更新 function.py

function.py

@@ -25,103 +25,51 @@ name = "陈瑞琪祥"
 
 
 def sigmoid(z):
-    """
-    Sigmoid函数，用于将线性输出转换为概率值。
-    """
     return 1 / (1 + np.exp(-z))
 
-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:
-    - weights (numpy array): 训练得到的权重。
-    """
-    # 初始化权重
-    weights = np.zeros(X.shape[1])
-    # 学习率和迭代次数
-    lr = learning_rate
-    n_iterations = iterations
-
-    for i in range(n_iterations):
-        # 计算模型预测值
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01):
+    m, n = X.shape
+    weights = np.zeros(n)
+    for i in range(iterations):
         linear_model = np.dot(X, weights)
         y_predicted = sigmoid(linear_model)
-        
-        # 计算梯度
-        gradient = np.dot(X.T, (y_predicted - y)) / len(y)
-        
-        # 更新权重
-        weights -= lr * gradient
-
+        gradient = np.dot(X.T, (y_predicted - y)) / m
+        # 添加L2正则化
+        gradient += regularization * np.r_[[0], weights[1:]]  # 不对偏置项进行正则化
+        weights -= learning_rate * gradient
     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。
-    """
-    # 计算线性组合
     linear_output = np.dot(inX, weights)
-    # 应用sigmoid函数
     probability = sigmoid(linear_output)
-    # 预测类别
     return 1 if probability > 0.5 else 0
 
 def load_data(filepath):
-    """
-    从文件中加载数据。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - X (np.array): 特征数据。
-    - y (np.array): 标签数据。
-    """
-    # 尝试使用numpy的genfromtxt函数读取数据，自动检测分隔符
-    try:
-        data = np.genfromtxt(filepath, delimiter=None, invalid_raise=False, filling_values=np.nan)
-    except ValueError as e:
-        print(f"Error reading file: {e}")
-        return None, None
-
-    # 如果数据文件中只有一列，可能是分隔符没有正确识别
-    if data.ndim == 1:
-        print("Data file may have an incorrect delimiter or only contains one column.")
-        return None, None
-
-    # 丢弃完全为NaN的行
+    data = np.genfromtxt(filepath, delimiter=',', invalid_raise=False, filling_values=np.nan)
     data = data[~np.isnan(data).any(axis=1)]
-
-    # 分离特征和标签
     X = data[:, :-1]
     y = data[:, -1]
-
     return X, y
-if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
 
-    # 加载测试集
+def feature_scaling(X):
+    # 特征归一化
+    X_min = X.min(axis=0)
+    X_max = X.max(axis=0)
+    X_scaled = (X - X_min) / (X_max - X_min)
+    return X_scaled
+
+if __name__ == "__main__":
+    X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
 
+    # 特征归一化
+    X_train_scaled = feature_scaling(X_train)
+    X_test_scaled = feature_scaling(X_test)
+
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    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[11], weights)
+    y_pred = predict_logreg(X_test_scaled[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")