更新 function.py

function.py

@@ -6,22 +6,22 @@ from sklearn.model_selection import train_test_split
 id = "202210423130"
 name = "董秋"
 
-# 定义常量
-IGNORE_ROWS = {2} | set(range(23, 28))  # 要忽略的行号
 
 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):
     """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
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
 
     for i in range(iterations):
         # 每次迭代打乱数据
         indices = np.random.permutation(m)
-        X, y = X[indices], y[indices]
+        X = X[indices]
+        y = y[indices]
 
         z = np.dot(X, weights)
         predictions = sigmoid(z)
@@ -33,32 +33,32 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
         # 更新权重
         weights -= learning_rate * gradient
 
-        # 动态调整学习率
+        # 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, labels = [], []
+    data = []
+    labels = []
 
     with open(filepath, 'r') as f:
-        for line_number, line in enumerate(f):
-            if line_number in IGNORE_ROWS:  # 忽略特定行
-                continue
-            
+        for line in f:
             values = line.strip().replace('?', '0').split()
             try:
                 values = [float(v) for v in values]
-
+                
                 # 合并特征23的取值
-                if values[22] in [2, 3]:  # 特征23（索引22）
+                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
                     labels.append(0)  # 死亡
                 elif values[22] == 1:
                     labels.append(1)  # 生存
@@ -66,26 +66,27 @@ def load_data(filepath):
                     continue  # 无效标签，丢弃
                 
                 # 用0填充缺失值
-                values = [0 if v == 0 else v for v in values]  # 用0填充
+                values = [0 if v == 0 else v for v in values]  # 直接用0填充
                 data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
-            except ValueError as e:
-                print(f"Line {line_number} has an error: {e}")  # 打印出错行信息
+            except ValueError:
+                continue
 
-    # 转换为numpy数组
     data = np.array(data)
     labels = np.array(labels)
 
     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")
-    
+
     # 归一化数据
     X = preprocess_data(X)