删除 'Bug476-ZhangWeiHao-BaoYuelin'

app/difficulty.py

@@ -8,7 +8,6 @@
 import pickle
 import math
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
-import snowballstemmer
 
 
 def load_record(pickle_fname):
@@ -19,12 +18,6 @@ def load_record(pickle_fname):
 
 
 def difficulty_level_from_frequency(word, d):
-    """
-    根据单词的频率进行难度的评级
-    :param word:
-    :param d:
-    :return:
-    """
     level = 1
     if not word in d:
         return level
@@ -37,62 +30,27 @@ def difficulty_level_from_frequency(word, d):
     return level
 
 
-def get_difficulty_level_for_words_and_tests(dic):
-    """
-    对原本的单词库中的单词进行难度评级
-    :param dic: 存储了单词库pickle文件中的单词的字典
-    :return:
-    """
-    d = {}
-    L = list(dic.keys())  # in dic, we have test types (e.g., CET4,CET6,BBC) for each word
-
-    for k in L:
-        if 'CET4' in dic[k]:
-            d[k] = 4  # CET4 word has level 4
-        elif 'CET6' in dic[k]:
-            d[k] = 6
-        elif 'BBC' in dic[k]:
-            d[k] = 8
-        # print(k, d[k])
-
-    return d  # {'apple': 4, ...}
-
-def simplify_the_words_dict(dic):
-    """
-    用于把保存了词库中评级后的词新建一个以词根为键、以同词根的最低等级为值
-    """
-    stem = snowballstemmer.stemmer('english')
-
-    res = {}
-    for j in dic:   # j 在字典中
-        temp = stem.stemWord(j)     # 提取j得词根
-        if not temp in res:         # 如果这个词根不在结果字典中，则以词根为键、以dic中的等级作为值添加
-            res[temp] = dic[j]
-        else:                   # 如果这个词在结果词典中，则比较一下单词的难度等级是否最小
-            if res[temp] > dic[j]:
-                res[temp] = dic[j]
-
-    return res
-
-
 def get_difficulty_level(d1, d2):
-    """
+    d = {}
-    d2 来自于词库的27000个已标记单词
+    L = list(d1.keys())  # in d1, we have freuqence for each word
-    d1 你个老六不会的词
+    L2 = list(d2.keys()) # in d2, we have test types (e.g., CET4,CET6,BBC) for each word
-    在d2的后面添加单词，没有新建一个新的字典
+    L.extend(L2)
-    """
+    L3 = list(set(L)) # L3 contains all words
-    d2 = get_difficulty_level_for_words_and_tests(d2)   # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+    for k in L3:
-    d2_sim = simplify_the_words_dict(d2)                # 提取d2的词根   {'appl': 4, 'abandon': 4, ...}
+        if k in d2:
-    stem = snowballstemmer.stemmer('english')
+            if 'CET4' in d2[k]:
+                d[k] = 4 # CET4 word has level 4
+            elif 'CET6' in d2[k]:
+                d[k] = 6
+            elif 'BBC' in d2[k]:
+                d[k] = 8
+                if k in d1: # BBC could contain easy words that are not in CET4 or CET6.  So 4 is not reasonable.  Recompute difficulty level.
+                    d[k] = min(difficulty_level_from_frequency(k, d1), d[k])
+        elif k in d1:
+            d[k] = difficulty_level_from_frequency(k, d1)
+
+    return d
 
-    for k in d1:        # 用户的词
-        for l in d2_sim:        # l是词库的某个单词的词根
-            if stem.stemWord(k) == l:   # 两者相等则视为同一难度的词
-                d2[k] = d2_sim[l]       # 给d2定级
-                break
-            else:       # 不相等则表明词库中没这词，按照单词的频率定级
-                d2[k] = difficulty_level_from_frequency(k, d1)
-    return d2
         
 
 def revert_dict(d):