Integer>();
            ArrayList<String> cutwords = ReadFiles.cutWords(file); //get cut word for one file
            
            dict = ReadFiles.normalTF(cutwords);
            allNormalTF.put(file, dict);
        }    
        return allNormalTF;
    }
    
    //tf for all file
    public static HashMap<String,HashMap<String, Float>> tfAllFiles(String dirc) throws IOException{
        HashMap<String, HashMap<String, Float>> allTF = new HashMap<String, HashMap<String, Float>>();
        List<String> filelist = ReadFiles.readDirs(dirc);
        
        for(String file : filelist){
            HashMap<String, Float> dict = new HashMap<String, Float>();
            ArrayList<String> cutwords = ReadFiles.cutWords(file); //get cut words for one file
            
            dict = ReadFiles.tf(cutwords);
            allTF.put(file, dict);
        }
        return allTF;
    }
    public static HashMap<String, Float> idf(HashMap<String,HashMap<String, Float>> all_tf){
        HashMap<String, Float> resIdf = new HashMap<String, Float>();
        HashMap<String, Integer> dict = new HashMap<String, Integer>();
        int docNum = FileList.size();
        
        for(int i = 0; i < docNum; i++){
            HashMap<String, Float> temp = all_tf.get(FileList.get(i));
            Iterator iter = temp.entrySet().iterator();
            while(iter.hasNext()){
                Map.Entry entry = (Map.Entry)iter.next();
                String word = entry.getKey().toString();
                if(dict.get(word) == null){
                    dict.put(word, 1);
                }else {
                    dict.put(word, dict.get(word) + 1);
                }
            }
        }
        System.out.println("IDF for every word is:");
        Iterator iter_dict = dict.entrySet().iterator();
        while(iter_dict.hasNext()){
            Map.Entry entry = (Map.Entry)iter_dict.next();
            float value = (float)Math.log(docNum / Float.parseFloat(entry.getValue().toString()));
            resIdf.put(entry.getKey().toString(), value);
            System.out.println(entry.getKey().toString() + " = " + value);
        }
        return resIdf;
    }
    public static void tf_idf(HashMap<String,HashMap<String, Float>> all_tf,HashMap<String, Float> idfs){
        HashMap<String, HashMap<String, Float>> resTfIdf = new HashMap<String, HashMap<String, Float>>();
            
        int docNum = FileList.size();
        for(int i = 0; i < docNum; i++){
            String filepath = FileList.get(i);
            HashMap<String, Float> tfidf = new HashMap<String, Float>();
            HashMap<String, Float> temp = all_tf.get(filepath);
            Iterator iter = temp.entrySet().iterator();
            while(iter.hasNext()){
                Map.Entry entry = (Map.Entry)iter.next();
                String word = entry.getKey().toString();
                Float value = (float)Float.parseFloat(entry.getValue().toString()) * idfs.get(word); 
                tfidf.put(word, value);
            }
            resTfIdf.put(filepath, tfidf);
        }
        System.out.println("TF-IDF for Every file is :");
        DisTfIdf(resTfIdf);
    }
    public static void DisTfIdf(HashMap<String, HashMap<String, Float>> tfidf){
        Iterator iter1 = tfidf.entrySet().iterator();
        while(iter1.hasNext()){
            Map.Entry entrys = (Map.Entry)iter1.next();
            System.out.println("FileName: " + entrys.getKey().toString());
            System.out.print("{");
            HashMap<String, Float> temp = (HashMap<String, Float>) entrys.getValue();
            Iterator iter2 = temp.entrySet().iterator();
            while(iter2.hasNext()){
                Map.Entry entry = (Map.Entry)iter2.next(); 
                System.out.print(entry.getKey().toString() + " = " + entry.getValue().toString() + ", ");
            }
            System.out.println("}");
        }
        
    }
    public static void main(String[] args) throws IOException {
        // TODO Auto-generated method stub
        String file = "D:/testfiles";

        HashMap<String,HashMap<String, Float>> all_tf = tfAllFiles(file);
        System.out.println();
        HashMap<String, Float> idfs = idf(all_tf);
        System.out.println();
        tf_idf(all_tf, idfs);
        
    }

}

結果如下圖：

常見問題

沒有加入lucene jar包

 

 

lucene包和je包版本不適合