Task 2 #Datawhale AI 夏令营

安装必要包 pandas

!pip install pandas openpyxl

读取数据

import pandas as pd
import re

# 读取Excel文件
df = pd.read_excel('训练集-语文.xlsx')
df = df.replace('．', '.', regex=True)
df = df.replace('（', '(', regex=True)


# 读取第二行（即第三行）“选项”列的内容
second_row_option_content = df.loc[2, '选项']

# 显示第二行“选项”列的内容
print(second_row_option_content)

处理数据

通过正则表达式，筛选所需数据，提取排列

通过dataframe链接数据特征

def chinese_multiple_choice_questions(questions_with_answers):
    # 输入的题目文本
    text = questions_with_answers

    # 正则表达式模式
    question_pattern = re.compile(r'\d+\..*?(?=\d+\.|$)', re.DOTALL)
    choice_pattern = re.compile(r'([A-D])\s*(.*?)(?=[A-D]|$|\n)', re.DOTALL)

    # 找到所有问题
    questions = question_pattern.findall(text)

    # 初始化选择题和简答题列表
    multiple_choice_questions = []
    short_answer_questions = []

        # 处理每个问题
    for id,question in enumerate(questions):
        # 检查是否是选择题
        if re.search(r'[A-D]', question):
            
            choices = choice_pattern.findall(question)
            question_text = re.split(r'\n', question.split('(')[0])[0]
            
            
            pattern_question = re.compile(r'(\d+)\.(.*)')
            matches_question = str(id+1)+'.'+ pattern_question.findall(question_text)[0][1] # 取出问题后重排序
            # print(str(id+1)+'.'+matches_question)
            
            multiple_choice_questions.append({
                'question': matches_question,
                'choices': choices
            })
        else:
            short_answer_questions.append(question.strip())
    return multiple_choice_questions

questions_list = []
for data_id in range(len(df[:3])):
    second_row_option_content = df.loc[data_id, '选项']
    questions_list.append(chinese_multiple_choice_questions(second_row_option_content))

def chinese_multiple_choice_answers(questions_with_answers):
    questions_with_answers = questions_with_answers.replace("