示例#1
0
  public static void RetrieveTrainMatrix() {
    try {
      BufferedReader flrdr =
          new BufferedReader(
              new FileReader("D:\\IR\\Assignment7\\Pytest\\part2\\output\\train_matrix.txt"));
      String line = "";
      int doc_count = 0;

      while ((line = flrdr.readLine()) != null) {
        SortedSet<Integer> word_ids = new TreeSet<Integer>();
        int val_count = 0;

        String[] key_value = line.split(" :: ");
        key_value[1] = key_value[1].substring(1, key_value[1].length() - 2);
        String[] values = key_value[1].split(",");

        FeatureNode[] node = new FeatureNode[values.length];

        for (String val : values) word_ids.add(Integer.parseInt(val.trim()));

        for (int val : word_ids) node[val_count++] = new FeatureNode(val, 1);

        if (spam_docs.contains(key_value[0].trim())) ylable[doc_count] = 1;
        else ylable[doc_count] = 0;

        train_matrix[doc_count++] = node;
      }
      flrdr.close();
    } catch (Exception e) {
      e.printStackTrace();
      System.exit(0);
    }
  }
示例#2
0
  public static void RetrieveSpamFiles() {
    try {
      BufferedReader flrdr =
          new BufferedReader(
              new FileReader("D:\\IR\\Assignment7\\Pytest\\part2\\output\\spam_docs.txt"));
      String line = flrdr.readLine();

      line = line.substring(1, line.length() - 1);

      for (String doc : line.split(",")) {
        spam_docs.add(doc.substring(2, doc.length() - 1).trim());
      }
      flrdr.close();
    } catch (Exception e) {
      e.printStackTrace();
    }
  }