仔细回顾一下神经网络到目前的内容，没跟上进度的同学补一下进度。

• 作业：对之前的信贷项目，利用神经网络训练下，尝试用到目前的知识点让代码更加规范和美观。

• import pandas as pd    #用于数据处理和分析，可处理表格数据。
  import numpy as np     #用于数值计算，提供了高效的数组操作。
  import matplotlib.pyplot as plt    #用于绘制各种类型的图表
  import seaborn as sns   #基于matplotlib的高级绘图库，能绘制更美观的统计图形。
  import warnings
  warnings.filterwarnings("ignore")
   
  import torch
  import torch.nn as nn
  import torch.optim as optim
  from sklearn.datasets import load_iris
  from sklearn.model_selection import train_test_split
  from sklearn.preprocessing import MinMaxScaler
  import time
  from tqdm import tqdm  # 导入tqdm库用于进度条显示
   
   # 设置中文字体（解决中文显示问题）
  plt.rcParams['font.sans-serif'] = ['SimHei']  # Windows系统常用黑体字体
  plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号
  data = pd.read_csv('data.csv')    #读取数据
   
  # 设置GPU设备
  device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
  print(f"使用设备: {device}")
   
  # 先筛选字符串变量 
  discrete_features = data.select_dtypes(include=['object']).columns.tolist()
  # Home Ownership 标签编码
  home_ownership_mapping = {
      'Own Home': 1,
      'Rent': 2,
      'Have Mortgage': 3,
      'Home Mortgage': 4
  }
  data['Home Ownership'] = data['Home Ownership'].map(home_ownership_mapping)
   
  # Years in current job 标签编码
  years_in_job_mapping = {
      '< 1 year': 1,
      '1 year': 2,
      '2 years': 3,
      '3 years': 4,
      '4 years': 5,
      '5 years': 6,
      '6 years': 7,
      '7 years': 8,
      '8 years': 9,
      '9 years': 10,
      '10+ years': 11
  }
  data['Years in current job'] = data['Years in current job'].map(years_in_job_mapping)
   
  # Purpose 独热编码，记得需要将bool类型转换为数值
  data = pd.get_dummies(data, columns=['Purpose'])
  data2 = pd.read_csv("data.csv") # 重新读取数据，用来做列名对比
  list_final = [] # 新建一个空列表，用于存放独热编码后新增的特征名
  for i in data.columns:
      if i not in data2.columns:
         list_final.append(i) # 这里打印出来的就是独热编码后的特征名
  for i in list_final:
      data[i] = data[i].astype(int) # 这里的i就是独热编码后的特征名
   
  # Term 0 - 1 映射
  term_mapping = {
      'Short Term': 0,
      'Long Term': 1
  }
  data['Term'] = data['Term'].map(term_mapping)
  data.rename(columns={'Term': 'Long Term'}, inplace=True) # 重命名列
  continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()  #把筛选出来的列名转换成列表
   
   # 连续特征用中位数补全
  for feature in continuous_features:     
      mode_value = data[feature].mode()[0]            #获取该列的众数。
      data[feature].fillna(mode_value, inplace=True)          #用众数填充该列的缺失值，inplace=True表示直接在原数据上修改。
   
  # 最开始也说了 很多调参函数自带交叉验证，甚至是必选的参数，你如果想要不交叉反而实现起来会麻烦很多
  # 所以这里我们还是只划分一次数据集
  from sklearn.model_selection import train_test_split
  X = data.drop(['Credit Default'], axis=1)  # 特征，axis=1表示按列删除
  y = data['Credit Default'] # 标签
  # 按照8:2划分训练集和测试集
  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # 80%训练集，20%测试集
  # 划分训练集和测试集
  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
   
  # 归一化数据
  scaler = MinMaxScaler()
  X_train = scaler.fit_transform(X_train)
  X_test = scaler.transform(X_test)
  X_train = torch.FloatTensor(X_train).to(device)
  y_train = torch.LongTensor(y_train.values).to(device) 
  X_test = torch.FloatTensor(X_test).to(device)
  y_test = torch.LongTensor(y_test.values).to(device) 
   
  batch_size = 64
  train_dataset = torch.utils.data.TensorDataset(X_train, y_train)
  train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
   
  input_size=X_train.shape[1]
  class MLP(nn.Module):
      def __init__(self, input_size):  # 添加input_size参数
          super(MLP, self).__init__()
          self.fc1 = nn.Linear(input_size, 64)  # 输入维度为实际特征数
          self.relu = nn.ReLU()
          self.dropout = nn.Dropout(0.2)  # 新增dropout层防止过拟合
          self.fc2 = nn.Linear(64, 2)  # 输出改为2个神经元（二分类问题）
      
      def forward(self, x):
          out = self.fc1(x)
          out = self.relu(out)
          out = self.dropout(out)
          out = self.fc2(out)
          return out
   
  # 实例化模型
  model = MLP(input_size=X_train.shape[1]).to(device) 
   
  # 分类问题使用交叉熵损失函数
  criterion = nn.CrossEntropyLoss()
   
  optimizer = optim.Adam(model.parameters(), lr=0.001)  # 改为Adam优化器
  criterion = nn.CrossEntropyLoss()
   
  num_epochs = 20000
  best_loss = float('inf')
  patience = 5       
  min_delta = 0.001  
  counter = 0        
   
  # 添加记录列表
  loss_history = []
  epoch_list = []
   
  start_time = time.time()
  with tqdm(total=num_epochs, desc="训练进度", unit="epoch") as pbar:
      for epoch in range(num_epochs):
          model.train()
          epoch_loss = 0.0
          
          # 训练步骤
          for inputs, labels in train_loader:
              optimizer.zero_grad()
              outputs = model(inputs)
              loss = criterion(outputs, labels)
              loss.backward()
              optimizer.step()
              epoch_loss += loss.item() * inputs.size(0)
          
          # 计算平均epoch损失
          avg_loss = epoch_loss / len(train_loader.dataset)
          loss_history.append(avg_loss)     
          epoch_list.append(epoch+1) 
          
          # 更新进度条
          pbar.set_postfix({'Train Loss': f'{avg_loss:.4f}'})
          pbar.update(1)
          
          # 早停逻辑（基于训练损失）
          if avg_loss < best_loss - min_delta:
              best_loss = avg_loss
              counter = 0
              best_weights = model.state_dict().copy()  # 保存最佳权重
          else:
              counter += 1
              if counter >= patience:
                  print(f"\n早停触发！第 {epoch+1} 个epoch后停止")
                  break
   
  # 加载最佳模型权重
  model.load_state_dict(best_weights)
   
  time_all = time.time() - start_time
  print(f'训练时间: {time_all:.2f}秒')
   
  # 可视化损失曲线
  plt.figure(figsize=(10, 6))
  plt.plot(epoch_list, loss_history)
  plt.xlabel('Epoch')
  plt.ylabel('Loss')
  plt.title('Training Loss over Epochs')
  plt.grid(True)
  plt.show()
   
  # 评估模型
  model.eval() # 设置模型为评估模式
  with torch.no_grad(): # torch.no_grad()的作用是禁用梯度计算，可以提高模型推理速度
      outputs = model(X_test)  # 对测试数据进行前向传播，获得预测结果
      _, predicted = torch.max(outputs, 1) # torch.max(outputs, 1)返回每行的最大值和对应的索引
   
      correct = (predicted == y_test).sum().item() # 计算预测正确的样本数
      accuracy = correct / y_test.size(0)
      print(f'测试集准确率: {accuracy * 100:.2f}%')

  

@浙大疏锦行