name_classify/functions.py

import re, ast, requests
import math, json
def save_dict_to_json(dictionary, filename):
    with open(filename, 'w', encoding='utf-8') as file:
        json.dump(dictionary, file, ensure_ascii=False, indent=4)

def load_dict_from_json(filename):
    with open(filename, 'r', encoding='utf-8') as file:
        return json.load(file)
def split_dataframe_to_dict(df, chunk_size=100):
    # 计算需要切割的份数
    num_chunks = math.ceil(len(df) / chunk_size)
    
    # 用于存储结果的字典
    result_dict = {}
    
    for i in range(num_chunks):
        # 切割 DataFrame
        start = i * chunk_size
        end = min((i + 1) * chunk_size, len(df))
        chunk = df.iloc[start:end]
        
        # 将切割后的 DataFrame 转换为字典并存储
        result_dict[f'chunk_{i+1}'] = chunk.to_dict(orient='records')
    
    return result_dict
def extract_list_from_string(input_string):
    # 使用正则表达式查找列表部分
    list_pattern = r'\[.*?\]'
    match = re.search(list_pattern, input_string, re.DOTALL)
    
    if match:
        list_string = match.group()
        try:
            # 使用 ast.literal_eval 安全地解析字符串
            result = ast.literal_eval(list_string)
            
            # 检查结果是否为列表
            if isinstance(result, list):
                return result
            else:
                print("解析结果不是列表")
                return None
        except Exception as e:
            print(f"解析错误: {e}")
            return None
    else:
        print("未找到列表结构")
        return None
def post_openai(messages):
   Baseurl = "https://fast.bemore.lol"
   Skey = "sk-dxl4rt2wWswbdrCr1c7b8500B68c43F5B6175b90F7D672C4"
   payload = json.dumps({
      "model": "gpt-4",
      "messages": messages
   })
   url = Baseurl + "/v1/chat/completions"
   headers = {
      'Accept': 'application/json',
      'Authorization': f'Bearer {Skey}',
      'User-Agent': 'Apifox/1.0.0 (https://apifox.com)',
      'Content-Type': 'application/json'
   }

   response = requests.request("POST", url, headers=headers, data=payload)

   # 解析 JSON 数据为 Python 字典
   print(response)
   data = response.json()

   # 获取 content 字段的值
   content = data['choices'][0]['message']['content']

   return content