更新 function.py

function.py

@@ -6,13 +6,11 @@ from sklearn.model_selection import train_test_split
 id = "202210423130"
 name = "董秋"
 
-
 def sigmoid(z):
     """Sigmoid 激活函数。"""
     return 1 / (1 + np.exp(-z))
 
-
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01, batch_size=32):
     """逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。"""
     m, n = X.shape
     weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
@@ -23,29 +21,31 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
         X = X[indices]
         y = y[indices]
 
-        z = np.dot(X, weights)
-        predictions = sigmoid(z)
-        gradient = np.dot(X.T, (predictions - y)) / m
+        for j in range(0, m, batch_size):  # 按照 batch size 迭代
+            X_batch = X[j:j + batch_size]
+            y_batch = y[j:j + batch_size]
 
-        # L2正则化
-        gradient += (lambda_reg / m) * weights
+            z = np.dot(X_batch, weights)
+            predictions = sigmoid(z)
+            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]
 
-        # 更新权重
-        weights -= learning_rate * gradient
+            # L2正则化
+            gradient += (lambda_reg / m) * weights
+
+            # 更新权重
+            weights -= learning_rate * gradient
 
         # 动态调整学习率，逐渐减小
         learning_rate *= 0.99
 
     return weights
 
-
 def predict_logreg(inX, weights):
     """逻辑回归预测函数。"""
     z = np.dot(inX, weights)
     prediction_prob = sigmoid(z)
     return 1 if prediction_prob >= 0.5 else 0
 
-
 def load_data(filepath):
     """加载数据并处理缺失值。"""
     data = []
@@ -76,13 +76,11 @@ def load_data(filepath):
 
     return data, labels
 
-
 def preprocess_data(X):
     """特征标准化。"""
     scaler = StandardScaler()
     return scaler.fit_transform(X)
 
-
 if __name__ == "__main__":
     # 加载数据集
     X, y = load_data("./data/horse-colic.data")
@@ -93,8 +91,9 @@ if __name__ == "__main__":
     # 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)
 
-    # 训练逻辑回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01)
+    # 训练逻辑回归模型，设置 batch size
+    batch_size = 32
+    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01, batch_size=batch_size)
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)