parent
c4378e73cd
commit
a83f91a88d
|
@ -24,7 +24,7 @@ def convert_test_type_to_difficulty_level(d):
|
|||
:return:
|
||||
"""
|
||||
result = {}
|
||||
L = list(d.keys()) # in dic, we have test types (e.g., CET4,CET6,BBC) for each word
|
||||
L = list(d.keys()) # in d, we have test types (e.g., CET4,CET6,BBC) for each word
|
||||
|
||||
for k in L:
|
||||
if 'CET4' in d[k]:
|
||||
|
@ -33,30 +33,13 @@ def convert_test_type_to_difficulty_level(d):
|
|||
result[k] = 5
|
||||
elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
|
||||
result[k] = 6
|
||||
elif 'OXFORD5000' in d[k]:
|
||||
elif 'OXFORD5000' in d[k] or 'IELTS' in d[k]:
|
||||
result[k] = 7
|
||||
elif 'BBC' in d[k]:
|
||||
result[k] = 8
|
||||
|
||||
return result # {'apple': 4, ...}
|
||||
|
||||
def simplify_the_words_dict(d):
|
||||
"""
|
||||
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')
|
||||
|
||||
result = {}
|
||||
for k in d: # j 在字典中
|
||||
temp = stem.stemWord(k) # 提取j得词根
|
||||
if temp not in result: # 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
|
||||
result[temp] = d[k]
|
||||
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 result[temp] > d[k]:
|
||||
result[temp] = d[k]
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def get_difficulty_level_for_user(d1, d2):
|
||||
"""
|
||||
|
@ -65,14 +48,13 @@ def get_difficulty_level_for_user(d1, d2):
|
|||
在d2的后面添加单词,没有新建一个新的字典
|
||||
"""
|
||||
d2 = convert_test_type_to_difficulty_level(d2) # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
|
||||
d2_simplified = simplify_the_words_dict(d2) # 提取d2的词根 {'appl': 4, 'abandon': 4, ...}
|
||||
stem = snowballstemmer.stemmer('english')
|
||||
|
||||
for k in d1: # 用户的词
|
||||
if k in d2: # 如果用户的词以原型的形式存在于词库d2中
|
||||
continue # 无需评级,跳过
|
||||
elif stem.stemWord(k) in d2_simplified: # 如果用户的词的词根存在于词库d2的词根库中
|
||||
d2[k] = d2_simplified[k] # 按照词根进行评级
|
||||
elif stem.stemWord(k) in d2: # 如果用户的词的词根存在于词库d2的词根库中
|
||||
d2[k] = d2[stem.stemWord(k)] # 按照词根进行评级
|
||||
break
|
||||
else:
|
||||
d2[k] = 3 # 如果k的词根都不在,那么就当认为是3级
|
||||
|
@ -108,7 +90,7 @@ def user_difficulty_level(d_user, d):
|
|||
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
|
||||
lst2 = [] # a list of tuples, (word, difficulty level)
|
||||
for word in lst:
|
||||
for word in lst:
|
||||
if word in d:
|
||||
lst2.append((word, d[word]))
|
||||
|
||||
|
|
Loading…
Reference in New Issue