filespamtester.java

Practical AI in Java 人工智能编程

import java.util.Vector;
import java.io.File;
import java.io.FileReader;
import java.io.BufferedReader;


public class FileSpamTester {
    public static void main(String[] args) throws Exception {
        BayesianTrainer bn = new BayesianTrainer();
        BayesianSpamChecker checker = new BayesianSpamChecker(bn.getWordProbabilityHashtable());
        Vector files = getFiles("./test_data");
        System.out.println("\n\nSPAM test:\n");
        for (int i=0, size=files.size(); i<size; i++) {
            String file_name = (String)files.get(i);
            BufferedReader fr = new BufferedReader(new FileReader(file_name));
            StringBuffer sb = new StringBuffer();
            while (true) {
                String s = fr.readLine();
                if (s == null) break;
                sb.append(s);
                sb.append("\n");
            }
            float probability = checker.probabilityOfSpam(sb.toString());
            System.out.println("file: "+file_name+", probability of being SPAM="+probability);
        }
    }

    public static final String fileSeparator = System.getProperty("file.separator");
    static public Vector getFiles(String path) {
        try {
            File dir = new File(path);
            LocalFileFilter filter = new LocalFileFilter();
            String[] ss = dir.list(filter);
            if (ss == null || ss.length == 0) return null;
            Vector v = new Vector(ss.length);
            for (int i = 0; i < ss.length; i++) {
                v.addElement(path + fileSeparator + ss[i]);
            }
            return v;
        } catch (Exception e) {
            System.out.println("Error in getFiles:" + e);
        }
        return null;
    }
}