데블스캠프2011/둘째날/Machine-Learning/NaiveBayesClassifier/김동준

Describe 데블스캠프2011/둘째날/Machine-Learning/NaiveBayesClassifier/김동준 here Train.java

package org.zeropage.machinelearn;

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

class Train {
	private Map<String,Integer> economyWord;
	private Map<String,Integer> politicWord;
	private int economyNum;
	private int politicNum;
	private boolean isSkipData(String inputStr) { // 자신의 사이트, 블로그, 페이지 주소의 경우 연관성이 떨어지므로 검색에서 제외
		if(inputStr.length() == 1 || inputStr.equals("http") || inputStr.equals("blog") || inputStr.equals("com") ||
			inputStr.equals("naver") || inputStr.equals("empas") || inputStr.equals("daum") || inputStr.equals("yahoo") ||
			inputStr.equals("tistory") || inputStr.equals("co") || inputStr.equals("kr") || inputStr.equals("www") || inputStr.equals("ohmynews") || 
			inputStr.equals("//") || inputStr.equals("블로그")) { 
			return true;
		}
		else { return false; }
	}
	public void TrainData() {
		this.economyNum = 0;
		this.politicNum = 0;
		this.economyWord = new HashMap<String,Integer>();
		this.politicWord = new HashMap<String,Integer>();
		try {
			Scanner economyLearn = new Scanner(new File("svm_data.tar/package/train/economy/index.economy.db"));
			while(economyLearn.hasNextLine()) {
				String[] a = economyLearn.nextLine().split(" ");
				for(String wordTmp:a) {
					if(isSkipData(wordTmp)) {continue;}
					if( this.economyWord.get(wordTmp) == null) {
						this.economyNum++;
						this.economyWord.put(wordTmp, 1);
					}
					else { this.economyWord.put(wordTmp, this.economyWord.get(wordTmp)+1); }
				}
			}
			economyLearn.close();
			Scanner politicLearn = new Scanner(new File("svm_data.tar/package/train/politics/index.politics.db"));
			while(politicLearn.hasNextLine()) {
				String[] a = politicLearn.nextLine().split(" ");
				for(String wordTmp:a) {
					if(isSkipData(wordTmp)) {continue; }
					if (this.politicWord.get(wordTmp) == null ) {
						this.politicNum++;
						this.politicWord.put(wordTmp, 1);
					}
					else { this.politicWord.put(wordTmp, this.politicWord.get(wordTmp)+1); }
				}
			}
			politicLearn.close();
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	public HashMap<String,Integer> getEconomyData() {
		return (HashMap<String, Integer>) this.economyWord;
	}
	public HashMap<String,Integer> getPoliticData() {
		return (HashMap<String, Integer>) this.politicWord;
	}
	public int getEconomyNumber() {
		return this.economyNum;
	}
	public int getPoliticNumber() {
		return this.politicNum;
	}
}

Analyzer.java

package org.zeropage.machinelearn;

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

public class Analyzer {
	private static HashMap<String,Integer> ecoData;
	private static HashMap<String,Integer> polData;
	private static Train machineTrain;
	
	private static double DocumentResult(File f, boolean isEconomy) {
		double negaNum = 0;
		double posiNum = 0;
		double ecoResultNum = 0;
		double polResultNum = 0;
		double reslt = 0;
		try {
			Scanner targetDocument = new Scanner(f);
			while(targetDocument.hasNextLine()) {
				String[] a = targetDocument.nextLine().split(" ");
				for(String wordTmp:a) {
					if(ecoData.get(wordTmp) == null) { ecoResultNum = 0; }
					else { ecoResultNum = ecoData.get(wordTmp); }
					if(polData.get(wordTmp) == null) { polResultNum = 0; }
					else { polResultNum = polData.get(wordTmp); }
					ecoResultNum += 1;
					polResultNum += 1;
					if(isEconomy && polData.get(wordTmp) == null) { polResultNum -= 0.5; } // 경제파트이면서 정치쪽에 없는 단어에 Advantage 부과
					if(!isEconomy && ecoData.get(wordTmp) == null) { ecoResultNum -= 0.5; } // 정치파트이면서 경제쪽에 없는 단어에 Adventage 부과
					if(isEconomy) { reslt += Math.log(ecoResultNum / polResultNum); }
					else { reslt += Math.log(polResultNum / ecoResultNum); }
				}
				if(reslt < 0) { negaNum+= 1; }
				else { posiNum += 1; }
				reslt = 0;
			}
			targetDocument.close();
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return posiNum / (posiNum+negaNum);
	}
	public static void Init() {
		machineTrain = new Train();
		machineTrain.TrainData();
		ecoData = machineTrain.getEconomyData();
		polData = machineTrain.getPoliticData();
	}
	public static void main(String[] args) {
		Init();
		double result1 = DocumentResult(new File("svm_data.tar/package/test/economy/economy.txt"), true);
		System.out.println(result1);
		double result2 = DocumentResult(new File("svm_data.tar/package/test/politics/politics.txt"), false);
		System.out.println(result2);
		System.out.println((result1 + result2) / 2);
	}
}

Train 의 Economy.txt 파일 적중도 : 0.995 (99.5%) Train 의 Politics.txt 파일 적중도 : 0.96 (96%) 전체 평균 적중도 : 0.9775 (97.75%) 위의 주석처럼 약간의 Advantage 와 필요없는 (http, //, blog, yahoo, empas, tistory 같은) 단어를 제외하고 작성할 수 있게 수정했습니다. 이 결과를 볼 수 있었으면 좋겠네요 ^^;;