更新 function.py

function.py

@@ -65,7 +65,7 @@ def load_data(filepath):
     labels = np.array(labels)
     
     num_features = data.shape[1]
-	    indices_to_remove = [2]  # 去掉特征3（索引2）
+    indices_to_remove = [2]  # 去掉特征3（索引2）
     
     if num_features > 23:
         indices_to_remove.extend(range(23, min(28, num_features)))
@@ -103,32 +103,4 @@ def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, ba
 if __name__ == "__main__":
     # 加载训练集
     try:
-        X_train, y_train = load_data("./data/horse-colic.data")
-    except FileNotFoundError as e:
-        print(e)
-        exit()
-
-    # 数据归一化处理
-    scaler = StandardScaler()
-    X_train = scaler.fit_transform(X_train)  # 使用训练集进行标准化
-
-    # k折交叉验证
-    avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
-    print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")
-
-    # 加载测试集
-    try:
-        X_test, y_test = load_data("./data/horse-colic.test")
-    except FileNotFoundError as e:
-        print(e)
-        exit()
-
-    # 测试集也需要进行相同的归一化
-    X_test = scaler.transform(X_test)  # 使用相同的Scaler进行测试集的标准化
-
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=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]}")
+        X_train, y_train = load_data("./data/hor