知识点回顾：

1. 过拟合的判断：测试集和训练集同步打印指标
2. 模型的保存和加载
   1. 仅保存权重
   2. 保存权重和模型
   3. 保存全部信息checkpoint，还包含训练状态
3. 早停策略

作业：对信贷数据集训练后保存权重，加载权重后继续训练50轮，并采取早停策略

import pandas as pd
import numpy as np
import random
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.metrics import classification_report, roc_auc_score
import matplotlib.pyplot as pltdef set_seed(seed=42):random.seed(seed)np.random.seed(seed)torch.manual_seed(seed)torch.cuda.manual_seed_all(seed)torch.backends.cudnn.deterministic = Trueset_seed(42)# 读取数据
data = pd.read_csv('data.csv')
target_col = 'Credit Default'
data = data.fillna(data.median(numeric_only=True))
data = data.fillna('Unknown')categorical_features = ['Home Ownership', 'Purpose', 'Term', 'Years in current job']
numerical_features = [col for col in data.columns if col not in categorical_features + [target_col]]for col in categorical_features:le = LabelEncoder()data[col] = le.fit_transform(data[col])X = data[categorical_features + numerical_features]
y = data[target_col]scaler = StandardScaler()
X[numerical_features] = scaler.fit_transform(X[numerical_features])X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)class CreditDataset(Dataset):def __init__(self, X, y):self.X = torch.tensor(X.values, dtype=torch.float32)self.y = torch.tensor(y.values, dtype=torch.float32)def __len__(self):return len(self.X)def __getitem__(self, idx):return self.X[idx], self.y[idx]train_dataset = CreditDataset(X_train, y_train)
test_dataset = CreditDataset(X_test, y_test)
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=256, shuffle=False)class CreditNet(nn.Module):def __init__(self, input_dim):super(CreditNet, self).__init__()self.model = nn.Sequential(nn.Linear(input_dim, 64),nn.BatchNorm1d(64),nn.ReLU(),nn.Dropout(0.3),nn.Linear(64, 32),nn.BatchNorm1d(32),nn.ReLU(),nn.Dropout(0.2),nn.Linear(32, 1))def forward(self, x):return self.model(x).squeeze(1)device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CreditNet(X_train.shape[1]).to(device)
criterion = nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)def train(model, loader, criterion, optimizer):model.train()total_loss = 0for X_batch, y_batch in loader:X_batch, y_batch = X_batch.to(device), y_batch.to(device)optimizer.zero_grad()outputs = model(X_batch)loss = criterion(outputs, y_batch)loss.backward()optimizer.step()total_loss += loss.item() * X_batch.size(0)return total_loss / len(loader.dataset)def evaluate(model, loader):model.eval()preds, targets = [], []with torch.no_grad():for X_batch, y_batch in loader:X_batch = X_batch.to(device)outputs = torch.sigmoid(model(X_batch)).cpu().numpy()preds.extend(outputs)targets.extend(y_batch.numpy())preds = np.array(preds)targets = np.array(targets)preds_label = (preds > 0.5).astype(int)auc = roc_auc_score(targets, preds)report = classification_report(targets, preds_label, digits=4)return auc, report# 训练主循环
epochs = 20
train_losses = []
test_aucs = []for epoch in range(epochs):train_loss = train(model, train_loader, criterion, optimizer)auc, _ = evaluate(model, test_loader)train_losses.append(train_loss)test_aucs.append(auc)print(f"Epoch {epoch+1}/{epochs} - Train Loss: {train_loss:.4f} - Test AUC: {auc:.4f}")# 可视化训练损失和AUC曲线
plt.figure(figsize=(12,5))
plt.subplot(1,2,1)
plt.plot(range(1, epochs+1), train_losses, marker='o')
plt.xlabel('Epoch')
plt.ylabel('Train Loss')
plt.title('Training Loss Curve')
plt.grid(True)
plt.subplot(1,2,2)
plt.plot(range(1, epochs+1), test_aucs, marker='o', color='orange')
plt.xlabel('Epoch')
plt.ylabel('Test AUC')
plt.title('Test AUC Curve')
plt.grid(True)
plt.tight_layout()
plt.show()# 保存模型权重
torch.save(model.state_dict(), "credit_model.pth")

# 定义早停类
class EarlyStopping:def __init__(self, patience=5, delta=1e-4):self.patience = patienceself.delta = deltaself.best_score = Noneself.counter = 0self.early_stop = Falsedef __call__(self, score):if self.best_score is None or score > self.best_score + self.delta:self.best_score = scoreself.counter = 0else:self.counter += 1if self.counter >= self.patience:self.early_stop = True# 加载权重并继续训练
model.load_state_dict(torch.load("credit_model.pth"))
epochs_continue = 50
early_stopping = EarlyStopping(patience=5, delta=1e-4)
train_losses2 = []
test_aucs2 = []for epoch in range(epochs_continue):train_loss = train(model, train_loader, criterion, optimizer)auc, _ = evaluate(model, test_loader)train_losses2.append(train_loss)test_aucs2.append(auc)print(f"[Continue] Epoch {epoch+1}/{epochs_continue} - Train Loss: {train_loss:.4f} - Test AUC: {auc:.4f}")early_stopping(auc)if early_stopping.early_stop:print("Early stopping triggered!")break# 可视化继续训练的曲线
plt.figure(figsize=(12,5))
plt.subplot(1,2,1)
plt.plot(range(1, len(train_losses2)+1), train_losses2, marker='o')
plt.xlabel('Epoch')
plt.ylabel('Train Loss')
plt.title('Continue Training Loss Curve')
plt.grid(True)
plt.subplot(1,2,2)
plt.plot(range(1, len(test_aucs2)+1), test_aucs2, marker='o', color='orange')
plt.xlabel('Epoch')
plt.ylabel('Test AUC')
plt.title('Continue Test AUC Curve')
plt.grid(True)
plt.tight_layout()
plt.show()# 最终评估
auc, report = evaluate(model, test_loader)
print(f"\nFinal Test AUC: {auc:.4f}")
print("Classification Report:\n", report)