TF-IDF(转)输出到文本

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
try
{
FileWriter writer = new FileWriter("d:\\DF.txt", true);

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);
// 输出到文件
writer.write(entry.getKey().toString() + " = "+ Float.parseFloat(entry.getValue().toString()) / wordLen+"\r\n");


}//end with while
writer.close();
}
catch(Exception ex)
{

}
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:");
try
{
FileWriter writer = new FileWriter("d:\\IDF.txt", true);
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);
writer.write(entry.getKey().toString() + " = " + value+"\r\n");

}
writer.close();
}
catch(Exception ex)
{
System.out.println("Error");
return null;
}
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();
try
{
FileWriter writer = new FileWriter("d:\\TF-IDF.txt", true);
String strtemp="";
while(iter1.hasNext()){
Map.Entry entrys = (Map.Entry)iter1.next();
System.out.println("FileName: " + entrys.getKey().toString());
//writer.write("FileName: " + entrys.getKey().toString());
System.out.print("{");
writer.write("{");
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() + ", ");
// 输出到文件
strtemp+=entry.getKey().toString() + " = " + entry.getValue().toString() + ", ";
//writer.write(entry.getKey().toString() + " = " + entry.getValue().toString() + ", ");

}
strtemp=strtemp.substring(0, strtemp.length()-2);
writer.write(strtemp);
System.out.println("}");
writer.write("}"+"\r\n");
}
writer.close();
}
catch(Exception ex)
{
System.out.println("error!");
return;
}
}
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);

}

}
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值