From 316a3944b0fa4d16fec1577f98e5e3f566e147e0 Mon Sep 17 00:00:00 2001 From: kkkkkxz <2897100651@qq.com> Date: Sat, 26 Oct 2024 18:36:13 +0800 Subject: [PATCH] sy2 --- function.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/function.py b/function.py index 8145e44..d1b0ae6 100644 --- a/function.py +++ b/function.py @@ -25,14 +25,17 @@ name = "孔祥芷" # 这里写自己的代码实现 -def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128): +def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01): """ - 对率回归训练函数。 + 对率回归训练函数，加入L2正则化。 Args: - X (numpy array): 特征数据。 - y (numpy array): 标签数据。 - - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。 + - numIter (int): 迭代次数。默认为1000。 + - learning_rate (float): 学习率。默认为0.06。 + - batch_size (int): 批量大小。默认为128。 + - lambda_reg (float): L2正则化参数。默认为0.01。 Returns: - numpy array: 训练得到的权重。 @@ -54,6 +57,9 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128): h = 1 / (1 + np.exp(-z)) # 计算h error = batch_y - h # 计算误差 gradient = np.dot(batch_X.T, error) / len(batch_y) # 计算梯度 + # 添加L2正则化 + reg_term = 2 * lambda_reg * weights + gradient += reg_term / len(batch_y) weights += learning_rate * gradient # 更新权重 return weights @@ -135,7 +141,7 @@ if __name__ == "__main__": print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")''' X_train, y_train = load_data("./data/horse-colic.data") X_test, y_test = load_data("./data/horse-colic.test") - weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01) + weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01,lambda_reg=0.2) error=0 for i in range(len(y_test)): y_pred = predict_logreg(X_test[i], weights)