请老师查阅我们组更新的vocabulary.py

app/vocabulary(2).py

@@ -0,0 +1,117 @@
+import pickle
+import string
+import os
+
+
+def read_pickle(file_name):
+    """Read data from a pickle file if it exists."""
+    if not os.path.isfile(file_name):
+        print(f"File {file_name} does not exist.")
+        return {}
+    with open(file_name, 'rb') as f:
+        return pickle.load(f)
+
+
+class VocabularyLevelEstimator:
+    # Load the word database for testing
+    _word_db = read_pickle('words_and_tests.p')
+
+    def evaluate_word_difficulty(self, word):
+        """Evaluate the difficulty level of a word."""
+        # Handle empty strings, punctuation only, or purely numeric strings.
+        if not word or all(ch in string.punctuation for ch in word) or word.isdigit():
+            return 0
+        return 5 if word in self._word_db else 0
+
+    @property
+    def difficulty_level(self):
+        return self.calculate_longest_words_level()
+
+
+class UserVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, vocab_dict):
+        self.vocab_dict = vocab_dict
+        # Use the last three words from the vocabulary dictionary.
+        self.recent_words = list(vocab_dict.keys())[-3:]
+
+    @property
+    def level(self):
+        """Calculate the user's vocabulary level considering word validity."""
+        valid_words = [word for word in self.recent_words if self.evaluate_word_difficulty(word) > 0]
+        valid_count = len(valid_words)
+
+        if valid_count == 0:
+            return 0
+
+        # Score for a single valid word
+        if valid_count == 1:
+            return self.score_single_word(valid_words[0])
+
+        # Logic for scoring multiple valid words
+        return self.score_multiple_words(valid_words)
+
+    def score_single_word(self, word):
+        """Evaluate the score of a single word."""
+        length = len(word)
+        if length < 7:
+            return 2
+        elif 7 <= length < 8:
+            return 5
+        return 6
+
+    def score_multiple_words(self, valid_words):
+        """Calculate the score for multiple valid words."""
+        total_score = 0
+        for word in valid_words:
+            length = len(word)
+            if length < 5:
+                total_score += 1
+            elif 5 <= length < 8:
+                total_score += 3
+            else:
+                total_score += 5
+
+        average_score = total_score / len(valid_words)
+        return min(int(average_score * 1.6), 8)
+
+
+class ArticleVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, article_text):
+        self.article_text = article_text
+        # Extract valid words and strip punctuation.
+        self.words = [
+            word.strip(string.punctuation)
+            for word in article_text.lower().split()
+            if word.strip(string.punctuation)
+        ]
+
+    @property
+    def level(self):
+        """Evaluate the article difficulty based on the longest ten valid words."""
+        valid_words = [word for word in self.words if self.evaluate_word_difficulty(word) > 0]
+        longest_words = sorted(valid_words, key=len, reverse=True)[:10]
+        if not longest_words:
+            return 0
+
+        difficulty_ratings = []
+        for word in longest_words:
+            length = len(word)
+            if length < 5:
+                difficulty_ratings.append(0.1)
+            elif 5 <= length < 8:
+                difficulty_ratings.append(0.2)
+            elif 8 <= length < 11:
+                difficulty_ratings.append(0.3)
+            else:
+                difficulty_ratings.append(0.5)
+
+        return sum(difficulty_ratings) + 2
+
+
+if __name__ == '__main__':
+    vocab_dict = read_pickle('frequency_mrlan85.pickle')
+    print(vocab_dict)
+    user = UserVocabularyLevel(vocab_dict)
+    print(user.level)
+    article = ArticleVocabularyLevel('This is an interesting article.')
+    print(article.level)