更新 function.py

function.py

@@ -31,14 +31,16 @@ import numpy as np
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.001, iterations=2000):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32):
     """
     对率回归训练函数。
 
     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**。
+    - learning_rate (float): 学习率，默认为 0.01。
+    - iterations (int): 迭代次数，默认为 1000。
+    - batch_size (int): 小批量大小，默认为 32。
 
     Returns:
     - numpy array: 训练得到的权重。
@@ -47,12 +49,18 @@ def train_logreg(X, y, learning_rate=0.001, iterations=2000):
     weights = np.zeros(n)
     bias = 0
     for _ in range(iterations):
-        z = np.dot(X, weights) + bias
-        h = sigmoid(z)
-        dw = (1/m) * np.dot(X.T, (h - y))
-        db = (1/m) * np.sum(h - y)
-        weights -= learning_rate * dw
-        bias -= learning_rate * db
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
+        for i in range(0, m, batch_size):
+            X_batch = X_shuffled[i:i+batch_size]
+            y_batch = y_shuffled[i:i+batch_size]
+            z = np.dot(X_batch, weights) + bias
+            h = sigmoid(z)
+            dw = (1/batch_size) * np.dot(X_batch.T, (h - y_batch))
+            db = (1/batch_size) * np.sum(h - y_batch)
+            weights -= learning_rate * dw
+            bias -= learning_rate * db
     return weights
 
 def predict_logreg(inX, weights):
@@ -105,8 +113,9 @@ if __name__ == "__main__":
     X_test, y_test = load_data("./data/horse-colic.test")
 
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=2000)  # 修改迭代次数
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, batch_size=32)  # 修改批量大小
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+