1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
| from sparkai.llm.llm import ChatSparkLLM, ChunkPrintHandler
from sparkai.core.messages import ChatMessage
import pandas as pd
import re
import json
import time
SPARKAI_URL = 'wss://spark-api.xf-yun.com/v3.5/chat'
SPARKAI_APP_ID = ''
SPARKAI_API_SECRET = ''
SPARKAI_API_KEY = ''
SPARKAI_DOMAIN = 'generalv3.5'
def call_sparkai(prompt):
spark = ChatSparkLLM(
spark_api_url=SPARKAI_URL,
spark_app_id=SPARKAI_APP_ID,
spark_api_key=SPARKAI_API_KEY,
spark_api_secret=SPARKAI_API_SECRET,
spark_llm_domain=SPARKAI_DOMAIN,
streaming=False,
)
messages = [ChatMessage(
role="user",
content=prompt
)]
handler = ChunkPrintHandler()
try:
a = spark.generate([messages], callbacks=[handler])
except Exception as e:
print(e)
return 'error'
return a.generations[0][0].text
cankao_content = '''
1. Which of the following is not a type of art form that Nick Smith uses in his pixelated collages?
A. Painting
B. Photography
C. Embroidery
D. Video art
Answer：C
2. What does the word "Psychology" in the title PSYCOLOURGY: January 2015 refer to in relation to Nick Smith's work?
A. The study of human behavior and mental processes
B. The concept of using colour to convey emotions and ideas
C. The use of pixelated /image in his collages
D. A specific series of artworks from 2015
Answer：B
3. Which of the following is true about Nick Smith's career as an artist?
A. He has only worked in the fine arts category
B. His work is primarily focused on interior design
C. He has never used hand-made collages in his work
D. His first collage experiment was inspired by Marilyn Monroe
Answer：D
4. Which of the following can be inferred about the text employed in Nick Smith's work?
A. It is always narrative and sequential
B. It is often open to interpretation by the viewer
C. It is always written in a specific language or script
D. It is always placed under each swatch of colour
Answer：B
'''
def get_questions(text):
text = text.replace('\n', ' ')+' '
pattern = re.compile(r'(\d+\..*?)(A\..*?\s{2})([B-D]\..*?\s{2})([B-D]\..*?\s{2})(D\..*?\s{2})', re.DOTALL)
matches = pattern.findall(text)
questions_dict_list = []
for match in matches:
question, option1, option2, option3, option4 = match
pattern_question = re.compile(r'(\d+)\.(.*)')
question_text = pattern_question.findall(question.strip())[0][1]
options = {option1[0]: option1, option2[0]: option2, option3[0]: option3, option4[0]: option4}
question_dict = {
'question': question_text,
'options': {
'A': options.get('A', '').strip(),
'B': options.get('B', '').strip(),
'C': options.get('C', '').strip(),
'D': options.get('D', '').strip()
}
}
questions_dict_list.append(question_dict)
return questions_dict_list
def remove_whitespace_and_newlines(input_string):
result = input_string.replace(" ", "").replace("\n", "").replace(".", "")
return result
def get_answers(text):
text = remove_whitespace_and_newlines(text)
pattern = re.compile(r'(\d)\s*([A-D])')
matches = pattern.findall(text)
res = []
for match in matches:
number_dot, first_letter = match
res.append(first_letter)
return res
def get_prompt_en(text):
prompt = f'''
你是⼀个⾼考选择题出题专家，你出的题有⼀定深度，你将根据阅读文本，出4道单项选择题，包含题目选项，以及对应的答案，注意：不⽤给出原文，每道题由1个问题和4个选项组成，仅存在1个正确答案，请严格按照要求执行。
The reading text is mainly in English. The questions and answers you raised need to be completed in English for at least the following points:
### 回答要求
(1)Understanding the main idea of the main idea.
(2)Understand the specific information in the text.
(3)infering the meaning of words and phrases from the context
### 阅读文本
{text}
'''
return prompt
def get_adddata_prompt_zero(reading, cankao_content, question, answer):
prompt = f'''你是一个高考英语阅读题出题专家，请阅读材料，需要参考参考内容 按照要求将题目、选项、答案对其补充完整。
###阅读材料
{reading}
###要求
1.需要将序号对应的题目与答案做匹配。
2.匹配后格式按照问题、ABCD四个选项顺序、答案的结构组合，按照参考内容格式输出。
3.如果选择题目数量不够四个请根据阅读材料及出题思路再生成题目，总题目达到四个。
4.题目中不能出现任何不合理的词汇、语法错误。
5.如果有简答题目与答案请忽略这部分内容，只处理选择题目。
6.题目编号从1开始。
###参考内容
{cankao_content}
###题目
{question}
###答案
{answer}
'''
return prompt
success = 0
fail = 0
def call_sparkai_with_retry(prompt, retries=3, delay=5):
for attempt in range(retries):
try:
resm = call_sparkai(prompt)
return resm
except TimeoutError:
if attempt < retries - 1:
print(f"请求超时，正在重试... ({attempt + 1}/{retries})")
time.sleep(delay)
else:
print("请求超时，已达到最大重试次数。")
return 'error'
def process_en(df):
global success
global fail
res_input = []
res_output = []
for id in range(len(df)):
data_options = df.loc[id, '选项']
data_answers = df.loc[id,'答案']
data_prompt = df.loc[id,'阅读文本']
prompt = get_adddata_prompt_zero(data_prompt, cankao_content, data_options, data_answers)
resm = call_sparkai_with_retry(prompt)
data_prompt = get_prompt_en(data_prompt)
if resm == 'error':
fail += 1
data_options = get_questions(data_options)
data_answers = get_answers(data_answers)
if(len(data_answers)==len(data_options)):
res = ''
for id,question in enumerate(data_options):
res += f'''
{id+1}.{question['question']}
{question['options']['A']}
{question['options']['B']}
{question['options']['C']}
{question['options']['D']}
answer:{data_answers[id]}
'''+'\n'
res_output.append(res)
res_input.append(data_prompt)
else:
success += 1
res_output.append(resm)
res_input.append(data_prompt)
return res_input,res_output
if __name__ == '__main__':
df = pd.read_excel('训练集-英语.xlsx')
df = df.replace('．', '.', regex=True).replace('А.', 'A.', regex=True).replace('В.', 'B.', regex=True).replace('С.', 'C.', regex=True).replace('D.', 'D.', regex=True)
en_input,en_output = process_en(df)
print("success:",success)
print("fail:",fail)
data = []
for i in range(len(en_input)):
data.append({'input':en_input[i],'output':en_output[i]})
with open('output_en.json', 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False, indent=4)
|