更新 function.py

function.py

@@ -42,20 +42,16 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     """
     m, n = X.shape
     weights = np.zeros(n)
-    
+
     for _ in range(iterations):
-        # 计算预测值
         z = np.dot(X, weights)
         predictions = 1 / (1 + np.exp(-z))
-        
-        # 计算损失的梯度
         gradient = np.dot(X.T, (predictions - y)) / m
-        
-        # 更新权重
         weights -= learning_rate * gradient
-        
+
     return weights
 
+
 def predict_logreg(inX, weights):
     """
     对率回归预测函数。
@@ -67,40 +63,27 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
-    z = np.dot(inX, weights)
+     z = np.dot(inX, weights)
     prediction_prob = 1 / (1 + np.exp(-z))
-    
     return 1 if prediction_prob >= 0.5 else 0
 
 # 这里也写自己的代码实现
 def load_data(filepath):
     data = []
     labels = []
-    
+
     with open(filepath, 'r') as f:
         for line in f:
             values = line.strip().replace('?', '0').split()
             try:
                 values = [float(v) for v in values]
-                data.append(values[:-1])
-                labels.append(values[-1])
+                data.append(values[:-1])  # 特征
+                labels.append(values[-1])  # 标签
             except ValueError:
                 continue
-    
+
     return np.array(data), np.array(labels)
 
-def preprocess_data(filepath):
-    # 加载数据
-    X, y = load_data(filepath)
-    
-    # 特征缩放
-    scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-    
-    # 拆分数据集
-    X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
-    
-    return X_train, X_test, y_train, y_test
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改