更新 function.py

function.py

@@ -26,104 +26,49 @@ name = "黎世浩"
 
 
 def load_data(filepath):
-    """
-    从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    # 读取数据，将非数值转换为NaN
     data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?')
-
-    # 分离特征和标签
     X = data[:, :-1]
     y = data[:, -1]
-
+    
     # 将缺失值填充为每列的平均值
     for i in range(X.shape[1]):
-        X[:, i] = np.where(np.isnan(X[:, i]), np.nanmean(X[:, i]), X[:, i])
-
+        X[:, i] = np.where(np.isnan(X[:, i]), np.mean(X[:, i]), X[:, i])
+    
     return X, y.astype(int)
 
 def scale_features(X):
-    """
-    对特征进行标准化处理。
-
-    Args:
-    - X (numpy array): 特征数据。
-
-    Returns:
-    - numpy array: 标准化后的特征数据。
-    """
     mean = np.mean(X, axis=0)
     std = np.std(X, axis=0)
-    # 避免除以零的错误
     std[std == 0] = 1
     scaled_X = (X - mean) / std
     return scaled_X
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - learning_rate (float): 学习率，默认为0.01。
-    - iterations (int): 迭代次数，默认为1000。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
-    
     for _ in range(iterations):
         for i in range(m):
             x_i = X[i]
             y_i = y[i]
-            # 计算预测值
             prediction = 1 / (1 + np.exp(-np.dot(x_i, weights)))
-            # 计算梯度
             gradient = x_i * (prediction - y_i)
-            # 更新权重
-            weights -= learning_rate * gradient
-    
+            weights -= learning_rate * (gradient + lambda_reg * weights)
     return weights
 
 def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
     prediction = 1 / (1 + np.exp(-np.dot(inX, weights)))
     return 1 if prediction > 0.5 else 0
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    # 加载训练集
     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")
-
-    # 特征缩放
+    
     X_train_scaled = scale_features(X_train)
     X_test_scaled = scale_features(X_test)
-
-    # 训练对率回归模型
+    
     weights = train_logreg(X_train_scaled, y_train, learning_rate=0.01, iterations=1000)
-
-    # 测试单个数据
-    y_pred = predict_logreg(X_test_scaled[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    
+    # 测试模型
+    y_pred = [predict_logreg(x, weights) for x in X_test_scaled]
+    accuracy = np.mean(y_pred == y_test)
+    print(f"Accuracy: {accuracy}")