更新 function.py

function.py

@@ -1,6 +1,8 @@
 # function.py
 import numpy as np
 from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import GridSearchCV
+from sklearn.linear_model import LogisticRegression
 
 """
 实验说明:
@@ -102,17 +104,42 @@ def load_data(filepath):
     return data, target_variable
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    # 加载训练集
+    # 加载训练集和测试集
     X_train, y_train = load_data("./data/horse-colic.data")
-
-    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, re
-    ='l1')
+    # 使用GridSearchCV进行超参数调优
+    param_grid = {
+        'learning_rate': [0.001, 0.01, 0.1],
+        'iterations': [100, 500, 1000]
+    }
 
-    # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    # 定义自定义逻辑回归模型
+    class CustomLogisticRegression:
+        def __init__(self, learning_rate=0.01, iterations=1000):
+            self.learning_rate = learning_rate
+            self.iterations = iterations
+            self.weights = None
+
+        def fit(self, X, y):
+            self.weights = train_logreg(X, y, self.learning_rate, self.iterations)
+
+        def predict(self, X):
+            return np.array([predict_logreg(x, self.weights) for x in X])
+
+    # 网格搜索
+    best_accuracy = 0
+    best_params = {}
+    
+    for lr in param_grid['learning_rate']:
+        for it in param_grid['iterations']:
+            model = CustomLogisticRegression(learning_rate=lr, iterations=it)
+            model.fit(X_train, y_train)
+            y_pred = model.predict(X_test)
+            accuracy = np.mean(y_pred == y_test)
+            print(f"学习率: {lr}, 迭代次数: {it}, 准确率: {accuracy}")
+            if accuracy > best_accuracy:
+                best_accuracy = accuracy
+                best_params = {'learning_rate': lr, 'iterations': it}
+
+    print(f"最佳参数: {best_params}, 最佳准确率: {best_accuracy}")