更新 function.py

function.py

@@ -68,8 +68,7 @@ def predict_logreg(X, weights):
 
 def load_data(filepath):
     """加载数据并处理缺失值。"""
-    data = []
-    labels = []
+    data, labels = [], []
 
     with open(filepath, 'r') as f:
         for line in f:
@@ -78,22 +77,22 @@ def load_data(filepath):
                 values = [float(v) for v in values]
 
                 # 合并特征23的取值
-                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
+                if values[22] in [2, 3]:  # 特征23（索引22）
                     labels.append(0)  # 死亡
                 elif values[22] == 1:
                     labels.append(1)  # 生存
                 else:
                     continue  # 无效标签，丢弃
 
-                # 用0填充缺失值
-                values = [0 if v == 0 else v for v in values]  # 直接用0填充
-                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
+                # 用0填充缺失值并提取特征
+                data.append([0 if v == 0 else v for v in values[:2] + values[3:23]])  # 保留特征1, 2 和特征4-23
             except ValueError:
                 continue
 
     data = np.array(data)
     labels = np.array(labels)
 
+    # 数据标准化
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
 
@@ -105,11 +104,11 @@ def accuracy(X, y, weights):
     return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载数据集
-    X, y = load_data("./horse-colic.data")
+    # 加载训练集
+    X_train, y_train = load_data("./horse-colic.data")
 
-    # 使用 train_test_split 打乱并随机抽取数据
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    # 使用 train_test_split 打乱并随机抽取训练和验证数据
+    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
 
     # K折交叉验证
     k = 5
@@ -131,6 +130,14 @@ if __name__ == "__main__":
     print(f"K折交叉验证得分: {accuracies}")
     print(f"平均准确率: {np.mean(accuracies):.4f}")
 
+    # 加载测试集
+    X_test, y_test = load_data("./horse-colic.test")
+
+    # 在测试集上评估最终模型
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.01, batch_size=32)
+    test_accuracy = accuracy(X_test, y_test, final_weights)
+    print(f"测试集的准确率: {test_accuracy:.4f}")
+
     # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
+    y_pred = predict_logreg(X_test[11], final_weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")