转自：http://www.cnblogs.com/ywl925/archive/2013/08/26/3275878.html
前言
前段时间，又具体看了自己以前整理的TF-IDF，这里把它发布在博客上，知识就是需要不断的重复的，否则就感觉生疏了。
TF-IDF理解
TF-IDF（term frequency–inverse document frequency）是一种用于资讯检索与资讯探勘的常用加权技术, TFIDF的主要思想是：如果某个词或短语在一篇文章中出现的频率TF高，并且在其他文章中很少出现，则认为此词或者短语具有很好的类别区分能力，适合用来分类。TFIDF实际上是：TF * IDF，TF词频(Term Frequency)，IDF反文档频率(Inverse Document Frequency)。TF表示词条在文档d中出现的频率。IDF的主要思想是：如果包含词条t的文档越少，也就是n越小，IDF越大，则说明词条t具有很好的类别区分能力。如果某一类文档C中包含词条t的文档数为m，而其它类包含t的文档总数为k，显然所有包含t的文档数n=m + k，当m大的时候，n也大，按照IDF公式得到的IDF的值会小，就说明该词条t类别区分能力不强。但是实际上，如果一个词条在一个类的文档中频繁出现，则说明该词条能够很好代表这个类的文本的特征，这样的词条应该给它们赋予较高的权重，并选来作为该类文本的特征词以区别与其它类文档。这就是IDF的不足之处.
TF公式：
以上式子中 是该词在文件中的出现次数，而分母则是在文件中所有字词的出现次数之和。
IDF公式：
- |D|：语料库中的文件总数
- ：包含词语的文件数目（即的文件数目）如果该词语不在语料库中，就会导致被除数为零，因此一般情况下使用
然后
TF-IDF案例
案例：假如一篇文件的总词语数是100个，而词语“母牛”出现了3次，那么“母牛”一词在该文件中的词频就是3/100=0.03。一个计算文件频率 (DF) 的方法是测定有多少份文件出现过“母牛”一词，然后除以文件集里包含的文件总数。所以，如果“母牛”一词在1,000份文件出现过，而文件总数是10,000,000份的话，其逆向文件频率就是 lg(10,000,000 / 1,000)=4。最后的TF-IDF的分数为0.03 * 4=0.12。
TF-IDF实现（Java）
这里采用了外部插件IKAnalyzer-2012.jar，用其进行分词，插件和测试文件可以从这里下载：点击
具体代码如下：
按 Ctrl+C 复制代码
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("输入的[]");
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);
}
}
按 Ctrl+C 复制代码
结果如下图：
常见问题
没有加入lucene jar包
lucene包和je包版本不适合
