于BERT的中文问答系统12

主要改进点

日志配置:

确保日志文件按日期和时间生成,便于追踪不同运行的记录。
数据处理:

增加了对数据加载过程中错误的捕获和日志记录,确保程序能够跳过无效数据并继续运行。
模型训练:

增加了重新训练模型的功能,用户可以选择重新训练现有模型或从头开始训练。
用户交互:

增加了输入验证,确保用户输入的问题不为空。

增加了模糊匹配功能,支持部分输入问题的匹配。
错误处理:

在关键步骤增加了异常捕获和日志记录,提高了程序的健壮性。

python 复制代码
import os
import json
import jsonlines
import torch
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from transformers import BertModel, BertTokenizer
import tkinter as tk
from tkinter import filedialog, messagebox
import logging
from difflib import SequenceMatcher
from datetime import datetime

# 配置日志
LOGS_DIR = os.path.join(PROJECT_ROOT, 'logs')
os.makedirs(LOGS_DIR, exist_ok=True)

def setup_logging():
    log_file = os.path.join(LOGS_DIR, datetime.now().strftime('%Y-%m-%d/%H-%M-%S/羲和.txt'))
    os.makedirs(os.path.dirname(log_file), exist_ok=True)
    logging.basicConfig(
        level=logging.INFO,
        format='%(asctime)s - %(levelname)s - %(message)s',
        handlers=[
            logging.FileHandler(log_file),
            logging.StreamHandler()
        ]
    )

# 获取项目根目录
PROJECT_ROOT = os.path.dirname(os.path.abspath(__file__))
setup_logging()

# 数据集类
class XihuaDataset(Dataset):
    def __init__(self, file_path, tokenizer, max_length=128):
        self.tokenizer = tokenizer
        self.max_length = max_length
        self.data = self.load_data(file_path)

    def load_data(self, file_path):
        data = []
        if file_path.endswith('.jsonl'):
            with jsonlines.open(file_path) as reader:
                for i, item in enumerate(reader):
                    try:
                        data.append(item)
                    except jsonlines.jsonlines.InvalidLineError as e:
                        logging.warning(f"跳过无效行 {i + 1}: {e}")
        elif file_path.endswith('.json'):
            with open(file_path, 'r') as f:
                try:
                    data = json.load(f)
                except json.JSONDecodeError as e:
                    logging.warning(f"跳过无效文件 {file_path}: {e}")
        return data

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        item = self.data[idx]
        question = item['question']
        human_answer = item['human_answers'][0]
        chatgpt_answer = item['chatgpt_answers'][0]

        try:
            inputs = self.tokenizer(question, return_tensors='pt', padding='max_length', truncation=True, max_length=self.max_length)
            human_inputs = self.tokenizer(human_answer, return_tensors='pt', padding='max_length', truncation=True, max_length=self.max_length)
            chatgpt_inputs = self.tokenizer(chatgpt_answer, return_tensors='pt', padding='max_length', truncation=True, max_length=self.max_length)
        except Exception as e:
            logging.warning(f"跳过无效项 {idx}: {e}")
            return self.__getitem__((idx + 1) % len(self.data))

        return {
            'input_ids': inputs['input_ids'].squeeze(),
            'attention_mask': inputs['attention_mask'].squeeze(),
            'human_input_ids': human_inputs['input_ids'].squeeze(),
            'human_attention_mask': human_inputs['attention_mask'].squeeze(),
            'chatgpt_input_ids': chatgpt_inputs['input_ids'].squeeze(),
            'chatgpt_attention_mask': chatgpt_inputs['attention_mask'].squeeze(),
            'human_answer': human_answer,
            'chatgpt_answer': chatgpt_answer
        }

# 获取数据加载器
def get_data_loader(file_path, tokenizer, batch_size=8, max_length=128):
    dataset = XihuaDataset(file_path, tokenizer, max_length)
    return DataLoader(dataset, batch_size=batch_size, shuffle=True)

# 模型定义
class XihuaModel(torch.nn.Module):
    def __init__(self, pretrained_model_name='F:/models/bert-base-chinese'):
        super(XihuaModel, self).__init__()
        self.bert = BertModel.from_pretrained(pretrained_model_name)
        self.classifier = torch.nn.Linear(self.bert.config.hidden_size, 1)

    def forward(self, input_ids, attention_mask):
        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
        pooled_output = outputs.pooler_output
        logits = self.classifier(pooled_output)
        return logits

# 训练函数
def train(model, data_loader, optimizer, criterion, device):
    model.train()
    total_loss = 0.0
    for batch in data_loader:
        try:
            input_ids = batch['input_ids'].to(device)
            attention_mask = batch['attention_mask'].to(device)
            human_input_ids = batch['human_input_ids'].to(device)
            human_attention_mask = batch['human_attention_mask'].to(device)
            chatgpt_input_ids = batch['chatgpt_input_ids'].to(device)
            chatgpt_attention_mask = batch['chatgpt_attention_mask'].to(device)

            optimizer.zero_grad()
            human_logits = model(human_input_ids, human_attention_mask)
            chatgpt_logits = model(chatgpt_input_ids, chatgpt_attention_mask)

            human_labels = torch.ones(human_logits.size(0), 1).to(device)
            chatgpt_labels = torch.zeros(chatgpt_logits.size(0), 1).to(device)

            loss = criterion(human_logits, human_labels) + criterion(chatgpt_logits, chatgpt_labels)
            loss.backward()
            optimizer.step()

            total_loss += loss.item()
        except Exception as e:
            logging.warning(f"跳过无效批次: {e}")

    return total_loss / len(data_loader)

# 主训练函数
def main_train(retrain=False):
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    logging.info(f'Using device: {device}')

    tokenizer = BertTokenizer.from_pretrained('F:/models/bert-base-chinese')
    model = XihuaModel(pretrained_model_name='F:/models/bert-base-chinese').to(device)

    if retrain:
        model.load_state_dict(torch.load(os.path.join(PROJECT_ROOT, 'models/xihua_model.pth'), map_location=device, weights_only=True))

    optimizer = optim.Adam(model.parameters(), lr=1e-5)
    criterion = torch.nn.BCEWithLogitsLoss()

    train_data_loader = get_data_loader(os.path.join(PROJECT_ROOT, 'data/train_data.jsonl'), tokenizer, batch_size=8, max_length=128)

    num_epochs = 5
    for epoch in range(num_epochs):
        train_loss = train(model, train_data_loader, optimizer, criterion, device)
        logging.info(f'Epoch [{epoch+1}/{num_epochs}], Loss: {train_loss:.4f}')

    torch.save(model.state_dict(), os.path.join(PROJECT_ROOT, 'models/xihua_model.pth'))
    logging.info("模型训练完成并保存")

# GUI界面
class XihuaChatbotGUI:
    def __init__(self, root):
        self.root = root
        self.root.title("羲和聊天机器人")

        self.tokenizer = BertTokenizer.from_pretrained('F:/models/bert-base-chinese')
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
        self.model = XihuaModel(pretrained_model_name='F:/models/bert-base-chinese').to(self.device)
        self.load_model()
        self.model.eval()

        # 加载训练数据集以便在获取答案时使用
        self.data = self.load_data(os.path.join(PROJECT_ROOT, 'data/train_data.jsonl'))

        self.create_widgets()

    def create_widgets(self):
        self.question_label = tk.Label(self.root, text="问题:")
        self.question_label.pack()

        self.question_entry = tk.Entry(self.root, width=50)
        self.question_entry.pack()

        self.answer_button = tk.Button(self.root, text="获取回答", command=self.get_answer)
        self.answer_button.pack()

        self.answer_label = tk.Label(self.root, text="回答:")
        self.answer_label.pack()

        self.answer_text = tk.Text(self.root, height=10, width=50)
        self.answer_text.pack()

        self.train_button = tk.Button(self.root, text="训练模型", command=self.train_model)
        self.train_button.pack()

        self.retrain_button = tk.Button(self.root, text="重新训练模型", command=lambda: self.train_model(retrain=True))
        self.retrain_button.pack()

    def get_answer(self):
        question = self.question_entry.get()
        if not question:
            messagebox.showwarning("输入错误", "请输入问题")
            return

        inputs = self.tokenizer(question, return_tensors='pt', padding='max_length', truncation=True, max_length=128)
        with torch.no_grad():
            input_ids = inputs['input_ids'].to(self.device)
            attention_mask = inputs['attention_mask'].to(self.device)
            logits = self.model(input_ids, attention_mask)
        
        if logits.item() > 0:
            answer_type = "人类回答"
        else:
            answer_type = "ChatGPT回答"

        specific_answer = self.get_specific_answer(question, answer_type)

        self.answer_text.delete(1.0, tk.END)
        self.answer_text.insert(tk.END, f"{answer_type}\n{specific_answer}")

    def get_specific_answer(self, question, answer_type):
        # 使用模糊匹配查找最相似的问题
        best_match = None
        best_ratio = 0.0
        for item in self.data:
            ratio = SequenceMatcher(None, question, item['question']).ratio()
            if ratio > best_ratio:
                best_ratio = ratio
                best_match = item

        if best_match:
            if answer_type == "人类回答":
                return best_match['human_answers'][0]
            else:
                return best_match['chatgpt_answers'][0]
        return "未找到具体答案"

    def load_data(self, file_path):
        data = []
        if file_path.endswith('.jsonl'):
            with jsonlines.open(file_path) as reader:
                for i, item in enumerate(reader):
                    try:
                        data.append(item)
                    except jsonlines.jsonlines.InvalidLineError as e:
                        logging.warning(f"跳过无效行 {i + 1}: {e}")
        elif file_path.endswith('.json'):
            with open(file_path, 'r') as f:
                try:
                    data = json.load(f)
                except json.JSONDecodeError as e:
                    logging.warning(f"跳过无效文件 {file_path}: {e}")
        return data

    def load_model(self):
        model_path = os.path.join(PROJECT_ROOT, 'models/xihua_model.pth')
        if os.path.exists(model_path):
            self.model.load_state_dict(torch.load(model_path, map_location=self.device, weights_only=True))
            logging.info("加载现有模型")
        else:
            logging.info("没有找到现有模型,将使用预训练模型")

    def train_model(self, retrain=False):
        file_path = filedialog.askopenfilename(filetypes=[("JSONL files", "*.jsonl"), ("JSON files", "*.json")])
        if not file_path:
            messagebox.showwarning("文件选择错误", "请选择一个有效的数据文件")
            return

        try:
            dataset = XihuaDataset(file_path, self.tokenizer)
            data_loader = DataLoader(dataset, batch_size=8, shuffle=True)
            
            # 加载已训练的模型权重
            if retrain:
                self.model.load_state_dict(torch.load(os.path.join(PROJECT_ROOT, 'models/xihua_model.pth'), map_location=self.device, weights_only=True))
                self.model.to(self.device)
                self.model.train()

            optimizer = torch.optim.Adam(self.model.parameters(), lr=1e-5)
            criterion = torch.nn.BCEWithLogitsLoss()
            num_epochs = 5
            for epoch in range(num_epochs):
                train_loss = train(self.model, data_loader, optimizer, criterion, self.device)
                logging.info(f'Epoch [{epoch+1}/{num_epochs}], Loss: {train_loss:.4f}')
            torch.save(self.model.state_dict(), os.path.join(PROJECT_ROOT, 'models/xihua_model.pth'))
            logging.info("模型训练完成并保存")
            messagebox.showinfo("训练完成", "模型训练完成并保存")
        except Exception as e:
            logging.error(f"模型训练失败: {e}")
            messagebox.showerror("训练失败", f"模型训练失败: {e}")

# 主函数
if __name__ == "__main__":
    # 启动GUI
    root = tk.Tk()
    app = XihuaChatbotGUI(root)
    root.mainloop()
相关推荐
胡耀超2 分钟前
2、CPU深度解析:从微架构到性能优化
python·性能优化·架构·arm·cpu·x86·多核心
en-route22 分钟前
使用 Flask 构建 Web 应用:静态页面与动态 API 访问
前端·python·flask
ZeroNews内网穿透24 分钟前
新版发布!“零讯”微信小程序版本更新
运维·服务器·网络·python·安全·微信小程序·小程序
hrrrrb2 小时前
【Python】文件处理(二)
开发语言·python
万粉变现经纪人5 小时前
如何解决 pip install 安装报错 ModuleNotFoundError: No module named ‘tokenizers’ 问题
python·selenium·测试工具·scrapy·beautifulsoup·fastapi·pip
编程武士6 小时前
从50ms到30ms:YOLOv10部署中图像预处理的性能优化实践
人工智能·python·yolo·性能优化
我的xiaodoujiao7 小时前
Windows系统Web UI自动化测试学习系列2--环境搭建--Python-PyCharm-Selenium
开发语言·python·测试工具
mCell7 小时前
长期以来我对 LLM 的误解
深度学习·llm·ollama
Ada's8 小时前
深度学习在自动驾驶上应用(二)
人工智能·深度学习·自动驾驶
傻啦嘿哟9 小时前
Python SQLite模块:轻量级数据库的实战指南
数据库·python·sqlite