app/difficulty.py

@@ -7,9 +7,6 @@
 
 import pickle
 import math
-from nltk import word_tokenize,pos_tag
-from nltk.corpus import wordnet
-from nltk.stem import WordNetLemmatizer
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
 
 
@@ -77,34 +74,6 @@ def revert_dict(d):
                 d2[date].append(k)
     return d2
 
-def get_wordnet_pos(tag):
-    if tag.startswith('J'):
-        return wordnet.ADJ
-    elif tag.startswith('V'):
-        return wordnet.VERB
-    elif tag.startswith('N'):
-       return wordnet.NOUN
-    elif tag.startswith('R'):
-        return wordnet.ADV
-    else:
-        return None
-
-
-def combine_words_through_grammar(lst,d): #通过语法合并同一单词的不同形式 
-    lst1=lst
-    tagged_sent = pos_tag(lst)     # 获取单词词性
-    print(tagged_sent)
-    wnl = WordNetLemmatizer()
-    lemmas_sent = []
-    for tag in tagged_sent:
-        wordnet_pos = get_wordnet_pos(tag[1]) or wordnet.NOUN
-        lemmas_sent.append(wnl.lemmatize(tag[0], pos=wordnet_pos)) # 词形还原
-    for index,change_word in enumerate(lemmas_sent):
-        for word2 in d:
-            if change_word==word2:
-                lst1[index]=change_word
-    return lst1  
-   
 
 def user_difficulty_level(d_user, d):
     d_user2 = revert_dict(d_user) # key is date, and value is a list of words added in that date
@@ -112,7 +81,6 @@ def user_difficulty_level(d_user, d):
     geometric = 1
     for date in sorted(d_user2.keys(), reverse=True): # most recently added words are more important while determining user's level
         lst = d_user2[date] # a list of words
-        lst=combine_words_through_grammar(lst,d) #合并单词的不同形式
         lst2 = [] # a list of tuples, (word, difficulty level)
         for  word in lst:
             if word in d: