更新 function.py

function.py

@@ -1,12 +1,14 @@
 import os
 import csv
 import numpy as np
-from sklearn.model_selection import train_test_split, GridSearchCV
+import torch
-from sklearn.linear_model import LogisticRegression
+import torch.nn as nn
+import torch.optim as optim
+from sklearn.model_selection import train_test_split
 from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, roc_auc_score
 from sklearn.preprocessing import StandardScaler
-from sklearn.pipeline import Pipeline
 from imblearn.over_sampling import SMOTE
+from torch.utils.data import DataLoader, TensorDataset
 
 # 读取 CSV 数据的函数
 def load_data(file_path):
@@ -35,6 +37,15 @@ def evaluate_model(y_true, y_pred, y_prob=None):
         auc = roc_auc_score(y_true, y_prob)
         print(f"AUC Score: {auc:.4f}")
 
+# 定义逻辑回归模型
+class LogisticRegressionModel(nn.Module):
+    def __init__(self, input_dim):
+        super(LogisticRegressionModel, self).__init__()
+        self.linear = nn.Linear(input_dim, 1)  # 线性层
+
+    def forward(self, x):
+        return torch.sigmoid(self.linear(x))  # 使用 Sigmoid 激活函数
+
 # 主函数
 def main():
     # 加载数据
@@ -48,28 +59,45 @@ def main():
     smote = SMOTE(random_state=42)
     X_train_res, y_train_res = smote.fit_resample(X_train, y_train)
 
-    # 创建管道，包含标准化和逻辑回归
+    # 标准化数据
-    pipeline = Pipeline([
+    scaler = StandardScaler()
-        ('scaler', StandardScaler()),  # 数据标准化
+    X_train_res = scaler.fit_transform(X_train_res)
-        ('classifier', LogisticRegression(max_iter=1000))  # 逻辑回归
+    X_test = scaler.transform(X_test)
-    ])
 
-    # 网格搜索以优化正则化参数 C
+    # 将数据转换为 Tensor
-    param_grid = {'classifier__C': [0.01, 0.1, 1, 10, 100]}
+    X_train_tensor = torch.FloatTensor(X_train_res)
-    grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring='accuracy')
+    y_train_tensor = torch.FloatTensor(y_train_res).view(-1, 1)
-    grid_search.fit(X_train_res, y_train_res)
+    X_test_tensor = torch.FloatTensor(X_test)
+    y_test_tensor = torch.FloatTensor(y_test).view(-1, 1)
 
-    # 输出最佳参数
+    # 创建数据加载器
-    print(f"Best Parameters: {grid_search.best_params_}")
+    train_dataset = TensorDataset(X_train_tensor, y_train_tensor)
+    train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
 
-    # 使用最佳模型进行预测
+    # 初始化模型、损失函数和优化器
-    best_model = grid_search.best_estimator_
+    input_dim = X_train_res.shape[1]
-    y_pred = best_model.predict(X_test)
+    model = LogisticRegressionModel(input_dim)
-    y_prob = best_model.predict_proba(X_test)[:, 1]  # 用于 AUC 计算
+    criterion = nn.BCELoss()  # 二元交叉熵损失
+    optimizer = optim.SGD(model.parameters(), lr=0.01)
+
+    # 训练模型
+    model.train()
+    for epoch in range(100):  # 训练 100 个 epoch
+        for inputs, labels in train_loader:
+            optimizer.zero_grad()
+            outputs = model(inputs)
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
 
     # 评估模型
-    evaluate_model(y_test, y_pred, y_prob)
+    model.eval()
+    with torch.no_grad():
+        y_pred_prob = model(X_test_tensor).numpy()
+        y_pred = (y_pred_prob > 0.5).astype(int)
+
+    # 评估模型
+    evaluate_model(y_test, y_pred, y_pred_prob)
 
 if __name__ == "__main__":
     main()
-