更新 function.py

function.py

@@ -32,26 +32,9 @@ from sklearn.preprocessing import StandardScaler
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regularization_strength=0.1):
-    """
-    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。
-    - iterations (int): 迭代次数。
-    - batch_size (int): 批量大小。
-    - regularization_strength (float): L2正则化强度。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32, regularization_strength=0.1):
     m, n = X.shape
     weights = np.random.randn(n) * 0.01
-    best_weights = weights.copy()
-    best_accuracy = 0
-    wait = 0
 
     for i in range(iterations):
         indices = np.random.permutation(m)
@@ -61,48 +44,20 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regul
         for j in range(0, m, batch_size):
             X_batch = X_shuffled[j:j + batch_size]
             y_batch = y_shuffled[j:j + batch_size]
+
             z = np.dot(X_batch, weights)
             h = sigmoid(z)
             gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch) + regularization_strength * weights
             weights -= learning_rate * gradient
 
-        # 计算训练集准确率
-        train_accuracy = accuracy(X, y, weights)
-        if train_accuracy > best_accuracy:
-            best_accuracy = train_accuracy
-            best_weights = weights.copy()
-            wait = 0
-        else:
-            wait += 1
-
-    return best_weights
+    return weights
 
 def predict_logreg(X, weights):
-    """
-    对率回归预测函数。
-
-    Args:
-    - X (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - numpy array: 预测的分类标签。
-    """
     z = np.dot(X, weights)
     h = sigmoid(z)
-    return np.where(h > 0.5, 1, 0)
+    return np.where(h >= 0.5, 1, 0)
 
 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。
-    """
     data = []
     labels = []
     with open(filepath, 'r') as f:
@@ -124,6 +79,7 @@ def accuracy(X, y, weights):
     return np.mean(predictions == y)
 
 if __name__ == "__main__":
+    # 读取数据
     X_train, y_train = load_data("./horse-colic.data")
     X_test, y_test = load_data("./horse-colic.test")
 
@@ -132,7 +88,9 @@ if __name__ == "__main__":
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
+    # 训练模型
     final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000, batch_size=64)
 
+    # 评估模型
     final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")