更新 function.py

function.py

@@ -2,6 +2,7 @@ import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.linear_model import LogisticRegression
 
 id = "202210423130"
 name = "董秋"
@@ -85,19 +86,24 @@ if __name__ == "__main__":
 
     # 定义参数网格
     param_grid = {
-        'learning_rate': [0.01, 0.05, 0.1],
-        'iterations': [500, 1000, 2000],
-        'lambda_reg': [0.01, 0.1, 1]
+        'C': [0.01, 0.1, 1.0, 10.0],  # L2正则化强度的倒数
+        'max_iter': [500, 1000, 2000]
     }
 
-    # 网格搜索中定义的参数
-    best_params = {'learning_rate': 0.1, 'iterations': 1000, 'lambda_reg': 0.01}
+    # 使用sklearn的LogisticRegression进行网格搜索
+    model = LogisticRegression(penalty='l2', solver='lbfgs')
+    grid_search = GridSearchCV(model, param_grid, cv=5)
+    grid_search.fit(X_train, y_train)
+
+    # 获取最佳参数
+    best_params = grid_search.best_params_
+    print(f"最佳参数: {best_params}")
 
     # 使用最佳参数重新训练模型
     weights = train_logreg(X_train, y_train, 
-                           learning_rate=best_params['learning_rate'], 
-                           iterations=best_params['iterations'], 
-                           lambda_reg=best_params['lambda_reg'])
+                           learning_rate=0.1, 
+                           iterations=best_params['max_iter'], 
+                           lambda_reg=1 / best_params['C'])  # 将C转换为lambda_reg
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)