1
0
Fork 0
Bug476-ZhangWeiHao-YuHuangtao
俞黄焘 2023-05-16 19:02:16 +08:00
parent 541f78c7ea
commit fc515a7b08
2 changed files with 9 additions and 9 deletions

View File

@ -7,7 +7,7 @@ import random, glob
import hashlib import hashlib
from datetime import datetime from datetime import datetime
from flask import Flask, request, redirect, render_template, url_for, session, abort, flash, get_flashed_messages from flask import Flask, request, redirect, render_template, url_for, session, abort, flash, get_flashed_messages
from difficulty import get_difficulty_level, text_difficulty_level, user_difficulty_level from difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
path_prefix = '/var/www/wordfreq/wordfreq/' path_prefix = '/var/www/wordfreq/wordfreq/'
@ -45,7 +45,7 @@ def get_today_article(user_word_list, articleID):
# Choose article according to reader's level # Choose article according to reader's level
d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p') d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p')
d2 = load_freq_history(path_prefix + 'static/words_and_tests.p') d2 = load_freq_history(path_prefix + 'static/words_and_tests.p')
d3 = get_difficulty_level(d1, d2) d3 = get_difficulty_level_for_user(d1, d2)
d = {} d = {}
d_user = load_freq_history(user_word_list) d_user = load_freq_history(user_word_list)

View File

@ -37,7 +37,7 @@ def difficulty_level_from_frequency(word, d):
return level return level
def get_difficulty_level_for_words_and_tests(d): def convert_test_type_to_difficulty_level(d):
""" """
对原本的单词库中的单词进行难度评级 对原本的单词库中的单词进行难度评级
:param d: 存储了单词库pickle文件中的单词的字典 :param d: 存储了单词库pickle文件中的单词的字典
@ -51,12 +51,12 @@ def get_difficulty_level_for_words_and_tests(d):
result[k] = 4 # CET4 word has level 4 result[k] = 4 # CET4 word has level 4
elif 'CET6' in d[k] or 'GRADUATE' in d[k]: elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
result[k] = 6 result[k] = 6
elif 'IELTS' in d[k]: # 雅思或研究生英语 elif 'IELTS' in d[k]: # 雅思
result[k] = 7 result[k] = 7
elif 'BBC' in d[k]: elif 'BBC' in d[k]:
result[k] = 8 result[k] = 8
# elif 'EnWords' in d[k]: # 除基础词汇外的绝大多数词,包括一些犄角旮旯的专业词汇,近九万个,定级不太好处理,绝大多数我是真不认识 elif 'EnWords' in d[k]: # 除基础词汇外的绝大多数词,包括一些犄角旮旯的专业词汇,近九万个,定级不太好处理,绝大多数我是真不认识
# result[k] = 7 result[k] = 3
return result # {'apple': 4, ...} return result # {'apple': 4, ...}
@ -78,13 +78,13 @@ def simplify_the_words_dict(d):
return result return result
def get_difficulty_level(d1, d2): def get_difficulty_level_for_user(d1, d2):
""" """
d2 来自于词库的27000个已标记单词 d2 来自于词库的27000个已标记单词
d1 用户不会的词 d1 用户不会的词
在d2的后面添加单词没有新建一个新的字典 在d2的后面添加单词没有新建一个新的字典
""" """
d2 = get_difficulty_level_for_words_and_tests(d2) # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...} 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, ...} d2_simplified = simplify_the_words_dict(d2) # 提取d2的词根 {'appl': 4, 'abandon': 4, ...}
stem = snowballstemmer.stemmer('english') stem = snowballstemmer.stemmer('english')
@ -181,7 +181,7 @@ if __name__ == '__main__':
#print(d2) #print(d2)
d3 = get_difficulty_level(d1, d2) d3 = get_difficulty_level_for_user(d1, d2)
s = ''' s = '''
South Lawn South Lawn