5555

function.py

@@ -1,5 +1,8 @@
 # function.py
 import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import accuracy_score
 """
 实验说明:
 - 自行编写实现数据加载与预测病马死亡的对率回归算法。
@@ -123,16 +126,28 @@ if __name__ == "__main__":
     # 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, numIter=1000, learning_rate=0.01, lambda_reg=0.2)
+    # 特征缩放
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
 
-    # 测试模型
-    error = 0
-    accuracy_list = []
-    for i in range(len(y_test)):
-        y_pred = predict_logreg(X_test[i], weights)
-        if y_pred != y_test[i]:
-            error += 1
-        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
-    accuracy = (len(y_test) - error) / len(y_test)
-    print(f"Accuracy: {accuracy}")
+    # 划分训练集和验证集
+    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
+
+    # 训练对率回归模型，使用早停法
+    best_weights = None
+    best_accuracy = 0
+    for iter in range(1, 1001):
+        weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1)
+        y_pred = [predict_logreg(x, weights) for x in X_val]
+        accuracy = accuracy_score(y_val, y_pred)
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_weights = weights
+        if iter > 10 and accuracy == best_accuracy:
+            break  # 早停
+
+    # 使用最佳权重在测试集上评估模型
+    y_pred_test = [predict_logreg(x, best_weights) for x in X_test]
+    accuracy_test = accuracy_score(y_test, y_pred_test)
+    print(f"Test Accuracy: {accuracy_test}")