구현

계획 복습

정규화

토큰화

개수 세기

보고

코드: 전체 실행

public class Main {
  public static void main(String[] args) {
    // Implementation: normalize, tokenize, count, and print top 5.
    String text = "Be yourself; everyone else is already taken. Be kind. Be clear.";
    // 1) Lowercase
    String lower = text.toLowerCase();
    // 2) Replace non letters with spaces
    String cleaned = lower.replaceAll("[^a-z]+", " ");
    // 3) Split on spaces and filter empties
    String[] tokens = cleaned.trim().split("\\s+");

    java.util.Map<String, Integer> freq = new java.util.HashMap<>();
    int total = 0;
    for (int i = 0; i < tokens.length; i = i + 1) {
      String w = tokens[i];
      if (w.length() == 0) continue;
      total = total + 1;
      Integer c = freq.get(w);
      if (c == null) freq.put(w, 1);
      else freq.put(w, c + 1);
    }

    // Print top 5 words using repeated selection (simple for small data)
    int topN = 5;
    for (int k = 0; k < topN; k = k + 1) {
      String bestWord = null;
      int bestCount = -1;
      for (java.util.Map.Entry<String,Integer> e : freq.entrySet()) {
        String word = e.getKey();
        int count = e.getValue();
        if (count > bestCount) {
          bestCount = count;
          bestWord = word;
        }
      }
      if (bestWord == null || bestCount < 0) break;
      System.out.println("#" + (k + 1) + " " + bestWord + " = " + bestCount);
      // mark as used so it will not be picked again
      freq.put(bestWord, -1000000);
    }

    System.out.println("Total words: " + total);
    System.out.println("Unique words: " + (freq.size()));
  }
}

일관성 확인

복습