TF-IDF理解及其Java实现代码实例

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);
	}
}